{
  "id": "AIBD-0307",
  "title": "Odakyu Electric Railway starts a Panasonic deep-learning “fall detection system” on existing station cameras at Kyōdō and Soshigaya-Ōkura stations",
  "summary": "From 1 April 2020 Odakyu's system analyzes existing platform camera video to flag people who fall onto the tracks or linger at the platform edge and alerts station staff; no outcomes are reported.",
  "date_observed": "2020-04-01",
  "date_basis": "unassessed",
  "date_precision": "unassessed",
  "benefit_status": null,
  "source_collection": null,
  "source_entry": null,
  "account": "Odakyu Electric Railway announced on 30 March 2020 (press release republished by Nikkei) a 転落検知システム (fall detection system). It would operate from the first train on 1 April 2020 at Kyōdō (経堂) and Soshigaya-Ōkura (祖師ヶ谷大蔵) stations on the Odakyu Line. It uses video from existing station cameras. Built with Panasonic System Solutions Japan, the system applies Panasonic's image-analysis and deep-learning technology to analyze the camera feeds in real time. It alerts a dedicated terminal in the station office, showing the camera image, when it detects a person fallen from the platform onto the tracks. It does the same for a person who has stayed at the platform edge for a set time and risks contact with a train. Staff can then take safety measures such as an emergency stop. Pre-learning to set each camera's detection area and to distinguish people from trains had run at both stations since December 2019. Impress Watch reported the launch on 31 March 2020. Neither source reports any detection, prevented accident or performance figure, and no later outcome report was found. Impress Watch (7 October 2024) reported a separate trial of Asilla's behavior-recognition “AI Security asilla” on all 20 existing cameras at Kakio and Tamagawa-Gakuen-mae stations. It ran from 10 October 2024 to 9 January 2025. It tested detection of falls from the platform, wheelchair and white-cane users, people lingering on the platform, disputes between passengers and suspicious objects. Results were not reported. Romanizations of station names are ours; the sources give them in Japanese.",
  "category": "general benefit",
  "unexpected": false,
  "purpose": "Built to detect people falling from the platform onto the tracks or lingering at the platform edge and alert station staff. No detection event is documented.",
  "system": "転落検知システム (fall detection system): Panasonic image-analysis and deep-learning on existing station cameras",
  "model_version": null,
  "developer": "Panasonic System Solutions Japan, with Odakyu Electric Railway",
  "deployer": "Odakyu Electric Railway",
  "location": "Kyōdō and Soshigaya-Ōkura stations, Odakyu Line, Japan",
  "domain": "Railway safety / platform fall detection",
  "segment": "Station platform monitoring",
  "benefit_type": "Increased Product Safety",
  "taxonomy_note": null,
  "registry_ids": {},
  "ratings": [
    {
      "group": "personal",
      "depth": null,
      "reason": "No fall, alert or prevented accident is reported by any source."
    },
    {
      "group": "organizational",
      "depth": null,
      "reason": "The operator describes the intended staff workflow; no count of alerts, false alarms or staff time saved is published."
    }
  ],
  "ai_role": {
    "status": "unassessed",
    "statement": "No event involving the system is documented. The account comes from Odakyu's own launch release and Impress Watch's report of it. They describe what the deep-learning analysis is meant to detect and how staff are alerted. The 2024 Asilla trial at two other stations is a separate system whose results were not reported."
