A Multi-Feature and Machine Learning Graded Pedestrian Detection Method

Ning Gao

《International Core Journal of Engineering》 5卷12期 (2019/11) Pp. 57-62

https://doi.org/10.6919/ICJE.201911_5(12).0008

摘要

Pedestrian detection is a hot topic in computer vision and has a wide application prospect in robotics, unmanned driving, virtual reality technology and some military fields. Pedestrians are in the most vulnerable position in the whole traffic system and are the most vulnerable people in traffic accidents. Data show that the number of casualties among pedestrians in traffic accidents is still high. In the field of computer vision and pattern recognition, a very important task is to make computers analyze images intelligently and understand images like people. If we can make the vehicle more intelligent and use pedestrian detection as a driver's assistant system, we can automatically detect the pedestrians in front of the vehicle. In this paper, based on artificial intelligence technology, multi-feature and machine learning hierarchical pedestrian detection methods are studied. It is expected that useful information can be obtained through uncertainty and machine learning to achieve a high degree of unity of theory and application, so as to better serve the development of artificial intelligence.

關鍵字

Pedestrian Detection ； Intelligence ； Traffic ； Artificial Intelligence

參考文獻

Ma Y, Lee E W M, Yuen R K K, et al. An Artificial Intelligence-Based Approach for Simulating Pedestrian Movement[J]. IEEE Transactions on Intelligent Transportation Systems, 2016, 17(11):3159-3170.

Htike K K, Hogg D. Adapting pedestrian detectors to new domains: A comprehensive review[J]. Engineering Applications of Artificial Intelligence, 2016, 50:142-158.

Xia D X, Su S Z, Geng L C, et al. Learning rich features from objectness estimation for human lying-pose detection[J]. Multimedia Systems, 2017, 23(4):515-526.

Bila C, Sivrikaya F, Khan M A, et al. Vehicles of the Future: A Survey of Research on Safety Issues[J]. IEEE Transactions on Intelligent Transportation Systems, 2016, PP(99):1-20.

Baltieri D, Vezzani R, Cucchiara R. Mapping Appearance Descriptors on 3D Body Models for People Re-identification[J]. International Journal of Computer Vision, 2015, 111(3):345-364.