检索结果-内蒙古大学图书馆

Multiple Object tracking With Attention to Appearance, Structure, Motion and Size

IEEE ACCESS 2019年 7卷 104423-104434页

作者： Karunasekera, Hasith Wang, Han Zhang, Handuo Nanyang Technol Univ Sch Elect & Elect Engn Singapore 639798 Singapore

Objective of multiple object tracking (MOT) is to assign a unique track identity for all the objects of interest in a video, across the whole sequence. tracking-by-detection is the most common approach used in addressing MOT problem. In this work, we propose a method to address MOT by defining a dissimilarity measure based on object motion, appearance, structure, and size. We calculate the appearance and structure-based dissimilarity measure by matching histograms following a grid architecture. Motion and size for each track are predicted using the information from track's history. These dissimilarity values are then used in the Hungarian algorithm, in the data association step for track identity assignment. In addition, we introduce a method to address any false detection in stable tracks. The proposed method runs in real time following an online approach. We evaluate our method in both MOT17 benchmark data-set for pedestrian tracking and KITTI benchmark data-set for vehicle tracking using the same system parameters to verify the robustness of the proposed method. The method can achieve state-of-the-art results in both benchmarks.

关键词： Multiple object tracking grid-based histograms tracking by detection online tracking multiple car tracking multiple human tracking

来源：评论

学校读者我要写书评

暂无评论

Not All Negatives Are Equal: Learning to Track With Multiple Background Clusters

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2018年第2期28卷 314-326页

作者： Zhu, Gao Porikli, Fatih Li, Hongdong Australian Natl Univ Res Sch Engn Acton ACT 2601 Australia CSIRO Data61 Alexandria NSW 1435 Australia Australian Ctr Robot Vis Brisbane Qld 4001 Australia

Conventional tracking-by-detection approaches for visual object tracking often assume that the task at hand is a binary foreground-versus-background classification problem, in which the background is a single, generic, and all-inclusive class. In contrast, here we argue that the background appearance, for the most part, possesses a more complicated structure that would benefit from further partitioning into multiple contextual clusters. Our observation is that, although the background class is contemplated to contain a vast intra-class variation, during the tracking process, only a small portion of this diversity is present at the current frame around the foreground object. This observation motivates us to build multiple fine-grained foreground-versus-contextual-cluster models that provide more discriminative classifications, and consequently more robust and accurate foreground object tracking. For each cluster, we employ a structured output support vector machine (SSVM), and in an online manner, we combine the responses of multiple classifiers. To this end, we apply a top-level SSVM that models the tracked foreground object. We show that our refined modeling of the background is better than naively growing the complexity of a single foreground-background classifier, i.e., increasing the number of support vectors that existing approaches rely on, which cause overfitting issues. Our extensive evaluations on large benchmark data sets demonstrate that our tracker consistently outperforms the current state-of-the-art while having comparable computational requirements.

关键词： Contextual clustering fine-grained model support vector machine (SVM) tracking by detection

来源：评论

学校读者我要写书评

暂无评论

Multiple Object tracking Using Edge Multi-Channel Gradient Model With ORB Feature

引用

IEEE ACCESS 2021年 9卷 2294-2309页

作者： Chen, Jieyu Xi, Zhenghao Wei, Chi Lu, Junxin Niu, Yuhui Li, Zhongfeng Shanghai Univ Engn Sci Sch Elect & Elect Engn Shanghai 201620 Peoples R China Univ Nottingham Dept Elect & Elect Engn Nottingham NG7 2RD England Yingkou Inst Technol Coll Elect Engn Yingkou 115014 Peoples R China

