检索结果-内蒙古大学图书馆

A novel Siamese Attention Network for visual object tracking of autonomous vehicles

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART D-JOURNAL OF AUTOMOBILE ENGINEERING 2021年第10-11期235卷 2764-2775页

作者： Chen, Jia Ai, Yibo Qian, Yuhan Zhang, Weidong Univ Sci & Technol Beijing Natl Ctr Mat Serv Safety 30 Xueyuan Rd Beijing 100083 Peoples R China Southern Marine Sci & Engn Guangdong Lab Innovat Grp Marine Engn Mat & Corros Control Zhuhai Peoples R China Aerosp Times FeiHong Technol Co Ltd Beijing Peoples R China

In the environment perception stage of autonomous driving, vehicles need to track its surrounding objects quickly and accurately to avoid dangerous behaviors. Therefore, visual object tracking has important practical application value in autonomous driving system. However, the performance of most hierarchical convolutional feature trackers are limited by ignoring the complex environment of autonomous driving. In this paper, a novel Siamese Attention Network to explore the rich spatial and channel information of objects was proposed. Because of the lack of important information between the channel and the spatial position, the tracking performance is reduced by the challenges of illumination change and deformation. The spatial attention block and channel attention block focus on the importance of different spatial positions and channels, respectively. The effective fusion of the two makes our tracker achieve the state-of-the art performance of 0.300 in the EAO criterion of 2017, which exceeds the baseline by 5.7%.

关键词： Autonomous vehicles Siamese network spatial attention block channel attention block visual object tracking

来源：评论

学校读者我要写书评

暂无评论

Unsupervised cycle-consistent adversarial attacks for visual object tracking

引用

DISPLAYS 2023年第1期80卷

作者： Yao, Rui Zhu, Xiangbin Zhou, Yong Shao, Zhiwen Hu, Fuyuan Zhang, Yanning China Univ Min & Technol Sch Comp Sci & Technol 1 Daxue Rd Xuzhou 221116 Peoples R China Minist Educ Peoples Republ China Engn Res Ctr Mine Digitizat Xuzhou 221116 Peoples R China Suzhou Univ Sci & Technol Sch Elect & Informat Engn Suzhou 215009 Peoples R China Natl Engn Lab Integrated Aerosp Ground Ocean Big 127 Youyi West Rd Xian 710072 Peoples R China Northwestern Polytech Univ Sch Comp Sci 127 West Youyi Rd Xian 710072 Peoples R China

Adversarial attacks on visual object tracking have been gaining momentum in the quest to assess and enhance the robustness and security of object tracking models. Most adversarial attack strategies for object tracking rely on fully supervised attacks;that is, they necessitate the use of labels. However, it is not feasible to apply these labeled video object tracking techniques to all attacks. As such, this paper presents an unsupervised attack methodology against visual object tracking models. The approach employs the cycle consistency principle of object tracking models to maximize the inconsistency between forward and backward tracking, thereby providing effective countermeasures. Additionally, this paper introduces a contextual attack method, leveraging the information from the attack object's region and its surrounding contextual regions. This strategy attacks the object region and its surrounding context regions simultaneously, aiming to decrease its response score to the attack. The proposed attack method is assessed across various types of deep learning-based object trackers. Experimental results on multiple benchmarks reveal that the suggested method yields competitive attack outcomes.

关键词： Adversarial attack visual object tracking Unsupervised attack Cycle consistency Context attack

来源：评论

学校读者我要写书评

暂无评论

TAT: Targeted backdoor attacks against visual object tracking

引用

PATTERN RECOGNITION 2023年第1期142卷

作者： Cheng, Ziyi Wu, Baoyuan Zhang, Zhenya Zhao, Jianjun Kyushu Univ Fac Informat Sci & Elect Engn Grad Sch Fukuoka 8190395 Japan Chinese Univ Hong Kong Shenzhen Res Inst Big Data Sch Data Sci Shenzhen 518172 Peoples R China

visual object tracking (VOT) is a fundamental computer vision task that aims to track a target in a se-quence of video frames. It has been broadly adopted in safety-and security-critical applications, such as self-driving systems and traffic control systems. However, the VOT models (i.e., the trackers) that rely on third-party training resources face a severe threat of backdoor attacks , which refer to the type of the attacks that poison a portion of training data and mislead the tracker to track a wrong target. A surge of research interest has arisen in backdoor attacks in the domain of image classification, as a measure to expose the potential security risks of the classifiers and inspire new defense techniques. Despite the prosperity of the research in backdoor attacks in image classification, there still lacks investigation in backdoor attacks against VOT, due to their unique challenges: first, the architecture of a VOT model is much more complicated than that of an image classifier;second, VOT targets a sequence of video frames rather than individual images. To bridge the gap, we propose a novel and effective tar geted backdoor attack approach TAT specifically against VOT tasks. In particular, TAT includes a basic version TAT-BA that can achieve effective and stealthy backdoor attacks against VOT trackers, and an advanced version TAT-DA that can evade two representative defense techniques. Our large-scale experimental evaluation demonstrates the effectiveness and the stealthiness of TAT . Moreover, we also demonstrate the perfor-mances of TAT-BA under real-world settings and the abilities of TAT-DA to counter defense techniques. The code will be available at https://***/MisakaZipi/TAT .(c) 2023 Elsevier Ltd. All rights reserved.