  },
  "evidence": [
    {
      "kind": "news report",
      "citation": "Impress Watch (2020). 既設の駅構内カメラで転落者自動検知。小田急. 31 March 2020.",
      "title": "既設の駅構内カメラで転落者自動検知。小田急",
      "url": "https://www.watch.impress.co.jp/docs/news/1243957.html",
      "date": "2020-03-31",
      "written_by": "independent",
      "quote": "ホームから線路への転落者を自動検知、駅係員に通知する「転落検知システム」の運用を4月1日より開始。小田急線経堂駅と祖師ヶ谷大蔵駅に設置される。"
    },
    {
      "kind": "press release",
      "citation": "Odakyu Electric Railway (2020). 小田急電鉄、既設の駅構内カメラを活用した「転落検知システム」を運用開始. Press release of 30 March 2020, republished by Nikkei.",
      "title": "小田急電鉄、既設の駅構内カメラを活用した「転落検知システム」を運用開始",
      "url": "https://www.nikkei.com/article/DGXLRSP531980_Q0A330C2000000/",
      "date": "2020-03-30",
      "written_by": "deployer",
      "quote": "パナソニックが有する画像解析とディープラーニング（深層学習）技術を鉄道環境に応用し、既設の駅構内カメラの映像をリアルタイムに解析を行い"
    },
    {
      "kind": "news report",
      "citation": "Impress Watch (2024). 小田急、駅構内カメラ映像に行動認識AI　転落や車いす、不審者検知. 7 October 2024 (the Asilla trial echo).",
      "title": "小田急、駅構内カメラ映像に行動認識AI　転落や車いす、不審者検知",
      "url": "https://www.watch.impress.co.jp/docs/news/1629496.html",
      "date": "2024-10-07",
      "written_by": "independent",
      "quote": "ホームからの転落や車いす利用者、不審者・不審物を適正に検知可能かを検証する。"
    }
  ],
  "replication": {
    "produced_by": [
      "Existing station cameras covering the platform edge and track at two stations",
      "Panasonic deep-learning image analysis trained from December 2019 to set detection areas and tell people from trains",
      "A dedicated terminal in the station office that shows the alert and video for staff to act on"
    ],
    "must_hold": [
      "Station staff present to confirm the alert and order an emergency stop",
      "Detection areas calibrated per camera; the sources give no accuracy or false-alarm figures"
    ],
    "echoes": [
      {
        "date": "2024-10-10",
        "setting": "Trial of Asilla's “AI Security asilla” behavior-recognition AI on 20 existing cameras at Kakio and Tamagawa-Gakuen-mae stations, 10 October 2024 to 9 January 2025, including detection of falls from the platform",
        "model_version": "AI Security asilla",
        "outcome": "unknown",
        "source": "Impress Watch, 7 October 2024, https://www.watch.impress.co.jp/docs/news/1629496.html"
      }
    ]
  },
  "paired_incident": null,
  "headline": "Odakyu starts Panasonic fall-detection AI on station cameras",
  "metric": null,
  "comparator": null,
  "later": {
    "status": "scaled",
    "date": "2024-10-10",
    "note": "Odakyu later extended AI analysis of existing station cameras, including detection of falls from the platform, to two more stations (Kakio and Tamagawa-Gakuen-mae) in a trial from 10 October 2024 to 9 January 2025, but with a different vendor's system (Asilla), and no result for either system has been reported.",
    "quote": "小田急電鉄と小田急ビルサービス、アジラは、小田急線柿生駅、玉川学園前駅で、コンコースやホームなどの既設駅構内カメラの映像に、行動認識AIを活用した解析を行なうことに関する実証実験を行なう。ホームからの転落や車いす利用者、不審者・不審物を適正に検知可能かを検証する。",
    "url": "https://www.watch.impress.co.jp/docs/news/1629496.html"
  },
  "value": null,
  "developer_country": "Japan",
  "deployer_country": "Japan",
  "unrated_because": null,
  "brief_notes": null,
  "brief": null,
  "revisions": [
    {
      "date": "2026-10-20",
      "change": "Record drafted from the cited sources.",
      "source": null,
      "editor": "AIBD"
    },
    {
      "date": "2026-10-21",
      "change": "Benefit type set to Increased Product Safety under Trustible's full taxonomy of 23 types; it was Improved Organizational Efficiency among the six first used.",
      "source": "https://trustible.ai/post/a-framework-for-measuring-the-benefits-of-ai/",
      "editor": "AIBD"
    },
    {
      "date": "2026-10-21",
      "change": "Added what happened since from the cited sources.",
      "source": "https://www.watch.impress.co.jp/docs/news/1629496.html",
      "editor": "AIBD"
    },
    {
      "date": "2026-10-21",
      "change": "Country of the developer and the deployer added from the organization's own site or a registry.",
      "source": "https://ja.wikipedia.org/wiki/%E3%83%91%E3%83%8A%E3%82%BD%E3%83%8B%E3%83%83%E3%82%AF_%E3%82%B3%E3%83%8D%E3%82%AF%E3%83%88; https://en.wikipedia.org/wiki/Odakyu_Electric_Railway",
      "editor": "AIBD"
    },
    {
      "date": "2026-10-21",
      "change": "Prose pass: account, purpose, the system's part rewritten in shorter sentences with abbreviations expanded; facts, figures and quotations unchanged.",
      "source": null,
      "editor": "AIBD"
    }
  ],
  "confidence": "reported",
  "shade": "medium",
  "claim_status": "Independently reported",
