Abstract
A novel pedestrian detection system based on vision in urban traffic situations is presented to help the driver perceive the pedestrian ahead of the vehicle. To enhance the accuracy and to decrease the time spent on pedestrian detection in such complicated situations, the pedestrian is detected by dividing their body into several parts according to their corresponding features in the image. The candidate pedestrian leg is segmented based on the gentle AdaBoost algorithm by training the optimized histogram of gradient features. The candidate pedestrian head is located by matching the pedestrian head and shoulder model above the region of the candidate leg. Then the candidate leg, head and shoulder are combined by parts constraint and threshold adjustment to verify the existence of the pedestrian. Finally, the experiments in real urban traffic circumstances were conducted. The results show that the proposed pedestrian detection method can achieve pedestrian detection rate of 92.1% with the average detection time of 0.2257 s.
Highlights
With the increase of automobile ownership and rapid development of transportation infrastructures, numerous traffic accidents have done great damage to human lives and properties, as well as to national economies every year all over the world
This paper presents a novel pedestrian detection system based on vision to realize active pedestrian protection in urban traffic situations
Unlike the traditional histograms of oriented gradient (HOG) based pedestrian method utilizing linear support vector machine (SVM) to train the samples, the weighted linear discriminant analysis (WLDA) is adopted to reduce the dimension of HOG features and the conventional threshold weak classifiers are replaced by look-up table (LUT) weak classifiers
Summary
With the increase of automobile ownership and rapid development of transportation infrastructures, numerous traffic accidents have done great damage to human lives and properties, as well as to national economies every year all over the world. With an aim trying to protect pedestrians from being hurt and avoiding great damage when the crashes happen, studies of automobile passive safety technologies mainly concentrate on pedestrian-friendly vehicle design, collision bumper, biomechanics, crash reconstruction analysis, and so on. The goal of automobile active safety designs for pedestrian protection is to avoid a pedestrian crash or reduce the impact speed based on the pedestrian detecting results [10]. Studies show that effective active crash avoidance measures combining perfect active safety system applied to automobile can provide greater possibility of implementing additional passive deployable features to ensure better protection for pedestrians, such as bumper airbag and hood leading edge airbag. This paper presents a novel pedestrian detection system based on vision to realize active pedestrian protection in urban traffic situations.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
