Random Occlusion-recovery for Person Re-identification

As a basic task of multi-camera surveillance system, person re-identification aims to re-identify a query pedestrian observed from non-overlapping cameras or across different time with a single camera. Recently, Deep learning based person re-identification models have achieved great success in many benchmarks. However, these supervised models require a large amount of labeled image data and the process of manual labeling spends much manpower and time. In this study, we introduce a method to automatically synthesize labeled person images and adopt them to increase the sample number for per identity in datasets. Specifically, we use the block rectangles to occlude the random parts of the persons in the images. Then, a generative adversarial network (GAN) model is proposed to use paired occlusion and original images to synthesize the de-occluded images that similar but not identical to the original images. Afterwards, we annotate the de-occluded images with the same labels of their corresponding raw image and use them to augment the training samples. We use the augmented datasets to train baseline model. The experiment results on Market-1501 and CUHK03 datasets show that the effectiveness of the proposed method.