检索结果-内蒙古大学图书馆

Visual object tracking via online sparse instance learning

JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION 2015年第1期26卷 231-246页

作者： Yan, Jia Chen, Xi Deng, Dexiang Zhu, Qiuping Wuhan Univ Sch Elect Informat Dept Elect Engn Wuhan 430072 Hubei Peoples R China Wuhan Univ Sch Int Software Wuhan 430072 Hubei Peoples R China

Sparse representation has been attracting much more attention in visual tracking. However most sparse representation based trackers only focus on how to model the target appearance and do not consider the learning of sparse representation when the training samples are imprecise, and hence may drift or fail in the challenging scene. In this paper, we present a novel online tracking algorithm. The tracker integrates the online multiple instance learning into the recent sparse representation scheme. For tracking, the integrated sparse representation combining texture, intensity and local spatial information is proposed to model the target. This representation takes both occlusion and appearance change into account. Then, an efficient online learning approach is proposed to select the most distinguishable features to separate the target from the background samples. In addition, the sparse representation is dynamically updated online with respect to the current context. Both qualitative and quantitative evaluations on challenging benchmark video sequences demonstrate that the proposed tracking algorithm performs favorably against several state-of-the-art methods. (C) 2014 Published by Elsevier Inc.

关键词： Visual tracking Multiple instance learning Integrated sparse representation tracking by detection Random projection Online learning Appearance variation Occlusion

来源：评论

学校读者我要写书评

暂无评论

SSAT: Self-Supervised Associating Network for Multiobject tracking

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2022年第11期32卷 7858-7868页

作者： Chung, Tae-Young Cho, MyeongAh Lee, Heansung Lee, Sangyoun Yonsei Univ Sch Elect & Elect Engn Seoul 03722 South Korea

Multi-object tracking (MOT), which is crucial for computer vision and video processing, has immense potential for improvement. Traditional tracking-by-detection approaches include feature-based object re-identification methods that use trained features, but these methods suffer from a lack of suitable training data. In training datasets used for MOT, every object in a video sequence must have its own location and ID. However, assigning IDs to each object in every sequence is considerably labor-intensive, and hence current MOT datasets are unsuitable for training re-identification networks. To resolve this issue, this paper proposes a novel self-supervised learning method using several short videos that contain no human-added labels, based on the idea that each video is a set of temporally corresponding image frames. We then describe how to improve tracking performance using a re-identification network trained in a self-supervised manner. In addition, ablation studies were conducted in order to define the optimal parameters, such as number of clips, data augmentation, and appropriate matching algorithms. The proposed approach achieved competitive performance compared with current best-practice methods including supervised methods, achieving MOT accuracy = 62.0% and ID F1-score = 62.7% on the MOT17 benchmark.

关键词： Target tracking Feature extraction Task analysis Training Visualization Training data Benchmark testing Multi-object tracking tracking by detection self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Face Association for Videos Using Conditional Random Fields and Max-Margin Markov Networks

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2016年第9期38卷 1762-1773页

作者： Du, Ming Chellappa, Rama Univ Maryland Dept Elect & Comp Engn College Pk MD 20742 USA

We address the video-based face association problem, in which one attempts to extract the face tracks of multiple subjects while maintaining label consistency. Traditional tracking algorithms have difficulty in handling this task, especially when challenging nuisance factors like motion blur, low resolution or significant camera motions are present. We demonstrate that contextual features, in addition to face appearance itself, play an important role in this case. We propose principled methods to combine multiple features using Conditional Random Fields and Max-Margin Markov networks to infer labels for the detected faces. Different from many existing approaches, our algorithms work in online mode and hence have a wider range of applications. We address issues such as parameter learning, inference and handling false positves/negatives that arise in the proposed approach. Finally, we evaluate our approach on several public databases.

关键词： Face association tracking by detection conditional random field max-margin Markov networks contextual features

来源：评论

学校读者我要写书评

暂无评论

Adaptive Compressive tracking via Online Vector Boosting Feature Selection

引用

IEEE TRANSACTIONS ON CYBERNETICS 2017年第12期47卷 4289-4301页

作者： Liu, Qingshan Yang, Jing Zhang, Kaihua Wu, Yi Nanjing Univ Informat Sci & Technol Jiangsu Key Lab Big Data Anal Technol Nanjing 210044 Jiangsu Peoples R China

Recently, the compressive tracking (CT) method has attracted much attention due to its high efficiency, but it cannot well deal with the large scale target appearance variations due to its data-independent random projection matrix that results in less discriminative features. To address this issue, in this paper, we propose an adaptive CT approach, which selects the most discriminative features to design an effective appearance model. Our method significantly improves CT in three aspects. First, the most discriminative features are selected via an online vector boosting method. Second, the object representation is updated in an effective online manner, which preserves the stable features while filtering out the noisy ones. Furthermore, a simple and effective trajectory rectification approach is adopted that can make the estimated location more accurate. Finally, a multiple scale adaptation mechanism is explored to estimate object size, which helps to relieve interference from background information. Extensive experiments on the CVPR2013 tracking benchmark and the VOT2014 challenges demonstrate the superior performance of our method.

