检索结果-内蒙古大学图书馆

47th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Liu, Siao Chen, Zhaoyu Li, Wei Zhu, Jiwei Wang, Jiafeng Zhang, Wenqiang Gan, Zhongxue Fudan Univ Acad Engn & Technol Shanghai Peoples R China Fudan Univ Sch Comp Sci Shanghai Peoples R China Dept Engn Res Ctr Intelligent Robot Ji Hua Lab Foshan Peoples R China

ISBN: (纸本)9781665405409

Recently, adversarial attacks have been applied in visual object tracking to deceive deep trackers by injecting imperceptible perturbations into video frames. However, previous work only generates the video-specific perturbations, which restricts its application scenarios. In addition, existing attacks are difficult to implement in reality due to the real-time of tracking and the re-initialization mechanism. To address these issues, we propose an offline universal adversarial attack called Efficient Universal Shuffle Attack. It takes only one perturbation to cause the tracker malfunction on all videos. To improve the computational efficiency and attack performance, we propose a greedy gradient strategy and a triple loss to efficiently capture and attack model-specific feature representations through the gradients. Experimental results show that EUSA can significantly reduce the performance of state-of-the-art trackers on OTB2015 and VOT2018.

关键词： Adversarial examples Offline attack visual object tracking Universal adversarial perturbation

来源：评论

学校读者我要写书评

暂无评论

Exploiting Acceleration of the Target for visual object tracking

引用

IEEE ACCESS 2021年 9卷 73818-73825页

作者： Chen, Xuejun Li, Da Zou, Qixiang Wuhan Univ Technol Sch Informat Engn Wuhan 430070 Peoples R China

Discriminative Correlation Filters (DCF) based trackers have achieved remarkable performance in visual object tracking in recent years. The trackers represent the target with hand-craft features or deep features. To reduce the computational cost and irrelevant information, such trackers choose the region of interest (ROI) as a search window to search the target rather than search exhaustively in each frame. The size of search window, which is fixed in most trackers, can greatly affect the performance of tracker. In order to characterize the motion state of the target, this paper presents the velocity and acceleration in the field of visual object tracking. It is observed that the acceleration can change the search window dynamically and achieve better performance. Experiments on the popular datasets OTB50 and OTB100 demonstrate that the DCF based trackers including the state-of-the-art (SOTA) trackers improve their performance by exploiting acceleration.

关键词： Target tracking Kalman filters Optical flow Correlation visualization Filtering theory object tracking visual object tracking acceleration of target dynamic search window

来源：评论

学校读者我要写书评

暂无评论

Siamese Attentional Cascade Keypoints Network for visual object tracking

引用

IEEE ACCESS 2021年 9卷 7243-7254页

作者： Wang, Ershen Wang, Donglei Huang, Yufeng Tong, Gang Xu, Song Pang, Tao Shenyang Aerosp Univ Sch Elect & Informat Engn Shenyang 110136 Peoples R China

visual object tracking is urgent yet challenging work since it requires the simultaneous and effective classification and estimation of a target. Thus, research on tracking has been attracting a considerable amount of attention despite the limitations of existing trackers owing to deformation, occlusion and motion. For most current tracking methods, researchers have proposed various ways to adopt a multi-scale search or anchors for estimation, but these methods always need prior knowledge and too many hyperparameters. To address these issues, we proposed a novel Siamese Attentional Cascade Keypoints tracking Network named SiamACN to exactly track the object by using keypoints prediction instead of anchors. Compared to complex target prediction, the anchor-free method is performed to avoid plaguy hyperparameters, and a simplified hourglass network with global attention is considered the backbone to improve the tracking efficiency. Further, our framework uses keypoints prediction around the target with cascade corner pooling to simplify the model. To certificate the superiority of our framework, extensive tests are conducted on five tracking benchmarks, including OTB-2015, VOT-2016, VOT-2018, LaSOT and UAV123. Our method achieves the leading performance with an accuracy of 61.2% on VOT2016 and favorably runs at 32 FPS against other competing algorithms, which confirms its effectiveness in real-time applications.

关键词： Target tracking Feature extraction visualization object tracking Detectors Correlation Corner detection visual object tracking siamese network hourglass network global attention cascade corner pooling

来源：评论

学校读者我要写书评

暂无评论

Two-Step Affine Transformation Prediction for visual object tracking

引用

IEEE ACCESS 2021年 9卷 36512-36521页

作者： Zheng, Weiwei Yu, Huimin Lu, Zhaohui Zhejiang Univ Coll Informat Sci & Elect Engn Hangzhou 310007 Peoples R China ZJU League Res & Dev Ctr Hangzhou 310007 Zhejiang Peoples R China Zhejiang Lijia Elect Technol Co Ltd Hangzhou 311800 Zhejiang Peoples R China

The main drawback of correlation filter scheme is that it can only predict translation of the object, ignoring the other affine transformations such as rotation, aspect ratio change, and scale change. This paper tries to address this problem by a two-step affine transformation prediction method. The first step is to predict coarse target translation by the correlation filter model with adaptive model update rate generation. Compared with fixed update rate in existing correlation filter based trackers, the presented method generates the update rate by Long Short-Term Memory model with inputs of historical target templates. The second step maps well-designed features to affine transformation parameters. The designed features contain the information of affine transformation which makes the learning of non-linear mapping function possible. The training samples for on-line filter model update are transformed to the same pose, and they help the learnt filter to represent the object better than non-aligned samples. The proposed network is trained from end to end and achieves competitive performance when comparing with state-of-the-arts trackers on four benchmarks, OTB100, UAV123, VOT2018, and VOT2020.

