检索结果-内蒙古大学图书馆

visual object tracking based on adaptive deblurring integrating motion blur perception

JOURNAL OF visual COMMUNICATION AND IMAGE REPRESENTATION 2025年 107卷

作者： Sun, Lifan Gong, Baocheng Liu, Jianfeng Gao, Dan Henan Univ Sci & Technol Sch Informat Engn Luoyang 471023 Peoples R China Longmen Lab Luoyang 471000 Peoples R China Henan Acad Sci Zhengzhou 450046 Peoples R China

visual object tracking in motion-blurred scenes is crucial for applications such as traffic monitoring and navigation, including intelligent video surveillance, robotic vision navigation, and automated driving. Existing tracking algorithms primarily cater to sharp images, exhibiting significant performance degradation in motion- blurred scenes. Image degradation and decreased contrast resulting from motion blur compromise feature extraction quality. This paper proposes a visual object tracking algorithm, SiamADP, based on adaptive deblurring and integrating motion blur perception. First, the proposed algorithm employs a blur perception mechanism to detect whether the input image is severely blurred. After that, an effective motion blur removal network is used to generate blur-free images, facilitating rich and useful feature information extraction. Given the scarcity of motion blur datasets for object tracking evaluation, four test datasets are proposed: three synthetic datasets and a manually collected and labeled real motion blur dataset. Comparative experiments with existing trackers demonstrate the effectiveness and robustness of SiamADP in motion blur scenarios, validating its performance.

关键词： visual object tracking Adaptive deblurring Siamese network Motion blur perception

来源：评论

学校读者我要写书评

暂无评论

visual object tracking With Multi-Frame Distractor Suppression

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2025年第3期35卷 2556-2569页

作者： Han, Yamin Cai, Mingyu Wu, Jie Bai, Zhixuan Zhuo, Tao Zhang, Hongming Zhang, Yanning Northwest A&F Univ Coll Informat Engn Xianyang 712100 Peoples R China Shaanxi Agr Informat Intelligent Sensing & Anal En Yangling 712100 Shaanxi Peoples R China Northwestern Polytech Univ Sch Comp Sci Xian 710072 Peoples R China Natl Engn Lab Integrated Aerosp Ground Ocean Big D Xian 710072 Peoples R China Shaanxi Prov Key Lab Speech & Image Informat Proc Xian 710072 Peoples R China

With the rapid development of CNN or Transformer, the present mainstream approaches regard an image patch as the reference of the target to perform tracking, which is known as template matching-based trackers. However, most existing template matching-based trackers only consider the per-frame localization accuracy, neglecting the potential distractor (similar object) dependencies among multiple video frames, which poses a fundamental challenge in template matching-based tracking. In this work, we propose a novel comprehensive framework with multi-frame distractor suppression for visual object tracking (MFDSTrack), which explicitly models the temporal history of both the target object and potential distractors. Specifically, we utilize a universal target candidate generation module to detect target candidates (both target and distractors), providing a holistic view of the scene. In addition, a temporal and distractor-aware association module is designed to suppress multi-frame distractors by adopting a simple encoder-decoder Transformer architecture. The encoder accepts inputs of target candidates' history, while the decoder takes current target candidate queries and the output of the encoder as inputs to associate current target candidate queries with historical trajectories. We extensively evaluate our trackers, MFDSTrack-SD, MFDSTrack-OS, MFDSTrack-GRM, and MFDSTrack-LT on the LaSOT, LaSOText, trackingNet, GOT-10k, UAV123, NFS, and OTB100 benchmark. Extensive experiments show that our methods outperform previous state-of-the-art trackers on seven tracking benchmarks.

