检索结果-内蒙古大学图书馆

occlusion detection of Dense Correspondence Fields Using Motion Statistics and Triangulation

IEEE ACCESS 2019年 7卷 83569-83580页

作者： Dong, Chong Wang, Zhisheng Xing, Changda Han, Jiaming Huang, Pingan Nanjing Univ Aeronaut & Astronaut Coll Automat Engn Nanjing 211100 Jiangsu Peoples R China Avic Xian Aircraft Ind Co Ltd Xian 710089 Shaanxi Peoples R China

Despite progress made in the accuracy and robustness of the dense matching technique in past years, efficient occlusion detection remains an open problem. In this paper, we present a two-step occlusion detection method to remove false matches in dense matching fields. First, a statistical dense matching method is developed by considering the correspondence between the grids to identify most occlusion regions. Second, to handle the potential misjudgment match in the occlusion boundary, a double-threshold filtering method is first used to reduce the noise in the grid image, which ensures that the gradient operator can accurately extract the boundary grid in the grid image;then, misjudgment matches in the boundary grid region are corrected based on the triangulation with descriptors. The results of the experiments comparing the proposed method and existing occlusion detection methods by, respectively, using the MPI-Sintel and KITTI datasets' test sequence show that the proposed method has higher accuracy and better robustness.

关键词： Dense matching occlusion detection motion statistics triangulation

来源：评论

学校读者我要写书评

暂无评论

occlusion detection using horizontally segmented windows for vehicle tracking

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2015年第1期74卷 227-243页

作者： Jo, Ahra Jang, Gil-Jin Han, Bohyung Ulsan Natl Inst Sci & Technol Sch Elect & Comp Engn Ulsan 689798 South Korea Pohang Univ Sci & Technol POSTECH Dept Comp Sci & Engn Pohang 790784 South Korea

This paper proposes an efficient algorithm for detecting occlusions in a video sequences of ground vehicles using color information. The proposed method uses a rectangular window to track a target vehicle, and the window is horizontally divided into several sub-regions of equal width. Each region is determined to be occluded or not based on the color histogram similarity to the corresponding region of the target. The occlusion detection results are used in likelihood computation of the conventional tracking algorithm based on particle filtering. Experimental results in real scenes show that the proposed method finds the occluded region successfully and improves the performance of the conventional trackers.

关键词： Computer vision Object tracking Particle filters occlusion detection Histogram similarity

来源：评论

学校读者我要写书评

暂无评论

occlusion detection FOR URBAN AERIAL TRUE ORTHOIMAGE GENERATION 36

OCCLUSION DETECTION FOR URBAN AERIAL TRUE ORTHOIMAGE GENERAT...

引用

36th IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Zhou, Guoqing Wang, Yuefeng Guilin Univ Technol Guangxi Key Lab Spatial Informat & Geomat Guangxi Peoples R China

ISBN: (纸本)9781509033324

Traditional ortho-rectification is the most commonly method, which used to rectify the deformation caused by centerprojection. However, the occlusion caused by high buildings could not be recognized by computer in the process of traditional ortho-rectification, and the double-mapping is raised. This is the so-called "ghost image". In order to eliminating double-mapping and detecting occlusion, this paper proposes a new method to detect the occlusion caused by buildings' visual walls. The basic principle is establishing a model to describe the relationship between ghost image and occlusion including its size and shape/boundary, and then this paper applies seed growing method to detect the occluded area on ghost image according to the building's boundary. The experimental results demonstrate that the proposed method have a better accuracy and efficiency.

关键词： occlusion detection ghost image building displacement of image

来源：评论

学校读者我要写书评

暂无评论

occlusion detection BY HEIGHT GRADIENT FOR TRUE ORTHOPHOTO GENERATION, USING LIDAR DATA

OCCLUSION DETECTION BY HEIGHT GRADIENT FOR TRUE ORTHOPHOTO G...

引用

International-Society-for-Photogrammetry-and-Remote-Sensing Hannover Workshop

作者： Oliveira, H. C. Galo, M. Univ Estadual Paulista Fac Sci & Technol FCT UNESP PPGCC Postgrad Program Cartog Sci Presidente Prudente SP Brazil Univ Estadual Paulista Dept Cartog Presidente Prudente SP Brazil

