Optage and Sanyo Electric Railway trial AI crossing cameras

AI system

System: AI image analysis of crossing cameras on edge devices with special-signal-lamp and IP-VPN alerts
Model: Not assessed
Release: Not assessed
Application developer: Optage (with K4Digital for accuracy verification)
Role: Not assessed
Configuration: Not assessed
Inputs and outputs: Not assessed
Autonomy: Not assessed
Workflow: Existing crossing surveillance cameras. Edge-device inference and a special signal lamp link. A telecom partner supplying the analysis.
Human oversight: Not assessed
Relation to AI: Trial design only. No detection or accuracy results were published in the sources.
AI contribution: Not assessed

Outcome identifiers: Not assessed
Benefit: Mynavi News (12 Aug 2020, from a press release): edge-device AI detects people including prams and wheelchairs in crossings and signals drivers via special signal lamps and an IP-VPN link to the op...
Category: Increased Product Safety
Status: Not assessed
Beneficiary groups: Society. Organizations. People.
Beneficiaries: Not assessed
Reach: Not assessed
Distribution and access: Not assessed
Duration: Not assessed
Expected?: Yes
Costs and harms: Not assessed

Studies: Not assessed
Study design: Not assessed
Measurement: Not assessed
Setting and sample: Not assessed
Measures: Not assessed
Comparison: Assumed alternative: the conventional crossing-detection system (従来システム)
Results: Assumed comparison. Reference: 従来システムでは難しかった歩行者やベビーカー、車イスなどを含む"人"の検知. Result: AIの画像解析技術が活用されており.
Additional value from AI: Not assessed
Limitations: Not assessed
Denominators: Not assessed
Materials for replication: Not assessed

Participants: Developer: Optage (with K4Digital for accuracy verification). Operator: Sanyo Electric Railway and Sanyo Electric Railway Information Center (trial).
Jurisdictions: Developer: Japan. Operator: Japan.
Ownership and control: Not assessed
Dependencies: Not assessed
Cross-border connections: Not assessed
Geopolitical implications: Not assessed

Conditions for replication: Accuracy in rain and at night, which the trial set out to verify.
Replication attempts: 1 follow-up entries. Benefit recurred: 1.
Later findings: No source confirms whether the full deployment targeted for spring 2021 took place.
Availability: Not assessed
Institutional decision: Not assessed
Grounds: Not assessed
Action and result: Not assessed
Success criterion: Not assessed

Assessed benefits: Society. Organizations. People.
Depth: Not assessed
Reasons: Society: No outcome is documented. Organizations: No outcome is documented. People: No outcome is documented.
Observed or intended: Not assessed
Rubric: Not assessed
Assessor and date: Not assessed
Alternative assessments: Not assessed
Fill: Independently reported

Kind: Not assessed
Related entries: Not assessed
Field: Railway safety. Level-crossing obstacle detection.
Purpose: The trial was built to detect people in crossings in real time and alert train drivers.
Dates: Date basis unassessed: 2020 (precision unassessed). Updated: 21 October 2026.
Stage: Not assessed
Version: SHA-256: 875b7ddd759f…