关键词： visual object tracking multi-frame distractor temporal and distractor-aware transformer visual object tracking multi-frame distractor temporal and distractor-aware transformer

来源：评论

学校读者我要写书评

暂无评论

visual object tracking using learnable target-aware token emphasis

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2025年 149卷

作者： Park, Minho Song, Jinjoo Yoon, Sang Min Kookmin Univ Coll Comp Sci HCI Lab 77 Jeongneung Ro Seoul 02707 South Korea

visual object tracking, which involves tracking the spatial location of a target object either within a single viewpoint or across various camera perspectives, is an important task in computer vision. Deep neural networks, especially vision transformers, typically outperform traditional methods and have thus become the preferred choice for visual object tasks. However, existing visual object tracking frameworks still struggle to adapt to targets with continuously changing appearances within the current frame, as they rely heavily on the static initial target template rather than continuously emphasizing the evolving target features. In this paper, we introduce a visual object tracking network with a learnable target-aware token emphasis, which is composed of vision transformer backbone embedded in the token emphasizer, localization head and target template update decision module. The learnable target-aware token emphasizer and target template update decision modules in the proposed model contribute to stabilizing visual object tracking across various scenarios. This is achieved not only by emphasizing features that have a relationship between the target template and the search region but also by reducing irrelevant features and consistently updating the high-quality target template online during the process. Qualitative and quantitative analyses, including ablation analysis across a diverse set of tracking benchmark datasets, validate the robustness of the proposed tracking framework. The code and trained models are available at https://***/qkdkralsgh/TETrack.

关键词： visual object tracking Target aware token emphasis Unified tracking model

来源：评论

学校读者我要写书评

暂无评论

visual object tracking With Discriminative Filters and Siamese Networks: A Survey and Outlook

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2023年第5期45卷 6552-6574页

作者： Javed, Sajid Danelljan, Martin Khan, Fahad Shahbaz Khan, Muhammad Haris Felsberg, Michael Matas, Jiri Khalifa Univ Sci & Technol EECS Dept Abu Dhabi 127788 U Arab Emirates Swiss Fed Inst Technol Dept Informat Technol & Elect Engn Comp Vis Lab CH-8092 Zurich Switzerland MBZUAI Comp Vis Dept Abu Dhabi U Arab Emirates Linkoping Univ Comp Vis Lab S-58183 Linkoping Sweden Czech Tech Univ Ctr Machine Percept Prague 16636 Czech Republic

Accurate and robust visual object tracking is one of the most challenging and fundamental computer vision problems. It entails estimating the trajectory of the target in an image sequence, given only its initial location, and segmentation, or its rough approximation in the form of a bounding box. Discriminative Correlation Filters (DCFs) and deep Siamese Networks (SNs) have emerged as dominating tracking paradigms, which have led to significant progress. Following the rapid evolution of visual object tracking in the last decade, this survey presents a systematic and thorough review of more than 90 DCFs and Siamese trackers, based on results in nine tracking benchmarks. First, we present the background theory of both the DCF and Siamese tracking core formulations. Then, we distinguish and comprehensively review the shared as well as specific open research challenges in both these tracking paradigms. Furthermore, we thoroughly analyze the performance of DCF and Siamese trackers on nine benchmarks, covering different experimental aspects of visual tracking: datasets, evaluation metrics, performance, and speed comparisons. We finish the survey by presenting recommendations and suggestions for distinguished open challenges based on our analysis.

关键词： Target tracking Correlation object tracking Feature extraction visualization Benchmark testing Training visual object tracking discriminative correlation filters siamese networks

来源：评论

学校读者我要写书评

暂无评论

visual object tracking via kernelized correlation filter and grey prediction

ENGINEERING RESEARCH EXPRESS

引用

ENGINEERING RESEARCH EXPRESS 2025年第1期7卷

作者： Lv, Mingming Xu, Qian Geng, Xinxin Fang, Jiwen Jiangsu Univ Sci & Technol Sch Mech Engn Zhenjiang 212100 Peoples R China

Due to the effects of deformation, scale changes and background interference, visual tracking has always been one of the challenging problems. In recent years, kernelized correlation filter (KCF) has attracted much attention. However, the tracking accuracy of KCF tracker is poor when the object fast motion, heavy occlusion and scale variation appear. Herein, this reason is analyzed that the KCF tracker generates candidate patches of object according to its location in the last frame. By establishing grey prediction model of object motion, we produce the candidate patches around the predicted location. Moreover, we apply an adaptive strategy to update model and employ a simple mechanism for scale estimation. We conduct our tracker on some tracking benchmarks, including OTB2013, VOT2016 and UAV123. Experimental results demonstrate the proposed tracking method has good and stable results.

