Robust Object Tracking Based on Simplified Codebook Masked Camshift Algorithm

Abstract EN

Moving targets detection and tracking is an important and basic issue in the field of intelligent videosurveillance.

The classical Codebook algorithm is simplified in this paper by introducing the average intensityinto the Codebook model instead of the original minimal and maximal intensities.

And a hierarchical matchingmethod between the current pixel and codeword is also proposed according to the average intensity in the highand low intensity areas, respectively.

Based on the simplified Codebook algorithm, this paper then proposes arobust object tracking algorithm called Simplified Codebook Masked Camshift algorithm (SCMC algorithm),which combines the simplified Codebook algorithm and Camshift algorithm together.

It is designed toovercome the sensitiveness of traditional Camshift algorithm to background color interference.

It usessimplified Codebook to detect moving objects, whose result is employed to mask color probability distributionimage, based on which we then use Camshift to predict the centroid and size of these objects.

Experimentresults show that the proposed simplified Codebook algorithm simultaneously improves the detection accuracyand computational efficiency.

And they also show that the SCMC algorithm can significantly reduce thepossibility of false convergence and result in a higher correct tracking rate, as compared with the traditionalCamshift algorithm.