摘要：AbstractThis paper demonstrates a method of identifying low performance vehicles in heterogeneous traffic on two-lane highways. Field data collected adopting video photographic survey technique was used to develop the method. Principal Component Analysis was used in the study to identify low performance vehicles based on sample outlier detection. Two parameters namely percent speed reduction and percent slower vehicles were identified and outliers were subsequently detected in multivariate settings. Around 33 percent of the total data points were detected as outliers and out of which around 29 percen t data points correspond to non-motorized vehicles. These outliers represent those vehicles that follow slower impeding vehicles by choice; no attempt of passing manoeuvre is usually made even if there is an opportunity to pass or dynamic characteristics of the vehicles do not permit them to perform passing manoeuvre. These vehicles in turn affect the traffic performance and therefore considered as low performance vehicles.
