Speed Estimation and Abnormality Detection from Surveillance Cameras
Abstract
Motivated by the increasing industry trends towards autonomous driving, vehicles, and transportation we focus on developing a traffic analysis framework for the automatic exploitation of a large pool of available data relative to traffic applications. We propose a cooperative detection and tracking algorithm for the retrieval of vehicle trajectories in video surveillance footage based on deep CNN features that is ultimately used for two separate traffic analysis modalities: (a) vehicle speed estimation based on a state of the art fully automatic camera calibration algorithm and (b) the detection of possibly abnormal events in the scene using robust optical flow descriptors of the detected vehicles and Fisher vector representations of spatiotemporal visual volumes. Finally we measure the performance of our proposed methods in the NVIDIA AI CITY challenge evaluation dataset.
Cite
Text
Giannakeris et al. "Speed Estimation and Abnormality Detection from Surveillance Cameras." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018. doi:10.1109/CVPRW.2018.00020Markdown
[Giannakeris et al. "Speed Estimation and Abnormality Detection from Surveillance Cameras." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018.](https://mlanthology.org/cvprw/2018/giannakeris2018cvprw-speed/) doi:10.1109/CVPRW.2018.00020BibTeX
@inproceedings{giannakeris2018cvprw-speed,
title = {{Speed Estimation and Abnormality Detection from Surveillance Cameras}},
author = {Giannakeris, Panagiotis and Kaltsa, Vagia and Avgerinakis, Konstantinos and Briassouli, Alexia and Vrochidis, Stefanos and Kompatsiaris, Ioannis},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2018},
pages = {93-99},
doi = {10.1109/CVPRW.2018.00020},
url = {https://mlanthology.org/cvprw/2018/giannakeris2018cvprw-speed/}
}