Ten Years of Pedestrian Detection, What Have We Learned?
This work provides a comprehensive review and incremental improvement for researchers in computer vision and pedestrian detection.
The paper analyzed a decade of pedestrian detection research by reviewing over 40 detectors in the Caltech benchmark, identifying three families of approaches with similar quality, and combined promising strategies to create a new decision forest detector that achieved state-of-the-art performance on the Caltech-USA dataset.
Paper-by-paper results make it easy to miss the forest for the trees.We analyse the remarkable progress of the last decade by discussing the main ideas explored in the 40+ detectors currently present in the Caltech pedestrian detection benchmark. We observe that there exist three families of approaches, all currently reaching similar detection quality. Based on our analysis, we study the complementarity of the most promising ideas by combining multiple published strategies. This new decision forest detector achieves the current best known performance on the challenging Caltech-USA dataset.