检索结果-内蒙古大学图书馆

Efficient Retrieval of Massive Ocean Remote Sensing Images via a Cloud-Based mean-shift algorithm

SENSORS 2017年第7期17卷 1693-1693页

作者： Yang, Mengzhao Song, Wei Mei, Haibin Shanghai Ocean Univ Coll Informat Technol Shanghai 201306 Peoples R China

The rapid development of remote sensing (RS) technology has resulted in the proliferation of high-resolution images. There are challenges involved in not only storing large volumes of RS images but also in rapidly retrieving the images for ocean disaster analysis such as for storm surges and typhoon warnings. In this paper, we present an efficient retrieval of massive ocean RS images via a Cloud-based mean-shift algorithm. Distributed construction method via the pyramid model is proposed based on the maximum hierarchical layer algorithm and used to realize efficient storage structure of RS images on the Cloud platform. We achieve high-performance processing of massive RS images in the Hadoop system. Based on the pyramid Hadoop distributed file system (HDFS) storage method, an improved mean-shift algorithm for RS image retrieval is presented by fusion with the canopy algorithm via Hadoop MapReduce programming. The results show that the new method can achieve better performance for data storage than HDFS alone and WebGIS-based HDFS. Speedup and scaleup are very close to linear changes with an increase of RS images, which proves that image retrieval using our method is efficient.

关键词： remote sensing (RS) fast retrieval ocean disasters mean-shift algorithm Hadoop system pyramid HDFS storage

来源：评论

学校读者我要写书评

暂无评论

Human Tracking Method Based on Multi-Template Color-Texture mean-shift algorithm 12

Human Tracking Method Based on Multi-Template Color-Texture ...

引用

IEEE International Conference on Mechatronics & Automation

作者： Wen, Linfeng Jia, Songmin Wang, Lijia Beijing Univ Technol Coll Elect & Control Engn Beijing 100124 Peoples R China Beijing Key Lab Computat Intelligence & Intellige Beijing 100124 Peoples R China Minist Educ Engn Res Ctr Digital Community Beijing 100124 Peoples R China

ISBN: (纸本)9781479970988

Human tracking is a hot topic and a challenging task during the past few decades. This paper present a multi templates based strategy for human detecting and tracking with a mobile robot. This method first determines the coarse location by using adaptive template matching algorithm (ATM) based on head-shoulder. Then, a multi-templates based method is presented to locate the person precisely. Multi templates considering the pose changes are obtained to represent the person. For each template, the mean-shift is proceeded. Then, the accurate position is obtained by fusing the results of the mean-shift from all the templates. After detecting the person, the templates are updated by considering the likelihood of the tracking results and the old templates. Finally, the method is evaluated on a mobile robot in complex environment. The experiment result shows that our method performs well when there are unclear disparity image and pose variations.

关键词： Human tracking Head-shoulder matching mean-shift algorithm Multi-template

来源：评论

学校读者我要写书评

暂无评论

mean-shift Shape Formation of Multi-Robot Systems Without Target Assignment

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2024年第2期9卷 1772-1779页

作者： Zhang, Yunjie Zhou, Rui Li, Xing Sun, Guibin Beihang Univ Sch Automat Sci & Elect Engn Beijing 100083 Peoples R China

The methods of shape formation in robot swarms are usually classified into two categories by whether assignment is used or not. The first is to use target assignment to assemble precise formation. However, the additional algorithm for re-assignment is required to handle unreasonable situations, which results in lower efficiency. The second, also called assignment-free method, is to use local behaviors to assemble formation, however, existing methods can rarely achieve the precise formation. In this letter, we present a distributed assignment-free algorithm to achieve the precise shape formation based on the mean-shift algorithm. Specifically, each target location in robot's perception range is equally regarded as a point of the mean-shift vector. Then, the weight value of each point is computed according to the density of the target location. Here, each robot obtains the density of the target location according to the distribution of its neighbors. Moreover, this density calculation also considers the states of non-neighboring robots via the hop-count algorithm, thus avoiding conflicts among robots. Subsequently, each robot can regard the calculated mean-shift vector as its control command. Finally, simulation results show that our algorithm can form precise shapes at least 8 times more efficient than the assignment-based approach and physical experiment results confirm that the proposed algorithm exhibits promising potential for practical applications.