Multiple object tracking based on tracking-by-detection is the most common method used in addressing illumination change and occlusion problems. In this paper, we present a tracking algorithm based on Edge Multi-channel Gradient Model. We first use the canny operator to extract the edges of the image, and establish a biologically inspired Multi-channel Gradient Model that integrate the spatio-temporal-spectral information of the edge to detect moving multiple objects. Under this model, the ORB feature is introduced to solve the problem of matching the object with the object library. Therefore, we can achieve object consistency, and the threshold classification method can solve the problem of multiple object occlusion in the process of persistent multiple object tracking. The experimental results show that the proposed method can effectively deal with the problems of occlusion and illumination changes. Compared with other state-of-the-art algorithms, the proposed algorithm achieves better performance on MOTA, MOTP, and IDF1. In particular, it performs best on IDSW on MOT2015 dataset, with an average improvement ratio of 28.99% over the second-place algorithm. In addition, our algorithm has a better performance in running time, achieving a good compromise between the speed and the accuracy.

关键词： Multiple object tracking multiple object detection ORB E-McGM tracking by detection

来源：评论

学校读者我要写书评

暂无评论

Real-time visual tracking via online weighted multiple instance learning

引用

PATTERN RECOGNITION 2013年第1期46卷 397-411页

作者： Zhang, Kaihua Song, Huihui Hong Kong Polytech Univ Dept Comp Hong Kong Hong Kong Peoples R China Chinese Univ Hong Kong Dept Geog & Resource Management Hong Kong Hong Kong Peoples R China

Adaptive tracking-by-detection methods have been widely studied with promising results. These methods first train a classifier in an online manner. Then, a sliding window is used to extract some samples from the local regions surrounding the former object location at the new frame. The classifier is then applied to these samples where the location of sample with maximum classifier score is the new object location. However, such classifier may be inaccurate when the training samples are imprecise which causes drift. Multiple instance learning (MIL) method is recently introduced into the tracking task, which can alleviate drift to some extent. However, the MIL tracker may detect the positive sample that is less important because it does not discriminatively consider the sample importance in its learning procedure. In this paper, we present a novel online weighted MIL (WMIL) tracker. The WMIL tracker integrates the sample importance into an efficient online learning procedure by assuming the most important sample (i.e., the tracking result in current frame) is known when training the classifier. A new bag probability function combining the weighted instance probability is proposed via which the sample importance is considered. Then, an efficient online approach is proposed to approximately maximize the bag likelihood function, leading to a more robust and much faster tracker. Experimental results on various benchmark video sequences demonstrate the superior performance of our algorithm to state-of-the-art tracking algorithms. (C) 2012 Elsevier Ltd. All rights reserved.

关键词： Visual tracking Multiple instance learning tracking by detection Sliding window

来源：评论

学校读者我要写书评

暂无评论

Appearance Guidance Attention for Multi-Object tracking

引用

IEEE ACCESS 2021年 9卷 103184-103193页

作者： Chen, Yong Huang, Junjie Liu, Huanlin Huang, Meiyong Zou, Zhibo Chongqing Univ Posts & Telecommun Key Lab Ind Internet Things & Network Control Minist Educ Chongqing 400065 Peoples R China Chongqing Univ Posts & Telecommun Key Lab Opt Fiber Commun Technol Chongqing 400065 Peoples R China

Appearance information is one of the most important matching indicators for multi-object data association. In tracking by detection model, appearance information and detection information are usually integrated in the same sub-network for learning and output. This phenomenon will result in the appearance embedding vectors to be coupled to the network inference method during learning stage. As a result, the appearance embedding vectors contains too much background information and affects the accuracy of data association. Based on the non-end-to-end tracking model, we design an appearance guidance attention module for the appearance extraction branch. This module can effectively strengthen the network's learning of the object visual appearance features and reduce the attention in the learning of background features. Finally, we utilize the appearance embedding vectors that decoupled from the inference method as the input of the back-end tracker and perform data association. The proposed method is tested on the MOT16 and MOT17 datasets. Experiments show that the proposed method provides more high-quality appearance representation information for the back-end tracker and the tracking performance on two datasets is better than other comparison models. At the same time, our model can reach 24.9FPS on a single 1080Ti GPU. The code is available at: https://***/JoJoliking/AGM

