检索结果-内蒙古大学图书馆

MLGT: multi-local guided tracker for visual object tracking

JOURNAL OF REAL-TIME IMAGE PROCESSING 2024年第2期21卷 54-54页

作者： Liang, Xingzhu Chen, Miaomiao Liu, Erhu Anhui Univ Sci & Technol Sch Comp Sci & Engn Huainan 232001 Anhui Peoples R China Anhui Univ Sci & Technol Inst Environm friendly Mat & Occupat Hlth Wuhu 10587 Anhui Peoples R China

Existing single-stream tracking pipelines achieve good performance improvements by joint feature extraction and interaction. These tracking pipelines establish a bidirectional information flow between the template frame and the search frame, using the correlation and dynamic changes between them to improve the modeling and representation capabilities of the object, thereby improving the accuracy and robustness of tracking. However, these tracking pipelines just use the highest level semantic information of the encoder, and the low-level features are only used to compute new activations, which cannot meet the fine-grained requirements of the tracking task. To solve this issue, we propose a new approach named multi-local guided tracker (MLGT), which merges features obtained at various depths to strengthen the interaction between different semantic information. Specifically, we divide the single-stream pipeline into fixed output stages, and each stage is responsible for extracting and processing different levels of features. Then, we pass the output features into an enhanced fusion module (EFM), which incorporates a shared encoder and concatenation operation. The encoder is used to further extract the information in the joint features, and the catenation operation used to fuse features from different output stages. We conduct extensive evaluations on five datasets, among which we achieve 70.5% SUC on the LaSOT dataset, which is 1.4% higher than the existing single-stream tracker OSTrack.

关键词： Transformer visual object tracking Single-stream tracker Enhanced fusion module

来源：评论

学校读者我要写书评

暂无评论

Dynamic template updating Siamese network based on status feedback with quality evaluation for visual object tracking

引用

JOURNAL OF ELECTRONIC IMAGING 2024年第1期33卷 013012-013012页

作者： Sun, Lifan Li, Xinxiang Gao, Dan Fan, Bo Henan Univ Sci & Technol Sch Informat Engn Luoyang Peoples R China Longmen Lab Luoyang Peoples R China

visual object tracking algorithms based on Siamese networks yield promising results through offline training on large benchmarks. However, they cannot adapt well to changes in the target's appearance and tracking scenarios during online tracking because they rely on a single initial template. Most existing template update algorithms use the tracking result of the previous frame to update the template. If the tracking results deteriorate, it can cause the tracker to accumulate incorrect templates, leading to tracking drift. In this work, we proposed a dynamic template updating Siamese network called dynamic template updating (DTU)-Track that utilizes status feedback with quality evaluation for visual object tracking. This network dynamically selects the tracking template for the next frame based on feedback from the tracking result of the previous frame. It calculates the updating quality score and tracking quality score by using the tracking result of the previous frame. The updating quality score determines whether the current tracking result can be stored in the template library. The tracking quality score quantifies the quality of the tracking status of the previous frame. The quality conversion module determines the number of templates required for the next frame by evaluating the tracking quality of the previous frame. The template extraction mechanism selects high-quality, diverse templates from the template library, thereby enabling the tracker to effectively adapt to changes in tracking scenarios and target's appearance in the subsequent frame. Extensive experiments on large-scale benchmarks, such as OTB-2015, UAV123, GOT-10k, trackingNet, and LaSOT, demonstrated our method's superiority over other algorithms in various tracking scenarios, yielding a real-time speed of 36 FPS.

