检索结果-内蒙古大学图书馆

A Two-Stage Outlier Filtering Framework for City-Scale localization Using 3D SfM Point Clouds

IEEE TRANSACTIONS ON image PROCESSING 2019年第10期28卷 4857-4869页

作者： Cheng, Wentao Chen, Kan Lin, Weisi Goesele, Michael Zhang, Xinfeng Zhang, Yabin Nanyang Technol Univ Sch Comp Sci & Engn Singapore 639798 Singapore Nanyang Technol Univ Fraunhofer Singapore Singapore 639798 Singapore Tech Univ Darmstadt Dept Comp Sci D-64283 Darmstadt Germany Univ Chinese Acad Sci Dept Comp Sci & Technol Beijing 100049 Peoples R China Tencent Median Lab Shenzhen 518057 Peoples R China

Three-dimensional structure-based localization aims to estimate the six-DOF camera pose of a query image by means of feature matches against a 3D Structure-from-Motion (SfM) point cloud. For city-scale SfM point clouds with tens of millions of points, it becomes more and more difficult to disambiguate matches. Therefore, a 3D structure-based localization method, which can efficiently handle matches with very large outlier ratios, is needed. We propose a two-stage outlier filtering framework for city-scale localization that leverages both visibility and geometry intrinsics of the SfM point clouds. First, we propose a visibility-based outlier filter, which is based on a bipartite visibility graph, to filter outliers on a coarse level. Second, we apply a geometry-based outlier filter to generate a set of fine-grained matches with a novel data-driven geometrical constraint for efficient inlier evaluation. The proposed two-stage outlier filtering framework only relies on the intrinsic information of the SfM point cloud. It is thus widely applicable to be embedded into the existing localization approaches. The experimental results on two real-world datasets demonstrate the effectiveness of the proposed two-stage outlier filtering framework for city-scale localization.

关键词： City-scale localization outlier filter image-based localization hybrid inlier evaluation

来源：评论

学校读者我要写书评

暂无评论

Lightweight Mobile Devices Indoor Location based on image Database 26

Lightweight Mobile Devices Indoor Location Based on Image Da...

引用

26th IEEE International Conference on Parallel and Distributed Systems (IEEE ICPADS)

作者： Gao, Ran Zhao, Yanchao Tang, Maoxing Nanjing Univ Aeronaut & Astronaut Coll Comp Sci & Technol Nanjing Peoples R China Collaborat Innovat Ctr Novel Software Technol & I Nanjing Peoples R China

ISBN: (纸本)9781728190747

Among the numerous indoor localization technologies, image-based solution has great advantages on convenient access from smartphone and its infrastructure-less deployment. However, the image-based localization also suffers from two key disadvantages, which hinders the universal application. Firstly, it requires a large amount of computing and storage resources, which is difficult to achieve for the mobile device, while cloudbased scheme incurs unacceptable delay. Secondly, although this solution doesn't require infrastructure, it still suffers from labor intensive image-database construction and updates. To overcome these limitations, we propose an image-based indoor localization method featured with realtime localization and labor-less image database update. This method mainly innovates in two aspects. First, we propose a mobile device compatible image database compressing framework, which enable realtime and accurate ondevice image searching even in a large scenario. Our localization method achieves resource efficiency (in terms of storage and processing) by only keeping image feature vectors, and employing the efficient k-mean tree to search for the best matched image. Secondly, to achieve labor-less image database updating, we mainly add high-quality and informative query image into the database. These query image could compensate the missing information or changed scenario in a up-to-date manner. We conduct real experiments in Android Platform to verify the feasibility and performance of the localization method. Experiment results show that our method has good accuracy (90% location errors are within 1.5m) and high real-time performance (average location delay is less than 0.5s).

