AI system
- System
-
踏切異常検知システム: 踏切滞留AI監視システム (skeleton-recognition AI) and 3D画像解析踏切監視システム (stereo-camera depth analysis)
- Model
-
Not assessed
- Release
-
Not assessed
- Application developer
-
OKI and Marubeni Network Solutions (AI system); Computer Systems Laboratory (3D image analysis)
- Role
-
Not assessed
- Configuration
-
Not assessed
- Inputs and outputs
-
Not assessed
- Autonomy
-
Not assessed
- Workflow
-
Camera coverage of smaller pedestrian crossings. Special signal lamps already used to warn drivers. A year-long trial before full operation.
- Human oversight
-
Not assessed
- Relation to AI
-
The AI detects and the signal lamps alert human drivers, who brake. No detection statistics are given.
- AI contribution
-
Not assessed
Benefits
- Outcome identifiers
-
Not assessed
- Benefit
-
Response.jp (11 Nov 2022): OKI and Marubeni Network Solutions' AI monitoring and a stereo-camera 3D system detect people or vehicles left in crossings, light special signal lamps for drivers and se...
- 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
Measurement
- Studies
-
Not assessed
- Study design
-
Not assessed
- Measurement
-
Not assessed
- Setting and sample
-
Not assessed
- Measures
-
Not assessed
- Comparison
-
Not assessed
- Results
-
Not assessed
- Additional value from AI
-
Not assessed
- Limitations
-
Not assessed
- Denominators
-
Not assessed
- Materials for replication
-
Not assessed
Money
- Kind of value
-
Not assessed
- Amount
-
Not assessed
- Currency and prices
-
Not assessed
- Period and unit
-
Not assessed
- Realization
-
Not assessed
- Recipients and payers
-
Not assessed
- Gross or net
-
Not assessed
- Included costs
-
Not assessed
- Comparison
-
Not assessed
- Method
-
Not assessed
- Return and payback
-
Not assessed
People and places
- Participants
-
Developer: OKI and Marubeni Network Solutions (AI system); Computer Systems Laboratory (3D image analysis). Operator: Seibu Railway.
- Jurisdictions
-
Developer:
Japan. Operator: Japan. - Ownership and control
-
Not assessed
- Dependencies
-
Not assessed
- Cross-border connections
-
Not assessed
- Geopolitical implications
-
Not assessed
Follow-up
- Conditions for replication
-
Detection remains reliable across weather and lighting. Drivers can stop in time once the lamp operates.
- Replication attempts
-
1 follow-up entries. Benefit recurred: 1.
- Later findings
-
No source after 14 November 2022 was available; the pre-launch report only states plans for two more crossings within fiscal 2022.
- Availability
-
Not assessed
- Institutional decision
-
Not assessed
- Grounds
-
Not assessed
- Action and result
-
Not assessed
- Success criterion
-
Not assessed
Evidence
- Source numbers
-
AIBD-0247-source-0001–0002
- Citations
-
Numbered references below.
- Language
-
Not assessed
- Source relationships
-
Independent
- Original evidence
-
Not assessed
- Access and versions
-
Not assessed
- Supported findings
-
Not assessed
- Evidence links
-
Not assessed
- Evidence strength
-
Not assessed
- Missing evidence
-
Not assessed
Grades
- Assessed benefits
-
Society. Organizations. People.
- Depth
-
Not assessed
- Reasons
-
Society: No outcome is documented. Organizations: Only stable operation in trials is reported. People: No individual outcome is documented.
- Observed or intended
-
Not assessed
- Rubric
-
Not assessed
- Assessor and date
-
Not assessed
- Alternative assessments
-
Not assessed
- Fill
-
Independently reported
Entry details
- Kind
-
Not assessed
- Related entries
-
Not assessed
- Field
-
Railway safety. Level-crossing obstacle detection.
- Purpose
-
The system is built to detect people or vehicles remaining inside a crossing and warn approaching train drivers.
- Dates
-
Date basis unassessed: 2022 (precision unassessed). Updated: 21 October 2026.
- Stage
-
Not assessed
- Version
-
SHA-256: 56ef2cfbd48e…
References
- Other identifiers
-
Not assessed
- Category mappings
-
Not assessed
- Brief
-
Not assessed
- Revisions
-
4 revisions. Latest: 21 October 2026.
Sources
-
News report Independent author
Response.jp (11 Nov 2022). 西武が踏切異常検知システムを本運用.
検知すると運転士へ危険を知らせる特殊信号発光機が作動
-
Registry label Independent author
OECD AI Incidents and Hazards Monitor, incident 2022-11-09-4a03: Seibu Railway Deploys AI-Based Crossing Detection to Prevent Accidents.
These real-time AI systems automatically alert train drivers to potential dangers, aiming to prevent accidents and enhance safety, especially at smaller pedestrian crossings.