关键词： visual object tracking Siamese network dynamic template quality evaluation template extraction mechanism status feedback

来源：评论

学校读者我要写书评

暂无评论

Precision in visual object tracking: a dual-branch approach

引用

JOURNAL OF ELECTRONIC IMAGING 2024年第2期33卷 023023-023023页

作者： Zhou, Wenjun Wang, Nan Liang, Dong Peng, Bo Southwest Petr Univ Sch Comp Sci & Software Engn Chengdu Peoples R China Nanjing Univ Aeronaut & Astronaut Nanjing Peoples R China

We propose a dual-branch Siamese network for visual object tracking. Our network architecture comprises two distinct branches: a shallow network branch and a deep network branch. The shallow network branch focuses on precise object localization and improving resistance to interference from similar objects. Meanwhile, the deep network branch emphasizes capturing abstract semantic features of the object. To enhance localization accuracy, we integrate a multi-scale KFFM into the shallow network. In addition, we leverage the attention mechanism to further enhance the model's robustness. Through extensive experiments on three publicly available datasets, we demonstrate that our method surpasses state-of-the-art tracking algorithms in terms of performance and accuracy. The source code of this work is available online at https://***/mbgzwn/***.

关键词： dual-branch structure Siamese network multi-scale features visual object tracking

来源：评论

学校读者我要写书评

暂无评论

Hunt-inspired Transformer for visual object tracking

引用

PATTERN RECOGNITION 2024年 156卷

作者： Zhang, Zhibin Xue, Wanli Zhou, Yuxi Zhang, Kaihua Chen, Shengyong Tianjin Univ Technol Sch Comp Sci & Engn 391 Bin Shui Xi Dao Rd Tianjin 300384 Peoples R China Shaanxi Digital Mapping Informat Technol Co Ltd 10 Zhang Ba 1st Rd Xian 710075 Shaanxi Peoples R China Nanjing Univ Informat Sci & Technol Sch Comp Sci 219 Ningliu Rd Nanjing 210044 Jiangsu Peoples R China

This paper presents a hunt-inspired Transformer for visual object tracking, dubbed as HuntFormer. The HuntFormer focuses on robust target detection and identification, simulating natural hunting processes. Specifically, the HuntFormer comprises two essential module designs including a predictor for detection and a verifier for identification. The predictor emulates the detection stage by designing a motion trajectory guided particle filter, which identifies potential target locations by predicting the motion state within a particle filtering framework. The predictor utilizes spatio-temporal correlation scores between dynamic target templates and the search region to guide the learning process to generate a set of reliable particles. This enables the base tracker to narrow its search range to focus on the target, and swiftly re-detect the target in case of model drift. Once the target is re-detected, the verifier assesses the detection result as a reliable tracked item. The verifier initially maintains a dynamic memory that stores reliable target templates and their corresponding locations in the motion trajectory. It then models the uncertainty of appearance information within this memory probabilistically. The output uncertainty score determines whether the memory gets updated or not. Ultimately, the predictor and the verifier collaborate, ensuring a robust tracking outcome. Extensive evaluations on six challenging benchmark datasets demonstrate HuntFormer's favorable performance against various stateof-the-art trackers. Notably, in the VOT-LT2022 tracking challenge, the HuntFormer won the third place with an F-score of 0.598, closely competing for the second place with an F-score of 0.600.

关键词： visual object tracking Particle filter Uncertainty estimation Transformer

来源：评论

学校读者我要写书评

暂无评论

Unified spatio-temporal attention mixformer for visual object tracking

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2024年 134卷

作者： Park, Minho Yoon, Gang-Joon Song, Jinjoo Yoon, Sang Min Kookmin Univ Coll Comp Sci HCI Lab 77 Jeongneung Ro Seoul 02707 South Korea Natl Inst Math Sci 70 Yuseong Daero 1689 Beon Gil Daejeon 34047 South Korea

In this paper, we present a unified spatio-temporal attention MixFormer framework for visual object tracking. Within the vision transformer framework, we design a cohesive network consisting of target template and search region feature extraction, cross -attention utilizing spatial and temporal information, and task -specific heads, all operating in an end -to -end manner. Incorporating spatial and temporal attention modules within the network enables simultaneous feature extraction and emphasis, allowing the model to concentrate on targetspecific discriminative features despite changes in illumination, occlusion, scale, camera pose, and background clutter. Stacking multiple non-hierarchical blocks allows meaningful features to be extracted while irrelevant features are discarded from the provided target template and search region. The simultaneous spatio-temporal attention module is employed to accentuate target appearance features and alleviate variation in the object state across frame sequences. Qualitative and quantitative analysis, including ablation tests based on various tracking benchmarks, validates the robustness of the proposed tracking methodology.

