结合遮挡级别的人体姿态估计方法
发布时间：2018-11-18 19:20
【摘要】：针对单目静态图像中姿态估计方法易受遮挡干扰的问题,提出基于部位遮挡级别的可形变姿态估计方法.首先定义遮挡级别为人体部位的被遮挡程度,其通过计算部位遮挡比例和部位方向获得;然后根据遮挡级别为每个部位建立对应级别的部位检测器,并给出基于遮挡级别的部位间形变模型;最后依据以上2个模型的总体匹配得分,获得最合理的人体姿态.在标准数据集IP和LSP上的实验结果表明,该方法提高了姿态估计的整体准确率,特别是减少了有遮挡情况下的部位误匹配问题.
[Abstract]:A deformable attitude estimation method based on occlusion level is proposed to solve the problem that the attitude estimation method in monocular still images is vulnerable to occlusion interference. Firstly, the degree of occlusion is defined as the degree of occlusion of human body, which is obtained by calculating the proportion and direction of occlusion. Then according to the occlusion level, the corresponding position detector is established for each position, and the deformation model between the parts based on the occlusion level is given. Finally, according to the overall matching score of the above two models, the most reasonable posture of the human body is obtained. The experimental results on the standard data sets IP and LSP show that the proposed method improves the overall accuracy of attitude estimation, especially reduces the mismatch problem in the case of occlusion.
【作者单位】： 东北大学计算机科学与工程学院;沈阳工程学院信息学院;沈阳航空航天大学计算机学院;
【基金】：国家自然科学基金(61170185) 辽宁省博士启动基金(20121034) 辽宁省教育厅科学研究一般项目(L2014070,L2015368,L201602)
【分类号】：TP391.41
[Abstract]:A deformable attitude estimation method based on occlusion level is proposed to solve the problem that the attitude estimation method in monocular still images is vulnerable to occlusion interference. Firstly, the degree of occlusion is defined as the degree of occlusion of human body, which is obtained by calculating the proportion and direction of occlusion. Then according to the occlusion level, the corresponding position detector is established for each position, and the deformation model between the parts based on the occlusion level is given. Finally, according to the overall matching score of the above two models, the most reasonable posture of the human body is obtained. The experimental results on the standard data sets IP and LSP show that the proposed method improves the overall accuracy of attitude estimation, especially reduces the mismatch problem in the case of occlusion.
【作者单位】： 东北大学计算机科学与工程学院;沈阳工程学院信息学院;沈阳航空航天大学计算机学院;
【基金】：国家自然科学基金(61170185) 辽宁省博士启动基金(20121034) 辽宁省教育厅科学研究一般项目(L2014070,L2015368,L201602)
【分类号】：TP391.41
【相似文献】
相关期刊论文 前10条
1 韩贵金;朱虹;;一种基于图结构模型的人体姿态估计算法[J];计算机工程与应用;2013年14期
2 王浩;刘则芬;方宝富;陈金金;;基于约束树形图结构外观模型的人体姿态估计[J];计算机科学;2014年03期
3 苏延超;艾海舟;劳世z，
本文编号：2340945
本文链接：https://www.wllwen.com/kejilunwen/ruanjiangongchenglunwen/2340945.html
