Anomaly Candidate Identification and Starting Time Estimation of Vehicles from Traffic Videos

Gaoang Wang, Xinyu Yuan, Aotian Zheng, Hung-Min Hsu, Jenq-Neng Hwang; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2019, pp. 382-390

Abstract


Anomaly event detection on road traffic has been a challenging field mainly due to lack of training data and a wide variety of anomaly cases. In this paper, we propose a novel two-stage framework for anomaly event detection inroad traffic based on anomaly candidate identification and starting time estimation of vehicles. First, we use Gaussian mixture models (GMMs) to generate the foreground mask and background image to identify the anomaly candidates. Foreground mask is used to produce the region of interest (ROI) to filter out the noise from the object detector, YOLOv3, in the background image. Then, we apply the TrackletNet Tracker (TNT) to extract the trajectory of anomaly candidate to estimate the anomaly starting time. Experimental results, with achieved S3 score performanceof93.62%, on the Track 3 testing set of CVPR AI CityChallenge 2019 City Flow dataset, show the effectiveness of the proposed framework and its robustness in different real scenes.

Related Material


[pdf]
[bibtex]
@InProceedings{Wang_2019_CVPR_Workshops,
author = {Wang, Gaoang and Yuan, Xinyu and Zheng, Aotian and Hsu, Hung-Min and Hwang, Jenq-Neng},
title = {Anomaly Candidate Identification and Starting Time Estimation of Vehicles from Traffic Videos},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2019}
}