关键词： Compressive tracking (CT) feature template model update tracking by detection

来源：评论

学校读者我要写书评

暂无评论

Adaptive Kalman Filter with power transformation for online multi-object tracking

引用

MULTIMEDIA SYSTEMS 2023年第3期29卷 1231-1244页

作者： Liu, Youyu Li, Yi Xu, Dezhang Yang, Qingyan Tao, Wanbao Anhui Polytech Univ Mech Engn Dept Wuhu 241000 Peoples R China Anhui Jianzhu Univ Coll Mech & Elect Engn Hefei 230601 Peoples R China

By introducing a low-score detection box association stage, the full-detection association can effectively enhance the accuracy and robustness of online multi-object tracking. However, this association would lead to a decline in tracking precision, the key point of which is that the fixed noise setting of Kalman Filter is difficult to balance the system requirements for high-score and low-score detection boxes. A Power-Adaptive Kalman Filter (PAKF) was proposed in this article. Taking the motion matching cost and confidence score as process and observation noise scale parameters, respectively, and combined with the power transformation, two adaptive factors were constructed to adjust the process and observation covariance matrices, respectively. Sufficient ablation experiments were conducted on the full validation set of MOT17. After introducing the PAKF into the ByteTrack and SORT, the High-Order tracking Accuracy, Multi-Object tracking Precision (MOTP) and ID F1 score of them were improved by about 1%, and their improvements were more obvious in complex scenarios. On the challenging HiEve benchmark dataset, after introducing the PAKF, the Multi-Object tracking Accuracy and MOTP of the ByteTrack were improved by 0.53% and 0.28%, respectively. It is more advantageous than other state-of-the-art online methods. The proposed PAKF can effectively improve the performances of the multi-object tracking algorithms based on the Kalman Filter and tracking-by-detection.

关键词： Adaptive Kalman Filter tracking by detection Online multi-object tracking Power transformation

来源：评论

学校读者我要写书评

暂无评论

A 3D Relative-Motion Context Constraint-Based MAP Solution for Multiple-Object tracking Problems

引用

SENSORS 2018年第7期18卷 2363-2363页

作者： Wang, Zhongli Fan, Litong Cai, Baigen Beijing Jiaotong Univ Sch Elect Informat & Engn Beijing 100044 Peoples R China Beijing Engn Res Ctr EMC & GNSS Technol Rail Tran Beijing 100044 Peoples R China Inner Mongolia Univ Finance & Econ Sch Comp Informat Management Hohot 010010 Peoples R China

Multi-object tracking (MOT), especially by using a moving monocular camera, is a very challenging task in the field of visual object tracking. To tackle this problem, the traditional tracking-by-detection-based method is heavily dependent on detection results. Occlusion and mis-detections will often lead to tracklets or drifting. In this paper, the tasks of MOT and camera motion estimation are formulated as finding a maximum a posteriori (MAP) solution of joint probability and synchronously solved in a unified framework. To improve performance, we incorporate the three-dimensional (3D) relative-motion model into a sequential Bayesian framework to track multiple objects and the camera's ego-motion estimation. A 3D relative-motion model that describes spatial relations among objects is exploited for predicting object states robustly and recovering objects when occlusion and mis-detections occur. Reversible jump Markov chain Monte Carlo (RJMCMC) particle filtering is applied to solve the posteriori estimation problem. Both quantitative and qualitative experiments with benchmark datasets and video collected on campus were conducted, which confirms that the proposed method is outperformed in many evaluation metrics.