关键词： Backdoor attack visual object tracking Targeted attack

来源：评论

学校读者我要写书评

暂无评论

visual object tracking in Spherical 360° Videos: A Bridging Approach 35

Visual Object Tracking in Spherical 360° Videos: A Bridging...

引用

35th International Conference on Image and Vision Computing New Zealand (IVCNZ)

作者： Finnie, Simon Zhang, Fang-lue Rhee, Taehyun Victoria Univ Wellington Computat Media Innovat Ctr Wellington New Zealand Victoria Univ Wellington Wellington New Zealand

ISBN: (纸本)9781728185798

We present a novel approach for adapting existing visual object trackers (VOT) to work for equirectangular video, utilizing image reprojection. Our system can easily be integrated with existing VOT algorithms, significantly increasing the accuracy and robustness of tracking in spherical 360 degrees environments without requiring retraining. Our adapted approach involves the orthographic projection of a subsection of the image centered around the tracked object each frame. Our projection reduces the distortion around the tracked object each frame, allowing the VOT algorithm to more easily track the object as it moves.

关键词： visual object tracking Equirectangular tracking Deep Learning

来源：评论

学校读者我要写书评

暂无评论

Pyramid Correlation based Deep Hough Voting for visual object tracking 13

Pyramid Correlation based Deep Hough Voting for Visual Objec...

引用

13th Asian Conference on Machine Learning (ACML)

作者： Wang, Ying Xu, Tingfa Li, Jianan Jiang, Shenwang Chen, Junjie Beijing Inst Technol Beijing Peoples R China

Most of the existing Siamese-based trackers treat tracking problem as a parallel task of classification and regression. However, some studies show that the sibling head structure could lead to suboptimal solutions during the network training. Through experiments we find that, without regression, the performance could be equally promising as long as we delicately design the network to suit the training objective. We introduce a novel voting-based classification-only tracking algorithm named Pyramid Correlation based Deep Hough Voting (short for PCDHV), to jointly locate the top-left and bottom-right corners of the target. Specifically we innovatively construct a Pyramid Correlation module to equip the embedded feature with fine-grained local structures and global spatial contexts;The elaborately designed Deep Hough Voting module further take over, integrating long-range dependencies of pixels to perceive corners;In addition, the prevalent discretization gap is simply yet effectively alleviated by increasing the spatial resolution of the feature maps while exploiting channel-space relationships. The algorithm is general, robust and simple. We demonstrate the effectiveness of the module through a series of ablation experiments. Without bells and whistles, our tracker achieves better or comparable performance to the SOTA algorithms on three challenging benchmarks (trackingNet, GOT-10k and LaSOT) while running at a real-time speed of 80 FPS. Codes and models will be released.

关键词： visual object tracking Siamese-based tracking algorithm Anchor-free Key point based Pixel-wise correlation Hough voting

来源：评论

学校读者我要写书评

暂无评论

Transformer Union Convolution Network for visual object tracking

引用

OPTICS COMMUNICATIONS 2022年 524卷

作者： Song, Zhehan Chen, Yiming Luo, Peng Feng, Huajun Xu, Zhihai Li, Qi Zhejiang Univ Coll Opt Sci & Engn Hangzhou 310027 Peoples R China Zhejiang Univ Coll Energy Engn Hangzhou 310027 Peoples R China

In visual object tracking, the existing Siamese-like neural network utilizes the superposition of different convolution modules to extract feature maps, which makes the network unable to obtain sufficient global information. Inspired by Transformer, we present a novel method named Transformer Union Convolution Network (TUC-Net) to take the advantage of its encoder-decoder structure. Through the combination of attention mechanism and convolution, the interaction of local and global information between image patches is realized. Specifically, the proposed method includes a feature interaction stage based on feature perception head followed by encoder and a feature fusion stage based on U-Net-like convolution structure and decoder. Experiments shows that our TUC-Net achieves promising results on five challenging datasets compared with state-of-the-art methods. The average running speed of our tracker is approximatively 20 fps on GPU. Besides, we design a dual-resolution camera system with high resolution and large field of view. TUC-Net can be well-equipped with the system and get excellent tracking results.

关键词： visual object tracking Transformer Transformer Union Convolution Network Dual-resolution camera system

来源：评论

学校读者我要写书评

暂无评论

MULTI-TASK OCCLUSION LEARNING FOR REAL-TIME visual object tracking

MULTI-TASK OCCLUSION LEARNING FOR REAL-TIME VISUAL OBJECT TR...