ISBN: (纸本)9781629935201

Nowadays, the use of orthophoto in urban areas has become common. It is known that in most parts of urban areas there are a great number of tall buildings which can cause occlusion regions during image acquisition. These occlusions appear both in aerial images and in the orthophotos generated from these images. It happens due to perspective projection of the imaging sensor, and also if digital models that represent only relief is used in the orthorectification process, instead of the Digital Surface Model (DSM) that takes into account the relief and all objects on the surface. Considering this context, the aim of this article is to introduce an alternative procedure for occlusion detection in aerial images, using LiDAR (Light detection And Ranging) data, aiming at the generation of true orthophotos. The presented method for occlusion detection is based on height gradient computation applied to a DSM of the region, instead of the building model that is considered in some approaches. These height gradients computed in radial directions are important for the identification of the beginning of the occlusions in these directions. The final limits of the occlusions are obtained from the projection of these initial points in the DSM. To evaluate the proposed method, both simulated and real data were considered. The simulated data correspond to an ideal urban area, without noise, and this experiment was only used to validate the implementation method. The real data set is composite by digital aerial images and LiDAR data. The LiDAR data available has the average density of 8 points/m(2). As preliminary results, the occlusion areas were detected and highlighted in the orthorectified images. To accomplish the evaluation of the proposed method, besides a visual analysis, a numerical evaluation based on index of completeness was computed, using as reference a manual detection of occlusion. It is possible to observe the potential of the proposed occlusion detection method, altho

关键词： True Orthophoto occlusion detection LiDAR Height Gradient Double Mapping DSM

来源：评论

学校读者我要写书评

暂无评论

occlusion detection Based on Fractal Texture Analysis in Surveillance Videos Using Tree-Based Classifiers 3rd

Occlusion Detection Based on Fractal Texture Analysis in Sur...

引用

3rd International Symposium on Security in Computing and Communications (SSCC)

作者： Arunnehru, J. Geetha, M. Kalaiselvi Nanthini, T. Annamalai Univ Dept Comp Sci & Engn Speech & Vis Lab Annamalainagar 608002 Tamil Nadu India

ISBN: (纸本)9783319229157;9783319229140

occlusion detection in video has been an active research for decades. This interest is motivated by numerous applications, such as visual surveillance, human-computer interaction, and sports event analysis. In this paper, an occlusion detection approach based on fractal texture analysis is proposed. Texture features are extracted from the segmented images using Segmentation-based Fractal Texture Analysis (SFTA) algorithm. The experiments are carried out using a PNNL-Parking-Lot dataset and the various tree-based classifiers such as random forest, random tree, decision tree (J48), and REP tree are used for classification. In the experiment results, random forest classifier showed the best performance with an overall accuracy rate of 98.3% for SET-1, 98.2% for SET-2, and 83.7% for SET-3, which outperforms other algorithms.

关键词： Video surveillance occlusion detection Texture analysis Feature extraction Tree based classifiers

来源：评论

学校读者我要写书评

暂无评论

occlusion detection and Recovery in Video Object Tracking Based on Adaptive Particle Filters

Occlusion Detection and Recovery in Video Object Tracking Ba...

引用

21st Chinese Control and Decision Conference

作者： Duan, Zhuohua Cai, Zixing Yu, Jinxia Shaoguan Univ Sch Comp Sci Shaoguan 512005 Peoples R China Cent South Univ Changsha Sch Informat Sci & Engn Changsha 410083 Peoples R China Henan Politech Univ Dept Comp Sci & Technol Jiaozuo 454003 Peoples R China

ISBN: (纸本)9781424427239

occlusion detection and recovery is a challenging task in robust real-time tracking of non-rigid objects. Particle filtering has proven very successful for non-linear and non-Gaussian estimation problems. The paper presents a method for occlusion detection and recovery for object tracking with adaptive particle filter. Firstly, object occlusion is detected with normalization factor. Secondly, adaptive transition function is employed to recovery from occlusion. Lastly, particle number is changed according to occlusion state. Experimental results show the presented method can detect occlusion and recover from it quickly.

关键词： Object tracking Particle Filter occlusion detection occlusion Recovery Adaptive

来源：评论

学校读者我要写书评

暂无评论

occlusion detection and Localization from Kinect Depth Images

Occlusion Detection and Localization from Kinect Depth Image...

引用

International Conference on Cyberworlds (CW)

作者： Zohra, Fatema Tuz Rahman, Md Wasiur Gavrilova, Marina Univ Calgary Dept Comp Sci Calgary AB Canada

ISBN: (纸本)9781509023035

Faces captured in a real-world scenario may suffer from large variations in shape and occlusions due to difference in illumination, variation in pose and orientation of a facial image. Automated face recognition or security reinforcement by surveillance techniques would be useless if the faces are occluded. Therefore, face occlusion detection has become very important not only for effective face recognition but also to prevent security threats. In this paper, for the very first time an occlusion detection method is proposed based on the depth information provided by Kinect RGB-D cameras. Uniform Local Binary Pattern (LBP) is used to effectively extract the features from the depth images and SVM binary classifier is then applied to identify the front face and the occluded face. For localizing occluded regions in the face image, a threshold based approach is proposed to identify the areas close to the camera. In the depth images, an object close to the camera has a higher pixel intensity than the object further from the camera. Thus, we assume that occluded regions have lower distance from the camera, i.e. higher intensity values. Based on this hypothesis, we extract the connected component with highest energy values as the potential occluded region from the depth image. The boundary of the detected occluded region is then corrected using the reference front face image. The occlusion detection and localization method have been evaluated on EUROKOM Kinect face database containing different types of occluded and unoccluded faces with neutral expressions. Experimental results show that the proposed method provides an average detection rate of 98.50% for front and occluded face images. We have also compared our proposed method with existing methods that use faces acquired using 3D scanners for occlusion detection.

