Search

[EN] Pedestrian detection is a particular case of object detection that helps to reduce accidents in advanced driver-assistance systems and autonomous vehicles. It is not an easy task because of the variability of the objects and the time constraints. A performance comparison of object detection methods, including both GPU and non-GPU implementations over a variety of on-road specific databases, is provided. Computer vision multi-class object detection can be integrated on sensor fusion modules where recall is preferred over precision. For this reason, ad hoc training with a single class for pedestrians has been performed and we achieved a significant increase in recall. Experiments have been carried out on several architectures and a special effort has been devoted to achieve a feasible computational time for a real-time system. Finally, an analysis of the input image size allows to fine-tune the model and get better results with practical costs., The author(s) disclosed receipt of the following financial support for the research, authorship, and/or publication of this article: This work was supported by PRYSTINE project which had received funding within the Electronic Components and Systems for European Leadership Joint Undertaking (ECSEL JU) in collaboration with the European Union's H2020 Framework Programme and National Authorities, under grant agreement no. 783190. It was also funded by Generalitat Valenciana through the Instituto Valenciano de Competitividad Empresarial (IVACE).