SmartSORT: an MLP-based method for tracking multiple objects in real-time

Abstract

With the recent advances in the object detection research field, tracking-by-detection has become the leading paradigm adopted by multi-object tracking algorithms. By extracting different features from detected objects, those algorithms can estimate the similarities and association patterns of objects along with successive frames. However, since similarity functions applied by tracking algorithms are handcrafted, it is difficult to use them in new contexts. In this study, it is investigated the use of artificial neural networks to learning a similarity function that can be used among detections. During training, multilayer perceptron (MLP) neural networks were introduced to correct and incorrect association patterns, sampled from a pedestrian tracking data set. For such, different motion and appearance feature combinations have been explored. Finally, a trained MLP has been inserted into a multiple-object tracking framework, which has been assessed on the MOT Challenge benchmark. Throughout the experiments, the proposed tracker matched the results obtained by state-of-the-art methods by scoring a tracking accuracy of 60.4%, while running 58% faster than DeepSORT, a recent and similar method used as a baseline. After all, this work demonstrates its method can be automatically trained for different tracking contexts and it has highly competitive cost-effectiveness for online real-time tracking applications.