PROJECT TITLE :

Enhanced fast compressive tracking based on adaptive measurement matrix

ABSTRACT:

Robust object tracking could be a difficult task as a result of of factors like create variation, illumination changes, abrupt motion and background muddle across the video sequence. With the introduction of the compressive sensing theory, researchers are provided with a brand new and effective approach of real-time object tracking. In this study, an enhanced quick compressive tracking based mostly on an adaptive measurement matrix is presented, which the authors have named 'adaptive quick compressive tracking’ (AFCT). The sparsity of the matrix and the number of columns are adaptively determined in keeping with the dimension of the Haar-like feature. This measurement matrix is mounted once it has been calculated when selecting a tracked rectangle region in the first frame. Unlike most of the existing compressive trackers, the proposed technique adopts a completely different adaptive measurement matrix for a completely different targeting object. Compared with the quick compressive tracking (FCT), each measurement part contains additional info for the first signal. So, stable object tracking is achieved by using fewer measurement parts. The proposed AFCT method will run in real time and outperforms FCT on many difficult video sequences in terms of potency, accuracy and robustness.