为了解决跟踪漂移问题, 提出了一种利用黑洞原理改进的稀疏外观模型目标跟踪算法,用来提高目标跟踪的鲁棒性。利用黑洞原理从目标模板中搜索聚类中心来降低目标模板数量。通过学习分类器用于构造目标特征; 用黑洞原理获取模板字典表示目标; 采用高斯分布运动模型获取目标样本, 在贝叶斯框架下根据观测模型获取最优目标位置实现跟踪。不同视频序列被用于改进的稀疏外观模型跟踪算法和其他先进目标跟踪算法进行仿真实验。实验结果表明, 实现了目标跟踪的目的, 有效地降低了目标局部遮挡问题的影响, 提高了目标跟踪精度。

In order to alleviate the tracking drift problem and improve the robustness of target tracking, an improved sparse appearance model tracking algorithm based on the black hole theory is proposed. The algorithm is used to reduce the number of the target templates by searching cluster centers from the target templates via black hole. The learning classification is used to select features, and then the template dictionary, which represented the object, is obtained by using the principle of black hole. Lastly the target samples are got by Gaussian function, and the best target location is obtained by using observation model under the Bayesian filter framework. Numerous experiments results show that the improved sparse appearance model target tracking algorithm via black hole can be used to realize the purpose of the target tracking, effectively reduce the influence of the partial occlusion of the target and improve target tracking accuracy.