Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.11323 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908538661502976 |
|---|---|
| author | Song, Jian Mei, Wei Xu, Yunfeng Fu, Qiang Kou, Renke Bu, Lina Long, Yucheng |
| author_facet | Song, Jian Mei, Wei Xu, Yunfeng Fu, Qiang Kou, Renke Bu, Lina Long, Yucheng |
| contents | Motion estimation is a crucial component in multi-object tracking (MOT).
It predicts the trajectory of objects by analyzing the changes in their positions in consecutive frames of images, reducing tracking failures and identity switches.
The Kalman filter (KF) based on the linear constant-velocity model is one of the most commonly used methods in MOT.
However, it may yield unsatisfactory results when KF's parameters are mismatched and objects move in non-stationary.
In this work, we utilize the learning-aided filter to handle the motion estimation of MOT.
In particular, we propose a novel method named Semantic-Independent KalmanNet (SIKNet), which encodes the state vector (the input feature) using a Semantic-Independent Encoder (SIE) by two steps.
First, the SIE uses a 1D convolution with a kernel size of 1, which convolves along the dimension of homogeneous-semantic elements across different state vectors to encode independent semantic information.
Then it employs a fully-connected layer and a nonlinear activation layer to encode nonlinear and cross-dependency information between heterogeneous-semantic elements.
To independently evaluate the performance of the motion estimation module in MOT, we constructed a large-scale semi-simulated dataset from several open-source MOT datasets.
Experimental results demonstrate that the proposed SIKNet outperforms the traditional KF and achieves superior robustness and accuracy than existing learning-aided filters.
The code is available at (https://github.com/SongJgit/filternet and https://github.com/SongJgit/TBDTracker). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_11323 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Motion Estimation for Multi-Object Tracking using KalmanNet with Semantic-Independent Encoding Song, Jian Mei, Wei Xu, Yunfeng Fu, Qiang Kou, Renke Bu, Lina Long, Yucheng Computer Vision and Pattern Recognition Artificial Intelligence Motion estimation is a crucial component in multi-object tracking (MOT). It predicts the trajectory of objects by analyzing the changes in their positions in consecutive frames of images, reducing tracking failures and identity switches. The Kalman filter (KF) based on the linear constant-velocity model is one of the most commonly used methods in MOT. However, it may yield unsatisfactory results when KF's parameters are mismatched and objects move in non-stationary. In this work, we utilize the learning-aided filter to handle the motion estimation of MOT. In particular, we propose a novel method named Semantic-Independent KalmanNet (SIKNet), which encodes the state vector (the input feature) using a Semantic-Independent Encoder (SIE) by two steps. First, the SIE uses a 1D convolution with a kernel size of 1, which convolves along the dimension of homogeneous-semantic elements across different state vectors to encode independent semantic information. Then it employs a fully-connected layer and a nonlinear activation layer to encode nonlinear and cross-dependency information between heterogeneous-semantic elements. To independently evaluate the performance of the motion estimation module in MOT, we constructed a large-scale semi-simulated dataset from several open-source MOT datasets. Experimental results demonstrate that the proposed SIKNet outperforms the traditional KF and achieves superior robustness and accuracy than existing learning-aided filters. The code is available at (https://github.com/SongJgit/filternet and https://github.com/SongJgit/TBDTracker). |
| title | Motion Estimation for Multi-Object Tracking using KalmanNet with Semantic-Independent Encoding |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2509.11323 |