姜明新,邱天爽,迟宏波.基于颜色与深度信息特征融合的一种多目标跟踪新算法[J].光电子激光,2015,26(7):1342~1348 |
基于颜色与深度信息特征融合的一种多目标跟踪新算法 |
A novel multi-object tracking algorithm based on RJMCMC with RGB and depth information fusion |
投稿时间:2015-01-30 |
DOI: |
中文关键词: RGB-D数据 多目标检测 多目标跟踪 可逆跳的马尔科夫链蒙特长洛(RJMCMC)粒子滤 波 |
英文关键词:RGB-D data multi-object detection multi-object tracking RJMCMC particle fi ltering |
基金项目:国家自然科学基金(6143060)和中国博士后科学基金(2014M551081,2015T80249)资助项目 (1.大连理工大学 电子信息与电气工程学部,辽宁 大连 116024; 2.大连 民族学院 信息与通信工程学院,辽宁 大连 116600; 3.首都航天机械公司,北京 100076) |
|
摘要点击次数: 1161 |
全文下载次数: 0 |
中文摘要: |
提出了一种基于颜色与深度信息特征融合的 可逆跳的马尔科夫链蒙特长洛(RJMCMC)多目标跟踪算法。首先,融合彩色信息和深度信息对 运动目标进行检测;然后,根据多目标检测的结果建 立观测似然模型,并构建合理的状态转移模型;最后,通过RJMCMC粒子滤波算法实现多目 标跟踪。实验 结果表明,本文提出的多目标跟踪算法具有较强的鲁棒性,能够稳定的跟踪多目标,具有较 高的准确率。 |
英文摘要: |
Multi-object tracking technique is o ne of the challenging issues in computer vision.In this paper,we propose a multi-object tracking algorithm based on RJMCMC with RGB and depth informatio n fusion.Firstly,the moving objects are detected by fusing color information and depth information.Then,the observation likelihood model is established according to the result of object detection,and a reasonab le sta te transition model is also established. Finally,the multi-object tracking result is obtained using RJMCMC particle fil tering algorithm.Experimental results show that the proposed method has strong robustness.The algorithm can steadily track multiple targets and has higher accuracy. |
查看全文 下载PDF阅读器 |
关闭 |
|
|
|
|
|