Identifying interactions of vehicles on the road is important for accident analysis and driving behavior assessment. Our interactions include those with passing/passed, cut-in, crossing, frontal, on-coming, parallel driving vehicles, and ego-vehicle actions to change lane, stop, turn, and speeding. We use visual motion recorded in driving video taken by a dashboard camera to identify such interaction. Motion profiles from videos are filtered at critical positions, which reduces the complexity from object detection, depth sensing, target tracking, and motion estimation. The results are obtained efficiently, and the accuracy is also acceptable. The results can be used in driving video mining, traffic analysis, driver behavior understanding, etc.
Detecting Vehicle Interactions in Driving Videos via Motion Profiles
2020-09-20
1721330 byte
Conference paper
Electronic Resource
English
Vehicle–Bicyclist Dynamic Position Extracted From Naturalistic Driving Videos
Online Contents | 2016
|Vehicle-Bicyclist Dynamic Position Extracted From Naturalistic Driving Videos
Online Contents | 2017
|Method for detecting vehicle speed based on road monitoring videos
European Patent Office | 2015
|