关键词： visual object tracking Unified vision transformer Spatio-temporal model

来源：评论

学校读者我要写书评

暂无评论

Transformer-based visual object tracking via fine-coarse concatenated attention and cross concatenated MLP

引用

PATTERN RECOGNITION 2024年 146卷

作者： Gao, Long Chen, Langkun Liu, Pan Jiang, Yan Li, Yunsong Ning, Jifeng Xidian Univ State Key Lab Integrated Serv Networks Xian 710071 Peoples R China Univ Sheffield Dept Elect & Elect Engn Sheffield S10 2TN England Northwest A&F Univ Coll Informat Engn Yangling 712100 Peoples R China

Transformer-based trackers have demonstrated promising performance in visual object tracking tasks. Never-theless, two drawbacks limited the potential performance improvement of transformer-based trackers. Firstly, the static receptive field of the tokens within one attention layer of the original self-attention learning neglects the multi-scale nature in the object tracking task. Secondly, the learning procedure of the multi-layer perception (MLP) in the feed forward network (FFN) is lack of local interaction information among samples. To address the above issues, a new self-attention learning method, fine-coarse concatenated attention (FCA), is proposed to learn self-attention with fine and coarse granularity information. Moreover, the cross-concatenation MLP (CC-MLP) is developed to capture local interaction information across samples. Based on the two proposed modules, a novel encoder and decoder are constructed, and augmented in an all-attention tracking algorithm, FCAT. Comprehensive experiments on popular tracking datasets, OTB2015, LaSOT, GOT-10K and trackingNet, reveal the effectiveness of FCA and CC-MLP, and FCAT achieves the state-of-art on the datasets.

关键词： visual object tracking Transformer Fine-coarse concatenated attention Multi-layer perceptron Siamese network

来源：评论

学校读者我要写书评

暂无评论

MIMtracking: Masked image modeling enhanced vision transformer for visual object tracking

引用

NEUROCOMPUTING 2024年 606卷

作者： Zhang, Shuo Zhang, Dan Zou, Qi York Univ Lassonde Sch Engn Toronto ON M3J 1P3 Canada Hong Kong Polytech Univ Dept Mech Engn Hung Hom Kowloon Hong Kong Peoples R China

Recently, one-stage trackers achieve state-of-the-art tracking results due to more sufficient integration of search and template representations. These methods usually adopt an encoder for synchronous feature generation and interaction. Despite their high performance, the one-stage approaches tend to feed the encoder full input representations that are highly redundant and dense during training. With a focus on tackling this problem, a novel algorithm termed MIMtracking is developed for visual target tracking. MIMtracking exploits an encoder and a decoder for masked image modeling during training. Randomly sampled discrete search embeddings and template embeddings serve as input of the encoder. The lightweight decoder takes full representations as input and progressively highlights the target region. This design alleviates input redundancy and reduces the computational cost of the training process, thereby allowing for more efficient learning of useful representations. The proposed MIMtracking achieves state-of-the-art tracking results on numerous tracking datasets, e.g., 51.5% area under curve (AUC) on LaSOText, outperforming the previous top tracker OSTrack by 2 %. Especially, our large model MIMtracking-L further improves the AUC to 53.4 % on LaSOText.

关键词： visual object tracking Masked image modeling (MIM) Vision Transformer (ViT)

来源：评论

学校读者我要写书评

暂无评论

Learning Spatial Fusion and Matching for visual object tracking 19th

Learning Spatial Fusion and Matching for Visual Object Track...

