作者: Gonçalo Monteiro , Miguel Ribeiro , João Marcos , Jorge Batista
DOI: 10.1007/978-3-540-74260-9_99
关键词: Wrong direction 、 ALARM 、 Robustness (computer science) 、 Mixture model 、 Optical flow 、 Image quality 、 Computer vision 、 Motion flow 、 Computer science 、 Surveillance camera 、 Artificial intelligence
摘要: In this paper a solution to detect wrong way drivers on highways is presented. The proposed based three main stages: Learning, Detection and Validation. Firstly, the orientation pattern of vehicles motion flow learned modelled by mixture gaussians. second stage (Detection Temporal Validation) applies model in order objects moving lane's opposite direction. third final uses an Appearance-based approach ensure detection vehicle before triggering alarm. This methodology has proven be quite robust terms different weather conditions, illumination image quality. Some experiments carried out with several movies from traffic surveillance cameras show robustness solution.