关键词： Data models Feature extraction Task analysis Trajectory Switches Target tracking Data mining Multi-object tracking tracking by detection attention mechanism appearance information

来源：评论

学校读者我要写书评

暂无评论

Real-time optical markerless tracking for augmented reality applications

引用

JOURNAL OF REAL-TIME IMAGE PROCESSING 2010年第2期5卷 129-138页

作者： Barandiaran, Inigo Paloc, Celine Grana, Manuel VICOMTech San Sebastian 20009 Spain

Augmented reality (AR) technology consists in adding computer-generated information (2D/3D) to a real video sequence in such a manner that the real and virtual objects appear coexisting in the same world. To get a realistic illusion, the real and virtual objects must be properly aligned with respect to each other, which requires a robust real-time tracking strategy-one of the bottlenecks of AR applications. In this paper, we describe the limitations and advantages of different optical tracking technologies, and we present our customized implementation of both recursive tracking and tracking by detection approaches. The second approach requires the implementation of a classifier and we propose the use of a Random Forest classifier. We evaluated both approaches in the context of an AR application for design review. Some conclusions regarding the performance of each approach are given.

关键词： Augmented reality Optical markerless tracking tracking by detection

来源：评论

学校读者我要写书评

暂无评论

Robust visual tracking via online multiple instance learning with Fisher information

引用

PATTERN RECOGNITION 2015年第12期48卷 3917-3926页

作者： Xu, Chao Tao, Wenyuan Meng, Zhaopeng Feng, Zhiyong Tianjin Univ Sch Comp Software Tianjin Peoples R China Tianjin Univ Sch Comp Sci & Technol Tianjin Peoples R China

Most tracking-by-detection approaches train the classifier in an supervised manner in which the samples near the tracked object location are labeled positively while those far from the object location are negative. However, the inaccuracy of the tracker may cause incorrectly labeled training samples, which in turn degrade the classifier when updating it, thereby leading to drift problem. Recently, multiple instance learning (MIL) is introduced into visual tracking with demonstrated success of dealing with drift. In MIL tracker, the samples are put into bags, and the classifier is a linear combination of some weak classifiers which are greedily selected via maximizing the likelihood function of the bags. However, the weak classifiers selected by the likelihood function are less informative to tell target from complex background than those from some information criterion (e.g., Fisher information criterion). In this paper, we show that using the Fisher information criterion instead of the likelihood function in the MIL can yield a more robust and efficient result. An online boosting feature selection approach is proposed via optimizing the Fisher information criterion, which can yield more robust and efficient tracking performance. Experimental evaluations on challenging sequences demonstrate the superiority of our tracker to state-of-the-art trackers in terms of efficiency, accuracy and robustness. (C) 2015 Elsevier Ltd. All rights reserved.

关键词： tracking by detection Multiple instance learning Fisher information

来源：评论

学校读者我要写书评

暂无评论

Multitarget tracking Using Hough Forest Random Field

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2016年第11期26卷 2028-2042页

作者： Xiang, Jun Sang, Nong Hou, Jianhua Huang, Rui Gao, Changxin Huazhong Univ Sci & Technol Natl Key Lab Sci & Technol Multispectral Informat Sch Automat Wuhan 430074 Peoples R China South Cent Univ Nationalities Hubei Key Lab Intelligent Wireless Commun Wuhan 430074 Peoples R China

This paper presents a novel tracking-by-detection approach for multitarget tracking. There are two major steps in our framework: data association to form global tracklet association, followed by trajectory estimation to deal with the remaining gaps. In the first step, we formulate tracklet association as an inference problem in a Hough forest random field, which combines Hough forest and conditional random field and allows us to model both local and global tracklet relationships in one unified model. In the second step, we improve the reversible-jump Markov chain Monte Carlo particle filtering method with explicit mutual-occlusion reasoning to fill in the remaining gaps from the first step and increase the overall tracking precision. Extensive experiments have been conducted on five public data sets, and the performance is comparable to that of the state-of-the-art method, if not better.

