多特征融合的行人检测算法

Multi-features Fusion Pedestrian Detection Algorithm

在分析颜色和纹理特征的基础上,提出了一种融合颜色特征LUV和纹理特征完全局部二值模式(CLBP)的行人检测算法,提取目标信息更加全面准确。采用交叉核SVM分类器对特征进行训练、检测,进一步提高算法的检测性能。实验结果表明,所提出的算法具有更高的检测准确性。

Based on the analysis of color and texture features,proposed a pedestrian detection algorithm that combines color feature LUV and texture feature completed local binary pattern（CLBP）.By fusing the two features,the extraction of target information is more comprehensive and accurate.The intersection-kernel SVM classifier is used to train features and detect them,which can further improve the detection performance of the algorithm.Experimental results show that the proposed algorithm has higher detection accuracy.