基于特征增强模块的小尺度行人检测

Small-scale Pedestrian Detection Based on Feature Enhancement Strategy

行人检测中,小尺度行人时常被漏检、误检。为了提升小尺度行人的检测准确率并且降低其漏检率,该文提出一个特征增强模块。首先,考虑到小尺度行人随着网络加深特征逐渐减少的问题,特征融合策略突破特征金字塔层级结构的约束,融合深层、浅层特征图,保留了大量小尺度行人特征。然后,考虑到小尺度行人特征容易与背景信息发生混淆的问题,通过自注意力模块联合通道注意力模块建模特征图空间、通道关联性,利用小尺度行人上下文信息和通道信息,增强了小尺度行人特征并且抑制了背景信息。最后,基于特征增强模块构建了一个小尺度行人检测器。所提方法在CrowdHuman数据集中小尺度行人的检测准确率为19.8%,检测速度为22帧/s,在CityPersons数据集中小尺度行人的误检率为13.1%。结果表明该方法对于小尺度行人的检测效果优于其他对比算法且实现了较快的检测速度。

In pedestrian detection,small-scale pedestrians are often missed and mistakenly detected.In order to improve detection precision and reduce miss detection rate of small-scale pedestrians,a feature enhancement module is proposed.First,considering the problem that small-scale pedestrians feature gradually decreases as network goes deeper,feature fusion strategy breaks through the constraints of feature pyramid structure and fuses deep and shallow feature maps to retain lots of small-scale pedestrian features.Then,considering the problem that small-scale pedestrian features are easily confused with background information,self-attention module combined with channel attention module models the spatial and channel correlation of feature maps,using small-scale pedestrian contextual information and channel information to enhance small-scale pedestrian features and suppress background information.Finally,a small-scale pedestrian detector is constructed based on the feature enhancement module.For small-scale pedestrians,the proposed algorithm has 19.8%detection accuracy,22 frames per second speed on CrowdHuman dataset and 13.1%miss rate on CityPersons dataset.The results show that the proposed algorithm performs better than other compared algorithms for small-scale pedestrian detection and achieves faster detection speed.