关键词： Shape formation multi-robot systems mean-shift algorithm

来源：评论

学校读者我要写书评

暂无评论

Research on Automatic Tracking and Size Estimation algorithm of "Low, Slow and Small" Targets Based on Gm-APD Single-Photon LIDAR

引用

DRONES 2025年第2期9卷 85-85页

作者： Guo, Dongfang Qu, Yanchen Zhou, Xin Sun, Jianfeng Yin, Shengwen Lu, Jie Liu, Feng Harbin Inst Technol Natl Key Lab Laser Spatial Informat Harbin 150001 Peoples R China Harbin Inst Technol Zhengzhou Res Inst Zhengzhou 450000 Peoples R China Harbin Inst Technol Res Ctr Space Opt Engn Harbin 150001 Peoples R China 44th Res Inst China Elect Technol Grp Corp Chongqing 400060 Peoples R China

In order to solve the problem of detecting, tracking and estimating the size of "low, slow and small" targets (such as UAVs) in the air, this paper designs a single-photon LiDAR imaging system based on Geiger-mode Avalanche Photodiode (Gm-APD). It improves the mean-shift algorithm and proposes an automatic tracking method that combines the weighted centroid method to realize target extraction, and the principal component analysis (PCA) method of the adaptive rotating rectangle is realized to fit the flight attitude of the target. This method uses the target intensity and distance information provided by Gm-APD LiDAR. It addresses the problem of automatic calibration and size estimation under multiple flight attitudes. The experimental results show that the improved algorithm can automatically track the targets in different flight attitudes in real time and accurately calculate their sizes. The improved algorithm is stable in the 1250-frame tracking experiment of DJI Elf 4 UAV with a flying speed of 5 m/s and a flying distance of 100 m. Among them, the fitting error of the target is always less than 2 pixels, while the size calculation error of the target is less than 2.5 cm. This shows the remarkable advantages of Gm-APD LiDAR in detecting "low, slow and small" targets. It is of practical significance to comprehensively improve the ability of UAV detection and C-UAS systems. However, the application of this technology in complex backgrounds, especially in occlusion or multi-target tracking, still faces certain challenges. In order to realize long-distance detection, further optimizing the field of view of the Gm-APD single-photon LiDAR is still a future research direction.

关键词： target tracking size estimation UAV Gm-APD LiDAR mean-shift algorithm

来源：评论

学校读者我要写书评

暂无评论

Adaptive Shape Formation Against Swarm-Scale Variants in Robot Swarms

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2024年第8期9卷 6776-6783页

作者： Li, Xing Zhou, Rui Sun, Guibin Beihang Univ Sch Automat Sci & Elect Engn Beijing 100083 Peoples R China

Shape formation of robot swarms is quite challenging when the robot number varies, as the number often needs to match the number of goal locations in the shape. For this challenge, state-of-the-art methods characterize the shape as a continuous region and distribute robots in the region. However, such methods can only handle a small swarm-scale variant due to the fixed shape size. In this letter, we propose a distributed adaptive shape formation method with variable shape size. The core idea is that each robot can dynamically adjust the shape size according to variants of local density, induced by variants of the robot number. Furthermore, this individual adjustment by each robot can be propagated through peer-to-peer communications. In particular, this strategy is integrated into our previous work, which employs the mean-shift algorithm to achieve the shape formation of large-scale robot swarms. In addition, we also adapt the mean-shift algorithm for redesigning all the negotiation and control components in the previous work such that a concise and unified alternative for shape formation can be provided via the mean-shift algorithm. Finally, simulation and experiment results demonstrate that the proposed method can achieve the desired shape with the robot number decreasing or increasing.

