检索结果-内蒙古大学图书馆

3rd International Conference on Intelligent Computing in Data Sciences (ICDS)

作者： Mrabti, Wafae Bellach, Benaissa Tairi, Hamid Univ Sidi Mohammed Ben Abdellah Dept Informat FSDM LIIAN Fes Morocco First Mohammed Univ Natl Sch Appl Sci LSE2I Oujda Morocco

ISBN: (纸本)9781728100036

tracking a moving person in an image sequence is an important task for many video surveillance applications. In this paper, a tracking by detection method based on a background subtraction method and the Kalman Filter predictor is proposed. Firstly, we extract the human target silhouette automatically using a background subtraction method. Secondly, we predict the location of the extracted human silhouette in the next frame using the predictor Kalman Filter. After that, we obtain the observation in the current frame using the background subtraction method. Finally, we update the tracker system by the correction step of Kalman Filter. Numerous experiments on several challenging image sequences illustrate the effectiveness of the proposed method.

关键词： tracking by detection Human silhouette extraction Background subtraction Kalman filter

来源：评论

学校读者我要写书评

暂无评论

Online multi-object tracking by detection based on generative appearance models

引用

COMPUTER VISION AND IMAGE UNDERSTANDING 2016年 152卷 88-102页

作者： Riahi, Dorra Bilodeau, Guillaume-Alexandre Polytech Montreal Dept Comp & Software Engn LITIV Lab Stn Ctr Ville POB 6079 Montreal PQ H3C 3A7 Canada

This paper presents a robust online multiple object tracking (MOT) approach based on multiple features. Our approach is able to handle MOT problems, like long-term and heavy occlusions and close similarity between target appearance models. The proposed MOT algorithm is based on the concept of multi-feature fusion. It selects the best position of the tracked target by using a robust appearance model representation. The appearance model of a target is built with a color model, a sparse appearance model, a motion model and a spatial information model. In order to select the optimal candidate (detection response) of the target, we calculate a linear affinity function that integrates similarity scores coming from each feature. In our MOT system, we formulate the problem as a data association problem between a set of detections and a set of targets according to their joint probability values. The proposed method has been evaluated on public video sequences. Compared with the state-of-the-art, we demonstrate that our MOT framework achieves competitive results and is capable of handling several challenging problems. (C) 2016 Published by Elsevier Inc.

关键词： Multiple object tracking Data association tracking by detection Sparse appearance model Multiple features

来源：评论

学校读者我要写书评

暂无评论

Augmented reality for narrow area navigation in jaw surgery: Modified tracking by detection volume subtraction algorithm

引用

INTERNATIONAL JOURNAL OF MEDICAL ROBOTICS AND COMPUTER ASSISTED SURGERY 2020年第3期16卷 e2097-e2097页

作者： Budhathoki, Srijana Alsadoon, Abeer Prasad, P. W. C. Haddad, Sami Maag, Angelika Charles Sturt Univ Sch Comp & Math Sydney Campus Sydney NSW Australia Study Grp Australia Dept Informat Technol Sydney Campus Sydney NSW Australia Greater Western Sydney Area Hlth Serv Dept Oral & Maxillofacial Serv Sydney NSW Australia Cent Coast Area Hlth Dept Oral & Maxillofacial Serv Gosford Australia

Background and Aim Jaw surgery based on augmented reality (AR) still has limitations in terms of navigating narrow areas. Surgeons need to avoid nerves, vessels, and teeth in their entirety, not just root canals. Inaccurate positioning of the surgical instrument may lead to positional or navigational errors and can result in cut blood vessels, nerve channels, or root canals. This research aims to decrease the positional error during surgery and improve navigational accuracy by reducing the positional error. Methodology The proposed 2D/3D system tracks the surgical instrument, consisting of the shaft and the cutting element, each part being assigned a different feature description. In the case of the 3D position estimation, the input vector is composed of image descriptors of the instrument and the output value consists of 3D coordinates of the cutter. Results Sample results from a jawbone-maxillary and mandibular jaw-demonstrate that the positional error is reduced. The system, thus, led to an improvement in alignment of the video accuracy by 0.25 to 0.35 mm from 0.40 to 0.55 mm and a decrease in processing time of 11 to 14 frames per second (fps) against 8 to 12 fps of existing solutions. Conclusion The proposed system is focused on overlaying only on the area to be operated on. Thus, this AR-based study contributes to accuracy in navigation of the deeper anatomical corridors through increased accuracy in positioning of surgical instruments.

