检索结果-内蒙古大学图书馆

Learning Adaptive Discriminative Correlation Filters via Temporal Consistency Preserving Spatial Feature Selection for Robust visual object tracking

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2019年第11期28卷 5596-5609页

作者： Xu, Tianyang Feng, Zhen-Hua Wu, Xiao-Jun Kittler, Josef Jiangnan Univ Sch Internet Things Engn Wuxi 214122 Jiangsu Peoples R China Univ Surrey Ctr Vis Speech & Signal Proc Guildford GU2 7XH Surrey England

With efficient appearance learning models, discriminative correlation filter (DCF) has been proven to be very successful in recent video object tracking benchmarks and competitions. However, the existing DCF paradigm suffers from two major issues, i.e., spatial boundary effect and temporal filter degradation. To mitigate these challenges, we propose a new DCF-based tracking method. The key innovations of the proposed method include adaptive spatial feature selection and temporal consistent constraints, with which the new tracker enables joint spatial-temporal filter learning in a lower dimensional discriminative manifold. More specifically, we apply structured spatial sparsity constraints to multi-channel filters. Consequently, the process of learning spatial filters can be approximated by the lasso regularization. To encourage temporal consistency, the filter model is restricted to lie around its historical value and updated locally to preserve the global structure in the manifold. Last, a unified optimization framework is proposed to jointly select temporal consistency preserving spatial features and learn discriminative filters with the augmented Lagrangian method. Qualitative and quantitative evaluations have been conducted on a number of well-known benchmarking datasets such as OTB2013, OTB50, OTB100, Temple-Colour, UAV123, and VOT2018. The experimental results demonstrate the superiority of the proposed method over the state-of-the-art approaches.

关键词： visual object tracking correlation filter feature selection temporal consistency

来源：评论

学校读者我要写书评

暂无评论

MSST-ResNet: Deep multi-scale spatiotemporal features for robust visual object tracking

引用

KNOWLEDGE-BASED SYSTEMS 2019年 164卷 235-252页

作者： Liu, Bing Liu, Qiao Zhu, Zhengyu Zhang, Taiping Yang, Yong Chongqing Univ Coll Comp Sci Chongqing Peoples R China Harbin Inst Technol Sch Comp Sci & Technol Shenzhen Grad Sch Harbin Heilongjiang Peoples R China Chongqing Univ Posts & Telecommun Coll Comp Sci & Technol Chongqing Peoples R China China Mobile IOT Co Ltd Open Platform Dept Chongqing Peoples R China

The performance of the tracking task directly depends on target object appearance features. Therefore, a robust method for constructing appearance features is crucial for avoiding tracking failure. The tracking methods based on Convolution Neural Network (CNN) have exhibited excellent performance in the past years. However, the features from each original convolutional layer are not robust to the size change of target object. Once the size of the target object has significant changes, the tracker drifts away from the target object. In this paper, we present a novel tracker based on multi-scale feature, spatiotemporal features and deep residual network to accurately estimate the size of the target object. Our tracker can successfully locate the target object in the consecutive video frames. To solve the multi-scale change issue in visual object tracking, we sample each input image with 67 different size templates and resize the samples to a fixed size. And then these samples are used to offline train deep residual network model with multi-scale feature that we have built up. After that spatial feature and temporal feature are fused into the deep residual network model with multi-scale feature, so that we can get deep multi-scale spatiotemporal features model, which is named MSST-ResNet feature model. Finally, MSST-ResNet feature model is transferred into the tracking tasks and combined with three different Kernelized Correlation Filters (KCFs) to accurately locate target object in the consecutive video frames. Unlike the previous trackers, we directly learn various change of the target appearance by building up a MSST-ResNet feature model. The experimental results demonstrate that the proposed tracking method outperforms the state-of-the-art tracking methods. (C) 2018 Elsevier B.V. All rights reserved.

