A fisheye-camera edge system detects potential bike-pedestrian collisions at intersections in real time, achieving 93.3% sensitivity and 92.3% specificity with a 3.3-second mean warning budget under simulated conditions.
Pedestrian crossing intention prediction from surveillance videos for over-the-horizon safety warning.IEEE Transac- tions on Intelligent Transportation Systems, 25(2):1394–1407
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Real-Time Bike-Pedestrian Safety System with Wide-Angle Perception and Evaluation Testbed for Urban Intersections
A fisheye-camera edge system detects potential bike-pedestrian collisions at intersections in real time, achieving 93.3% sensitivity and 92.3% specificity with a 3.3-second mean warning budget under simulated conditions.