Haar Wavelets and Edge Orientation Histograms for On–Board Pedestrian Detection

www.cvc.uab.es/adas Abstract. On–board pedestrian detection is a key task in advanced driver assistance systems. It involves dealing with aspect–changing ob-jects in cluttered environments, and working in a wide range of distances, and often relies on a classification step that labels image regions of inter-est as pedestrians or non–pedestrians. The performance of this classifier is a crucial issue since it represents the most important part of the de-tection system, thus building a good classifier in terms of false alarms, missdetection rate and processing time is decisive. In this paper, a pedes-trian classifier based on Haar wavelets and edge orientation histograms (HW+EOH) with AdaBoost is compared with the current state–of– the–art best human–based classifier: support vector machines using his-tograms of oriented gradients (HOG). The results show that HW+EOH classifier achieves comparable false alarms/missdetections tradeoffs but at much lower processing time than HOG.