关键词： Conditional random field (CRF) Hough forest (HF) multitarget tracking occlusion reasoning reversible-jump Markov chain Monte Carlo (RJMCMC) tracking by detection trajectory estimation

来源：评论

学校读者我要写书评

暂无评论

Multi-Object tracking Based on a Novel Feature Image With Multi-Modal Information

引用

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2023年第8期72卷 9909-9921页

作者： An, Yi Wu, Jialin Cui, Yunhao Hu, Huosheng Dalian Univ Technol Sch Control Sci & Engn Dalian 116023 Peoples R China Xinjiang Univ Sch Elect Engn Urumqi 830046 Peoples R China Dalian Univ Technol Sch Mech Engn Dalian 116023 Peoples R China Univ Essex Sch Comp Sci & Elect Engn Colchester CO4 3SQ England

Multi-object tracking technology plays a crucial role in many applications, such as autonomous vehicles and security monitoring. This paper proposes a multi-object tracking framework based on the multi-modal information of 3D point clouds and color images. At each sampling instant, the 3D point cloud and image acquired by a LiDAR and a camera are fused into a color point cloud, where objects are detected by the Point-GNN method. And, a novel height-intensity-density (HID) image is constructed from the bird's eye view. The HID image truly reflects the shapes and materials of objects and effectively avoids the influence of object occlusion, which is helpful to object tracking. In two sequential HID images, a new rotation kernel correlation filter is proposed to predict the objects. Furthermore, an object retention module and an object re-recognition module are developed to overcome the object matching failure in the in-between frames. The proposed method takes full advantage of the multi-modal data and effectively achieves the information complementation to improve the accuracy of multi-object tracking. The experiments with the KITTI dataset show that the proposed method has the best performance among the existing traditional multi-object tracking methods.

关键词： Image processing kernel correlation filter multi-object tracking point cloud tracking by detection

来源：评论

学校读者我要写书评

暂无评论

Robust Welding Seam tracking and Recognition

引用

IEEE SENSORS JOURNAL 2017年第17期17卷 5609-5617页

作者： Li, Xianghui Li, Xinde Khyam, Mohammad Omar Ge, Shuzhi Sam Southeast Univ Key Lab Measurement & Control CSE Minist Educ Sch Automat Nanjing 210096 Jiangsu Peoples R China Nanyang Technol Univ Sch Elect & Elect Engn Singapore 639798 Singapore Natl Univ Singapore Dept Elect & Comp Engn Singapore 117580 Singapore

In the process of automatic welding based on structured light vision, the precise localization of the welding seam in an image has an important influence on the quality of the welding. However, in practice, there is much interference, such as spatter and arc, which introduces great challenges for accurate welding seam localization. In this paper, we considered welding seam localization problem as visual target tracking and based on that, we proposed a robust welding seam tracking algorithm. Prior to the start of welding, the seam is separated using a cumulative gray frequency, which is utilized to adaptively determine the initial position and size of the search window. During the welding process, large seam motion range may result in only a portion of the welding seam exists in the search window. To prevent that, a tracking-by-detection method is used to calculate the location of the search window. Usually, the intersection of seam and noise, e.g., spatter, has a severe influence on the accuracy of feature points localization. In order to solve this problem, a sequence gravity method (SGM) for extracting a smoother center line of welding seam is proposed, which is able to reduce the impact of interference. The double-threshold recursive least square method is used to fit the curve obtained by SGM with the aim of improving the real-time performance and accuracy of the system. Finally, the superiority of the proposed algorithm is well demonstrated by comparison with other solutions for seam tracking and recognition through extensive experiments.

关键词： tracking by detection welding tracking sequence gravity method double-threshold recursive least square fitting

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：