Many techniques and models have been proposed for verhicles surveillance in highways. In the past, tracking algorithms based on Kalman filter have been largely used for their efficiency in the prediction and low computational cost. However, predictive filters can not solve long-lasting occlusions. In this paper, we propose a new mixed predictive and probabilistic tracking that exploits the advantages of predictive filters for moving vehicles and adopts probabilistic and appearance-based tracking for stopped vehicles. The proposed tracking is part of a complete video surveillance system, oriented to control tunnels and highways from cluttered views, that is implemented in an embedded DSP platform and provides background suppression, a novel shadow detection algorithm, tracking, and scene recognition module. The experimental results are obtained over several hours of videos acquired in pre-existing platforms of CCTV surveillance systems.
Predictive and Probabilistic Tracking to Detect Stopped Vehicles
2005-01-01
4566073 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
SYSTEMS AND METHODS TO DETECT VEHICLE QUEUE LENGTHS OF VEHICLES STOPPED AT A TRAFFIC LIGHT SIGNAL
Europäisches Patentamt | 2017
|Systems and methods to detect vehicle queue lengths of vehicles stopped at a traffic light signal
Europäisches Patentamt | 2018
|