Re-identification Loss in Combination Spaces for Multiple Object Tracking

The joint-detection-and-tracking framework shares network features of detection and re-identification (re-ID), which drives multi-object tracking (MOT) to be simple, fast and accurate. Most of the existing algorithms utilize global information of image to optimize re-ID feature, which result in weak representation of features and a large number of ID switches in the association phase. To solve the above problems, we present a loss function for re-ID task based on cosine space and angle space. Specifically, the algorithm maximizes the decision boundary distance between different categories in cosine space and angle space, respectively, so as to improve the compactness of feature distribution in the same category and expand the variability of feature between different categories. For the problem of small number of pedestrian samples with the same ID, a mixed data augmentation method is introduced based on statistical information of object location and motion distribution. Experimental results of MOTChallenge benchmark show that the proposed method obtains different degrees of improvement in MOTA and IDF1 scores compared with the baseline model, and the IDs metric decreases significantly, while it can cope with tracking scenarios of different complexity.