检索结果-内蒙古大学图书馆

Robust kernelized correlation filter with scale adaption for real-time single object tracking

JOURNAL OF REAL-TIME IMAGE PROCESSING 2018年第3期15卷 583-596页

作者： Li, Ce Liu, Xingchao Su, Xiangbo Zhang, Baochang Beihang Univ Sch Automat Sci & Elect Engn Beijing Peoples R China China Univ Min & Technol Dept Comp Sci Beijing Peoples R China

kernelized correlation filter (KCF) is a kind of efficient method for real-time tracking, but remains being challenged by the drifting problem due to inaccurate localization caused by the scale variation and wrong candidate selection. In this paper, we propose a new scale adaptive kernelized correlation filter tracker, termed as SKCF, which estimates an accurate scale and models the distribution of correlation response to address the template drifting problem. In SKCF, a scale adaption method is used to find an accurate candidate. Thus we improve its capacity to drastic scale change which usually happens for unmanned aerial vehicles (UAVs)-based applications. The SKCF also introduces a Gaussian distribution to model the correlation response of the target image to select a better candidate in tracking procedure. Extensive experiments are performed on two commonly used tracking benchmarks and also a new benchmark for UAV tracking with complex scale variations. The results show that the proposed SKCF significantly improves the performance compared to the baseline KCF and achieves better performance than state-of-the-art single object trackers at real-time.

关键词： Real-time Single object tracking kernelized correlation filter Scale adaption Unmanned aerial vehicles

来源：评论

学校读者我要写书评

暂无评论

The Performance Comparison of Different Feature to kernelized correlation filter Tracker 10

The Performance Comparison of Different Feature to Kernelize...

引用

10th International Conference on Graphics and Image Processing (ICGIP)

作者： Liu, Mengna Diao, Chen Cheng, Xu Chen, Shengyong Tianjin Univ Technol Sch Comp & Engn Tianjin 300384 Peoples R China Tianjin Univ Technol Sch Elect & Elect Engn Tianjin 300384 Peoples R China

ISBN: (数字)9781510628298

ISBN: (纸本)9781510628298

Feature extraction plays an important role in the tracking process. However, most attention is paid to the performance of the tracker without considering the sensitivity of feature to the environment. In this paper, the tracker based on the kernelized correlation filter (KCF) is chosen to compare the tracking performance of different features such as the grayscale, the Histogram of Oriented Gradients (HOG) and the Color Names on scenarios with different attributes. The tracking accuracies corresponding to different features on sequences with various attributes are compared and validated through the OTB-100 dataset and the ALOV300++ dataset. The results show that the HOG gets the best tracking performance on image sequences with attributes such as background clutters, illumination variation, out-of-plane rotation, occlusion, deformation compared with grayscale and the Color Names. And the grayscale gets the best performance for motion blur, in-plane rotation. The Color Names obtains the best result with scale variation. And the reasons for performance differences between the three features are analyzed. It can be concluded that the accuracy of a tracker can be improved by choosing a proper feature according to the attributes of scenes.

关键词： Object tracking kernelized correlation filter feature representation HOG Color Names grayscale

来源：评论

学校读者我要写书评

暂无评论

Automatic Failure Detection and Correction for Real-Time Object Tracking with kernelized correlation filter

Automatic Failure Detection and Correction for Real-Time Obj...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Shin, Jungsup Kim, Heegwang Jeong, Dasol Paik, Joonki Chung Ang Univ Image Proc & Intelligent Syst Lab Seoul South Korea

ISBN: (纸本)9781538679104

This paper proposes an algorithm that estimates tracking failure and track the target object again. The proposed algorithm consists of three steps: 1) Tracking target object with KCF tracker. 2) Estimating tracking failure by analysing correlation values. 3) Re-capturing the target object using multiple search windows and re-tracking. Experimental results shows that the proposed algorithm effectively corrects tracking failure situations.

关键词： object tracking kernelized correlation filter occlusion handling blurring handling

来源：评论

学校读者我要写书评

暂无评论

A Novel Tracker based on the kernelized correlation filter 7

A Novel Tracker based on the Kernelized Correlation Filter

引用

7th International Conference on Optical and Photonic Engineering (icOPEN)

作者： Chen, Dongxun Jiang, Zhen Wei, Yanxia Shanghai Univ Dept Precis Mech Engn Shanghai Peoples R China Liaocheng Univ Liaocheng Shandong Peoples R China

ISBN: (数字)9781510631601

ISBN: (纸本)9781510631601

correlation filter based tracking methods are the core component of most trackers which achieve the excellent performance in term of the accuracy and robustness in visual tracking. However, there are still lots of challenging situations, such as occlusion or illumination, which confines and limits the performance of trackers. To cope with the above problems, in this paper, we suggest an effective tracking method via part-based strategy. Compared with the conventional tracking algorithms based on correlation filter, our tracker employs the novel strategy to validate and estimate the target's final position, avoiding merely utilizing the maximum response in the response map as the target position which is often prone to drift away from the target. In addition, to effectively deal with occlusion, we divide the sample into multiple parts. When the sample is partly occluded, the visible part can still provide effective clues for tracking, ensuring the robustness of tracker. A large number of conveys are conducted on the public databases, and experimental results show that the proposed algorithm has obvious performance improvement in the case of dealing with target occlusion, and the real-time performance is also pretty good.

