Abstract
Pedestrian detection based on images is one key technology of intelligent vehicles, and it is also widely applied in intelligent robots, intelligent surveillance. This paper mainly focuses on implementing a pedestrian detection system, which is classified by linear SVM with optimized Hog (Histograms of Oriented Gradients) as the extracted features. Then some experiments were done to find out that how the changing resolution of training set, times of bootstrapping iterations and different size and steps of the sliding windows affect the overall performance of detecting systems.
Full Text 
Sign-in/Register to access full text options
Sign-in/Register to access full text options 
Published version (
Free)
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
