Real-Time Humans Detection in Urban Scenes
Julien Bégard, Nicolas Allezard, Patrick Sayd · 2007
We address the issue of real-time pedestrians detection in a urban environment. This is a challenging task owing to the high variability of appearances and poses that humans can have and to the complexity of backgrounds. We propose a solution made of gradient-based local descriptors combined to form strong classifiers and organized in a cascaded detector. We developed for this an extension of the Histograms of Oriented Gradients (HOGs) and added a new component to the histogram which represents the strength of edges or the amount of information in the histogram support. We also implemented a learning algorithm based on Real Adaboost where two phases – selection first, then refinement of weights – provide more robustness to the detector. We evaluated our system by comparing it to the cascaded detector of Haar features of Viola & Jones [7] and to the SVM of HOGs features of Dalal & Triggs [1]. To ensure an equitable and valid comparison, we used the database proposed in [1]. Our system outperforms them in detection results and in time needs. 1