融合理论在步态识别中的应用研究

摘要

近年来,基于信息融合理论的步态识别已成为生物特征识别领域最为活跃的研究方向之一.从特征级融合和决策级融合两种层次,多特征融合、多模态融合以及多视角融合3个方面对融合理论在步态识别中的应用进行了综述.进一步,为了研究融合理论对步态识别算法性能的影响,提出一种融合了静态形体特征和动态模型特征的步态识别算法.通过在CMU步态数据库上的详细实验比较和分析,研究了不同融合策略以及步速变化对步态识别算法性能的影响.%Recently, fusion-based gait recognition has become one of the hottest topics in the domain of biometrics recognition. This paper firstly discussed two different levels of fusion methods,feature-level fusion and decision-level fusion, then summarized the latest fusion-based gait recognition methods from three categories: multi-feature fusion,multi-bio-metric fusion and multi-view fusioa Furthermore, a gait recognition method via fusing shape and kinematics features was proposed to verify the effectiveness of fusion. Experimental results on CMU databases demonstrate the feasibility of the proposed algorithm and show that fusion can be an effective strategy to improve the recognition perfor-mance.