摘要： 利用单尺度特征映射进行多尺度行人检测存在准确率和效率较低的问题。为此，提出一种基于多分辨率滤波通道的多尺度检测方法。应用尺度感知池增强感受域对应性，通过软决策树实现尺度不变性，在使用滑动窗口分类策略时，结合地平面约束和稀疏网格来降低计算成本，加快行人检测速度。在Caltech数据集上的实验结果表明，该方法的检测准确率达88.89%，检测速度达15.68 frame/s，其检测准确率优于VJ、WordChannels等方法。

关键词: 行人检测, 多分辨率滤波通道, 尺度感知池, 软决策树, 滑动窗口

Abstract: To address the problem of low accuracy and efficiency of single-scale feature mapping for multi-scale pedestrian detection,a multi-scale detection method based on multi-resolution filter channels is proposed.The scale perception pool is used to enhance the perception field correspondence,and the scale invariance is achieved through a soft decision tree.When using the sliding window classification strategy,the ground plane constraint and sparse grid are combined to reduce the calculation cost and form an acceleration strategy.Experimental results on the Caltech dataset show that the detection accuracy of the method is 88.89%,and the detection rate is 15.68 frame/s,its detection accuracy is higher than VJ,WordChannels and other methods.

Key words: pedestrian detection, Multi-Resolution Filter Channel(MRFC), scale-aware pool, Soft Decision Tree(SDC), sliding window

中图分类号: 

• TP391