Abstract

Many agencies nationwide have adopted video vehicle detection technology as an alternative to inductive loops. While many product evaluations have been performed, the majority of these evaluations have concentrated on freeway applications where speed and volume were the primary evaluation criteria. At an actuated intersection, the metrics of speed and volume do not necessarily represent how well a device will operate as a presence detector. Video detection was evaluated at two signalized intersections in West Lafayette, Indiana and Noblesville, Indiana. A camera on each approach was located at the vendor recommended position, at a height of 40 feet and offset so that the camera was approximately inline with the lane line dividing the left-turn lane and through lane. Two additional cameras were located on each approach at less optimal horizontal and vertical locations. Additionally at the West Lafayette site, a fourth camera was located directly above the stop bar so that it looked down onto the detection zone. Inductive loops were used as baseline data to screen for discrepancies. Each time the loop detectors were not in agreement with a specific video detector, a discrepancy was noted. A digital video recording was later observed to determine whether the video detector or the loop detector was in error. An analysis of the data showed video detection was found to produce statistically significantly more false detections and missed detections than the loop detectors on most phases. Generally, only very small variations in video detector performance were observed at the different camera locations. The video detection was also evaluated in terms of its’ consistency of detector turn-on and turn-off times. The video detection displays an undesirable inconsistency between night periods and day periods where it tends to activate 1 to 3 seconds earlier during the night period due to headlight reflections on the pavement. However, the camera at West Lafayette located directly above the stop bar displayed very consistent behavior between the night and day periods.

Abstract

Video detection has become increasingly popular for presence detection at signalized intersections because of its versatility. However, several reports have documented performance problems in specific systems. This paper quantifies the performance of three different commercially available video detection systems. The systems were tested in May and September 2005 for presence detection accuracy. Prior to the May 2005 test, a representative from each vendor configured the video detection zones to match the loop detection zone as closely as possible. The outputs from the loop detection for the through-right and left-turn lane groups were compared with the corresponding output from each of the video detection systems. Whenever there was a discrepancy between the loop and video, a digital video was observed to determine the cause of the discrepancy. Missed calls and false calls were categorized for each system. The errors were also categorized according to the impact that they would have on signal operations. During a 24hr test on two separate days, the number of missed detections longer than 5 seconds ranged from 9 to 147, and the number of false calls longer than 5 seconds ranged from 16 to 149.