Controlling Traffic Signals TRIZ Cases

A controller uses image sequences and optional radar to track traffic light motion and choose the best frame for reliable signal-state detection.

Gesture recognition paired with stored user profiles adapts vehicle settings to improve comfort while keeping function control intuitive and reliable.

Video analytics at controlled intersections identify unsafe red-light approaches and trigger in-vehicle warnings or forced braking to prevent collisions.

Camera-detected lane marks are tied to road segments to update shared AV navigation models while reducing map data volume and processing load.

Gesture-verified vehicle controls use stored user profiles to adapt commands, improving intuitive operation without manual setting changes.

Camera-detected lane arrows and marks update road-segment models with less map data, improving autonomous navigation through intersections.

Sparse maps use polynomial road features and key landmarks to cut storage and transfer needs while preserving autonomous navigation accuracy.

A sidewalk mat uses pedestrian weight to trigger crosswalk alert lights, avoiding push buttons and complex sensors for more reliable driver warning.

Probe data estimates whether an approaching vehicle can stop before an unsignalized intersection and warns nearby vehicles to slow or stop.

At unsignalized intersections, CAVs compare branch priority locally to coordinate entry times while cutting infrastructure, computation, and data exchange.

Roadside LED LiFi sends traffic data to vehicles through visible light, enabling reliable speed control without GPS or weather-sensitive sensing.

Cross-checking SPAT messages with nearby V2X vehicle data helps block unreliable traffic signal inputs before automated actions.

AI image processing in a roadside camera assesses sidewalk conditions in real time and sends alerts to vehicles and smartphones.