关键词： Robots Shape Robot sensing systems Collision avoidance Multi-robot systems Heuristic algorithms Sun Adaptive shape formation variable swarm scale density feedback mean-shift algorithm multi-robot systems

来源：评论

学校读者我要写书评

暂无评论

Clustering of Image Covariance Matrixes on Lie Group Manifold

引用

AUTOMATIC CONTROL AND COMPUTER SCIENCES 2024年第2期58卷 209-215页

作者： Zheng, Mingliang Taihu Univ Wuxi Sch Mech & Elect Engn Wuxi 214064 Jiangsu Peoples R China Huainan Normal Univ Sch Mech & Elect Engn Huainan 232038 Peoples R China

An image clustering method based on covariance matrix and mean-shift algorithm on Lie group manifold is proposed. Firstly, according to the extracted multidimensional correlation features of image, the covariance matrixes are calculated to form a Lie group manifold. Secondly, by using the mapping relationship between Lie group and Lie algebra, the steps of covariance matrixes clustering based on mean-shift algorithm on Lie group are established. Finally, the example verifies that the mean-shift algorithm on Lie group manifold can better obtain the clustering information of the image covariance matrixes, and the average accuracy of image classification is 95.80%, which improves accuracy by 3.1% compared to traditional algorithms. Moreover, if the kernel function, bandwidth and threshold are set up reasonably, the image clustering is more efficient and accurate. For the unit Gaussian kernel function, the optimal bandwidth is 1.2, the optimal threshold is 0.8. It provides an algorithmic basis for the application of Lie group machine learning in high-precision automatic target clustering.

关键词： image clustering covariance matrix Lie group manifold mean-shift algorithm

来源：评论

学校读者我要写书评

暂无评论

An extended TLD tracking algorithm using co-training learning for low frame rate videos

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2023年第16期82卷 24743-24769页

作者： Moridvaisi, Hooman Razzazi, Farbod Pourmina, Mohammadali Dousti, Massoud Islamic Azad Univ Dept Elect & Comp Engn Sci & Res Branch Tehran Iran

The conventional tracking-learning-detection (TLD) algorithm is sensitive to illumination changes, clutter, significant changes of target shape between consecutive frames. In addition, low frame rate scenarios result in drift in object position or even missing the object. To solve these problems and enhance the tracking robustness, in this paper, TLD algorithm was extended in two folds. First, Kalman filter and mean-shift algorithms were combined for the tracking part and second, co-training semi-supervised learning algorithm was used for the learning part of the conventional TLD structure. The Kalman filter estimates the position of the target in the next frame based on the previous positions of the target. This reduces tracking failure. On the other hands, the mean-shift tracking algorithm is robust to rotation, partial occlusion and scale changing. In the learning part of TLD structure, two training tracking algorithms with two independent classifiers were run on the current frame simultaneously. Its structure makes data of both pools (color features and target templates) update by the results of other algorithm, in addition to the results of the corresponding algorithm in each of the tracking and detection algorithms. Therefore, classifiers can learn faster changing features of the target during the consecutive frames in online tracking process. Finally, the extended structure can solve the problem of lost object in LFR videos tracking and other similar challenges simultaneously. In terms of overlap ratio metric, comparing with conventional TLD and extended kernelized correlation filters (EKCF) algorithms, the success rate of our algorithm under various scenarios has increased by 161.03% and 255.82% respectively and under other scenarios, in terms of precision metric, it has increased by 18.46% and 1479.47%, respectively. Accordingly, comparative evaluations of the proposed method to other top state-of-the-art tracking algorithms under various scenarios present

关键词： Object tracking Kalman filter mean-shift algorithm Learning algorithm Tracking learning detection

来源：评论

学校读者我要写书评

暂无评论

Moving Up the Cluster Tree with the Gradient Flow*

引用

SIAM JOURNAL ON MATHEMATICS OF DATA SCIENCE 2023年第2期5卷 400-421页

作者： Arias-Castro, Ery Qiao, Wanli Univ Calif San Diego Dept Math San Diego CA 92093 USA George Mason Univ Dept Stat Fairfax VA 22030 USA

This paper establishes a strong correspondence between two important clustering approaches that emerged in the 1970s: clustering by level sets or cluster tree as proposed by Hartigan, and clustering by gradient lines or gradient flow as proposed by Fukunaga and Hostetler. This correspondence is drawn by showing that the gradient ascent flow provides a natural way to move up the cluster tree.

