面向行人再识别的特征融合与鉴别零空间方法

Feature Fusion and Discriminative Null Space for Person Re-identification

针对行人再识别技术易受到光照、姿态和视角等因素影响,同一个人外观特征变化明显,较难提取其不变特征,导致识别率偏低的问题,本文提出面向行人再识别的融合特征与鉴别零空间方法。首先利用HSV、LAB、RGB和YCr Cb四种颜色特征和Gabor滤波器提取条纹特征,GOG描述子提取块状特征,并将这两种特征融合成一个特征向量,然后将融合后的的特征投影到鉴别零空间,降低特征维数,最后利用欧氏距离计算距离进行行人再识别。本文所提方法在VIPeR、Prids_450s和CUHK01数据库上的rank1识别率分别是52.7%、72.2%和59.7%,实验结果表明所提方法能充分融合行人图像特征,对环境有较强鲁棒性,可有效提高识别率。

The person re-identification technology is vulnerable to the light,posture and view perspective,thus appearance feature is changed seriously,it is difficult to extract invariant features,which will lead to the problem of the low recognition rate. In this paper,a method of feature fusion and discriminative null space for person re-identification is proposed. Firstly,the stripe feature is extracted by HSV,LAB,RGB and YCr Cb four color characteristics and Gabor filter,and GOG descriptor is used to extracted block feature,then those features are concatenated into a whole feature vector,which is projected into discriminative null space to reduce their feature dimension. Finally,Euclidean distance is applied to compute personal distance to achieve re-identify person. Experimental results show that,rank1 recognition rate of the proposed method could achieve 52. 7%,72. 2% and 59. 7% on VIPeR、Prids_ 450 s and CUHK01 database respectively,which shows that the proposed method can sufficiently describe personal picture feature,and has a strong robustness for environment which can effectively improve the recognition rate.