Title :
Pedestrian detection with a Large-Field-Of-View deep network
Author :
Angelova, Anelia ; Krizhevsky, Alex ; Vanhoucke, Vincent
Author_Institution :
Google Res., Mountain View, CA, USA
Abstract :
Pedestrian detection is of crucial importance to autonomous driving applications. Methods based on deep learning have shown significant improvements in accuracy, which makes them particularly suitable for applications, such as pedestrian detection, where reducing the miss rate is very important. Although they are accurate, their runtime has been at best in seconds per image, which makes them not practical for onboard applications. We present a Large-Field-Of-View (LFOV) deep network for pedestrian detection, that can achieve high accuracy and is designed to make deep networks work faster for detection problems. The idea of the proposed Large-Field-of-View deep network is to learn to make classification decisions simultaneously and accurately at multiple locations. The LFOV network processes larger image areas at much faster speeds than typical deep networks have been able to, and can intrinsically reuse computations. Our pedestrian detection solution, which is a combination of a LFOV network and a standard deep network, works at 280 ms per image on GPU and achieves 35.85 average miss rate on the Caltech Pedestrian Detection Benchmark.
Keywords :
learning (artificial intelligence); object detection; pedestrians; Caltech pedestrian detection benchmark; LFOV deep network; deep learning; large-field-of-view deep network; Computer architecture; Context; Graphics processing units; Microprocessors; Proposals; Standards; Training;
Conference_Titel :
Robotics and Automation (ICRA), 2015 IEEE International Conference on
Conference_Location :
Seattle, WA
DOI :
10.1109/ICRA.2015.7139256