检索结果-内蒙古大学图书馆

23rd International Conference on Information Fusion (FUSION)

作者： Javed, Sajid Zhang, Xiaoxiong Seneviratne, Lakmal Dias, Jorge Werghi, Naoufel Khalifa Univ Sci & Technol Khalifa Univ Ctr Autonomous Robot Syst KUCARS Abu Dhabi U Arab Emirates

ISBN: (纸本)9780578647098

visual object tracking (VOT) is an essential task for many computer vision applications. VOT becomes challenging when a target object faces severe occlusion, drastic illumination changes, and scale variation problems. In the literature, Discriminative Correlation Filters (DCFs)-based tracking methods have achieved promising results in terms of accuracy and efficiency in many complex VOT scenarios. A plethora of DCFs trackers have been proposed which exploit information observed in past frames to create and update DCFs for VOT. To adapt to target appearance variations, the DCFs are enhanced by incorporating spatial and temporal consistency constraints. Nevertheless, the performance degradation is observed for these methods because of the aforementioned limitations. To address these issues, we propose a novel algorithm based on bidirectional DCFs for VOT. In this algorithm, we propose the original idea of leveraging information from both past and future frames. The proposed algorithm first tracks the target object forward in the video sequence and then its uses the predicted location of the last window frame and track the target object backward towards the current frame. We design an appearance consistency loss function by taking the L2 norm between the regression target of the forward tracking and response map of the backward tracking to obtain the resulting response map. Our proposed algorithm realizes a highly accurate DCFs because forward and backward tracking information are fused together for consistent VOT. Although, a result will be output with some small delay because information is taken from a future to the present period, our proposed algorithm has the merit of addressing the drastic appearance variations VOT challenges. We evaluate our proposed tracker using deep features on three publicly available challenging datasets. Our results demonstrate the superior performance of the proposed tracker compared to the existing state-of-the-art trackers.

关键词： visual object tracking Correlation Filters Deep Learning

来源：评论

学校读者我要写书评

暂无评论

visual object tracking by Using Ranking Loss 17

Visual Object Tracking by Using Ranking Loss

引用

IEEE/CVF International Conference on Computer Vision (ICCV)

作者： Cevikalp, Hakan Saribas, Hasan Benligiray, Burak Kahvecioglu, Sinem Eskisehir Osmangazi Univ Elect & Elect Engn Dept Eskisehir Turkey Eskisehir Tech Univ Elect & Elect Engn Dept Eskisehir Turkey

ISBN: (纸本)9781728150239

This paper introduces a novel deep neural network tracker for robust object tracking. To this end, we employ a ranking loss which provides a fine-tuning of the target object position and returns more precise bounding boxes framing the target object. This is achieved by systematically learning to give higher scores to the candidate regions better framing the target object than the regions that frame the object with less accuracy. As a result, the risk of tracking error accumulation and drifts are largely mitigated, and the object is tracked more successfully: When the proposed network is used with a simple yet effective model update rule, our proposed tracker achieves the state-of-the-art results on all tested challenging tracking datasets. Especially, our results on the OTB (object tracking Benchmark) datasets are very promising. The proposed tracker outperforms both deep neural network and correlation filter based trackers, MDNet and ECO, by about 2%, which is a significant improvement over the previous state-of-the-art.

关键词： Deep neural network classifier Ranking loss visual object tracking

来源：评论

学校读者我要写书评

暂无评论

An Implementation of a Robust visual object tracking System 13

An Implementation of a Robust Visual Object Tracking System

引用

13th International Conference on Advanced Technologies for Communications (ATC)

作者： Nguyen, An Hoang Mai, Linh Do, Hung Ngoc Vietnam Natl Univ Hochiminh City Sch Elect Engn Int Univ Hochiminh City Vietnam

