DoTA: Unsupervised Detection of Traffic Anomaly in Driving Videos
Yu Yao, Xizi Wang, Mingze Xu +4
IEEE Transactions on Pattern Analysis and Machine Intelligence
Benchmark (surveying)
Video anomaly detection (VAD) has been extensively studied for static cameras but is much more challenging in egocentric driving videos where the scenes are extremely dynamic. This paper proposes an...
Thermal Infrared Image Colorization for Nighttime Driving Scenes With Top-Down Guided Attention
Fuya Luo, Yunhan Li, Guang Zeng +3
IEEE Transactions on Intelligent Transportation Systems
Computer science
Benefitting from insensitivity to light and high penetration of foggy environments, infrared cameras are widely used for sensing in nighttime traffic scenes. However, the low contrast and lack of...