  "claim_basis": "Sources: two independent news reports and the deployer's press release. The cited evidence includes no independent study or report and no finding by a regulator or court.",
  "profile": {
    "case_id": "AIBD-0307",
    "catalog_version": "1.0.0",
    "source_fingerprint": "c44bc917ed3fdf686824c871338c7e216102b6fb829b483716a82177e1352767",
    "collection_refs": [
      {
        "collection_id": "aibd",
        "version": "snapshot-8bf7cfec9cb185aa"
      },
      {
        "collection_id": "aibd",
        "version": "2026-10-25"
      },
      {
        "collection_id": "chanticleer",
        "version": "2026-10-25"
      }
    ],
    "source_ids": [
      "AIBD-0307-source-0001",
      "AIBD-0307-source-0002",
      "AIBD-0307-source-0003"
    ],
    "families": {
      "strategic assessments": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "record_ids": []
      },
      "evaluations": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "record_ids": []
      },
      "monetary observations": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "record_ids": []
      },
      "institutional decisions": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "record_ids": []
      }
    },
    "fields": {
      "actors[]": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "developer": "Panasonic System Solutions Japan, with Odakyu Electric Railway",
            "deployer": "Odakyu Electric Railway"
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "developer",
            "deployer"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "actors[].ownership_control": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "ai_contribution": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "ai_relationship": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "category": "general benefit",
            "ai_role": {
              "status": "unassessed",
              "statement": "No event involving the system is documented. The account comes from Odakyu's own launch release and Impress Watch's report of it. They describe what the deep-learning analysis is meant to detect and how staff are alerted. The 2024 Asilla trial at two other stations is a separate system whose results were not reported."
            }
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "ai_role",
            "category"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "assessments[].alternatives": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "assessments[].assessor_date": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "assessments[].depth": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "assessments[].display_confidence": {
        "state": "value_present",
        "value": {
          "kind": "structured",
          "data": {
            "confidence": "medium",
            "evidence_word": "reported",
            "claim_status": "Independently reported",
            "basis": "Sources: two independent news reports and the deployer's press release. The cited evidence includes no independent study or report and no finding by a regulator or court.",
            "interpretation": "Existing display rule preserved; the richer outcome-specific confidence question still needs review."
          }
        },
        "provenance": {
          "kind": "curatorial",
          "basis": "Derived from the existing case display properties; not a new evidentiary judgment.",
          "record_fields": [],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "assessments[].rationale": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "ratings": [
              {
                "group": "personal",
                "reason": "No fall, alert or prevented accident is reported by any source."
              },
              {
                "group": "organizational",
                "reason": "The operator describes the intended staff workflow; no count of alerts, false alarms or staff time saved is published."
              }
            ]
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "ratings"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "assessments[].rubric_version": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "assessments[].status_basis": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "assessments[].target": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "ratings": [
              {
                "group": "personal",
                "reason": "No fall, alert or prevented accident is reported by any source."
              },
              {
                "group": "organizational",
                "reason": "The operator describes the intended staff workflow; no count of alerts, false alarms or staff time saved is published."