关键词： visual object tracking Residual network Kernelized correlation filter Spatiotemporal features Multi-scale features

来源：评论

学校读者我要写书评

暂无评论

visual-inertial object tracking: Incorporating camera pose into motion models

引用

EXPERT SYSTEMS WITH APPLICATIONS 2023年第PartA期229卷

作者： Shahbazi, Mohammad Mirtajadini, Seyed Hojat Fahimi, Hamidreza Iran Univ Sci & Technol Sch Mech Engn Hengam St Tehran *** Iran Univ Tehran Fac New Sci & Technol North Kargar St Tehran *** Iran Amirkabir Univ Technol Dept Aerosp Engn Hafez Ave Tehran *** Iran

visual object tracking for autonomy of aerial robots could become challenging especially in the presence of target or camera fast motions and long-term occlusions. This paper presents a visual-inertial tracking paradigm by incorporating the camera kinematics states into the visual object tracking pipelines. We gathered a dataset of image sequences with the addition of camera's position and orientation measurements as well as the object's position measurement. For the cases of long-term object occlusion, we provide ground-truth boxes derived from mapping the measured object position onto the image frame. A search zone proposal method is developed based on the estimation of object future position represented in the inertial frame and projected back onto the image frame using the camera states. This search zone, which is robust to fast camera/target motions, is fused into the original search zone settings of the base tracker. Also proposed is a measure indicating the confidence of a tracking structure in keeping track of a correct target and reporting the tracking failure in-time. Accordingly, the model updating mechanism of base tracker is modulated to avoid recovering of wrong objects as the target. The proposed modifications are benchmarked on nine visual object tracking algorithms including five state-of-art deep learning structures, namely DiMP, PrDiMP, KYS, ToMP, and MixFormer. Most of the trackers are remarkably improved by the modifications with up to 8% increase in precision. Modified PrDiMP tracker yields the best precision of 68.4%, more than all considered original (and modified) trackers. Source code and dataset are made available online.1

关键词： visual object tracking object tracking dataset Aerial robot Deep learning visual-inertial navigation

来源：评论

学校读者我要写书评

暂无评论

visual object tracking based on discriminant DCT features

引用

DIGITAL SIGNAL PROCESSING 2019年 95卷 102572-000页

作者： Sharma, Vijay K. Mahapatra, K. K. Acharya, Bibhudendra Natl Inst Technol Dept Elect & Commun Engn Raipur 492010 CG India Natl Inst Technol Dept Elect & Commun Engn Rourkela 769008 Odisha India

In this paper, a visual object tracking method is proposed based on sparse 2-dimensional discrete cosine transform (2D DCT) coefficients as discriminative features. To select the discriminative DCT coefficients, we give two propositions. The propositions select the features based on estimated mean of feature distributions in each frame. Some intermediate tracking instances are obtained by (a) computing feature similarity using kernel, (b) finding the maximum classifier score computed using ratio classifier, and (c) combinations of both. Another intermediate tracking instance is obtained using incremental subspace learning method. The final tracked instance amongst the intermediate instances are selected by using a discriminative linear classifier learned in each frame. The linear classifier is updated in each frame using some of the intermediate tracked instances. The proposed method has a better tracking performance as compared to state-of-the-art video trackers in a dataset of 50 challenging video sequences. (C) 2019 Elsevier Inc. All rights reserved.

关键词： visual object tracking Discriminative DCT feature Feature selection Kernel based similarity Incremental learning Linear classifier

来源：评论

学校读者我要写书评

暂无评论

Re-identification framework for long term visual object tracking based on object detection and classification

引用

SIGNAL PROCESSING-IMAGE COMMUNICATION 2020年 88卷 115969-115969页

作者： Nousi, Paraskevi Triantafyllidou, Danai Tefas, Anastasios Pitas, Ioannis Aristotle Univ Thessaloniki Dept Informat Thessaloniki Greece

In this paper, we address the problem of long-term visual object tracking and we present an efficient real-time single object tracking system suitable for integration in autonomous platforms that need to encompass intelligent capabilities. We propose a novel long-term tracking framework for classification based re-detection and tracking, that incorporates state estimation, object re-identification and automated management of tracking and detection results. Our method integrates a novel object re-identification technique which efficiently filters a number of detection candidates and systematically corrects the tracking results. Through extensive experimental validation on the UAV123, UAV20L and TLP datasets, we demonstrate the effectiveness of the proposed system and its advantage over several state-of-the art trackers. The results furthermore highlight the proposed tracker's ability to handle challenges arising from real-world and long-term scenarios, such as variations in pose, scale, occlusions and out-of-view situations. Furthermore, we propose a variant that is suitable for deployment on autonomous robots, such as Unmanned Aerial Vehicles.