关键词： image-based localization real-time smartphone-based localization indoor location image database update

来源：评论

学校读者我要写书评

暂无评论

A review of Visual-based localization 19

A review of Visual-Based Localization

引用

International Conference on Robotics, Intelligent Control and Artificial Intelligence (RICAI)

作者： Xin, Xing Jiang, Jie Zou, Yin Natl Univ Def Technol Coll Syst Engn Changsha Peoples R China

ISBN: (纸本)9781450372985

The visual-based localization (VBL) obtains the corresponding pose estimation in the localization system by utilizing various useful information in the surrounding environment, such as images, point cloud models, geometric information, semantic information. In recent years, visual-based localization (VBL) has been widely concerned by scientists, mainly because the commonly used GPS localization system cannot be effectively used in various environments. When GPS localization fails in some scenes such as very messy environments and severe signal occlusion, we can consider using visual-based localization to obtain the pose of the query images. Visual-based localization (VBL) has been widely used in the field of visual tasks, such as augmented reality, unmanned vehicle navigation, robotics, closed-loop detection, SFM (Structure from Motion) models. After years of development, the methods of visual-based localization (VBL) have been enriched and developed, In order to better understand the latest developments in VBL, overall research status and possible future development trends, we need make a systematic detailed classification of VBL. Although the predecessors have summarized the methods of VBL, due to the many new breakthroughs in VBL in recent years, the original summary is not perfect enough. So this paper will make a new and more detailed review of VBL in recent years. This paper divides the visualbased localization methods into three categories: image-based localization, localization based on learning model and localization based on 3D structure. And we also detail the principle, development of methods and the advantages and disadvantages of each method and future development trends.

关键词： Visual-based localization image-based localization localization based on learning model localization based on 3D structure

来源：评论

学校读者我要写书评

暂无评论

A survey on Visual-based localization: On the benefit of heterogeneous data

引用

PATTERN RECOGNITION 2018年 74卷 90-109页

作者： Piasco, Nathan Sidibe, Desire Demonceaux, Cedric Gouet-Brunet, Valerie Arts & Metiers Univ CNRS FRE 2005 Le2i Bourgogne Franche Comte France Univ Paris Est ENSG IGN LaSTIG MATIS F-94160 St Mande France

We are surrounded by plenty of information about our environment. From these multiple sources, numerous data could be extracted: set of images, 3D model, coloured points cloud... When classical localization devices failed (e.g. GPS sensor in cluttered environments), aforementioned data could be used within a localization framework. This is called Visual based localization (VBL). Due to numerous data types that can be collected from a scene, VBL encompasses a large amount of different methods. This paper presents a survey about recent methods that localize a visual acquisition system according to a known environment. We start by categorizing VBL methods into two distinct families: indirect and direct localization systems. As the localization environment is almost always dynamic, we pay special attention to methods designed to handle appearances changes occurring in a scene. Thereafter, we highlight methods exploiting heterogeneous types of data. Finally, we conclude the paper with a discussion on promising trends that could permit to a localization system to reach high precision pose estimation within an area as large as possible. (C) 2017 Elsevier Ltd. All rights reserved.

关键词： image-based localization Visual geo-localization Camera relocalisation Pose estimation

来源：评论

学校读者我要写书评

暂无评论

Learning Spatial-Aware Cross-View Embeddings for Ground-to-Aerial Geolocalization 10th

Learning Spatial-Aware Cross-View Embeddings for Ground-to-A...

引用

10th International Conference on image and Graphics (ICIG)

作者： Cao, Rui Zhu, Jiasong Li, Qing Zhang, Qian Li, Qingquan Liu, Bozhi Qiu, Guoping Univ Nottingham Int Doctoral Innovat Ctr Ningbo Peoples R China Univ Nottingham Sch Comp Sci Ningbo Peoples R China Shenzhen Univ Coll Informat Engn Shenzhen Peoples R China Shenzhen Univ Guangdong Key Lab Intelligent Informat Proc Shenzhen Peoples R China Shenzhen Univ Shenzhen Key Lab Spatial Smart Sensing & Serv Shenzhen Peoples R China Univ Nottingham Sch Comp Sci Nottingham England

ISBN: (纸本)9783030341206;9783030341190

image-based geolocalization is an important alternative to GPS-based localization in GPS-denied situations. Among them, ground-to-aerial geolocalization is particularly promising but also difficult due to drastic viewpoint and appearance differences between ground and aerial images. In this paper, we propose a novel spatial-aware Siamese-like network to address the issue by exploiting the spatial transformer layer to effectively alleviate the large view variation and learn location discriminative embeddings from the cross-view images. Furthermore, we propose to combine the triplet ranking loss with a simple and effective location identity loss to further enhance the performances. We test our method on a publicly available dataset and the results show that the proposed method outperforms state-of-the-art by a large margin.

