Detection and classification of vehicles from omnidirectional videos using multiple silhouettes

Abstract

To detect and classify vehicles in omnidirectional videos, we propose an approach based on the shape (silhouette) of the moving object obtained by background subtraction. Different from other shape-based classification techniques, we exploit the information available in multiple frames of the video. We investigated two different approaches for this purpose. One is combining silhouettes extracted from a sequence of frames to create an average silhouette, the other is making individual decisions for all frames and use consensus of these decisions. Using multiple frames eliminates most of the wrong decisions which are caused by a poorly extracted silhouette from a single video frame. The vehicle types we classify are motorcycle, car (sedan) and van (minibus). The features extracted from the silhouettes are convexity, elongation, rectangularity and Hu moments. We applied two separate methods of classification. First one is a flowchartbased method that we developed and the second is K-nearest neighbour classification. 60% of the samples in the dataset are used for training. To ensure randomization in the experiments, threefold cross-validation is applied. The results indicate that using multiple silhouettes increases the classification performance.

Classification of vehicles with omnidirectional and PTZ cameras

“…olarak ayrılmıştır. [5]'te ise, dışbükey-lik, uzanım, dikdörtgensellik ve Hu moment öznitelikleri çıkarılarak motosiklet, araba ve dolmuş ayırt edilmiştir. HOG öznitelikleri ile tümyönlü kameralarda nesne bulmaya örnek olarak HOG hesabı tümyönlü kameralara matematiksel olarak uyarlanarak yaya, araba ve dolmuş tespiti yapılmıştır [6], [7].…”

Combining Shape-Based and Gradient-Based Classifiers for Vehicle Classification

“…In a previous study, we showed that using multiple frames of a video has a better classification performance than using a single silhouette in a single frame [19]. Among a few approaches of using multiple silhouettes, 'average silhouette' was the best performing one.…”

“…In one of our previous studies with omnidirectional cameras [19], we detect each vehicle type separately using shape features extracted from the foreground silhouettes.…”

A Hybrid Camera System for High-Resolutionization of Target Objects in Omnidirectional Images

“…Recent studies of omnidirectional cameras have examined topics such as object recognition in omnidirectional images, coding of omnidirectional images, and combining omnidirectional images [14][15][16][17][18][19][20][21][22][23][24][25][26][27][32][33][34][35][36][37]. In one example of research on object recognition using omnidirectional cameras, Premachandra et al [35] proposed a moving object detection system for road intersections and demonstrated the advantages of using omnidirectional cameras for traffic surveillance.…”