联合特征融合和判别性外观模型的多目标跟踪  

Multi-target tracking algorithm based on feature fusion and discriminative appearance model

作　　者：黄奇[1,2] 项俊[3] 侯建华[1,2] 张华[1,2] 笪邦友[1,2] 

机构地区：[1]中南民族大学电子信息工程学院,武汉430074 [2]中南民族大学智能无线通信湖北省重点实验室,武汉430074 [3]华中科技大学自动化学院,武汉430074

出　　处：《中国图象图形学报》2015年第9期1188-1198,共11页Journal of Image and Graphics

基　　金：湖北省自然科学基金项目(2012FFA113);武汉市科技供需对接计划项目(201051824575);中南民族大学中央高校基本科研业务费专项资金(CZW14057;CZW15013)

摘　　要：目的针对基于检测的目标跟踪问题,提出一种联合多特征融合和判别性外观模型的多目标跟踪算法。方法对时间滑动窗内的检测器输出响应,采用双阈值法对相邻帧目标进行初级关联,形成可靠的跟踪片,从中提取训练样本;融合多个特征对样本进行鲁棒表达,利用Adaboost算法在线训练分类器,形成目标的判别性外观模型;再利用该模型对可靠的跟踪片进行多次迭代关联,形成目标完整的轨迹。结果 4个视频数据库的目标跟踪结果表明,本文算法能较好的处理目标间遮挡、目标自身形变,以及背景干扰。对TUD-Crossing数据库的跟踪结果进行了定量分析,本文算法的FAF(跟踪视频序列时,平均每帧被错误跟踪的目标数)为0.21、MT(在整个序列中,有超过80%视频帧被跟踪成功目标数占视频序列目标总数的比例)为84.6%、ML(在整个序列中,有低于20%视频帧被跟踪成功目标数占视频序列目标总数的比例)为7.7%、Frag(视频序列目标真值所对应轨迹在跟踪中断开的次数)为9、IDS(在跟踪中,目标身份的改变次数)为4;与其他同类型多目标跟踪算法相比,本文算法在FAF和Frag两个评估参数上表现出色。结论融合特征能对目标进行较为全面的表达、判别性外观模型能有效地应用于跟踪片关联,本文算法能实现复杂场景下的多目标跟踪,且可以应用到一些高级算法的预处理中,如行为识别中的轨迹检索。Objective A tracking-by-detection multi-target algorithm is proposed based on feature fusion and discriminative appearance models. Method To identify the responses of the detector in each sliding window, a dual-threshold strategy is adopted to perform low-level association and generate reliable traeklets between adjacent frames. Training samples are col- lected from these tracklets. Then, we merge several features to robustly describe the training samples and use the Ada- boost algorithm to train the classifier, i. e. , discriminative appearance model, online. Finally, the discriminative appear- ance model is used to link the tracklets into longer ones to form the final complete target trajectories by an iterative process. Result Experimental results on four challenging databases （TUD-Stadtmitte, TUD-Campus, TUD-Crossing, and Town-Center） show that the proposed method can efficiently deal with occlusions, target deformation, and background in- terference. The tracking results on the TUD-Crossing database are quantitatively analyzed, and the performance metrics of our algorithm are as follows ： the FAF is 0. 21, the MT is 84. 6% , the ML is 7.7% , the Frag is 9, and the IDS is 4. The proposed method outperforms several state-of-the-art approaches in terms of FAF and Frag. Conclusion The multi-feature fusion is appropriate for target expression, and the discriminative appearance model is effective for tracklets association. The proposed algorithm exhibits satisfactory performance in a complex scene and can be further applied to the preprocessing of some advanced algorithms, such as trajectory retrieval in behavior recognition.

关 键 词：多目标跟踪 判别性外观模型 ADABOOST 时间滑动窗 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]