步态识别是生物特征识别领域一个新的研究方向，它旨在根据人们走路的姿势进行身份识别。本文首先对步态识别的影响因素与性能预测进行了概括，然后从运动检测、周期检测、特征提取、识别算法4个方面对当前研究成果进行了全面的综述，最后讨论了当前研究的难点与发展趋势。

As a new direction in biometric, gait recognition aims to recognize individuals by the way they walk. In this paper, influencing factors and performance prediction to gait recognition are generalized at first. Subsequently, four major issues involved in a gait recognition system are reviewed in detail, namely motion detection, period detection, feature extraction and recognition methods. Finally, some research challenges and future directions in gait recognition are discussed.