Video detection has become increasingly popular for presence detection atsignalized intersections because of its versatility and ease of installation. However,several reports have documented performance problems in specific systems. Thispaper quantifies the performance of three different commercially available videodetection systems. The systems were tested in May and September 2005 for presencedetection accuracy.Prior to the May 2005 test, a representative from each vendor configured thevideo detection zones to match the loop detection zones as closely as possible. Theoutputs from the loop detection for the through-right and left-turn lane groups werecompared with the corresponding output from each of the video detection systems.Whenever there was a discrepancy between the loop and video, a digital video wasobserved to determine the cause of the discrepancy.Missed calls and false calls were categorized for each system. The errors werealso 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 5seconds ranged from 9 to 147, and the number of false calls longer than 5 secondsranged from 14 to 159. The loop detectors had one false call longer than 5 seconds andone missed call longer than five seconds during both tests.Although technology has advanced in the two years since this test wascompleted, the results documented in this paper apply to a large number of installationsthat have not been upgraded since the Fall of 2005. Furthermore, this paper highlightsthe importance of developing rigorous detection performance specifications so agenciescan make informed decision about the relative advantages and disadvantages ofalternative detection technology.