Developing a robust vehicle tracking system is an active area of study in the field of automotive tracking. Such a system is also helpful in providing support to collision avoidance, lane change instructions and merge assistance. Fast Compressive Tracking (FCT) algorithm has recently been proposed for object tracking. FCT has not been explored on vehicle tracking datasets LISA and TME Motorway. In this paper, FCT has been evaluated in the context of LISA and TME Motorway datasets. Though sparsity has been exploited in FCT, the basic idea of feature selection is still the integral image representation (IIR) of a single image patch. It is proposed to modify the feature selection as a combination of both linear and nonlinear transformation of IIR of image sub-patches rather than a single image patch. The modified FCT (MFCT) has been evaluated using LISA and TME Motorway datasets which encompass varying traffic, weather, and road conditions. The proposed algorithm has been shown to perform better than the existing vehicle trackers in terms of true positive rate, false detection rate, accuracy, and centre location error.
Vehicle tracking using modified fast compressive tracking algorithm
01.07.2017
461397 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
IEEE | 2017
|Vehicle Tracking Algorithm using H Filter
British Library Online Contents | 2005
|VEHICLE TRACKING DEVICE, VEHICLE TRACKING METHOD, AND VEHICLE TRACKING PROGRAM
Europäisches Patentamt | 2020
|Compressive tracking based on online Hough forest
British Library Online Contents | 2017
|