关键词： visual object tracking Long-term tracking Re-detection Deep learning

来源：评论

学校读者我要写书评

暂无评论

LEARNING HIERARCHICAL FEATURES FOR visual object tracking WITH RECURSIVE NEURAL NETWORKS 26

LEARNING HIERARCHICAL FEATURES FOR VISUAL OBJECT TRACKING WI...

引用

26th IEEE International Conference on Image Processing (ICIP)

作者： Wang, Li Liu, Ting Wang, Bing Lin, Jie Yang, Xulei Wang, Gang ASTAR I2R Singapore Singapore Nanyang Technol Univ Singapore Singapore

ISBN: (纸本)9781538662496

Recently, deep learning has achieved very promising results in visual object tracking. Deep neural networks in existing tracking methods require a lot of training data to learn a large number of parameters. However, training data is not sufficient for visual object tracking as annotations of a target object are only available in the first frame of a test sequence. In this paper, we propose to learn hierarchical features for visual object tracking by using tree structure based Recursive Neural Networks (RNN), which have a relatively small number of parameters compared to other deep neural networks (e.g. Convolutional Neural Networks (CNN)) due to all basic modules in RNN share only one set of parameters. Experimental results demonstrate that our feature learning algorithm can significantly improve tracking performance on benchmark datasets.

关键词： Deep learning feature learning visual object tracking Recursive Neural Networks

来源：评论

学校读者我要写书评

暂无评论

Real-Time visual object tracking Based on Reinforcement Learning with Twin Delayed Deep Deterministic Algorithm 1

引用

9th International Conference on Intelligence Science and Big Data Engineering (IScIDE)

作者： Zheng, Shengjie Wang, Huan Nanjing Univ Sci & Technol Nanjing Peoples R China

ISBN: (数字)9783030361891

ISBN: (纸本)9783030361891;9783030361884

object tracking as a low-level vision task has always been a hot topic in computer vision. It is well known that Challenges such as background clutters, fast object motion and occlusion et al. affect a lot the robustness or accuracy of existing object tracking methods. This paper proposes a reinforcement learning model based on Twin Delayed Deep Deterministic algorithm (TD3) for single object tracking. The model is based on the deep reinforcement learning model, Actor-Critic (AC), in which the Actor network predicts a continuous action that moves the target bounding box in the previous frame to the object position in the current frame and adapts to the object size. The Critic network evaluates the confidence of the new bounding box online to determine whether the Critic model needs to be updated or re-initialized. In further, in our model we use TD3 algorithm to further optimize the AC model by using two Critic networks to jointly predict the bounding box confidence, and to obtain the smaller predicted value as the label to update the network parameters, thereby rendering the Critic network to avoid excessive estimation bias, accelerate the convergence of the loss function, and obtain more accurate prediction values. Also, a small amount of random noise with upper and lower bounds are added to the action in the Actor model, and the search area is reasonably expanded in offline learning to improve the robustness of the tracking method under strong background interference and fast object motion. The Critic model can also guide the Actor model to select the best action and continuously update the state of the tracking object. Comprehensive experimental results on the OTB-2013 and OTB-2015 benchmarks demonstrate that our tracker performs best in precision, robustness, and efficiency when compared with state-of-the-art methods.