关键词： Object tracking global and local model kernelized correlation filter

来源：评论

学校读者我要写书评

暂无评论

Comparison of Object Tracking Methods and Performance Analysis of kernelized correlation filter with Different Appearance Models 29

Comparison of Object Tracking Methods and Performance Analys...

引用

29th IEEE Conference on Signal Processing and Communications Applications (SIU)

作者： Musaoglu, Elnura Ozturk, Ceyda Nur Bursa Uludag Univ Bilgisayar Muhendisligi Bolumu Bursa Turkey Ozveri Ar Ge Merkezi Ozdilek Ev Tekstil San & Tic Bursa Turkey

ISBN: (纸本)9781665436496

Object tracking enables determination of relevant objects in the moving images without the need for object detection in each frame. There are various studies that are based on correlation, deep learning and different methods in this field in the literature. In these studies, different appearance models such as Scale Invariant Feature Transform (SIFT), Histogram of Oriented Gradient (HOG), motion model, convolutional neural network features are used to model the object to be tracked. Having operations performed in Fourier space, the correlation approach is effective in making object tracking systems run in real time. Using the correlation filter with the convolutional neural network, the success of object tracking can be increased. The aim of this study is to compare different object tracking methods and analyze the effect of different appearance models on object tracking. Object tracking comparison (OTB-100) data set which includes 100 images series prepared in different environments and conditions, was used. Two measures of precision and success were computed for performance measurement. When the obtained results of the experiments on the OTB data set were evaluated, it was observed that the combined use of the correlation filter and convolutional neural network increased the object tracking performance.

关键词： Object Tracking Convolutional Neural Network kernelized correlation filter Deep Features

来源：评论

学校读者我要写书评

暂无评论

Target Tracking Based on Collaborative Learning kernelized correlation filter

Target Tracking Based on Collaborative Learning Kernelized C...

引用

International Symposium in Sensing and Instrumentation in IoT Era (ISSI)

作者： Sun, Bin Li, Chaofeng Zeng, Liling Sang, Qingbing Jiangnan Univ Sch Internet Things Engn Wuxi 214122 Peoples R China Shanghai Maritime Univ Inst Logist Sci & Engn Shanghai 201306 Peoples R China

ISBN: (纸本)9781538656389

In this paper, a tracking algorithm based on collaborative learning kernelized correlation filter is proposed. According to the framework of KCF, two trackers based on HoG and CN are cooperatively trained, and independent scale adaptive algorithm is used at the same time, and we call it collaborative learning kernelized correlation filter (CL-KCF) algorithm. Our experimental results show that the proposed algorithm has higher tracking accuracy and robustness than other trackers, and can automatically adapt to the target's scale change.

关键词： target tracking kernelized correlation filter scale estimation collaborative learning

来源：评论

学校读者我要写书评

暂无评论

A Kalman filter-Based kernelized correlation filter Algorithm for Pose Measurement of a Micro-Robot

引用

MICROMACHINES 2021年第7期12卷 774-774页

作者： Zhang, Heng Zhan, Hongwu Zhang, Libin Xu, Fang Ding, Xinbin Zhejiang Univ Technol Mech Engn Coll Hangzhou 310023 Peoples R China

This paper proposes a moving-target tracking algorithm that measures the pose of a micro-robot with high precision and high speed using the Kalman filter-based kernelized correlation filter (K2CF) algorithm. The adaptive Kalman filter can predict the state of linearly and nonlinearly fast-moving targets. The kernelized correlation filter algorithm then accurately detects the positions of the moving targets and uses the detection results to modify the moving states of the targets. This paper verifies the performance of the algorithm on a monocular vision measurement platform and using a pose measurement method. The K2CF algorithm was embedded in the micro-robot's attitude measurement system, and the tracking performances of three different trackers were compared under different motion conditions. Our tracker improved the positioning accuracy and maintained real-time operation. In a comparison study of K2CF and many other algorithms on Object Tracking Benchmark-50 and Object Tracking Benchmark-100 video sequences, the K2CF algorithm achieved the highest accuracy. In the 400 mm x 300 mm field of view, when the target radius is about 3 mm and the inter-frame acceleration displacement does not exceed 5.6 mm, the root-mean-square error of position and attitude angle can satisfy the precision requirements of the system.