              }
            ]
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "ratings"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "availability": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "brief": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "case_kind": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "case_links[]": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "claims[].evidence_links": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "claims[].evidence_strength": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "claims[].missingness": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "claims[].proposition": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "cross_border_flows[]": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "decisions[].action_outcome": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "institutional decisions"
      },
      "decisions[].grounds": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "institutional decisions"
      },
      "decisions[].institution_task": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "institutional decisions"
      },
      "decisions[].success_criterion": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "institutional decisions"
      },
      "deployment_stage": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "economics[].amount": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "monetary observations"
      },
      "economics[].costs[]": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "monetary observations"
      },
      "economics[].counterfactual": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "monetary observations"
      },
      "economics[].currency_price_basis": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "monetary observations"
      },
      "economics[].gross_net": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "monetary observations"
      },
      "economics[].measure_type": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "monetary observations"
      },
      "economics[].period_unit": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "monetary observations"
      },
      "economics[].realization": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "monetary observations"
      },
      "economics[].recipient_payer": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "monetary observations"
      },
      "economics[].return_payback": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "monetary observations"
      },
      "economics[].valuation_method": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "monetary observations"
      },
      "evaluations[].ai_uplift": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "evaluations"
      },
      "evaluations[].comparator": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "evaluations"
      },
      "evaluations[].design": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "evaluations"
      },
      "evaluations[].effect": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "evaluations"
      },
      "evaluations[].exposure": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "evaluations"
      },
      "evaluations[].id": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "evaluations"
      },
      "evaluations[].measurement_method": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "evaluations"
      },
      "evaluations[].metric": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "evaluations"
      },
      "evaluations[].reproduction_materials": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "evaluations"
      },
      "evaluations[].setting_sample": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "evaluations"
      },
      "evaluations[].uncertainty_limitations": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "evaluations"
      },
      "external_references[]": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "follow_up[]": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "later": {
              "status": "scaled",
              "date": "2024-10-10",
              "note": "Odakyu later extended AI analysis of existing station cameras, including detection of falls from the platform, to two more stations (Kakio and Tamagawa-Gakuen-mae) in a trial from 10 October 2024 to 9 January 2025, but with a different vendor's system (Asilla), and no result for either system has been reported.",
              "quote": "小田急電鉄と小田急ビルサービス、アジラは、小田急線柿生駅、玉川学園前駅で、コンコースやホームなどの既設駅構内カメラの映像に、行動認識AIを活用した解析を行なうことに関する実証実験を行なう。ホームからの転落や車いす利用者、不審者・不審物を適正に検知可能かを検証する。",
              "url": "https://www.watch.impress.co.jp/docs/news/1629496.html"
            }
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "later"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "human_oversight": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "id": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "id": "AIBD-0307"
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "id"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "infrastructure_dependencies[]": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "outcomes[].beneficiaries": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "outcomes[].beneficiary_count": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "outcomes[].benefit_type": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "benefit_type": "Increased Product Safety"
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "benefit_type"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "outcomes[].claim": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "account": "Odakyu Electric Railway announced on 30 March 2020 (press release republished by Nikkei) a 転落検知システム (fall detection system). It would operate from the first train on 1 April 2020 at Kyōdō (経堂) and Soshigaya-Ōkura (祖師ヶ谷大蔵) stations on the Odakyu Line. It uses video from existing station cameras. Built with Panasonic System Solutions Japan, the system applies Panasonic's image-analysis and deep-learning technology to analyze the camera feeds in real time. It alerts a dedicated terminal in the station office, showing the camera image, when it detects a person fallen from the platform onto the tracks. It does the same for a person who has stayed at the platform edge for a set time and risks contact with a train. Staff can then take safety measures such as an emergency stop. Pre-learning to set each camera's detection area and to distinguish people from trains had run at both stations since December 2019. Impress Watch reported the launch on 31 March 2020. Neither source reports any detection, prevented accident or performance figure, and no later outcome report was found. Impress Watch (7 October 2024) reported a separate trial of Asilla's behavior-recognition “AI Security asilla” on all 20 existing cameras at Kakio and Tamagawa-Gakuen-mae stations. It ran from 10 October 2024 to 9 January 2025. It tested detection of falls from the platform, wheelchair and white-cane users, people lingering on the platform, disputes between passengers and suspicious objects. Results were not reported. Romanizations of station names are ours; the sources give them in Japanese.",
            "benefit_type": "Increased Product Safety"
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "account",
            "benefit_type"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "outcomes[].distribution": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "outcomes[].duration": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "outcomes[].id": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "outcomes[].stakeholder_group": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "ratings": [
              {
                "group": "personal",
                "reason": "No fall, alert or prevented accident is reported by any source."
