RT Journal Article
T1 Automated detection of vehicles with anomalous trajectories in traffic surveillance videos.
A1 Fernández-Rodríguez, Jose David
A1 García-González, Jorge
A1 Benítez-Rochel, Rafaela
A1 Molina-Cabello, Miguel Ángel
A1 Ramos-Jiménez, Gonzalo Pascual
A1 López-Rubio, Ezequiel
K1 Videovigilancia electrónica
K1 Visión artificial (Robótica)
K1 Demodulación (Electrónica)
AB Video feeds from traffic cameras can be useful for many purposes, the most critical of which are related to monitoringroad safety. Vehicle trajectory is a key element in dangerous behavior and traffic accidents. In this respect, it is crucial to detectthose anomalous vehicle trajectories, that is, trajectories that depart from usual paths. In this work, a model is proposed toautomatically address that by using video sequences from traffic cameras. The proposal detects vehicles frame by frame, trackstheir trajectories across frames, estimates velocity vectors, and compares them to velocity vectors from other spatially adjacenttrajectories. From the comparison of velocity vectors, trajectories that are very different (anomalous) from neighboring trajectoriescan be detected. In practical terms, this strategy can detect vehicles in wrong-way trajectories. Some components of the model areoff-the-shelf, such as the detection provided by recent deep learning approaches; however, several different options are consideredand analyzed for vehicle tracking. The performance of the system has been tested with a wide range of real and synthetic trafficvideos.
PB IOS Press
YR 2023
FD 2023-05-10
LK https://hdl.handle.net/10630/30222
UL https://hdl.handle.net/10630/30222
LA eng
NO Fernández-Rodríguez, J. D., García-González, J., Benítez-Rochel, R., Molina-Cabello, M. A., Ramos-Jiménez, G., & López-Rubio, E. (2023). Automated detection of vehicles with anomalous trajectories in traffic surveillance videos. Integrated Computer-Aided Engineering, 30(3), 293–309.
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 21 ene 2026