激光与光电子学进展, 2017, 54 (9): 091004, 网络出版: 2017-09-06   

基于HSV颜色特征和贡献度重构的行人跟踪 下载: 726次

Pedestrian Tracking Based on HSV Color Features and Reconstruction by Contributions
作者单位
1 首都师范大学信息工程学院, 北京 100048
2 首都师范大学电子系统可靠性技术北京市重点实验室, 北京 100048
3 成像技术北京市高精尖创新中心, 北京 100048
4 首都师范大学高可靠嵌入式系统技术北京市工程技术研究中心, 北京 100048
摘要
在光照、背景变化、遮挡、噪声、快速运动等复杂环境下, 准确地实现行人跟踪一直是富有挑战性的任务。针对这些问题, 提出基于HSV颜色特征和贡献度重构的行人跟踪算法。在粒子滤波的框架内, 从HSV空间提取目标的混合颜色特征生成目标模板集, 依据不同区域对跟踪结果的影响对区域进行贡献度分配, 并将其引入到一个自适应的正则化模型中, 将具有最小重构误差的区域判定为待跟踪目标。为了增强算法的稳健性, 跟踪过程中对模板进行实时更新。在OTB 100个序列上进行测试, 本文算法得到跟踪结果的平均中心误差和跟踪成功率两项指标分别为0.6624 pixel和0.4153, 优于同类其他算法。实验结果表明, 该算法能够在复杂的视频场景中实现对行人的连续跟踪, 且稳健性较好, 有利于在实际系统中的实现。
Abstract
It is a challenging task to track pedestrian accurately in complicated environment such as illumination, background variation, occlusion, noise and fast motion. Aiming at these problems, the tracing algorithm based on HSV color features and reconstruction by contributions is proposed. The proposed algorithm extracts the mixed color features of target in HSV space to generate the target template set within the particle filter framework. According to the influence of different regions on the tracking results, the contribution of the region is distributed. And it is introduced into the adaptive regularization model, and the region with the minimum reconstruction error is determined as the target to be tracked. In order to be more robust, the templates are updated in real time during the tracking progress. The average center error of tracking results and tracking success rate of 100 sequences tested in OTB are 0.6624 pixel and 0.4153, respectively, and the proposed algorithm has better performance than others. Experimental results show that the proposed algorithm can realize the continuous tracking for pedestrian in complex video scenes and is beneficial to be realized in the practice system with better robustness.

刘梦飞, 付小雁, 尚媛园, 丁辉. 基于HSV颜色特征和贡献度重构的行人跟踪[J]. 激光与光电子学进展, 2017, 54(9): 091004. Liu Mengfei, Fu Xiaoyan, Shang Yuanyuan, Ding Hui. Pedestrian Tracking Based on HSV Color Features and Reconstruction by Contributions[J]. Laser & Optoelectronics Progress, 2017, 54(9): 091004.

本文已被 5 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!