              },
              {
                "group": "organizational",
                "reason": "The operator describes the intended staff workflow; no count of alerts, false alarms or staff time saved is published."
              }
            ]
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "ratings"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "outcomes[].status": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "outcomes[].tradeoffs": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "outcomes[].unexpected": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "unexpected": false,
            "purpose": "Built to detect people falling from the platform onto the tracks or lingering at the platform edge and alert station staff. No detection event is documented."
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "unexpected",
            "purpose"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "places[]": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "location": "Kyōdō and Soshigaya-Ōkura stations, Odakyu Line, Japan",
            "developer_country": "Japan",
            "deployer_country": "Japan"
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "location",
            "developer_country",
            "deployer_country"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "purpose": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "purpose": "Built to detect people falling from the platform onto the tracks or lingering at the platform edge and alert station staff. No detection event is documented."
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "purpose"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "record_dates": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "date_observed": "2020-04-01",
            "revisions": [
              {
                "date": "2026-10-20",
                "change": "Record drafted from the cited sources.",
                "editor": "AIBD"
              },
              {
                "date": "2026-10-21",
                "change": "Benefit type set to Increased Product Safety under Trustible's full taxonomy of 23 types; it was Improved Organizational Efficiency among the six first used.",
                "source": "https://trustible.ai/post/a-framework-for-measuring-the-benefits-of-ai/",
                "editor": "AIBD"
              },
              {
                "date": "2026-10-21",
                "change": "Added what happened since from the cited sources.",
                "source": "https://www.watch.impress.co.jp/docs/news/1629496.html",
                "editor": "AIBD"
              },
              {
                "date": "2026-10-21",
                "change": "Country of the developer and the deployer added from the organization's own site or a registry.",
                "source": "https://ja.wikipedia.org/wiki/%E3%83%91%E3%83%8A%E3%82%BD%E3%83%8B%E3%83%83%E3%82%AF_%E3%82%B3%E3%83%8D%E3%82%AF%E3%83%88; https://en.wikipedia.org/wiki/Odakyu_Electric_Railway",
                "editor": "AIBD"
              },
              {
                "date": "2026-10-21",
                "change": "Prose pass: account, purpose, the system's part rewritten in shorter sentences with abbreviations expanded; facts, figures and quotations unchanged.",
                "editor": "AIBD"
              }
            ]
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "date_observed",
            "revisions"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "replication.attempts[]": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "replication": {
              "produced_by": [
                "Existing station cameras covering the platform edge and track at two stations",
                "Panasonic deep-learning image analysis trained from December 2019 to set detection areas and tell people from trains",
                "A dedicated terminal in the station office that shows the alert and video for staff to act on"
              ],
              "must_hold": [
                "Station staff present to confirm the alert and order an emergency stop",
                "Detection areas calibrated per camera; the sources give no accuracy or false-alarm figures"
              ],
              "echoes": [
                {
                  "date": "2024-10-10",
                  "setting": "Trial of Asilla's “AI Security asilla” behavior-recognition AI on 20 existing cameras at Kakio and Tamagawa-Gakuen-mae stations, 10 October 2024 to 9 January 2025, including detection of falls from the platform",
                  "model_version": "AI Security asilla",
                  "outcome": "unknown",
                  "source": "Impress Watch, 7 October 2024, https://www.watch.impress.co.jp/docs/news/1629496.html"
                }
              ]
            }
