A Graph Convolutional Neural Network Based Approach for Traffic Monitoring Using Augmented Detections with Optical Flow

This paper presents a novel method for Multi-Object Tracking (MOT) using Graph Convolutional Neural Network 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 the 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. To increase the detector's sensitivity, a new approach is also presented that propagates previous frame detections into each new frame using optical flow. These are treated as added object proposals which are then classified as objects. A new traffic monitoring dataset is additionally provided, which includes naturalistic video footage from current infrastructure cameras in Virginia Beach City. Experimental evaluation demonstrates the efficacy of the proposed approaches on the provided dataset and the popular MOT Challenge Benchmark.