基于深度学习的行人属性识别

Pedestrian Attribute Recognition Based on Deep Learning

针对监控场景的背景杂乱及行人被遮挡等问题,提出一种基于背景抑制的行人属性识别方法,该方法可以减小背景对行人属性识别的影响。首先,改进卷积神经网络以生成三个分支,将分支分别用于行人图像、人体区域、背景区域的特征提取;然后,将区域对比损失函数和加权交叉熵损失函数作为网络的联合代价函数。在此联合代价函数的约束下,神经网络学习到的特征具有背景杂乱不变性,从而提高了行人属性识别的准确度。将所提方法在PETA和RAP两个行人属性数据集上进行验证。与其他现有方法相比,所提方法在平均精度、准确度、精确度等指标上性能均有所提升,证明了所提方法的有效性。

In this study,we propose a pedestrian attribute recognition method based on background suppression to solve the problems of background clutter and object occlusion associated with the monitor scene.The proposed method can reduce the impact of the background on pedestrian attribute recognition.First,three branches are generated by improving the convolutional neural network.These three branches are used to extract the features of the pedestrian images,human body regions,and background regions.Then,the regional contrast loss function and weighted cross-entropy loss function are considered to constitute the joint cost function of the network.The features learned by the neural network exhibit background clutter invariance under the constraint of the joint cost function.Therefore,the proposed method can improve the pedestrian attribute recognition accuracy.The proposed method was verified using the PETA and RAP pedestrian attribute datasets.The results denote that the proposed method exhibits improved the mean accuracy,accuracy,precision,and other performance indicators when compared with those exhibited by the remaining methods,confirming its effectiveness.