2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
The rapid recent advancements in the computation ability of everyday computers have made it possible to widely apply deep learning methods to the analysis of traffic surveillance videos. Traffic flow prediction, anomaly detection, vehicle re-identification, and vehicle tracking are basic components in traffic analysis. Among these applications, traffic flow prediction, or vehicle speed estimation, is one of the most important research topics of recent years. Good solutions to this problem could prevent traffic collisions and help improve road planning by better estimating transit demand. In the 2018 NVIDIA AI City Challenge, we combine modern deep learning models with classic computer vision approaches to propose an efficient way to predict vehicle speed. In this paper, we introduce some state-of-the-art approaches in vehicle speed estimation, vehicle detection, and object tracking, as well as our solution for Track 1 of the Challenge.
Shuai Hua, Manika Kapoor, and David Anastasiu. "Vehicle Tracking and Speed Estimation from Traffic Videos" 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2018). https://doi.org/10.1109/CVPRW.2018.00028
This article was published in S. Hua, M. Kapoor and D. C. Anastasiu, "Vehicle Tracking and Speed Estimation from Traffic Videos," 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Salt Lake City, Utah, USA, 2019, pp. 153-1537.; the final form of this article can be found at http://doi.ieeecomputersociety.org/10.1109/CVPRW.2018.00028
© 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.