ISBN: (纸本)9781728180656

Robust visual tracking system with high level of accuracy against complex tracking scenarios containing many visual attributes has been a challenging research topic in computer vision field. Among different types of visual attributes, scale variation is considered as one of the most difficult problems. Existing tracking methods either fail to handle great change of target size, or employ exhaustive scale estimation with the cost of high computational load. This paper presents a method of accurately adapting the change in target scale which employs dense spatio-temporal context for localizing target position, with the intention to increase tracking performance while maintaining low computational cost. In particular, the tracking task for determining target position is computed by utilizing the spatiotemporal context relationship between the target and its surrounding regions. Then the spatial correlation is analyzed to update target position in subsequent frames. In the meantime, the model also estimates the change of target by applying a scale filter, which learns the change in appearance of a set of various value of scales. Finally, the proposed method is evaluated by using the image sequences in TB100 dataset with different performance evaluation tests.

关键词： visual object tracking scale variation spatiotemporal context adaptive scale estimation

来源：评论

学校读者我要写书评

暂无评论

CSASN: Learning Complementary Spatial-Aware Siamese Networks for visual object tracking 32

CSASN: Learning Complementary Spatial-Aware Siamese Networks...

引用

32nd IEEE International Conference on Tools with Artificial Intelligence (ICTAI)

作者： She, Ying Yi, Yang Sun Yat Sen Univ Sch Data & Comp Sci Guangzhou Peoples R China

ISBN: (纸本)9781728192284

Recently, Siamese networks have drawn great attention in visual object tracking due to their balanced accuracy and speed. However, most such trackers inherently learn the general object representation which cannot discriminate targets from similar distractors robustly, thus making it easier to drift. To tackle this challenging problem, we propose a novel architecture named Complementary Spatial-Aware Siamese Network (CSACN), which consists of two branches. In the Siamese branch, a Siamese network with a Correlation Filter(CF) layer cascaded is adopted for convolutional feature extraction and online tracking process. In the Complementary Spatial-Aware(CSA) branch, target-specific features are extracted from Histogram-related Probability Module (HPM) and Edge-related Template Module (ETM) to further boost the tracking capacity. Especially, a novel Spatial-Aware Module (SAM) is employed to penalize large inter-frame movements, thus correcting the object location effectively. Finally, an adaptive update strategy is proposed to alleviate the contamination of training samples. Extensive evaluations on OTB-2013, OTB-2015, VOT-2016 and VOT-2017 datasets demonstrate that CSASN is very promising for various challenging scenarios compared with several state-of-the-art trackers while running at 45 frames per second.

关键词： visual object tracking model drift Siamese network Complementary Spatial-Aware network model update

来源：评论

学校读者我要写书评

暂无评论

STResNet_CF Tracker: The Deep Spatiotemporal Features Learning for Correlation Filter Based Robust visual object tracking

引用

IEEE ACCESS 2019年 7卷 30142-30156页

作者： Zhu, Zhengyu Liu, Bing Rao, Yunbo Liu, Qiao Zhang, Rui Chongqing Univ Coll Comp Sci Chongqing 400044 Peoples R China Chongqing Univ Posts & Telecommun Coll Comp Sci & Technol Chongqing 400065 Peoples R China Univ Elect Sci & Technol China Sch Informat & Software Engn Chengdu 610054 Sichuan Peoples R China Harbin Inst Technol Shenzhen Grad Sch Sch Comp Sci & Technol Shenzhen 518000 Peoples R China

Constructing a robust appearance model of the visual object is a crucial task for visual object tracking. Recently, more and more studies combine spatial feature with a temporal feature to improve the tracking performance. These methods successfully apply the features from spatial and temporal to address the problem for tracking. This paper presents a novel method for visual object tracking based on spatiotemporal feature combined with correlation filters. In this paper, the visual features of a target object are extracted from a spatial-temporal residual network (STResNet) appearance model with two sub-networks. The STResNet appearance model learns separately spatial feature and temporal feature, respectively, so that we can effectively utilize spatial context around the surrounding of the target object in each frame and the temporal relationship between successive frames to refine the appearance representation of the target object. Finally, our spatiotemporal fusion feature from STResNet appearance model is incorporated into the correlation filter for robust visual object tracking. The experimental results show that our method achieves similar or better performance compared with the other tracking methods based on convolutional neural networks or correlation filter.