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "replication"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "replication.conditions": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "replication": {
              "produced_by": [
                "Existing station cameras covering the platform edge and track at two stations",
                "Panasonic deep-learning image analysis trained from December 2019 to set detection areas and tell people from trains",
                "A dedicated terminal in the station office that shows the alert and video for staff to act on"
              ],
              "must_hold": [
                "Station staff present to confirm the alert and order an emergency stop",
                "Detection areas calibrated per camera; the sources give no accuracy or false-alarm figures"
              ],
              "echoes": [
                {
                  "date": "2024-10-10",
                  "setting": "Trial of Asilla's “AI Security asilla” behavior-recognition AI on 20 existing cameras at Kakio and Tamagawa-Gakuen-mae stations, 10 October 2024 to 9 January 2025, including detection of falls from the platform",
                  "model_version": "AI Security asilla",
                  "outcome": "unknown",
                  "source": "Impress Watch, 7 October 2024, https://www.watch.impress.co.jp/docs/news/1629496.html"
                }
              ]
            }
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "replication"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "revision_history[]": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "revisions": [
              {
                "date": "2026-10-20",
                "change": "Record drafted from the cited sources.",
                "editor": "AIBD"
              },
              {
                "date": "2026-10-21",
                "change": "Benefit type set to Increased Product Safety under Trustible's full taxonomy of 23 types; it was Improved Organizational Efficiency among the six first used.",
                "source": "https://trustible.ai/post/a-framework-for-measuring-the-benefits-of-ai/",
                "editor": "AIBD"
              },
              {
                "date": "2026-10-21",
                "change": "Added what happened since from the cited sources.",
                "source": "https://www.watch.impress.co.jp/docs/news/1629496.html",
                "editor": "AIBD"
              },
              {
                "date": "2026-10-21",
                "change": "Country of the developer and the deployer added from the organization's own site or a registry.",
                "source": "https://ja.wikipedia.org/wiki/%E3%83%91%E3%83%8A%E3%82%BD%E3%83%8B%E3%83%83%E3%82%AF_%E3%82%B3%E3%83%8D%E3%82%AF%E3%83%88; https://en.wikipedia.org/wiki/Odakyu_Electric_Railway",
                "editor": "AIBD"
              },
              {
                "date": "2026-10-21",
                "change": "Prose pass: account, purpose, the system's part rewritten in shorter sentences with abbreviations expanded; facts, figures and quotations unchanged.",
                "editor": "AIBD"
              }
            ]
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "revisions"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "sector": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "domain": "Railway safety / platform fall detection",
            "segment": "Station platform monitoring"
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "domain",
            "segment"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "sources[].access_version": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "sources[].citation_locator": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "evidence": [
              {
                "kind": "news report",
                "citation": "Impress Watch (2020). 既設の駅構内カメラで転落者自動検知。小田急. 31 March 2020.",
                "title": "既設の駅構内カメラで転落者自動検知。小田急",
                "url": "https://www.watch.impress.co.jp/docs/news/1243957.html",
                "date": "2020-03-31",
                "written_by": "independent",
                "quote": "ホームから線路への転落者を自動検知、駅係員に通知する「転落検知システム」の運用を4月1日より開始。小田急線経堂駅と祖師ヶ谷大蔵駅に設置される。"
              },
              {
                "kind": "press release",
                "citation": "Odakyu Electric Railway (2020). 小田急電鉄、既設の駅構内カメラを活用した「転落検知システム」を運用開始. Press release of 30 March 2020, republished by Nikkei.",
                "title": "小田急電鉄、既設の駅構内カメラを活用した「転落検知システム」を運用開始",
                "url": "https://www.nikkei.com/article/DGXLRSP531980_Q0A330C2000000/",
                "date": "2020-03-30",
                "written_by": "deployer",
                "quote": "パナソニックが有する画像解析とディープラーニング（深層学習）技術を鉄道環境に応用し、既設の駅構内カメラの映像をリアルタイムに解析を行い"
              },
              {
                "kind": "news report",
                "citation": "Impress Watch (2024). 小田急、駅構内カメラ映像に行動認識AI　転落や車いす、不審者検知. 7 October 2024 (the Asilla trial echo).",
