SiamMOT: Siamese Multi-Object Tracking
arXiv:2105.11595
Abstract
In this paper, we focus on improving online multi-object tracking (MOT). In particular, we introduce a region-based Siamese Multi-Object Tracking network, which we name SiamMOT. SiamMOT includes a motion model that estimates the instance's movement between two frames such that detected instances are associated. To explore how the motion modelling affects its tracking capability, we present two variants of Siamese tracker, one that implicitly models motion and one that models it explicitly. We carry out extensive quantitative experiments on three different MOT datasets: MOT17, TAO-person and Caltech Roadside Pedestrians, showing the importance of motion modelling for MOT and the ability of SiamMOT to substantially outperform the state-of-the-art. Finally, SiamMOT also outperforms the winners of ACM MM'20 HiEve Grand Challenge on HiEve dataset. Moreover, SiamMOT is efficient, and it runs at 17 FPS for 720P videos on a single modern GPU. Codes are available in \url{https://github.com/amazon-research/siam-mot}.
References in corpus (14)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Simple Online and Realtime Tracking
- R-FCN: Object Detection via Region-based Fully Convolutional Networks
- In Defense of the Triplet Loss for Person Re-Identification
- MOT16: A Benchmark for Multi-Object Tracking
- CrowdHuman: A Benchmark for Detecting Human in a Crowd
- Argoverse: 3D Tracking and Forecasting with Rich Maps
- Siamese Instance Search for Tracking
- Deeper and Wider Siamese Networks for Real-Time Visual Tracking
- Distractor-aware Siamese Networks for Visual Object Tracking
- DirectPose: Direct End-to-End Multi-Person Pose Estimation
- A Twofold Siamese Network for Real-Time Object Tracking
- How To Train Your Deep Multi-Object Tracker
- Fusion of Head and Full-Body Detectors for Multi-Object Tracking