Split and Connect: A Universal Tracklet Booster for Multi-Object Tracking

Abstract

Multi-object tracking (MOT) is an essential task in the computer vision field. With the fast development of deep learning technology in recent years, MOT has achieved great improvement. However, some challenges still remain, such as sensitiveness to occlusion, instability under different lighting conditions, non-robustness to deformable objects, etc. To address such common challenges in most of the existing trackers, in this paper, a tracklet booster algorithm is proposed, which can be built upon any other tracker. The motivation is simple and straightforward: split tracklets on potential ID-switch positions and then connect multiple tracklets into one if they are from the same object. In other words, the tracklet booster consists of two parts, i.e., Splitter and Connector. First, an architecture with stacked temporal dilated convolution blocks is employed for the splitting position prediction via label smoothing strategy with adaptive Gaussian kernels. Then, a multi-head self-attention based encoder is exploited for the tracklet embedding, which is further used to connect tracklets into larger groups. We conduct sufficient experiments on MOT17 and MOT20 benchmark datasets, which demonstrates promising results. Combined with the proposed tracklet booster, existing trackers usually can achieve large improvements on the IDF1 score, which shows the effectiveness of the proposed method.

References in corpus (20)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Deformable DETR: Deformable Transformers for End-to-End Object Detection
• MOT16: A Benchmark for Multi-Object Tracking
• MOT20: A benchmark for multi object tracking in crowded scenes
• TransTrack: Multiple Object Tracking with Transformer
• Pre-Trained Image Processing Transformer
• Lifted Disjoint Paths with Application in Multiple Object Tracking
• A Multi-cut Formulation for Joint Segmentation and Tracking of Multiple Objects
• Multi-Target, Multi-Camera Tracking by Hierarchical Clustering: Recent Progress on DukeMTMC Project
• Out of the Box: Reasoning with Graph Convolution Nets for Factual Visual Question Answering
• DEFT: Detection Embeddings for Tracking
• Joint Monocular 3D Vehicle Detection and Tracking
• Tracklets Predicting Based Adaptive Graph Tracking
• Simple Unsupervised Multi-Object Tracking
• GCNNMatch: Graph Convolutional Neural Networks for Multi-Object Tracking via Sinkhorn Normalization
• Tracking Objects as Points
• Learnable Graph Matching: Incorporating Graph Partitioning with Deep Feature Learning for Multiple Object Tracking
• Learning a Proposal Classifier for Multiple Object Tracking
• Exploring Severe Occlusion: Multi-Person 3D Pose Estimation with Gated Convolution