A New Architecture for Neural Enhanced Multiobject Tracking
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916428600311808 |
|---|---|
| author | Wei, Shaoxiu Liang, Mingchao Meyer, Florian |
| author_facet | Wei, Shaoxiu Liang, Mingchao Meyer, Florian |
| contents | Multiobject tracking (MOT) is an important task in robotics, autonomous driving, and maritime surveillance. Traditional work on MOT is model-based and aims to establish algorithms in the framework of sequential Bayesian estimation. More recent methods are fully data-driven and rely on the training of neural networks. The two approaches have demonstrated advantages in certain scenarios. In particular, in problems where plenty of labeled data for the training of neural networks is available, data-driven MOT tends to have advantages compared to traditional methods. A natural thought is whether a general and efficient framework can integrate the two approaches. This paper advances a recently introduced hybrid model-based and data-driven method called neural-enhanced belief propagation (NEBP). Compared to existing work on NEBP for MOT, it introduces a novel neural architecture that can improve data association and new object initialization, two critical aspects of MOT. The proposed tracking method is leading the nuScenes LiDAR-only tracking challenge at the time of submission of this paper. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_06294 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A New Architecture for Neural Enhanced Multiobject Tracking Wei, Shaoxiu Liang, Mingchao Meyer, Florian Signal Processing Machine Learning Robotics Multiobject tracking (MOT) is an important task in robotics, autonomous driving, and maritime surveillance. Traditional work on MOT is model-based and aims to establish algorithms in the framework of sequential Bayesian estimation. More recent methods are fully data-driven and rely on the training of neural networks. The two approaches have demonstrated advantages in certain scenarios. In particular, in problems where plenty of labeled data for the training of neural networks is available, data-driven MOT tends to have advantages compared to traditional methods. A natural thought is whether a general and efficient framework can integrate the two approaches. This paper advances a recently introduced hybrid model-based and data-driven method called neural-enhanced belief propagation (NEBP). Compared to existing work on NEBP for MOT, it introduces a novel neural architecture that can improve data association and new object initialization, two critical aspects of MOT. The proposed tracking method is leading the nuScenes LiDAR-only tracking challenge at the time of submission of this paper. |
| title | A New Architecture for Neural Enhanced Multiobject Tracking |
| topic | Signal Processing Machine Learning Robotics |
| url | https://arxiv.org/abs/2410.06294 |