关键词： visual object tracking correlation filter grey prediction model update scale estimation

来源：评论

学校读者我要写书评

暂无评论

visual object tracking Based on Light-Field Imaging in the Presence of Similar Distractors

引用

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 2023年第3期19卷 2705-2716页

作者： Wang, Mianzhao Shi, Fan Cheng, Xu Zhao, Meng Zhang, Yao Jia, Chen Tian, Weiwei Chen, Shengyong Tianjin Univ Technol Engn Res Ctr Learning Based Intelligent Syst Key Lab Comp Vis & Syst Minist Educ Tianjin 300384 Peoples R China Norwegian Univ Sci & Technol Dept Mfg & Civil Engn NO-2802 Gjovik Norway

visual object tracking is of great importance in the field of computer vision. One of the main challenges is the difficulty of identifying moving targets from nearby similar distractors with a single-view image of the scene. To overcome this challenge, in this article, we acquire multiview images of the scenes by using a light-field camera. The multiview images are able to capture the 4-D structure instead of the 2-D plane of the objects but are more difficult to process. Therefore, we propose a novel representation for multiview images, i.e., the macro-epipolar plane image (macro-EPI), which highlights both spatial topological and angular information of the target and distractors. It is obtained by slicing the original multiview images into pieces and properly restacking these pieces in an ordinal manner. The resulting macro-EPI is mapped into the 2-D space;therefore, we adapt a modified autoencoder network to train a macro-EPI feature extractor. Thereafter, we design a composite framework of two-pattern convolution filters based on a discriminative correlation filter for object tracking, which successfully discriminates the target from the distractors by merging the macro-EPI features and the single-view image features. The experiments also show that our method outperforms the state-of-the-art methods in the presence of similar distractors.

关键词： Light-field imaging macro-epipolar plane image (macro-EPI) visual object tracking

来源：评论

学校读者我要写书评

暂无评论

visual object tracking in First Person Vision

引用

INTERNATIONAL JOURNAL OF COMPUTER VISION 2023年第1期131卷 259-283页

作者： Dunnhofer, Matteo Furnari, Antonino Farinella, Giovanni Maria Micheloni, Christian Univ Udine Machine Learning & Percept Lab Via Sci 206 I-33100 Udine Italy Univ Catania Image Proc Lab Viale A Doria 6 I-95125 Catania Italy

The understanding of human-object interactions is fundamental in First Person Vision (FPV). visual tracking algorithms which follow the objects manipulated by the camera wearer can provide useful information to effectively model such interactions. In the last years, the computer vision community has significantly improved the performance of tracking algorithms for a large variety of target objects and scenarios. Despite a few previous attempts to exploit trackers in the FPV domain, a methodical analysis of the performance of state-of-the-art trackers is still missing. This research gap raises the question of whether current solutions can be used "off-the-shelf" or more domain-specific investigations should be carried out. This paper aims to provide answers to such questions. We present the first systematic investigation of single object tracking in FPV. Our study extensively analyses the performance of 42 algorithms including generic object trackers and baseline FPV-specific trackers. The analysis is carried out by focusing on different aspects of the FPV setting, introducing new performance measures, and in relation to FPV-specific tasks. The study is made possible through the introduction of TREK-150, a novel benchmark dataset composed of 150 densely annotated video sequences. Our results show that object tracking in FPV poses new challenges to current visual trackers. We highlight the factors causing such behavior and point out possible research directions. Despite their difficulties, we prove that trackers bring benefits to FPV downstream tasks requiring short-term object tracking. We expect that generic object tracking will gain popularity in FPV as new and FPV-specific methodologies are investigated.

