Sparse Message Passing Network with Feature Integration for Online Multiple Object Tracking
This work addresses robust tracking with reduced identity switches for computer vision applications, representing an incremental improvement over existing MOT methods.
The paper tackles the problem of frequent identity switches in online Multiple Object Tracking by proposing a simple online Message Passing Network with two novel contributions: an IoU-guided feature integration function for better long-term tracking and a hierarchical sampling strategy for sparser graphs. Experimental results show it outperforms many state-of-the-art methods and generalizes well to improve private detection-based methods.
Existing Multiple Object Tracking (MOT) methods design complex architectures for better tracking performance. However, without a proper organization of input information, they still fail to perform tracking robustly and suffer from frequent identity switches. In this paper, we propose two novel methods together with a simple online Message Passing Network (MPN) to address these limitations. First, we explore different integration methods for the graph node and edge embeddings and put forward a new IoU (Intersection over Union) guided function, which improves long term tracking and handles identity switches. Second, we introduce a hierarchical sampling strategy to construct sparser graphs which allows to focus the training on more difficult samples. Experimental results demonstrate that a simple online MPN with these two contributions can perform better than many state-of-the-art methods. In addition, our association method generalizes well and can also improve the results of private detection based methods.