关键词： augmented reality jaw surgery navigation surgical instruments tracking by detection

来源：评论

学校读者我要写书评

暂无评论

A Convolutional Neural Network based 3D Ball tracking by detection in Soccer Videos 11

A Convolutional Neural Network based 3D Ball Tracking by Det...

引用

11th International Conference on Machine Vision (ICMV)

作者： Kamble, Paresh R. Keskar, Avinash G. Bhurchandi, Kishor M. Visvesvaraya Natl Inst Technol Dept Elect & Commun Engn Nagpur Maharashtra India

ISBN: (数字)9781510627499

ISBN: (纸本)9781510627499

tracking of ball in sports videos is one of the most challenging tasks in computer vision and video processing domain. Recent ball tracking approaches fail to handle tracking of a small size and fast moving ball. Inaccurate 2D ball detection leads to further deterioration of 3D ball tracking results. This paper presents a soccer ball tracking by detection approach using a pre-trained Convolutional Neural Network (CNN). The proposed algorithm used CNN for identifying ball from background and other moving objects like players and referees. The 2D ball detection results are fine-tuned for identifying true ball positions. True ball positions, from cameras shooting the scene from different angle, are further mapped on ground plane. The actual ball movement is tracked in 3D from top-view. Experiments show that the proposed algorithm can tackle challenges like small ball size, shape changes, occlusion and tracking high-speed balls.

关键词： Ball detection tracking by detection ball tracking soccer sport convolutional neural network deep learning

来源：评论

学校读者我要写书评

暂无评论

MULTI-PERSON tracking by detection IN THERMAL CAMERAS

MULTI-PERSON TRACKING BY DETECTION IN THERMAL CAMERAS

引用

IADIS International Conference on Computer Graphics, Visualization, Computer Vision and Image Processing part of the IADIS Multi Conference on Computer Science and Information Systems

作者： Kwak, Joon-Young Hong, June-Hyeok Ko, Byoung-Chul Nam, Jae-Yeal Keimyung Univ Dept Comp Engn Daegu South Korea

ISBN: (纸本)9789728939892

This paper presents a robust multi-person tracking algorithm by person detection using thermal images. The person tracking and detection continuously exchange information during the process each other in order to self-correct and self-update. First, a person is detected by analyzing hotspot regions in the images, and then, tracking is performed on each frame using the random forest classifier as the online learning algorithm. Second, we solve the association problem with our proposed association-check method, which considers both the spatial distance and the likelihood between target regions and detected regions. The proposed algorithm is successfully applied to a few thermal videos, including those with complex backgrounds, and the tracking results demonstrate reasonable performance.

关键词： Multi-person tracking person detection tracking by detection random forest association check

来源：评论

学校读者我要写书评

暂无评论

tracking-by-detection Algorithm for Underwater Target Based on Improved Multi-Kernel Correlation Filter

引用

REMOTE SENSING 2024年第2期16卷 323页

作者： Yue, Wenrong Xu, Feng Yang, Juan Chinese Acad Sci Inst Acoust Ocean Acoust Technol Lab Beijing 100190 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China

Joint detection and tracking of weak underwater targets are challenging problems whose complexity is intensified when the target is disturbed by reverberation. In the low signal-to-reverberation ratio (SRR) environment, the traditional detection and tracking methods perform poorly in tracking robustness because they only consider the target motion characteristics. Recently, the kernel correlation filter (KCF) based on target features has received lots of attention and gained great success in visual tracking. We propose an improved multi-kernel correlation filter (IMKCF) tracking-by-detection algorithm by introducing the KCF into the field of underwater weak target detection and tracking. It is composed of the tracking-by-detection, the adaptive reliability check, and the re-detection modules. Specifically, the tracking-by-detection part is built on the multi-kernel correlation filter (MKCF), and it uses multi-frame data weighted averaging to update. The reliability check helps keep the tracker from corruption. The re-detection module, integrated with a Kalman filter, identifies target positions when the tracking is unreliable. Finally, the experimental data processing and analysis show that the proposed method outperforms the single-kernel methods and some traditional tracking methods.