关键词： Kalman filter kernelized correlation filter target tracking machine vision pose measurement

来源：评论

学校读者我要写书评

暂无评论

Improved target tracking algorithm based on kernelized correlation filter

引用

JOURNAL OF ELECTRONIC IMAGING 2019年第2期28卷 021008-021008页

作者： Liang, Hua Gang Gao, Dong Mei Li, Jiang Wei Pang, Li Qin Changan Univ Elect & Control Engn Dept Xian Shaanxi Peoples R China

We propose an improved object tracking algorithm based on kernelized correlation filter (KCF), which can overcome the drawback of traditional KCF algorithms in that they cannot effectively adapt to target-scale variations and target occlusion in tracking. First, the target-scale pyramid is built, whose histogram of oriented gradients feature extracted of every layer multiplied by the correlation filters;the maximum response of current scale of the filters is the best target scale. In addition, the improved algorithm is combined with the improved correlation filter framework, and the background information around the target is appropriately increased. When the target is occluded, the background information can be effectively used to track the target. The proposed algorithm is validated on the benchmark evaluation and compared with the traditional algorithms, such as KCF and circulation structure of tracking-by-detection with kernel. The results indicate that our tracking accuracy can reach 66.9% and the success rate can be 58.2. When the target is scale variation, the accuracy and success rate increase by 1.1% and 10.3%, respectively, compared with KCF. If the tracked target is occluded, a second improved algorithm is compared with the detection algorithm which only adds the scale detection, the tracking accuracy increases by 8%, and the success rate increases by 4.9%. (C) 2019 SPIE and IS&T

关键词： target tracking kernelized correlation filter scale pyramid background information

来源：评论

学校读者我要写书评

暂无评论

Real-Time Tracking Target System Based on kernelized correlation filter in Complicated Areas

引用

SENSORS 2024年第20期24卷 6600页

作者： Mbouombouo Mboungam, Abdel Hamid Zhi, Yongfeng Fonzeu Monguen, Cedric Karel Northwestern Polytech Univ Sch Automat Xian 710002 Peoples R China Karlsruhe Inst Technol KIT Inst Chem Technol & Polymer Chem Engesserstr 20 D-76131 Karlsruhe Germany

The achievement of rapid and reliable image object tracking has long been crucial and challenging for the advancement of image-guided technology. This study investigates real-time object tracking by offering an image target based on nuclear correlation tracking and detection methods to address the challenge of real-time target tracking in complicated environments. In the tracking process, the nuclear-related tracking algorithm can effectively balance the tracking performance and running speed. However, the target tracking process also faces challenges such as model drift, the inability to handle target scale transformation, and target length. In order to propose a solution, this work is organized around the following main points: this study dedicates its first part to the research on kernelized correlation filters (KCFs), encompassing model training, object identification, and a dense sampling strategy based on a circulant matrix. This work developed a scale pyramid searching approach to address the shortcoming that a KCF cannot forecast the target scale. The tracker was expanded in two stages: the first stage output the target's two-dimensional coordinate location, and the second stage created the scale pyramid to identify the optimal target scale. Experiments show that this approach is capable of resolving the target size variation problem. The second part improved the KCF in two ways to meet the demands of a long-term object tracking task. This article introduces the initial object model, which effectively suppresses model drift. Secondly, an object detection module is implemented, and if the tracking module fails, the algorithm is redirected to the object detection module. The target detection module utilizes two detectors, a variance classifier and a KCF. Finally, this work includes trials on object tracking experiments and subsequent analysis of the results. Initially, this research provides a tracking algorithm assessment system, including an assessment metho

关键词： object detection real-time object tracking kernelized correlation filter model drift variance classifier

来源：评论

学校读者我要写书评

暂无评论

Visual object tracking with multi-scale superpixels and color-feature guided kernelized correlation filters

引用

SIGNAL PROCESSING-IMAGE COMMUNICATION 2018年 63卷 44-62页

作者： Wang, Jun Liu, Weibin Xing, Weiwei Zhang, Shunli Beijing Jiaotong Univ Inst Informat Sci Beijing 100044 Peoples R China Beijing Jiaotong Univ Sch Software Engn Beijing 100044 Peoples R China

While discriminative correlation filter based tracking algorithms have achieved competitive results and demonstrated successfully, there still remain some challenges, such as handling the scenarios of scale variation, fast motion, etc. A region of interest with a fixed size, which is usually used by discriminative correlation filter based tracking algorithms to train correlation filter and track object, makes the trackers hard to deal with the challenges of fast motion and scale variation. It also restricts the use of object structure information. In this paper, we propose a Multi-Scale Superpixels and Color Feature Guided Kemelized correlation filters (MSSCF-KCF) to deal with the problems mentioned above. Firstly, we treat tracking procedure as optimizing the combination of components of an object, and propose a multi-scale superpixel method to segment object image based on a proposed global confidence mask which determines the center and size of object patches automatically. Then, KCF is embedded into Bayesian filter framework, in which the proposed color guided confidence map is viewed as an observation model, to expand the tracking range and improve the performance when handling fast motion. Finally, we propose a center distance matrix of each object patch to use structure information of object. A novel min-max criterion as well as drop-out strategy is used to search the optimal combination and estimate the state of object, which also helps the tracker to cope with scale variation. Besides, monitoring update strategy is proposed to monitor tacking operation and adjust parameters dynamically. The proposed algorithm is tested on a self-made dataset and some challenging sequences with a novel evaluation criterion. The results demonstrate the feasibility and effectiveness compared with the state-of-the-art methods.

关键词： Visual tracking Superpixel kernelized correlation filter Bayesian filter Color feature guided confidence map Multi-scale superpixels

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：