TY - BOOK
T1 - Evaluation of video detection systems. Volume 2, Effects of illumination conditions in the performance of video detection systems
AU - Medina, Juan C.
AU - Benekohal, R. F.
AU - Chitturi, Madhav V.
PY - 2009
Y1 - 2009
N2 - The evaluation of three Video Detection Systems (VDS) at an instrumented signalized intersection in Rantoul Illinois, at both stop bar and advance detection zones, was performed under a wide range of lighting and weather conditions. The evaluated VDS are: Autoscope, Iteris and Peek. This document describes the effects of different illumination conditions (dawn, sunny morning, cloudy noon, dusk, and night) on false, missed, stuck-on, and dropped calls (errors in detection). Results showed that the illumination conditions significantly affect the performance of VDS. The best performance was found during cloudy noon conditions, with false calls lower than 4% for four of the six detection zones, but for the other two zones false calls were up to 18% and up to 21%, missed calls lower than 1% at stop bar, and up to 2.8% at advance zones, stuck-on calls lower than 1%, and no dropped calls. During dawn, false calls increased for the three VDS (up to 23%), and missed calls increased by 18% only in one system in one specific zone. During a sunny morning, false calls increased in greater proportion in zones where vehicle shadows were more prominent (up to 21% at stop bar and up to 43% at advance zones). Results during the dusk condition followed trends similar to the dawn, but with higher increases in false calls (ranging from no change to about 50% increase), and higher increases in the missed calls observed for one VDS. Lastly, during night, false calls increased for specific zones and systems, and various trends with relatively small changes were found in terms of missed calls. The findings of this study are published in four separate volumes. The other three volumes cover the effects of detection zone configuration changes, windy conditions, and adverse weather conditions.
AB - The evaluation of three Video Detection Systems (VDS) at an instrumented signalized intersection in Rantoul Illinois, at both stop bar and advance detection zones, was performed under a wide range of lighting and weather conditions. The evaluated VDS are: Autoscope, Iteris and Peek. This document describes the effects of different illumination conditions (dawn, sunny morning, cloudy noon, dusk, and night) on false, missed, stuck-on, and dropped calls (errors in detection). Results showed that the illumination conditions significantly affect the performance of VDS. The best performance was found during cloudy noon conditions, with false calls lower than 4% for four of the six detection zones, but for the other two zones false calls were up to 18% and up to 21%, missed calls lower than 1% at stop bar, and up to 2.8% at advance zones, stuck-on calls lower than 1%, and no dropped calls. During dawn, false calls increased for the three VDS (up to 23%), and missed calls increased by 18% only in one system in one specific zone. During a sunny morning, false calls increased in greater proportion in zones where vehicle shadows were more prominent (up to 21% at stop bar and up to 43% at advance zones). Results during the dusk condition followed trends similar to the dawn, but with higher increases in false calls (ranging from no change to about 50% increase), and higher increases in the missed calls observed for one VDS. Lastly, during night, false calls increased for specific zones and systems, and various trends with relatively small changes were found in terms of missed calls. The findings of this study are published in four separate volumes. The other three volumes cover the effects of detection zone configuration changes, windy conditions, and adverse weather conditions.
UR - http://hdl.handle.net/2142/14258
M3 - Technical report
T3 - ICT Series
BT - Evaluation of video detection systems. Volume 2, Effects of illumination conditions in the performance of video detection systems
PB - Illinois Center for Transportation
CY - Urbana, Ill
ER -