Multi-Template Temporal Siamese Network for Long-Term Object Tracking
- URL: http://arxiv.org/abs/2211.13812v1
- Date: Thu, 24 Nov 2022 22:07:33 GMT
- Title: Multi-Template Temporal Siamese Network for Long-Term Object Tracking
- Authors: Ali Sekhavati and Won-Sook Lee
- Abstract summary: Siamese Network based trackers use the first frame as the ground truth of an object and fail when target appearance changes significantly in next frames.
We propose two ideas to solve both problems.
This tracker achieves state-of-the-art performance on the long-term tracking dataset UAV20L by improving the success rate by a large margin of 15%.
- Score: 0.6853165736531939
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Siamese Networks are one of most popular visual object tracking methods for
their high speed and high accuracy tracking ability as long as the target is
well identified. However, most Siamese Network based trackers use the first
frame as the ground truth of an object and fail when target appearance changes
significantly in next frames. They also have dif iculty distinguishing the
target from similar other objects in the frame. We propose two ideas to solve
both problems. The first idea is using a bag of dynamic templates, containing
diverse, similar, and recent target features and continuously updating it with
diverse target appearances. The other idea is to let a network learn the path
history and project a potential future target location in a next frame. This
tracker achieves state-of-the-art performance on the long-term tracking dataset
UAV20L by improving the success rate by a large margin of 15% (65.4 vs 56.6)
compared to the state-of-the-art method, HiFT. The of icial python code of this
paper is publicly available.
Related papers
- Motion-to-Matching: A Mixed Paradigm for 3D Single Object Tracking [27.805298263103495]
We propose MTM-Tracker, which combines motion modeling with feature matching into a single network.
In the first stage, we exploit the continuous historical boxes as motion prior and propose an encoder-decoder structure to locate target coarsely.
In the second stage, we introduce a feature interaction module to extract motion-aware features from consecutive point clouds and match them to refine target movement.
arXiv Detail & Related papers (2023-08-23T02:40:51Z) - MBPTrack: Improving 3D Point Cloud Tracking with Memory Networks and Box
Priors [59.55870742072618]
3D single object tracking has been a crucial problem for decades with numerous applications such as autonomous driving.
We present MBPTrack, which adopts a Memory mechanism to utilize past information and formulates localization in a coarse-to-fine scheme.
arXiv Detail & Related papers (2023-03-09T07:07:39Z) - Target-Aware Tracking with Long-term Context Attention [8.20858704675519]
Long-term context attention (LCA) module can perform extensive information fusion on the target and its context from long-term frames.
LCA uses the target state from the previous frame to exclude the interference of similar objects and complex backgrounds.
Our tracker achieves state-of-the-art performance on multiple benchmarks, with 71.1% AUC, 89.3% NP, and 73.0% AO on LaSOT, TrackingNet, and GOT-10k.
arXiv Detail & Related papers (2023-02-27T14:40:58Z) - Single Object Tracking through a Fast and Effective Single-Multiple
Model Convolutional Neural Network [0.0]
Recent state-of-the-art (SOTA) approaches are proposed based on taking a matching network with a heavy structure to distinguish the target from other objects in the area.
In this article, a special architecture is proposed based on which in contrast to the previous approaches, it is possible to identify the object location in a single shot.
The presented tracker performs comparatively with the SOTA in challenging situations while having a super speed compared to them (up to $120 FPS$ on 1080ti)
arXiv Detail & Related papers (2021-03-28T11:02:14Z) - Multiple Convolutional Features in Siamese Networks for Object Tracking [13.850110645060116]
Multiple Features-Siamese Tracker (MFST) is a novel tracking algorithm exploiting several hierarchical feature maps for robust tracking.
MFST achieves high tracking accuracy, while outperforming the standard siamese tracker on object tracking benchmarks.
arXiv Detail & Related papers (2021-03-01T08:02:27Z) - MFST: Multi-Features Siamese Tracker [13.850110645060116]
Multi-Features Siamese Tracker (MFST) is a novel tracking algorithm exploiting several hierarchical feature maps for robust deep similarity tracking.
MFST achieves high tracking accuracy, while outperforming several state-of-the-art trackers, including standard Siamese trackers.
arXiv Detail & Related papers (2021-03-01T07:18:32Z) - Graph Attention Tracking [76.19829750144564]
We propose a simple target-aware Siamese graph attention network for general object tracking.
Experiments on challenging benchmarks including GOT-10k, UAV123, OTB-100 and LaSOT demonstrate that the proposed SiamGAT outperforms many state-of-the-art trackers.
arXiv Detail & Related papers (2020-11-23T04:26:45Z) - Learning Spatio-Appearance Memory Network for High-Performance Visual
Tracking [79.80401607146987]
Existing object tracking usually learns a bounding-box based template to match visual targets across frames, which cannot accurately learn a pixel-wise representation.
This paper presents a novel segmentation-based tracking architecture, which is equipped with a local-temporal memory network to learn accurate-temporal correspondence.
arXiv Detail & Related papers (2020-09-21T08:12:02Z) - Efficient Adversarial Attacks for Visual Object Tracking [73.43180372379594]
We present an end-to-end network FAN (Fast Attack Network) that uses a novel drift loss combined with the embedded feature loss to attack the Siamese network based trackers.
Under a single GPU, FAN is efficient in the training speed and has a strong attack performance.
arXiv Detail & Related papers (2020-08-01T08:47:58Z) - Ocean: Object-aware Anchor-free Tracking [75.29960101993379]
The regression network in anchor-based methods is only trained on the positive anchor boxes.
We propose a novel object-aware anchor-free network to address this issue.
Our anchor-free tracker achieves state-of-the-art performance on five benchmarks.
arXiv Detail & Related papers (2020-06-18T17:51:39Z) - TAO: A Large-Scale Benchmark for Tracking Any Object [95.87310116010185]
Tracking Any Object dataset consists of 2,907 high resolution videos, captured in diverse environments, which are half a minute long on average.
We ask annotators to label objects that move at any point in the video, and give names to them post factum.
Our vocabulary is both significantly larger and qualitatively different from existing tracking datasets.
arXiv Detail & Related papers (2020-05-20T21:07:28Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.