引用

IEEE International Conference on Image Processing (ICIP)

作者： Sahin, Gozde Itti, Laurent Univ Southern Calif Comp Sci Dept University Pk PA 90089 USA

ISBN: (纸本)9781665441155

Occlusion handling is one of the important challenges in the field of visual tracking, especially for real-time applications, where further processing for occlusion reasoning may not always be possible. In this paper, an occlusion-aware real-time object tracker is proposed, which enhances the baseline SiamRPN model with an additional branch that directly predicts the occlusion level of the object. Experimental results on GOT-10k and VOT benchmarks show that learning to predict occlusion levels end-to-end in this multi-task learning framework helps improve tracking accuracy, especially on frames that contain occlusions. Up to 7% improvement on EAO scores can be observed for occluded frames, which are only 11% of the data. The performance results over all frames also indicate the model does favorably compared to the other trackers.

关键词： visual object tracking siamese network occlusion

来源：评论

学校读者我要写书评

暂无评论

Adaptive decision-level fusion and complementary mining for visual object tracking with deeper networks

引用

JOURNAL OF ELECTRONIC IMAGING 2020年第4期29卷 43024-43024页

作者： Meng, Xiaoyan Chen, Yangzhou Xin, Le Beijing Univ Technol Fac Informat Technol Beijing Peoples R China Beijing Univ Technol Minist Educ Engn Res Ctr Intelligent Percept & Autonomous Con Coll Artificial Intelligence & Automat Beijing Peoples R China

Multiple region proposal networks (RPNs) have been recently combined with the Siamese network with deeper backbone networks for tracking and shown excellent accuracy with high efficiency. Although the destruction of the strict translation invariance caused by network padding in the original ResNet-50 is solved by a custom sampling strategy, its impact is not eliminated from the network structure itself, and the multilayer feature fusion is insufficient. To this end, we propose an object tracking framework based on SiamRPN with the deeper backbone networks and cascaded RPN (D-CRPN). First, we exploit the cropping-inside residual units for reforming ResNet-50 to break the spatial invariance restriction and train the robust backbone networks for visual tracking. Then, the feature transfer blocks are proposed to achieve the effective integration of the outputs of multiple blocks in a specific network stage. Finally, to improve the robustness of our tracker, we present a quality measure for the synthetic response maps of RPN modules and then use it to calculate the adaptive weights for the linear weighting method. The extensive evaluation performed on OTB100, VOT2016, and VOT2018 benchmark datasets demonstrates that the proposed D-CRPN tracker outperforms most of the state-of-the-art approaches while maintaining real-time tracking speed. (C) 2020 SPIE and IS&T

关键词： visual object tracking deep neural networks Siamese network cascaded region proposal networks

来源：评论

学校读者我要写书评

暂无评论

Learning target-focusing convolutional regression model for visual object tracking

引用

KNOWLEDGE-BASED SYSTEMS 2020年 194卷 105526-105526页

作者： Yuan, Di Fan, Nana He, Zhenyu Harbin Inst Technol Sch Comp Sci & Technol Shenzhen 518055 Peoples R China Peng Cheng Lab Shenzhen 518055 Peoples R China

Discriminative correlation filters (DCFs) have been widely used in the tracking community recently. DCFs-based trackers utilize samples generated by circularly shifting from an image patch to train a ridge regression model, and estimate target location using a response map generated by the correlation filters. However, the generated samples produce some negative effects and the response map is vulnerable to noise interference, which degrades tracking performance. In this paper, to solve the aforementioned drawbacks, we propose a target-focusing convolutional regression (CR) model for visual object tracking tasks (called TFCR). This model uses a target-focusing loss function to alleviate the influence of background noise on the response map of the current tracking image frame, which effectively improves the tracking accuracy. In particular, it can effectively balance the disequilibrium of positive and negative samples by reducing some effects of the negative samples that act on the object appearance model. Extensive experimental results illustrate that our TFCR tracker achieves competitive performance compared with state-of-the-art trackers. (C) 2020 Elsevier B.V. All rights reserved.

关键词： visual object tracking Discriminative correlation filters Target-focusing model Convolutional regression

来源：评论

学校读者我要写书评

暂无评论

Combining complementary trackers for enhanced long-term visual object tracking

引用

IMAGE AND VISION COMPUTING 2022年 122卷

作者： Dunnhofer, Matteo Simonato, Kristian Micheloni, Christian Univ Udine Machine Learning & Percept Lab Via Sci 206 I-33100 Udine Italy

Several different algorithms have been studied to combine the capabilities of baseline trackers in the context of short-term visual object tracking. Despite such an extended interest, the long-term setting has not been taken into consideration by previous studies. In this paper, we explicitly consider long-term tracking scenarios and provide a framework to fuse the characteristics of complementary state-of-the-art trackers to achieve enhanced tracking performance. Our strategy perceives whether the two trackers are following the target object through an online learned deep verification model. Such a target recognition strategy enables the activation of a decision strategy which selects the best performing tracker as well as it corrects their performance when failing. The proposed solution is studied extensively and the comparison with several other approaches reveals that it beats the state-of-the-art on the long-term visual tracking benchmarks LTB-35, LTB-5 0, TLP, and LaSOT. (c) 2022 Elsevier B.V. All rights reserved.

关键词： Video tracking visual object tracking Long-term visual tracking Deep learning

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：