关键词： tracking by detection 3D relative-motion model sequential Bayesian framework multi-object tracking

来源：评论

学校读者我要写书评

暂无评论

Spatio-temporal 3D pose estimation of objects in stereo images

引用

6th International Conference on Computer Vision Systems

作者： Barrois, Bjoern Woehler, Christian Daimler AG Res Grp D-89013 Ulm Germany

ISBN: (纸本)9783540795469

In this contribution we describe a vision system for model-based 3D detection and spatio-temporal pose estimation of objects in cluttered scenes. As low-level features, our approach requires 3D depth points along with information about their motion and the direction of the local intensity gradient. We extract these features by spacetime stereo based on local image intensity modelling. After applying a graph-based clustering approach to obtain an initial separation between the background and the object, a 3D model is adapted to the 3D point cloud based on an ICP-like optimisation technique, yielding the translational, rotational, and internal degrees of freedom of the object. We introduce an extended constraint line approach which allows to estimate the temporal derivatives of the translational and rotational pose parameters directly from the spacetime stereo data. Our system is evaluated in the scenario of person-independent "tracking by detection" of the hand-forearm limb moving in a non-uniform manner through a cluttered scene. The temporal derivatives of the current pose parameters are used for initialisation in the subsequent image. Typical accuracies of the estimation of pose differences between subsequent images are 1-3 mm for the translational motion, which is comparable to the pixel resolution, and 1-3 degrees for the rotational motion.

关键词： 3D scene segmentation 3D pose estimation spacetime stereo temporal pose derivatives tracking by detection

来源：评论

学校读者我要写书评

暂无评论

MULTIPLE TARGET tracking WITH STRUCTURAL INFERENCE

MULTIPLE TARGET TRACKING WITH STRUCTURAL INFERENCE

引用

IEEE International Conference on Multimedia and Expo Workshops (ICMEW)

作者： Zhang, Chenyuan Cai, Ling Zhang, Yinghua Zhao, Yuming Shanghai Jiao Tong Univ Sch Elect Informat & Elect Engn Shanghai 200030 Peoples R China

ISBN: (纸本)9781479947614

In this paper we propose a novel multiple target tracking model composed of two detectors and a tracker. An on-line detector and a tracker are used to generate target candidates, whose confidence scores are then evaluated by the off-line trained detectors. In the data association stage, the high-efficient inference in a structural model leads to the optimal tracking result. The experimental results demonstrate that our tracking model can overcome the occlusion and appearance changing problems. The tracking results can be applied to analyze the structural information of a single target or among multiple targets.

关键词： Multiple target tracking tracking by detection Structural model Belief propagation

来源：评论

学校读者我要写书评

暂无评论

Real-Time Multiple Pedestrians tracking in Multi-camera System 26th

Real-Time Multiple Pedestrians Tracking in Multi-camera Syst...

引用

26th International Conference on MultiMedia Modeling (MMM)

作者： Chen, Muchun Chen, Yugang Truong Tan Loc Ni, Bingbing Shanghai Jiao Tong Univ Shanghai Peoples R China Minivision Tan Uyen Vietnam

ISBN: (纸本)9783030377311;9783030377304

This paper proposes a novel 3D realtime multi-view multi-target tracking framework featured by a global-to-local tracking by detection model and a 3D tracklet-to-tracklet data association scheme. In order to enable the realtime performance, the former maximizes the utilization of temporal differences between consecutive frames, resulting in a great reduction of the average frame-wise detection time. Meanwhile, the latter accurately performs multi-target data association across multiple views to calculate the 3D trajectories of tracked objects. Comprehensive experiments on PETS-09 dataset well demonstrate the outstanding performance of the proposed method in terms of efficiency and accuracy in multi-target 3d trajectory tracking tasks, compared to the state-of-the art methods.

关键词： Multi-view multi-object tracking tracking by detection Computer vision Deep learning

来源：评论

学校读者我要写书评

暂无评论

MULTIPLE OBJECT tracking BASED ON SPARSE GENERATIVE APPEARANCE MODELING

MULTIPLE OBJECT TRACKING BASED ON SPARSE GENERATIVE APPEARAN...

引用

IEEE International Conference on Image Processing (ICIP)

作者： Riahi, Dorra Bilodeau, Guillaume-Alexandre Polytech Montreal LITIV Lab Montreal PQ Canada

ISBN: (纸本)9781479983391

This paper addresses multiple object tracking which still remains a challenging problem because of factors like frequent occlusions, unknown number of targets and similarity in objects' appearance. We propose a novel approach for multiple object tracking using a multiple feature framework. The main focus of the proposed method is to build a robust appearance model. The appearance model of an object is built using a color model, a sparse appearance model, a motion model and spatial information. We validated the proposed algorithm on four publicly available videos with comparisons with state-of-the-art approaches. We demonstrate that our algorithm achieves competitive results.

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

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：