Multiple Object Tracking with Correlation Learning

Abstract

Recent works have shown that convolutional networks have substantially improved the performance of multiple object tracking by simultaneously learning detection and appearance features. However, due to the local perception of the convolutional network structure itself, the long-range dependencies in both the spatial and temporal cannot be obtained efficiently. To incorporate the spatial layout, we propose to exploit the local correlation module to model the topological relationship between targets and their surrounding environment, which can enhance the discriminative power of our model in crowded scenes. Specifically, we establish dense correspondences of each spatial location and its context, and explicitly constrain the correlation volumes through self-supervised learning. To exploit the temporal context, existing approaches generally utilize two or more adjacent frames to construct an enhanced feature representation, but the dynamic motion scene is inherently difficult to depict via CNNs. Instead, our paper proposes a learnable correlation operator to establish frameto-frame matches over convolutional feature maps in the different layers to align and propagate temporal context. With extensive experimental results on the MOT datasets, our approach demonstrates the effectiveness of correlation learning with the superior performance and obtains stateof-the-art MOTA of 76.5% and IDF1 of 73.6% on MOT17.

Lightweight high-precision pedestrian tracking algorithm in complex occlusion scenarios

“…Search for branches and targetsCross-attention calculations are performed between branches so that the search branch learns the target information. In addition, similar twin network models such as TranT [19]and STARK [20] can show good results.Qiang Wang et al, "proposed to use a local correlation module to model the topological relationship between the target and the surrounding environment [21], the modified model can effectively improve the pedestrian identification ability in complex and occlusion scenes. Jiawei He proposed a new learnable graph matching method for target tracking task, which turns the association problem into an undirected graph matching problem [22].…”

TdmTracker: Multi-Object Tracker Guided by Trajectory Distribution Map

“…Afterward, the subsequent problem is to correctly associate the targets between frames by calculating similarity between features extracted from detection patches in the front and back frames and considering the location of the tracked objects. Traditional tracking-by-detection paradigm treats MOT as two tasks, object detection and data association [5]. In terms of object detection, there are many mature backbone networks for feature extraction such as VGG16, GoogLeNet, ResNet, DenseNet, Darnet19, etc.…”