由于运动人体是一个复杂的非刚体，三维人体运动极其复杂，一般都有上百个自由度，且各部位之间存在自遮挡(self-occlusion)现象，因此，在跟踪过程中一般采用基于模型的方法比较有效。
基于36个网页-相关网页
·2,447,543篇论文数据，部分数据来源于NoteExpress
实验结果表明，该算法具有较强的处理局部自遮挡问题能力，对3D人手模型的不精确性也具有更好的鲁棒性。
Compared with the relevant algorithms, our algorithm can more effectively deal with hand self-occlusion issues, and is more robust to 3D human hand models as well.
很多因素都能导致数据缺失的出现，比如自遮挡、成像因素导致的图像模糊、以及特征提取算法的不完善等因素。
Data deficiency may be caused by many factors such as self-occlusion, the image blur and the imperfection of the feature extraction algorithm.
针对人体运动过程中存在的五种自遮挡现象，分别利用人体下肢在运动过程中的规律和几何关系，部分地解决了肢体运动的自遮挡问题，使跟踪过程更连续；
Geometrical relationship between low limbs and rules of human motion are used to partially solve the problem of self-occlusions, which makes the tracking more continuous;
应用推荐