中文摘要：

针对传统基于可穿戴传感设备步态周期检测方法需要用户高度配合的问题，本文采用计算机视觉的方法来研究高精度步态周期检测算法。受帧差法的启示，本文设计一种全新的步态图像表达特征一帧差步态时空特征，该特征不仅蕴含了步态运动的空间，还含有步态运动的时间信息，能较好地表达步态运动周期中的各个状态。基于帧差步态时空特征，设计足趾离地状态检测算法，进而实现步态周期的自动检测。实验结果表明，本方法能精确检测步态周期中的足趾离地状态帧。

英文摘要：

To address the problem of sensor-based gait cycle detection method, which needs high coopera- tion of users. Vision-based method is used to develop an accurate gait cycle detection algorithm. Inspired by the idea of frame difference, a novel gait representation feature, namely frame difference temporal and spatial （FDTS） feature is designed. FDTS contains the temporal and spatial information of gait. Thus it can accurately present all states of gait cycle. A new toe-off detection algorithm is first proposed based on FDTS. Then a gait cycle detection method is presented based on the toe-off detection algorithm. Experi- ments on the public dataset demonstrate the state-of-the-art performance of the method.