Evaluation of Thermal Image Video Sensors for Stop Bar Detection at Signalized Intersections

Abstract

Thermal image sensors for stop bar presence detection have recently been introduced to the traffic industry as an alternative to cameras sensitive only to the visual spectrum. This new detection technology, from two manufacturers, was evaluated side by side with a video detection system. Inductive loops were used for a comparison to identify discrepancies that warranted the manual establishment of ground truth of the video images. The video camera and two thermal sensors operated simultaneously over a 24-h period, and discrepancies in the loop versus thermal or video detection calls were validated from recorded video. No missed call events longer than 10 s were observed, and only a modest number of false calls were made by the test systems. The bias in activation and termination times was also evaluated during day and night operation for each system. The study found that the median time difference in activating a detection zone was about 1 s when the day and night operations of the detection system were compared with a video camera. This finding is consistent with past studies that reported nighttime detection challenges related to headlight projections. However, the thermal cameras had virtually no change in median activation times when day and nighttime operations were compared. This encouraging finding suggests that integrating cameras sensitive to the infrared spectrum holds considerable promise for improving the quality of nighttime video detection.

Advanced Gap Seeking Logic for Actuated Signal Control Using Vehicle Trajectory Data: Proof of Concept

“…Some detection systems can identify vehicle positions and speeds, but the data are converted into detection zone occupancy because controllers cannot currently receive position and speed data from detectors. Radar detection systems have had this ability for several years, and advances in analysis of video, infrared, and LiDAR are likely to extend such capabilities to other systems in the future (28)(29)(30). If AIS technologies are employed for trajectory acquisition, they might achieve high levels of penetration more quickly than vehicle-to-infrastructure communication.…”

Understanding the Factors Underlying Variation in Detection Errors of Video- and Thermal-Imaging Cameras

“…To tackle the lighting issue associated with video-imaging cameras, thermal-imaging technology has recently found its application in vehicle detection and has been evaluated in different circumstances (12)(13)(14). Different from video-imaging cameras, thermal-imaging cameras produce images on the basis of difference in thermal energy emitted by objects and do not rely on visible light.…”