Abstract
AbstractPedestrian detection is widely applied in surveillance, autonomous robotic navigation, and automotive safety. However, there are many occlusion problems in real life. This paper summarizes the research progress of pedestrian detection technology with occlusion. First, according to different occlusion, it can be divided into two categories: inter-class occlusion and intra-class occlusion. Second, it summarizes the traditional method and deep learning method to deal with occlusion. Furthermore, the main ideas and core problems of each method model are analyzed and discussed. Finally, the paper gives an outlook on the problems to be solved in the future development of pedestrian detection technology with occlusion.
Funder
China National Textile and Apparel Council
National Natural Science Foundation of China
Shaanxi Provincial Education Department
Publisher
Springer Science and Business Media LLC
Subject
General Earth and Planetary Sciences,General Environmental Science
Reference50 articles.
1. Risse B, Mangan M, Del Pero L, Webb B (2017) Visual tracking of small animals in cluttered natural environments using a freely moving camera. In: IEEE international conference on computer vision workshops (ICCVW) Venic, pp 2840–2849
2. Luo Y, Yin D, Wang A, Wu W (2018) Pedestrian tracking insurveillance video based on modified CNN. Multimed Tools Appl 77:24041–24058
3. Brunetti A, Buongiorno D, Trotta GF, Bevilacqua V (2018) Computer vision and deep learning techniques for pedestriandetection and tracking: a survey. Neuro Comput 300:17–33
4. Hou L, Wan W, Hwang JN, Muhammad R, Yang M, Han K (2017) Human tracking over camera networks: a review. Eurasip J Adv Signal Process 1:356–367
5. Chang M-F, Lambert J, Sangkloy P, Singh J, Sławomir B, Hartnett A, Wang D, Carr P, Lucey S, Ramanan D, Hays J (2019) Argoverse: 3D tracking and forecasting with rich maps. IEEE Conf Comput Vision Pattern Recognit, pp 8748–8757
Cited by
55 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献