关键词： Correlation Target tracking Adaptation models Training Predictive models Mathematical model visualization Affine transformation correlation filter feature alignment visual object tracking

来源：评论

学校读者我要写书评

暂无评论

Exploring the Effects of Blur and Deblurring to visual object tracking

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2021年 30卷 1812-1824页

作者： Guo, Qing Feng, Wei Gao, Ruijun Liu, Yang Wang, Song Tianjin Univ Sch Comp Sci & Technol Coll Intelligence & Comp Tianjin 300350 Peoples R China State Adm Cultural Heritage Key Res Ctr Surface Monitoring & Anal Cultural Re Beijing 100061 Peoples R China Tianjin Univ Tianjin Key Lab Cognit Comp & Applicat Tianjin 300350 Peoples R China Nanyang Technol Univ Sch Comp Sci & Engn Singapore 639798 Singapore Zhejiang Univ Inst Comp Innovat Hangzhou 310027 Peoples R China Univ South Carolina Dept Comp Sci & Engn Columbia SC 29208 USA

The existence of motion blur can inevitably influence the performance of visual object tracking. However, in contrast to the rapid development of visual trackers, the quantitative effects of increasing levels of motion blur on the performance of visual trackers still remain unstudied. Meanwhile, although image-deblurring can produce visually sharp videos for pleasant visual perception, it is also unknown whether visual object tracking can benefit from image deblurring or not. In this paper, we present a Blurred Video tracking (BVT) benchmark to address these two problems, which contains a large variety of videos with different levels of motion blurs, as well as ground-truth tracking results. To explore the effects of blur and deblurring to visual object tracking, we extensively evaluate 25 trackers on the proposed BVT benchmark and obtain several new interesting findings. Specifically, we find that light motion blur may improve the accuracy of many trackers, but heavy blur usually hurts the tracking performance. We also observe that image deblurring is helpful to improve tracking accuracy on heavily-blurred videos but hurts the performance of lightly-blurred videos. According to these observations, we then propose a new general GAN-based scheme to improve a tracker's robustness to motion blur. In this scheme, a fine-tuned discriminator can effectively serve as an adaptive blur assessor to enable selective frames deblurring during the tracking process. We use this scheme to successfully improve the accuracy of 6 state-of-the-art trackers on motion-blurred videos.

关键词： tracking Benchmark testing object tracking visualization Target tracking Robustness Video tracking visual object tracking motion blur blurred video tracking deblurring

来源：评论

学校读者我要写书评

暂无评论

Efficient correlation information mixer for visual object tracking

引用

KNOWLEDGE-BASED SYSTEMS 2024年 285卷

作者： Chen, Hang Zhang, Weiguo Yan, Danghui Huang, Lei Yu, Chao Hubei Polytech Univ Sch Elect & Elect Informat Engn Huangshi 435003 Peoples R China Northwestern Polytech Univ Sch Automat Xian 710072 Peoples R China

Recently, Siamese tracking framework has been widely used in the visual tracking community. Siamese trackers usually use Cross-Correlation to aggregate templates and search information, so they realize the encoding of target information. However, the previous Cross-Correlation methods either ignore the object channel semantic information or ignore the object's local information. This seriously limits the representation of embedded correlation features and reduces the performance of the trackers. In this paper, to solve these problems, we propose an effective correlation information mixer for visual target tracking. We design an information fusion network to efficiently aggregate template features and search features. In the information fusion network, we use Depthwise Cross-Correlation and Pointwise Cross-Correlation to extract the channel semantic information and local information of the object respectively, and use the correlation information mixer to fully fuse the two correlation maps to achieve the optimal target information encoding. Extensive experimental results show that our tracker achieves competitive performance compared with other state-of-the-art trackers on four benchmarks, including OTB, VOT, UAV123, and LaSOT.

