FAMNet: Joint Learning of Feature, Affinity and Multi-dimensional Assignment for Online Multiple Object Tracking
arXiv:1904.04989
Abstract
Data association-based multiple object tracking (MOT) involves multiple separated modules processed or optimized differently, which results in complex method design and requires non-trivial tuning of parameters. In this paper, we present an end-to-end model, named FAMNet, where Feature extraction, Affinity estimation and Multi-dimensional assignment are refined in a single network. All layers in FAMNet are designed differentiable thus can be optimized jointly to learn the discriminative features and higher-order affinity model for robust MOT, which is supervised by the loss directly from the assignment ground truth. We also integrate single object tracking technique and a dedicated target management scheme into the FAMNet-based tracking system to further recover false negatives and inhibit noisy target candidates generated by the external detector. The proposed method is evaluated on a diverse set of benchmarks including MOT2015, MOT2017, KITTI-Car and UA-DETRAC, and achieves promising performance on all of them in comparison with state-of-the-arts.
References in corpus (6)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Simple Online and Realtime Tracking
- MOT16: A Benchmark for Multi-Object Tracking
- MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking
- UA-DETRAC: A New Benchmark and Protocol for Multi-Object Detection and Tracking
- Tracking The Untrackable: Learning To Track Multiple Cues with Long-Term Dependencies
Cited by in corpus (5)
- TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Model
- Multi-object Tracking via End-to-end Tracklet Searching and Ranking
- ArTIST: Autoregressive Trajectory Inpainting and Scoring for Tracking
- Online Multiple Object Tracking with Cross-Task Synergy
- Know Your Surroundings: Panoramic Multi-Object Tracking by Multimodality Collaboration