双域滤波三元组度量学习的行人再识别

Pedestrian Re-IDentification Algorithm Based on Dual-domain Filtering and Triple Metric Learning

在图像的捕获、传输或者处理过程中都有可能产生噪声,当图像被大量噪声影响时,许多行人再识别(ReID)方法将很难提取具有足够表达能力的行人特征,表现出较差的鲁棒性。该文主要针对低质图像的行人再识别问题,提出双域滤波分解构建3元组,用于训练度量学习模型。所提方法主要分为两个部分,首先分析了监控视频中不同图像噪声的分布特性,通过双域滤波进行图像增强。然后基于双域滤波分解对图像噪声具有很好的分离作用,该文提出一种新的3元组构建方式。在训练阶段,将双域滤波生成的低频原始图像和高频噪声图像,与原图一起作为输入3元组,网络可以进一步抑制噪声分量。同时优化了损失函数,将3元组损失和对比损失组合使用。最后利用re-ranking扩充排序表,提高识别的准确率。在加噪Market-1501和CUHK03数据集上的平均Rank-1为78.3%和21.7%,平均准确率均值(mAP)为66.9%和20.5%。加噪前后的Rank-1精度损失只有1.9%和7.8%,表明该文模型在含噪情况表现出较强的鲁棒性。

Noise may be generated in the process of image capture,transmission or processing.When the image is affected by a large amount of noise,it is difficult for many pedestrian Re-IDentification(ReID)methods to extract pedestrian features with sufficient expressive ability,which shows poor robustness.This paper focuses on the pedestrian re-identification with low quality image.The dual-domain filtering decomposition is proposed to construct triplet,which is used to train metric learning model.The proposed method mainly consists of two parts.Firstly,the distribution characteristics of different image noise in surveillance videos is analyzed and images are enhanced by dual-domain filtering.Secondly,based on the separation effect of dual-domain filtering,a new triplet is proposed.In the training stage,the original image with the low-frequency component,the noise with high-frequency component generated by the dual-domain filtering and the original image are used as the input triplet.So the noise component can be further suppressed by the network.At the same time,the loss function is optimized,and the triple loss and contrast loss are used in combination.Finally,re-ranking is used to expand the sorting table to improve the accuracy of identification.The average Rank-1 on the noisy Market-1501 and CUHK03 datasets are 78.3%and 21.7%,and the mean Average Precision(mAP)is 66.9%and 20.5%.The accuracy loss of Rank-1 before and after adding noise is only 1.9%and 7.8%,which indicates that the model in this paper shows strong robustness in the case of noise.