关键词： visual object tracking Depthwise cross correlation Pointwise cross correlation Correlation information mixer

来源：评论

学校读者我要写书评

暂无评论

visual object tracking via precise localization

引用

JOURNAL OF ELECTRONIC IMAGING 2020年第3期29卷

作者： Liu, Xiaodong Jiang, Min Kong, Jun Jiangnan Univ Jiangsu Prov Engn Lab Pattern Recognit & Computat Wuxi Jiangsu Peoples R China

Recently, trackers composed of a target estimation module and a target classification module have presented excellent accuracy with high efficiency. However, they underperform when encountering background semantic interference, large-scale variation, and long-term tracking. To address these problems, we propose a two-stage tracking framework. First, we propose a more applicable objective function for tracking tasks named metrizable intersection over union by considering the alignment mode and the center distance between two bounding boxes. Second, multilevel features are used to eliminate the semantic ambiguity by exploring diverse semantic information. Third, a meta-synthetic decision strategy is proposed to determine the optimum location of the target. In comprehensive experiments on OTB100, Lasot, trackingNet, TColor-128, UAV123, and UAV20L, our method performs favorably against state-of-the-art trackers. (C) 2020 SPIE and IS&T

关键词： visual object tracking multilevel feature fusion meta-synthetic decision metrizable intersection over union

来源：评论

学校读者我要写书评

暂无评论

visual object tracking via iterative ant particle filtering

引用

IET IMAGE PROCESSING 2020年第8期14卷 1636-1644页

作者： Wang, Fasheng Wang, Yanbo He, Jianjun Sun, Fuming Li, Xucheng Zhang, Junxing Dalian Minzu Univ Sch Informat & Commun Engn Dalian Peoples R China Dalian Neusoft Univ Informat Sch Comp & Software Dalian Peoples R China

visual object tracking remains a challenging task in computer vision although important progress has been made in the past decades. Particle filter (PF) is now a standard framework for solving non-linear/non-Gaussian problems, especially in visual object tracking. This study proposes an ant colony optimisation (ACO)-based iterative PF for object tracking. In the proposed method, the basic idea of ACO is used to simulate the behaviour of a particle moving toward the posterior distribution. Such idea is incorporated into the particle filtering framework in order to overcome the well-known particle impoverishment problem. An iterative unscented Kalman filter is used to design a proposal distribution for particle generation in order to generate better predicted sample states. For the likelihood model, the authors adopt the locality sensitive histogram to model the appearance of the target object, which can better handle the illumination variation during tracking. The experimental results demonstrate that the proposed tracker shows better performance than the other tracking methods.

关键词： computer vision Kalman filters object tracking particle filtering (numerical methods) nonlinear filters ant colony optimisation iterative methods particle impoverishment problem iterative unscented Kalman filter particle generation target object visual object tracking iterative ant particle filtering ant colony optimisation-based ACO-based iterative PF posterior distribution locality sensitive histogram illumination variation

来源：评论

学校读者我要写书评

暂无评论

DYNAMIC TEMPLATE UPDATE FOR visual object tracking 29

DYNAMIC TEMPLATE UPDATE FOR VISUAL OBJECT TRACKING

引用

IEEE International Conference on Image Processing (ICIP)

作者： Yun, Kibum Shim, Kyujin Ko, Kangwook Kim, Changick Korea Adv Inst Sci & Technol KAIST Daejeon South Korea

ISBN: (数字)9781665496209

ISBN: (纸本)9781665496209

Siamese-based trackers have recently demonstrated impressive performance and high speed. Despite their great success, conventional siamese trackers are prone to be fooled when facing appearance variations of target objects because they refer to fixed templates captured from first frames to track target objects in the rest of videos. To address this issue, we propose a novel siamese-based tracking framework utilizing a dual template which consists of a static template and a dynamic template. The dynamic template is updated every update interval and allows the tracker to catch appearance variations of the target over time. Furthermore, we introduce a reliability score which prevents incorrect dynamic templates from degrading tracking performance to ensure reliable dynamic template updates. Experimental results show that our method possesses better discriminability and robustness than the baseline, which utilizes a single static template.

关键词： visual object tracking Siamese network Dynamic template update

来源：评论

学校读者我要写书评

暂无评论

Channel-independent spatially regularized discriminative correlation filter for visual object tracking

引用

JOURNAL OF REAL-TIME IMAGE PROCESSING 2021年第1期18卷 233-243页

作者： Varfolomieiev, A. Natl Tech Univ Ukraine Fac Elect Igor Sikorsky Kyiv Polytech Inst 37 Perem Prospect Kiev Ukraine

The study proposes the improvements for visual object trackers based on discriminative correlation filters. These improvements consist in the development of the channel-independent spatially regularized method for filter calculation, which is based on the alternating direction method of multipliers as well as in the use of additional features that are the result of the backprojection of normalized weighted object histogram. The VOT Challenge 2018 benchmark has confirmed that the proposed approaches allow to increase the tracking robustness. Particularly, by the value of expected average overlap (EAO = 0.1828), the tracker that uses these approaches (CISRDCF) can reach the level of more computationally complex competitors that utilize convolutional neural features. At the same time, the software-optimized version of the CISRDCF tracker, which implements the suggested improvements has moderate computational complexity and can operate in the real-time both on the PC and on the mid-range ARM-based processors, making the CISRDCF tracker promising for embedded applications.

关键词： visual object tracking Discriminative correlation filter Alternating direction method of multipliers Embedded devices

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：