Nighttime vehicle detection and classification via headlights trajectories matching

Vehicle detection and classification is an essential application in traffic surveillance system (TSS). However, recognizing moving vehicle at nighttime is more challenging because of either poorly (lack of street lights) or brightly illuminations and chaos traffic of motorbikes. Adding to this is various type of vehicles travels on the same road which falsifies the pairing results. So, this research proposes an algorithm for vehicle detection and classification at nighttime surveillance scenes which consists of headlight segmentation, headlight detection, headlight tracking and pairing and vehicle classification (two-wheeled and four-wheeled vehicles). First, bright objects are segmented by using the luminance and color variations. Then, the candidate headlights are detected and validated through the characteristics of the headlights such as area, centroid, rims, and shape. Afterward, we present a way to tracking and pairing the headlights by calculating the area ratio, spatial information on the vertical and horizontal of a headlight. Finally, the vehicle is classified into two-wheeled and four-wheeled vehicles. The novelty of our work is that headlights are validated and paired using trajectory tracing technique. The evaluation results are promising for a detection rate of 81.19% in nighttime scenes.