Detection of Motorcycles in Urban Traffic Using Video Analysis: A Review

Motorcycles are Vulnerable Road Users (VRU) and as such, in addition to bicycles pedestrians, they the traffic actors most affected by accidents urban areas. Automatic video processing for surveillance cameras has potential effectively detect track these road users. The present review focuses on algorithms used detection tracking of motorcycles, using infrastructure provided CCTV cameras. Given importance results achieved Deep Learning theory field computer vision, use such techniques motorcycles is also reviewed. paper ends describing performance measures generally used, publicly available datasets (introducing Urban Motorbike Dataset (UMD) with quantitative evaluation different detectors), discussing challenges ahead presenting a set conclusions proposed future work this evolving area.