                "title": "小田急、駅構内カメラ映像に行動認識AI　転落や車いす、不審者検知",
                "url": "https://www.watch.impress.co.jp/docs/news/1629496.html",
                "date": "2024-10-07",
                "written_by": "independent",
                "quote": "ホームからの転落や車いす利用者、不審者・不審物を適正に検知可能かを検証する。"
              }
            ]
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "evidence"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "sources[].id": {
        "state": "value_present",
        "value": {
          "kind": "identifiers",
          "identifiers": [
            "AIBD-0307-source-0001",
            "AIBD-0307-source-0002",
            "AIBD-0307-source-0003"
          ],
          "role": "Existing evidence items, in their original order"
        },
        "provenance": {
          "kind": "curatorial",
          "basis": "Stable within the fingerprinted record version; no source content or source review has been added.",
          "record_fields": [],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "complete"
      },
      "sources[].language": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "sources[].relationship": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "evidence": [
              {
                "kind": "news report",
                "citation": "Impress Watch (2020). 既設の駅構内カメラで転落者自動検知。小田急. 31 March 2020.",
                "title": "既設の駅構内カメラで転落者自動検知。小田急",
                "url": "https://www.watch.impress.co.jp/docs/news/1243957.html",
                "date": "2020-03-31",
                "written_by": "independent",
                "quote": "ホームから線路への転落者を自動検知、駅係員に通知する「転落検知システム」の運用を4月1日より開始。小田急線経堂駅と祖師ヶ谷大蔵駅に設置される。"
              },
              {
                "kind": "press release",
                "citation": "Odakyu Electric Railway (2020). 小田急電鉄、既設の駅構内カメラを活用した「転落検知システム」を運用開始. Press release of 30 March 2020, republished by Nikkei.",
                "title": "小田急電鉄、既設の駅構内カメラを活用した「転落検知システム」を運用開始",
                "url": "https://www.nikkei.com/article/DGXLRSP531980_Q0A330C2000000/",
                "date": "2020-03-30",
                "written_by": "deployer",
                "quote": "パナソニックが有する画像解析とディープラーニング（深層学習）技術を鉄道環境に応用し、既設の駅構内カメラの映像をリアルタイムに解析を行い"
              },
              {
                "kind": "news report",
                "citation": "Impress Watch (2024). 小田急、駅構内カメラ映像に行動認識AI　転落や車いす、不審者検知. 7 October 2024 (the Asilla trial echo).",
                "title": "小田急、駅構内カメラ映像に行動認識AI　転落や車いす、不審者検知",
                "url": "https://www.watch.impress.co.jp/docs/news/1629496.html",
                "date": "2024-10-07",
                "written_by": "independent",
                "quote": "ホームからの転落や車いす利用者、不審者・不審物を適正に検知可能かを検証する。"
              }
            ]
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "evidence"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "sources[].upstream_sources": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "strategic_assessments[]": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "strategic assessments"
      },
      "summary": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "summary": "From 1 April 2020 Odakyu's system analyzes existing platform camera video to flag people who fall onto the tracks or linger at the platform edge and alerts station staff; no outcomes are reported.",
            "account": "Odakyu Electric Railway announced on 30 March 2020 (press release republished by Nikkei) a 転落検知システム (fall detection system). It would operate from the first train on 1 April 2020 at Kyōdō (経堂) and Soshigaya-Ōkura (祖師ヶ谷大蔵) stations on the Odakyu Line. It uses video from existing station cameras. Built with Panasonic System Solutions Japan, the system applies Panasonic's image-analysis and deep-learning technology to analyze the camera feeds in real time. It alerts a dedicated terminal in the station office, showing the camera image, when it detects a person fallen from the platform onto the tracks. It does the same for a person who has stayed at the platform edge for a set time and risks contact with a train. Staff can then take safety measures such as an emergency stop. Pre-learning to set each camera's detection area and to distinguish people from trains had run at both stations since December 2019. Impress Watch reported the launch on 31 March 2020. Neither source reports any detection, prevented accident or performance figure, and no later outcome report was found. Impress Watch (7 October 2024) reported a separate trial of Asilla's behavior-recognition “AI Security asilla” on all 20 existing cameras at Kakio and Tamagawa-Gakuen-mae stations. It ran from 10 October 2024 to 9 January 2025. It tested detection of falls from the platform, wheelchair and white-cane users, people lingering on the platform, disputes between passengers and suspicious objects. Results were not reported. Romanizations of station names are ours; the sources give them in Japanese."
