基于稀疏模型和Gabor小波字典的跟踪算法

Tracking algorithm based on sparse model and Gabor wavelet dictionary

基于稀疏表示理论的目标跟踪方法可以通过激活少量神经元完成目标的动态跟踪,但是要求在当前图像背景中的遮挡或者目标物的姿态变化是可以进行稀疏表示的小面积范围.针对这一问题,基于Gabor函数和稀疏理论提出一种强鲁棒性的目标跟踪算法.该算法首先使用目标模板在初始帧中创建Gabor字典,其次使用该字典对候选目标完成稀疏表示,最后通过对Gabor字典的更新完成目标跟踪.实验结果表明了算法的有效性.

Adaptive tracking methods are widely used for object tracking in computer vision.In the tracking process,the features used to describe the target and candidate target have a great impact on the target tracking results.It is difficult to find the features of the target,especially in the case of illumination change,morphological change,complex background and occlusion.Although some breakthroughs have been made in visual tracking in recent years,it is still a challenging problem to develop a robust tracker for the complex and changing scenes,such as illumination variation,partial occlusion,back ground clutter and pose changes.In this paper,aiming at the change of illumination and pose variation,a new algorithm based on sparse model and Gabor wavelet dictionary is proposed,which is based on the feature extraction of Gabor function.The method builds a Gabor dictionary through the target template in the initial frame,and then the candidate object is represented by the Gabor dictionary in the tracking process.As a result,a more generalized and high-effective tracker is constructed.Experimentally,our algorithm is shown to be able able to outperform state-of-the-art trackers on various benchmark videos.The results show the effectiveness of the tracking algorithm.