引用

19th Pacific Rim International Conference on Artificial Intelligence (PRICAI)

作者： Xiao, Wei Zhang, Zili Southwest Univ Coll Comp & Informat Sci Chongqing 400715 Peoples R China

ISBN: (纸本)9783031208676;9783031208683

Siamese network based trackers have achieved outstanding performance in visual object tracking, which in essence is the application of the efficient cross-correlation as the matching function. However, it is experimentally found that the cross-correlation based matching function is difficult to generate accurate tracking results in some challenging environments, such as background clutters and fast motion. Thus, a new Siamese-based tracker named SiamFAM is proposed. Specifically, from the perspective of feature fusion, a new matching function named Concatenation is introduced into our tracker, which can reduce the influence of background clutters by fine-grained matching with little computational overhead. Meanwhile, an adaptively spatial feature fusion (ASFF) module is proposed, which can take full use of multi-layer features and reduce poor prediction results during the prediction process. In addition, a refinement module is adopted to reduce the occurrence of tracking drift. Extensive experiments are conducted on six challenging benchmarks, including VOT2016, VOT2019, UAV123, NFS, OTB100, and LaSOT, demonstrating that our tracker is practical and can achieve a leading performance.

关键词： visual object tracking Siamese network Feature fusion

来源：评论

学校读者我要写书评

暂无评论

Towards accurate estimation for visual object tracking with multi-hierarchy feature aggregation

引用

NEUROCOMPUTING 2021年 451卷 252-264页

作者： Wu, Jingjing Jiang, Jianguo Qi, Meibin Li, Xiaohong Hefei Univ Technol Hefei Peoples R China Hefei Univ Technol Minist Educ Key Lab Knowledge Engn Big Data Hefei Peoples R China

Many methods achieve the visual object tracking task with deep learning technologies. As the deep features of different levels contain various semantic information and functions, this paper presents a multi hierarchy feature aggregation approach to tackle the specific issues in the tracking task, which consists of two aspects. On one hand, this paper integrates the features captured by the offline and online classifiers at the score level, which constructs complementary roles of these classifiers to enhance the stability of classification. Besides, the proposed offline classifier is continuously optimized with different levels of features to reinforce classification constraints. On the other hand, we design a butterfly attention module to promote the capacity of multi-hierarchy feature aggregation in the regression network, which aims to fuse and strengthen the multi-scale features by attending to their spatial information. It can capture more spatial contexts by utilizing the self-attention mechanism during the fusion procedure, and preserve the hierarchy of the features during the strengthening process. Extensive experiments on four public data sets, i.e., VOT2018, OTB100, NFS and LaSOT datasets, demonstrate the effectiveness of the proposed methods. (c) 2021 Elsevier B.V. All rights reserved.

关键词： visual object tracking Multi-hierarchy feature aggregation Classification score fusion Butterfly attention module

来源：评论

学校读者我要写书评

暂无评论

Siamese visual object tracking: A Survey

引用

IEEE ACCESS 2021年 9卷 110149页

作者： Ondrasovic, Milan Tarabek, Peter Univ Zilina Dept Math Methods & Operat Res Zilina 01026 Slovakia

object tracking belongs to active research areas in computer vision. We are interested in matching-based trackers exploiting deep machine learning known as Siamese trackers. Their powerful capabilities stem from similarity learning. This tracking paradigm is promising due to its inherent balance between performance and efficiency, so trackers of this type are suitable for real-time generic object tracking. There is an upsurge in research interest in Siamese trackers and the lack of available specialized surveys in this category. In this survey, we aim to identify and elaborate on the most significant challenges the Siamese trackers face. Our goal is to answer what design decisions the authors made and what problems they attempted to solve in the first place. We thus perform an in-depth analysis of the core principles on which Siamese trackers operate with a discussion of incentives behind them. Besides, we provide an up-to-date qualitative and quantitative comparison of the prominent Siamese trackers on established benchmarks. Among other things, we discuss current trends in developing Siamese trackers. Our survey could help absorb the details about the underlying principles of Siamese trackers and the challenges they face.

关键词： Target tracking object tracking visualization Benchmark testing Training Task analysis Feature extraction visual object tracking deep learning Siamese neural networks similarity learning fully convolutional networks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：