关键词： kinect sensor depth images binary classifier occlusion detection

来源：评论

学校读者我要写书评

暂无评论

occlusion detection for Automatic Video Editing 20

Occlusion Detection for Automatic Video Editing

引用

28th ACM International Conference on Multimedia (MM)

作者： Liao, Junhua Duan, Haihan Li, Xin Xu, Haoran Yang, Yanbing Cai, Wei Chen, Yanru Chen, Liangyin Sichuan Univ Chengdu Peoples R China Chinese Univ Hong Kong Shenzhen Inst Artificial Intelligence & Robot Soc Shenzhen Peoples R China Sichuan Univ Inst Ind Internet Res Chengdu Peoples R China

ISBN: (纸本)9781450379885

Videos have become the new preference comparing with images in recent years. However, during the recording of videos, the cameras are inevitably occluded by some objects or persons that pass through the cameras, which would highly increase the workload of video editors for searching out such occlusions. In this paper, for releasing the burden of video editors, a frame-level video occlusion detection method is proposed, which is a fundamental component of automatic video editing. The proposed method enhances the extraction of spatial-temporal information based on C3D yet only using around half amount of parameters, with an occlusion correction algorithm for correcting the prediction results. In addition, a novel loss function is proposed to better extract the characterization of occlusion and improve the detection performance. For performance evaluation, this paper builds a new large scale dataset, containing 1,000 video segments from seven different real-world scenarios, which could be available at: https://***/occlusiondetection/. All occlusions in video segments are annotated frame by frame with bounding-boxes so that the dataset could be utilized in both frame-level occlusion detection and precise occlusion location. The experimental results illustrate that the proposed method could achieve good performance on video occlusion detection compared with the state-of-the-art approaches. To the best of our knowledge, this is the first study which focuses on occlusion detection for automatic video editing.

关键词： occlusion detection Automatic Video Editing Human-Computer Interaction Deep Learning

来源：评论

学校读者我要写书评

暂无评论

occlusion detection in Visual Tracking: A New Framework and A New Benchmark 25th

Occlusion Detection in Visual Tracking: A New Framework and ...

引用

25th International Conference on Neural Information Processing (ICONIP)

作者： Niu, Xiaoguang Gu, Yueyang Lu, Zhifeng Hong, Zehua Tian, Yi Xu, Kuan Yang, Jie Fang, Xingqi Qiao, Yu Shanghai Jiao Tong Univ Inst Image Proc & Pattern Recognit Dept Automat Shanghai Peoples R China Shanghai Electromech Engn Inst Shanghai Peoples R China

ISBN: (纸本)9783030042127;9783030042110

occlusion remains being a challenge in visual object tracking. The robustness to occlusion is critical for tracking algorithms, though not much attention has been paid to it. In this paper, we first propose an occlusion detection framework which calculates the proportion of the target that is occluded, hence to decide whether to update the model of target. This framework can be integrated with existing tracking algorithms to increase their robustness to occlusion. Then we introduce a new benchmark which contains sequences where occlusion is the main difficulty. The sequences are chosen from public benchmarks and are fully annotated. The proposed framework is combined with several standard trackers and evaluated on the new benchmark. The experimental results show that our framework can improve the tracking performance, with explicit incorporation of occlusion detection.

关键词： Visual tracking occlusion detection Benchmark

来源：评论

学校读者我要写书评

暂无评论

occlusion detection IN DENSE STEREO ESTIMATION WITH CONVEX OPTIMIZATION 24

OCCLUSION DETECTION IN DENSE STEREO ESTIMATION WITH CONVEX O...

引用

24th IEEE International Conference on Image Processing (ICIP)

作者： Tan, Pauline Chambolle, Antonin Monasse, Pascal DOTA ONERA Palaiseau France Univ Paris Saclay CNRS Ecole Polytech CMAP F-91128 Palaiseau France Univ Paris Est CNRS LIGM Marne La Vallee France

ISBN: (纸本)9781509021758

In this paper, we propose a dense two-frame stereo algorithm which handles occlusion in a variational framework. Our method is based on a new regularization model which includes both a constraint on the occlusion width and a visibility constraint in nonoccluded areas. The minimization of the resulting energy functional is done by convex relaxation. A post-processing then detects and fills the occluded regions. We also propose a novel dissimilarity measure that combines color and gradient comparison with a variable respective weight, to benefit from the robustness of the comparison based on local variations while avoiding the fattening effect it may generate.

关键词： Stereo-matching occlusion detection variational method convex relaxation

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：