关键词： active sonar low signal-to-reverberation ratio underwater target tracking by detection kernel correlation filter

来源：评论

学校读者我要写书评

暂无评论

tracking-by-detection of surgical instruments in minimally invasive surgery via the convolutional neural network deep learning-based method

引用

COMPUTER ASSISTED SURGERY 2017年第sup1期22卷 26-35页

作者： Zhao, Zijian Voros, Sandrine Weng, Ying Chang, Faliang Li, Ruijian Shandong Univ Sch Control Sci & Engn Jinan 250061 Shandong Peoples R China Univ Grenoble Alpes TIMC IMAG INSERM CNRS Grenoble France Bangor Univ Sch Comp Sci Bangor Gwynedd Wales Shandong Univ Qilu Hosp Dept Cardiol Jinan Shandong Peoples R China

Background: Worldwide propagation of minimally invasive surgeries (MIS) is hindered by their drawback of indirect observation and manipulation, while monitoring of surgical instruments moving in the operated body required by surgeons is a challenging problem. tracking of surgical instruments by vision-based methods is quite lucrative, due to its flexible implementation via software-based control with no need to modify instruments or surgical workflow. Methods: A MIS instrument is conventionally split into a shaft and end-effector portions, while a 2D/3D tracking-by-detection framework is proposed, which performs the shaft tracking followed by the end-effector one. The former portion is described by line features via the RANSAC scheme, while the latter is depicted by special image features based on deep learning through a well-trained convolutional neural network. Results: The method verification in 2D and 3D formulation is performed through the experiments on ex-vivo video sequences, while qualitative validation on in-vivo video sequences is obtained. Conclusion: The proposed method provides robust and accurate tracking, which is confirmed by the experimental results: its 3D performance in ex-vivo video sequences exceeds those of the available state-of-the-art methods. Moreover, the experiments on in-vivo sequences demonstrate that the proposed method can tackle the difficult condition of tracking with unknown camera parameters. Further refinements of the method will refer to the occlusion and multi-instrumental MIS applications.

关键词： tracking by detection minimally invasive surgery surgical vision convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

A Robust Long-Term Pedestrian tracking-by-detection Algorithm Based on Three-Way Decision 1

引用

International Joint Conference on Rough Sets (IJCRS)

作者： Wang, Ziye Miao, Duoqian Zhao, Cairong Luo, Sheng Wei, Zhihua Tongji Univ Dept Comp Sci & Technol Shanghai 201804 Peoples R China Tongji Univ Key Lab Embedded Syst & Serv Comp Minist Educ Shanghai Peoples R China

ISBN: (数字)9783030228156

ISBN: (纸本)9783030228156;9783030228149

Pedestrian detection Technology has become a hot research topic in target detection field recent years. But how to track the pedestrian target accurately in real time is still a challenge problem. Recently deep learning has got the extensive research and application in both target tracking and target detection. However, the tracking effect based on deep learning needs to be improved in the motion blur and occlusion cases. In this paper, we propose a new model that combines the target tracking and target detection and introduce the idea of granular computing to realize high-precision long-term robust pedestrian tracking. In this model, we use a pre-trained tracking model to track the specified object and use the three-way decision theory to judge the color histogram feature and correct the results by the detector. Compared with the separated tracker, our model invokes the target detector to detect the current frame when the tracking result is wrong and the detection result which is the most similar to the target is selected as the tracking result. Experimental results show that our model can significantly improve the tracking accuracy especially in the complex situations, compared with the separated tracker and the detector.