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "summary",
            "account"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "systems[].autonomy_permissions": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "systems[].component_role": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "systems[].deployment_configuration": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "systems[].inputs_outputs": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "systems[].model_name": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "systems[].model_version": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "systems[].product_name": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "system": "転落検知システム (fall detection system): Panasonic image-analysis and deep-learning on existing station cameras"
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "system"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "systems[].provider": {
        "state": "value_present",
        "value": {
          "kind": "structured",
          "data": {
            "application_developer": "Panasonic System Solutions Japan, with Odakyu Electric Railway"
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Mapped from the existing case description without a new external source review.",
          "record_fields": [
            "developer"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "taxonomy_crosswalks[]": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "title": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "title": "Odakyu Electric Railway starts a Panasonic deep-learning “fall detection system” on existing station cameras at Kyōdō and Soshigaya-Ōkura stations",
            "headline": "Odakyu starts Panasonic fall-detection AI on station cameras"
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "title",
            "headline"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "version": {
        "state": "value_present",
        "value": {
          "kind": "identifiers",
          "identifiers": [
            "c44bc917ed3fdf686824c871338c7e216102b6fb829b483716a82177e1352767"
          ],
          "role": "SHA-256 of normalized original case data"
        },
        "provenance": {
          "kind": "curatorial",
          "basis": "Deterministic content version assigned by the local migration.",
          "record_fields": [],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "complete"
      },
      "workflow": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "account": "Odakyu Electric Railway announced on 30 March 2020 (press release republished by Nikkei) a 転落検知システム (fall detection system). It would operate from the first train on 1 April 2020 at Kyōdō (経堂) and Soshigaya-Ōkura (祖師ヶ谷大蔵) stations on the Odakyu Line. It uses video from existing station cameras. Built with Panasonic System Solutions Japan, the system applies Panasonic's image-analysis and deep-learning technology to analyze the camera feeds in real time. It alerts a dedicated terminal in the station office, showing the camera image, when it detects a person fallen from the platform onto the tracks. It does the same for a person who has stayed at the platform edge for a set time and risks contact with a train. Staff can then take safety measures such as an emergency stop. Pre-learning to set each camera's detection area and to distinguish people from trains had run at both stations since December 2019. Impress Watch reported the launch on 31 March 2020. Neither source reports any detection, prevented accident or performance figure, and no later outcome report was found. Impress Watch (7 October 2024) reported a separate trial of Asilla's behavior-recognition “AI Security asilla” on all 20 existing cameras at Kakio and Tamagawa-Gakuen-mae stations. It ran from 10 October 2024 to 9 January 2025. It tested detection of falls from the platform, wheelchair and white-cane users, people lingering on the platform, disputes between passengers and suspicious objects. Results were not reported. Romanizations of station names are ours; the sources give them in Japanese.",
            "replication": {
              "produced_by": [
                "Existing station cameras covering the platform edge and track at two stations",
                "Panasonic deep-learning image analysis trained from December 2019 to set detection areas and tell people from trains",
                "A dedicated terminal in the station office that shows the alert and video for staff to act on"
              ],
              "must_hold": [
                "Station staff present to confirm the alert and order an emergency stop",
                "Detection areas calibrated per camera; the sources give no accuracy or false-alarm figures"
              ],
              "echoes": [
                {
                  "date": "2024-10-10",
                  "setting": "Trial of Asilla's “AI Security asilla” behavior-recognition AI on 20 existing cameras at Kakio and Tamagawa-Gakuen-mae stations, 10 October 2024 to 9 January 2025, including detection of falls from the platform",
                  "model_version": "AI Security asilla",
                  "outcome": "unknown",
                  "source": "Impress Watch, 7 October 2024, https://www.watch.impress.co.jp/docs/news/1629496.html"
                }
              ]
            }
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "account",
            "replication"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      }
    },
    "summary": {
      "total": 91,
      "addressed": 91,
      "known": 27,
      "reviewed": 0,
      "record_mapped": 27,
      "not_assessed": 64,
      "complete": false,
      "by_state": {
        "value_present": 27,
        "not_reported": 0,
        "unresolved": 0,
        "not_assessed": 64,
        "not_applicable": 0,
        "withheld": 0,
        "source_unavailable": 0
      }
    }
  }
}