关键词： visual object tracking Reinforcement learning Actor-Critic model Twin Delayed Deep Deterministic algorithm

来源：评论

学校读者我要写书评

暂无评论

Target Aware visual object tracking 16th

Target Aware Visual Object Tracking

引用

16th International Conference on Image Analysis and Recognition (ICIAR)

作者： Ozer, Caner Gurkan, Filiz Gunsel, Bilge Istanbul Tech Univ Multimedia Signal Proc & Pattern Recognat Grp Istanbul Turkey

ISBN: (纸本)9783030272722;9783030272715

We propose a visual object tracker that improves accuracy while significantly decreasing false alarm rate. This is achieved by a late fusion scheme that integrates the motion model of particle sampling with the region proposal network of Mask R-CNN during inference. The qualified bounding boxes selected by the late fusion are fed into the Mask R-CNN's head layer for the detection of the tracked object. We refer the introduced scheme, TAVOT, as target aware visual object tracker since it is capable of minimizing false detections with the guidance of variable rate particle sampling initialized by the target region of interest. It is shown that TAVOT is capable of modeling temporal video content with a simple motion model thus constitutes a promising video object tracker. Performance evaluation performed on VOT2016 video sequences demonstrates that TAVOT 22% increases the success rate, while 73% decreasing the false alarm rate compared to the baseline Mask R-CNN. Compared to the top tracker of VOT2016 around 5% increase at the success rate is reported where intersection over union is greater than 0.5.

关键词： visual object tracking Region proposal network Particle filtering

来源：评论

学校读者我要写书评

暂无评论

Fast visual object tracking using Ellipse Fitting for Rotated Bounding Boxes 17

Fast Visual Object Tracking using Ellipse Fitting for Rotate...

引用

IEEE/CVF International Conference on Computer Vision (ICCV)

作者： Chen, Bao Xin Tsotsos, John K. York Univ Dept Elect Engn & Comp Sci Toronto ON Canada York Univ Ctr Vis Res Toronto ON Canada

ISBN: (纸本)9781728150239

In this paper, we demonstrate a novel algorithm that uses ellipse fitting to estimate the bounding box rotation angle and size with the segmentation(mask) on the target for online and real-time visual object tracking. Our method, SiamMask_E, improves the bounding box fitting procedure of the state-of-the-art object tracking algorithm SiamMask and still retains a fast-tracking frame rate (80 fps) on a system equipped with GPU (GeForce GTX 1080 Ti or higher). We tested our approach on the visual object tracking datasets (VOT2016, VOT2018, and VOT2019) that were labeled with rotated bounding boxes. By comparing with the original SiamMask, we achieved an improved Accuracy of 64.5% and 30.3% EAO on VOT2019, which is 4.9% and 2% higher than the original SiamMask. The implementation is available on GitHub: https://***/baoxinchen/siammask_e.

关键词： Ellipse fitting Siamese visual object tracking

来源：评论

学校读者我要写书评

暂无评论

Global Motion-Aware Robust visual object tracking for Electro Optical Targeting Systems

引用

SENSORS 2020年第2期20卷 566-566页

作者： Kim, Byeong Hak Lukezic, Alan Lee, Jong Hyuk Jung, Ho Min Kim, Min Young Kyungpook Natl Univ Sch Elect Engn Daehakro 80 Daegu 41566 South Korea Hanwha Syst Co 1gongdanro Gumi 39376 South Korea Univ Ljubljana Fac Comp & Informat Sci Ljubljana 1501 Slovenia Kyungpook Natl Univ Res Ctr Neurosurg Robot Syst Daehakro 80 Daegu 41566 South Korea

Although recently developed trackers have shown excellent performance even when tracking fast moving and shape changing objects with variable scale and orientation, the trackers for the electro-optical targeting systems (EOTS) still suffer from abrupt scene changes due to frequent and fast camera motions by pan-tilt motor control or dynamic distortions in field environments. Conventional context aware (CA) and deep learning based trackers have been studied to tackle these problems, but they have the drawbacks of not fully overcoming the problems and dealing with their computational burden. In this paper, a global motion aware method is proposed to address the fast camera motion issue. The proposed method consists of two modules: (i) a motion detection module, which is based on the change in image entropy value, and (ii) a background tracking module, used to track a set of features in consecutive images to find correspondences between them and estimate global camera movement. A series of experiments is conducted on thermal infrared images, and the results show that the proposed method can significantly improve the robustness of all trackers with a minimal computational overhead. We show that the proposed method can be easily integrated into any visual tracking framework and can be applied to improve the performance of EOTS applications.

关键词： visual object tracking camera motion motion aware robust tracking

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：