关键词： Long-term tracking tracking by detection Color histogram Granular computing Three-way decision

来源：评论

学校读者我要写书评

暂无评论

An improved framework based on tracking-by-detection for simultaneous estimation of yield and maturity level in cherry tomatoes

引用

MEASUREMENT 2024年 226卷

作者： Qi, Zhongxian Zhang, Wenqiang Yuan, Ting Rong, Jiacheng Hua, Wanjia Zhang, Zhiqin Deng, Xue Zhang, Junxiong Li, Wei China Agr Univ Coll Engn Qinghua Rd E 17 Beijing 100083 Peoples R China

Automated and accurate counting and ripeness level estimation play key roles in the precision management of cherry tomatoes in greenhouses. This study presents an enhanced framework based on tracking by detection to simultaneously estimate the count and ripeness levels for cherry tomato bunches in greenhouses. Ripeness value is determined by the proportional relationship between the number of ripe and unripe fruits in a tomato bunch. To accurately detect fruit kernels in small sizes and blurred ROIs, a lightweight detector called NanoDet is employed. To reduce ripeness estimation errors caused due to shading, the ripeness value with the highest frequency is selected as the estimate when multiple detections of the same bunch are detected. The ripeness values are categorized into five levels and combined with the counting results. The study's results demonstrate that it achieves 92.79% accuracy in counting and 90.84% accuracy in estimating ripeness levels. The improved algorithm has a processing rate of 15 frames per second. These results demonstrate the potential and value of the enhanced method for counting cherry tomatoes and estimating their ripeness levels.

关键词： Cherry tomato Yield estimation Maturity level estimation Computer vision tracking by detection Deep learning

来源：评论

学校读者我要写书评

暂无评论

Yolo-3DMM for Simultaneous Multiple Object detection and tracking in Traffic Scenarios

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2024年第8期25卷 9467-9481页

作者： Liu, Lichen Song, Xiangyu Song, Huansheng Sun, Shijie Han, Xian-Feng Akhtar, Naveed Mian, Ajmal Changan Univ Sch Informat Engn Xian 710000 Shaanxi Peoples R China Peng Cheng Lab Shenzhen 518066 Peoples R China Southwest Univ Coll Comp & Informat Sci Chongqing 400715 Peoples R China Univ Melbourne Sch Comp & Informat Syst Parkville Vic 3010 Australia Univ Western Australia Sch Comp Sci & Software Engn Crawley WA 6009 Australia

Video-based multiple object tracking (MOT) is a fundamental task in intelligent transportation with applications ranging from automated traffic surveillance to autonomous driving. MOT methods commonly follow a tracking-by-detection paradigm, tracking objects by associating their detections across video frames. However, insofar, these methods have not used the entire vehicle trajectory motion characteristics to perform tracking, which converts the vehicle localization problem into a motion parameter estimation problem. Moreover, MOT methods mainly rely on off-the-shelf detectors. An independently trained detector is sub-optimal for the tracking-by-detection paradigm and adversely affects the overall system performance. In this article, we address these issues by proposing a novel MOT method for moving vehicles in traffic scenarios. Our tracker treats the vehicle tracks as unified 3D spatio-temporal trajectory instances and leverages the power of deep learning to extract vehicle motion from the 3D instances. We propose a new simultaneous detection and tracking network, called YOLO-3D Motion Model Network (Yolo-3DMM) that employs spatio-temporal features of traffic videos for simultaneous vehicle detection and tracking in an end-to-end manner. We adopt a variety of different vehicle tracking datasets to evaluate our method. Moreover, we also propose a tunnel MOT dataset from real highway tunnel surveillance in Guangdong, China to expand the experimental scenarios. To establish the efficacy of our method, we evaluate it on 100 different roadside traffic scenarios. Our method shows excellent performance on UA-DETRAC and Omni-MOT datasets. It achieves a PR-MOTA score of 29.40% on UA-DETRAC and gets a 69.7% MOTA score on the Omni-MOT dataset.

关键词： Multi-object tracking simultaneous detection and tracking tracking by detection motion-based prediction

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：