Deep Spatio-Temporal Representation for Detection of Road Accidents Using Stacked Autoencoder

• Published in: IEEE transactions on intelligent transportation systems Vol. 20; no. 3; pp. 879 - 887
• Main Authors: Singh, Dinesh, Mohan, Chalavadi Krishna
• Format: Journal Article
• Language: English
• Published: IEEE 01.03.2019
• Subjects: Accident detection; Accidents; anomaly detection; deep learning; Feature extraction; stacked autoencoder; Target tracking; Trajectory; Urban areas; Videos

Vision-based detection of road accidents using traffic surveillance video is a highly desirable but challenging task. In this paper, we propose a novel framework for automatic detection of road accidents in surveillance videos. The proposed framework automatically learns feature representation from...