基于逆运动学的人体步态特征提取

近年来，人体运动分析成为了计算机视觉和图像处理技术中的一个最活跃的研究课题。其研究在虚拟现实、智能监视系统、高级用户接口、运动分析和基于模型的图像编码等方面具有广阔的应用前景。该文提出了一种基于逆运动学的方法来提取人体步态特征的运动分析方法，对于每个图像序列，先采用背景减除算法检测行人的运动轮廓，然后根据人体运动的特点，寻找每帧图像中人体踝关节的位置，通过得到的踝关节位置使用逆运动学的方法来预测其他关节点位置，通过实验发现，这种方法在提取步态特征中取得了很好的效果。

Extraction of Human Gait Signatures Based on Inverse Kinematics

Human motion analysis is currently one of the most active research topics in the domain of computer vision and image processing. This strong interest is driven by a wide spectrum of promising applications in many areas such as virtual reality, smart surveillance, advanced user interface, motion analysis and model-based image coding, etc. This paper proposes a simple and efficient algorithm for extracting gait signatures by the inverse kinematics method. For each image sequence, a subtraction algorithm is first used to segment and detect the moving silhouettes of a walking figure from the background. Then, the ankle position is found out in image by body properties. Based on the inverse kinematics the other joint position is finally predicted. And the local search is used to accurate matching the joint position. The experimental results demonstrate that the proposed algorithm is effective in gait signatures extraction of the human motion.