关键词： First person vision Egocentric vision visual object tracking Single object tracking

来源：评论

学校读者我要写书评

暂无评论

APR-Net Tracker: Attention Pyramidal Residual Network for visual object tracking

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE 2025年第1期9卷 552-564页

作者： Liu, Bing Yuan, Di Li, Xiaofang Chongqing Univ Posts & Telecommun Sch Automat Chongqing 400065 Peoples R China Xidian Univ Guangzhou Inst Technol Guangzhou 510555 Peoples R China Changzhou Inst Technol Changzhou 213032 Jiangsu Peoples R China Jiangsu Collaborat Innovat Ctr Cultural Creat Changzhou 213032 Jiangsu Peoples R China

visual object tracking has attracted much attention thanks to its remarkable capability to identify a moving target accurately in real-world video scenarios. Recently, tracking performance has improved significantly. However, there is still a lot of progress space to achieve consummate tracking performance because of the complex and varied target and its surrounding background. How to trade-off between accuracy, robustness, and approximately real-time performance is crucial for visual object tracking. We find that when attention mechanisms are integrated into the pyramidal residual network, they can subtly describe the appearance of the target object, which provides a strong guarantee for accurate, robust, and high-performance visual object tracking. Based on this find, we propose a simple yet powerful visual object tracking algorithm, APR-Net, that automatically searches various scales and significant regions. The comprehensive experimental results on multiple benchmarks demonstrate that the proposed APR-Net tracker attains the desired performance improvement in accuracy and robustness while achieving near real-time tracking performance in various real-world applications.

关键词： Attention mechanism visual object tracking pyramidal convolutional residual network deep learning

来源：评论

学校读者我要写书评

暂无评论

Keypoint prediction enhanced Siamese networks with attention for accurate visual object tracking

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 268卷

作者： Sakthi, K. S. Sachin Joo, Young Hoon Jeong, Jae Hoon Kunsan Natl Univ Sch IT Informat & Control Engn 558 Daehak Ro Gunsan Si 54150 Jeonbuk South Korea Kunsan Natl Univ Coll Comp & Software 558 Daehak Ro Gunsan Si 54150 Jeonbuk South Korea

visual object tracking (VOT) is crucial for many computer vision applications, including autonomous vehicles, surveillance systems, and human-computer interaction. Despite recent advancements, many tracking methods still face difficulties in handling occlusion, illumination changes, and scale variation, which negatively impact tracking accuracy. To overcome these challenges, we present a novel framework, keypoint prediction enhanced Siamese networks with self-attention, designed for robust visual object tracking. Our method utilizes keypoint prediction to provide spatial context, significantly improving performance in complex scenarios. Additionally, we introduce a progressive heatmap refinement technique that sharpens the target localization over multiple stages, further improving accuracy under challenging conditions. The integration of a self-attention mechanism helps the model focus on relevant features, increasing adaptability across diverse tracking environments. Moreover, a cross-attention mechanism is incorporated to enable efficient feature exchange between template and search regions, allowing the model to better distinguish the target from surrounding distractions. Our approach has been extensively tested on benchmark datasets like LaSOT, GOT-10K, OTB100, and UAV123. The results confirm its superior accuracy and reliability compared to state-of-the-art methods, establishing it as an excellent solution for real-world applications.

关键词： Siamese networks Keypoint prediction Attention visual object tracking

来源：评论

学校读者我要写书评

暂无评论

MATI: Multimodal Adaptive tracking Integrator for Robust visual object tracking

引用

SENSORS 2024年第15期24卷 4911页

作者： Li, Kai Cai, Lihua He, Guangjian Gong, Xun Chinese Acad Sci Changchun Inst Opt Fine Mech & Phys Changchun 130033 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China

visual object tracking, pivotal for applications like earth observation and environmental monitoring, encounters challenges under adverse conditions such as low light and complex backgrounds. Traditional tracking technologies often falter, especially when tracking dynamic objects like aircraft amidst rapid movements and environmental disturbances. This study introduces an innovative adaptive multimodal image object-tracking model that harnesses the capabilities of multispectral image sensors, combining infrared and visible light imagery to significantly enhance tracking accuracy and robustness. By employing the advanced vision transformer architecture and integrating token spatial filtering (TSF) and crossmodal compensation (CMC), our model dynamically adjusts to diverse tracking scenarios. Comprehensive experiments conducted on a private dataset and various public datasets demonstrate the model's superior performance under extreme conditions, affirming its adaptability to rapid environmental changes and sensor limitations. This research not only advances visual tracking technology but also offers extensive insights into multisource image fusion and adaptive tracking strategies, establishing a robust foundation for future enhancements in sensor-based tracking systems.

关键词： visual object tracking vision transformer adaptive tracking mechanism multimodal dataset

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：