Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2403.01606 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913343075254272 |
|---|---|
| author | Huang, Yuxiang Zelek, John |
| author_facet | Huang, Yuxiang Zelek, John |
| contents | Motion segmentation is a fundamental problem in computer vision and is crucial in various applications such as robotics, autonomous driving and action recognition. Recently, spectral clustering based methods have shown impressive results on motion segmentation in dynamic environments. These methods perform spectral clustering on motion affinity matrices to cluster objects or point trajectories in the scene into different motion groups. However, existing methods often need the number of motions present in the scene to be known, which significantly reduces their practicality. In this paper, we propose a unified model selection technique to automatically infer the number of motion groups for spectral clustering based motion segmentation methods by combining different existing model selection techniques together. We evaluate our method on the KT3DMoSeg dataset and achieve competitve results comparing to the baseline where the number of clusters is given as ground truth information. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_01606 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Unified Model Selection Technique for Spectral Clustering Based Motion Segmentation Huang, Yuxiang Zelek, John Computer Vision and Pattern Recognition Artificial Intelligence Motion segmentation is a fundamental problem in computer vision and is crucial in various applications such as robotics, autonomous driving and action recognition. Recently, spectral clustering based methods have shown impressive results on motion segmentation in dynamic environments. These methods perform spectral clustering on motion affinity matrices to cluster objects or point trajectories in the scene into different motion groups. However, existing methods often need the number of motions present in the scene to be known, which significantly reduces their practicality. In this paper, we propose a unified model selection technique to automatically infer the number of motion groups for spectral clustering based motion segmentation methods by combining different existing model selection techniques together. We evaluate our method on the KT3DMoSeg dataset and achieve competitve results comparing to the baseline where the number of clusters is given as ground truth information. |
| title | A Unified Model Selection Technique for Spectral Clustering Based Motion Segmentation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2403.01606 |