Multi-Target Tracking with Transferable Convolutional Neural Networks
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2022
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909201269260288 |
|---|---|
| author | Owerko, Damian Kanatsoulis, Charilaos I. Bondarchuk, Jennifer Bucci Jr, Donald J. Ribeiro, Alejandro |
| author_facet | Owerko, Damian Kanatsoulis, Charilaos I. Bondarchuk, Jennifer Bucci Jr, Donald J. Ribeiro, Alejandro |
| contents | Multi-target tracking (MTT) is a classical signal processing task, where the goal is to estimate the states of an unknown number of moving targets from noisy sensor measurements. In this paper, we revisit MTT from a deep learning perspective and propose a convolutional neural network (CNN) architecture to tackle it. We represent the target states and sensor measurements as images and recast the problem as an image-to-image prediction task. Then we train a fully convolutional model at small tracking areas and transfer it to much larger areas with numerous targets and sensors. This transfer learning approach enables MTT at a large scale and is also theoretically supported by our novel analysis that bounds the generalization error. In practice, the proposed transferable CNN architecture outperforms random finite set filters on the MTT task with 10 targets and transfers without re-training to a larger MTT task with 250 targets with a 29% performance improvement. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2210_15539 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Multi-Target Tracking with Transferable Convolutional Neural Networks Owerko, Damian Kanatsoulis, Charilaos I. Bondarchuk, Jennifer Bucci Jr, Donald J. Ribeiro, Alejandro Signal Processing Machine Learning Multi-target tracking (MTT) is a classical signal processing task, where the goal is to estimate the states of an unknown number of moving targets from noisy sensor measurements. In this paper, we revisit MTT from a deep learning perspective and propose a convolutional neural network (CNN) architecture to tackle it. We represent the target states and sensor measurements as images and recast the problem as an image-to-image prediction task. Then we train a fully convolutional model at small tracking areas and transfer it to much larger areas with numerous targets and sensors. This transfer learning approach enables MTT at a large scale and is also theoretically supported by our novel analysis that bounds the generalization error. In practice, the proposed transferable CNN architecture outperforms random finite set filters on the MTT task with 10 targets and transfers without re-training to a larger MTT task with 250 targets with a 29% performance improvement. |
| title | Multi-Target Tracking with Transferable Convolutional Neural Networks |
| topic | Signal Processing Machine Learning |
| url | https://arxiv.org/abs/2210.15539 |