关键词： clustering level sets cluster tree gradient lines gradient flow mean-shift algorithm dynamical systems

来源：评论

学校读者我要写书评

暂无评论

Product typicality attribute mining method based on a topic clustering ensemble

引用

ARTIFICIAL INTELLIGENCE REVIEW 2022年第8期55卷 6629-6654页

作者： Sun, Jing-Tao Zhang, Qiu-Yu Xian Univ Posts & Telecommun Sch Comp Sci & Technol Xian 710121 Shaanxi Peoples R China Xian Univ Posts & Telecommun Shaanxi Key Lab Network Data Anal & Intelligent P Xian 710121 Shaanxi Peoples R China Xian Key Lab Big Data & Intelligent Comp Xian 710121 Shaanxi Peoples R China Lanzhou Univ Technol Sch Comp & Commun Lanzhou 730050 Gansu Peoples R China

Despite the extensive application of topic models in natural language processing tasks in recent years, the Chinese texts of short comments characterised by large scale, high noise and small information points have put forward higher requirements for the accuracy and stability of the results, which fails to be satisfied by existing topic models. In this paper, a product typicality attribute mining method based on a topic clustering ensemble was proposed. By introducing multiple topic models into ensemble learning, the problems of semantic representation loss, clustering inefficiency and lack of interpretability in the mining of product typicality attributes of short comment texts should be solved. By an effective combination of the topic clustering algorithm based on the diversity of speech, the topic clustering ensemble algorithm based on the Non-negative matrix factorization, and the interpretation method of product typicality attributes based on the mean-shift algorithm, an unsupervised model of product typicality attribute mining for short comment texts is constructed. As shown by the experimental results, the modelling method assumes favourable performance in topic clustering and feature selection, suggesting its advantages in product typicality attribute identification and interpretability compared with common methods.

关键词： LDA models Integrated learning Non-negative matrix factorization mean-shift algorithm

来源：评论

学校读者我要写书评

暂无评论

mean-shift Tracking algorithm based on Kalman Filter using Adaptive Window and Sub-blocking 11

Mean-Shift Tracking Algorithm based on Kalman Filter using A...

引用

11th World Congress on Intelligent Control and Automation

作者： Wang, Xingmei Hu, Zhihao Feng, Jingjiao Li, Lin Harbin Engn Univ Comp Sci & Technol Harbin Heilongjiang Pr Peoples R China Harbin Engn Univ Informat & Commun Engn Harbin Heilongjiang Pr Peoples R China

ISBN: (纸本)9781479958252

To reduce the tracking errors caused by highspeed motion and variable motion in the process of moving target tracking, a novel mean-shift tracking algorithm based on Kalman filter using adaptive window and sub-blocking is proposed in this paper. Moving target's utmost position is predicted by combining Kalman filter and historical information, which is used as the initial position. During describing feature model of target and candidate regions, they are blocked and each sub-block region is processed by reducing RGB interval, by which computational efficiency will be improved. Finally, window bandwidth will be enlarged and reduced according to Bhattacharyya coefficient, and it achieves accurate moving target tracking by adaptive window. The comparison experiments of the Coastguard standard image sequence and car image sequence demonstrate that the proposed tracking algorithm is insensitive to high-speed motion and variable motion of moving target, and it has better tracking performance.

关键词： Moving target tracking mean-shift algorithm Kalman filter algorithm Sub-blocking

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

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

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：