关键词： Spatiotemporal residual network correlation filter visual object tracking deep learning convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Semantics-Aware visual object tracking

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2019年第6期29卷 1687-1700页

作者： Yao, Rui Lin, Guosheng Shen, Chunhua Zhang, Yanning Shi, Qinfeng China Univ Min & Technol Sch Comp Sci & Technol Xuzhou 221116 Jiangsu Peoples R China Nanyang Technol Univ Sch Comp Sci & Engn Singapore 639798 Singapore Univ Adelaide Sch Comp Sci Adelaide SA 5005 Australia Northwestern Polytech Univ Sch Comp Sci Xian 710072 Shaanxi Peoples R China

In this paper, we propose a semantics-aware visual object tracking method, which introduces semantics into the tracking procedure and extends the model of an object with explicit semantics prior to enhancing the robustness of three key aspects of the tracking framework, i.e., appearance model, search scheme, and scale adaptation. We first present a semantic object proposal generation method for video sequences to generate high-quality category-oriented object proposals. Then, a hybrid semantics-aware tracking algorithm with semantic compatibility is proposed. This algorithm takes full advantages of globally sparse semantic object proposal prediction and locally dense prediction with a template model and semantic distractor-aware color appearance model. Furthermore, we propose to exploit semantics to localize object accurately via an energy minimization framework-based scale adaptation method, which jointly integrates dense location prior, instance-specific color, and category-specific semantic information. Extensive experiments are conducted on two widely used benchmarks, and the results demonstrate that our method achieves the state-of-the-art performance.

关键词： visual object tracking semantic object proposal appearance model search scheme scale adaptation

来源：评论

学校读者我要写书评

暂无评论

One-Shot Scale and Angle Estimation for Fast visual object tracking

引用

IEEE ACCESS 2019年 7卷 55477-55484页

作者： Lee, Dong-Hyun Kumoh Natl Inst Technol Dept Elect Engn Gumi 39257 South Korea Kumoh Natl Inst Technol Dept IT Convergence Engn Gumi 39257 South Korea

visual object tracking is the process of tracking an arbitrary object in a video, where the bounding box of the object is given in the first frame. Siamese network-based visual object tracking approaches have recently received considerable attention for their high speed and superior performance. However, for scale and angle estimation, Siamese trackers require multiple search regions, which increases the computation time, thereby decreasing the real-time tracking performance. This paper proposes a one-shot Siamese network, named Siam-OS, for fast and efficient visual object tracking. Siam-OS uses only a single search region and estimates the scale and angle of the target bounding box. This significantly reduces the number of computations required for the deep convolutional feature extraction, and thus increases the tracking speed. The experimental results with visual object tracking (VOT) benchmarks show the effectiveness of the proposed Siam-OS in terms of the accuracy, robustness, expected average overlap, and speed.

关键词： visual object tracking deep convolutional neural networks Siamese networks

来源：评论

学校读者我要写书评

暂无评论

Quadruplet Network With One-Shot Learning for Fast visual object tracking

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2019年第7期28卷 3516-3527页

作者： Dong, Xingping Shen, Jianbing Wu, Dongming Guo, Kan Jin, Xiaogang Porikli, Fatih Beijing Inst Technol Sch Comp Sci Beijing Lab Intelligent Informat Technol Beijing 100081 Peoples R China Alibaba Grp Hangzhou 311121 Zhejiang Peoples R China Zhejiang Univ State Key Lab CAD&CG Hangzhou 310058 Zhejiang Peoples R China Australia Natl Univ Res Sch Engn Canberra ACT 0200 Australia

