Moving Target Detection and Tracking for Smartphone Automatic Focusing

[Abstract] In this paper, a non⁃contact auto⁃focusing method is proposed for the essential function of auto⁃focusing in mobile devices. Firstly, we introduce an effective target detection method combining the 3⁃frame difference algorithm and Gauss mixture model, which is robust for complex and changing background. Secondly, a stable tracking method is proposed using the local binary patter feature and camshift tracker. Auto⁃focusing is achieved by using the coordinate obtained during the detection and tracking procedure. Experiments show that the proposed method can deal with complex and changing background. When there exist multiple moving objects, the proposed method also has good detection and tracking performance. The proposed method implements high efficiency, which means it can be easily used in real mobile device systems.

[Keywords] moving target detection; frame⁃difference method; background modeling method; camshift tracking; meanshift tracking; auto⁃focusing