GCNNMatch: Graph Convolutional Neural Networks for Multi-Object Tracking via Sinkhorn Normalization
This addresses the challenge of accurately tracking multiple objects in real-time for applications like surveillance and autonomous driving, representing a novel paradigm rather than an incremental improvement.
The paper tackled the problem of online Multi-Object Tracking by proposing a novel method using Graph Convolutional Neural Networks and Sinkhorn normalization for object association, achieving top performance on MOT '15, '16, '17, and '20 Challenges among state-of-the-art online approaches.
This paper proposes a novel method for online Multi-Object Tracking (MOT) using Graph Convolutional Neural Network (GCNN) based feature extraction and end-to-end feature matching for object association. The Graph based approach incorporates both appearance and geometry of objects at past frames as well as the current frame into the task of feature learning. This new paradigm enables the network to leverage the "context" information of the geometry of objects and allows us to model the interactions among the features of multiple objects. Another central innovation of our proposed framework is the use of the Sinkhorn algorithm for end-to-end learning of the associations among objects during model training. The network is trained to predict object associations by taking into account constraints specific to the MOT task. Experimental results demonstrate the efficacy of the proposed approach in achieving top performance on the MOT '15, '16, '17 and '20 Challenges among state-of-the-art online approaches. The code is available at https://github.com/IPapakis/GCNNMatch.