In the same vein of discriminative one-shot learning, Siamese networks allow recognizing an object from a single exemplar with the same class label. However, they do not take advantage of the underlying structure of the data and the relationship among the multitude of samples as they only rely on the pairs of instances for training. In this paper, we propose a new quadruplet deep network to examine the potential connections among the training instances, aiming to achieve a more powerful representation. We design a shared network with four branches that receive a multi-tuple of instances as inputs and are connected by a novel loss function consisting of pair loss and triplet loss. According to the similarity metric, we select the most similar and the most dissimilar instances as the positive and negative inputs of triplet loss from each multi-tuple. We show that this scheme improves the training performance. Furthermore, we introduce a new weight layer to automatically select suitable combination weights, which will avoid the conflict between triplet and pair loss leading to worse performance. We evaluate our quadruplet framework by model-free tracking-by-detection of objects from a single initial exemplar in several visual object tracking benchmarks. Our extensive experimental analysis demonstrates that our tracker achieves superior performance with a real-time processing speed of 78 frames/s. Our source code is available.

关键词： Quadruplet deep network visual object tracking Siamese deep network

来源：评论

学校读者我要写书评

暂无评论

A visual object tracking benchmark for cell motility in time-lapse imaging

引用

SIGNAL IMAGE AND VIDEO PROCESSING 2019年第6期13卷 1063-1070页

作者： Demir, H. Seckin Cetin, A. Enis Atalay, Rengul Cetin Aselsan Microelect Guidance & Electroopt Business Sect TR-06750 Ankara Turkey Univ Illinois Dept Elect & Comp Engn Chicago IL 60607 USA METU Grad Sch Informat Canc Syst Biol Lab TR-06800 Ankara Turkey

Automatic tracking of cells is a widely studied problem in various biomedical applications. Although there are numerous approaches for the video object tracking task in different contexts, the performance of these methods depends on many factors regarding the specific application they are used for. This paper presents a comparative study that specifically targets cell tracking problem and compares performance behavior of the recent algorithms. We propose a framework for the performance evaluation of the tracking algorithms and compare several state-of-the-art object tracking approaches on an extensive time-lapse inverted microscopy dataset. We report the quantitative evaluations of the algorithms based on success rate and precision performance metrics.

关键词： visual object tracking Cell motility tracking benchmark

来源：评论

学校读者我要写书评

暂无评论

Learning Adaptive Discriminative Correlation Filters via Temporal Consistency Preserving Spatial Feature Selection for Robust visual object tracking

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2019年第11期28卷 5596-5609页

作者： Xu, Tianyang Feng, Zhen-Hua Wu, Xiao-Jun Kittler, Josef Jiangnan Univ Sch Internet Things Engn Wuxi 214122 Jiangsu Peoples R China Univ Surrey Ctr Vis Speech & Signal Proc Guildford GU2 7XH Surrey England

With efficient appearance learning models, discriminative correlation filter (DCF) has been proven to be very successful in recent video object tracking benchmarks and competitions. However, the existing DCF paradigm suffers from two major issues, i.e., spatial boundary effect and temporal filter degradation. To mitigate these challenges, we propose a new DCF-based tracking method. The key innovations of the proposed method include adaptive spatial feature selection and temporal consistent constraints, with which the new tracker enables joint spatial-temporal filter learning in a lower dimensional discriminative manifold. More specifically, we apply structured spatial sparsity constraints to multi-channel filters. Consequently, the process of learning spatial filters can be approximated by the lasso regularization. To encourage temporal consistency, the filter model is restricted to lie around its historical value and updated locally to preserve the global structure in the manifold. Last, a unified optimization framework is proposed to jointly select temporal consistency preserving spatial features and learn discriminative filters with the augmented Lagrangian method. Qualitative and quantitative evaluations have been conducted on a number of well-known benchmarking datasets such as OTB2013, OTB50, OTB100, Temple-Colour, UAV123, and VOT2018. The experimental results demonstrate the superiority of the proposed method over the state-of-the-art approaches.

关键词： visual object tracking correlation filter feature selection temporal consistency

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：