关键词： image-based localization Cross-view geolocalization image retrieval Deep metric learning

来源：评论

学校读者我要写书评

暂无评论

localization for mobile robots using skyline in panoramic images

JOURNAL OF THE FACULTY OF ENGINEERING AND ARCHITECTURE OF GA...

引用

JOURNAL OF THE FACULTY OF ENGINEERING AND ARCHITECTURE OF GAZI UNIVERSITY 2019年第3期34卷 1630-1644页

作者： Koku, Ahmet Bugra Orta Dogu Tekn Univ Muhendisl Fak Makina Muhendisligi Bolumu TR-06800 Ankara Turkey

Advances in robotics liberated robots from factory floors by the end of 20th century. Use of robots in our daily lives is only expected to increase in time. Robots, while relieving us of the burden of tedious, hard and dangerous tasks, most of them are still expected to be territorial, i.e. they will operate in a predefined or rather bounded environment. For enhanced performance, a robot should be familiar with its territory. In this work, use of skylines extracted from panoramic images is studied in order to provide localization. To achieve localization, first a special map is prepared using a series of panoramic images taken from the territory. images, those taken from the vicinity of this map at different times and under different weather conditions, are localized on this map. Given that the proposed method only focuses on a small portion of the panoramic image, it is relatively easier to implement in various hardware platforms (especially those with limited computational capabilities) in comparison to the methods that process the whole image.

关键词： Panoramic images skyline robot localization image-based localization territorial robots

来源：评论

学校读者我要写书评

暂无评论

Fusion of WiFi and Vision based on Smart Devices for Indoor localization 16

Fusion of WiFi and Vision based on Smart Devices for Indoor ...

引用

16th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and Its Applications in Industry (VRCAI)

作者： Guo, Jing Zhang, Shaobo Zhao, Wanqing Peng, Jinye Northwest Univ Coll Informat Sci & Technol Xian Shaanxi Peoples R China

ISBN: (纸本)9781450360876

Indoor localization is an important problem with a wide range of applications such as indoor navigation, robot mapping, especially augmented reality(AR). One of most important tasks in AR technology is to estimate the target objects' position information in real environment. The existed AR systems mostly utilize specialized marker to locate, some AR systems track real 3D object in real environment but need to get the the position information of index points in environment in advance. The above methods are not efficiency and limit the application of AR system, so that solving indoor localization problem has significant meaning for the development of AR technology. The development of computer vision (CV) techniques and the ubiquity of intelligent devices with cameras provides the foundation for offering accurate localization services. However, pure CV-based solutions usually involve hundreds of photos and pre-calibration to construct an densely sampled 3D model, which is a labor-intensive overhead for practical deployment. And a large amount of computation cost is difficult to satisfy the requirement for efficiency in mobile device. In this paper, we present iStart, a lightweight, easy deployed, image-based indoor localization system, which can be run on smart phone and VR/AR devices like HTC Vive, Google Glasses and so on. With core techniques rooted in data hierarchy scheme of WiFi fingerprints and photos, iStart also acquires user localization with a single photo of surroundings with high accuracy and short delay. Extensive experiments in various environments show that 90 percentile location deviations are less than 1 m, and 60 percentile location deviations are less than 0.5 m.

关键词： indoor localization image-based localization WiFi fingerprint smart devices CV model

来源：评论

学校读者我要写书评

暂无评论

Artificial Neural Networks Aided image localization for Pedestrian Dead Reckoning for Indoor Navigation Applications 5

Artificial Neural Networks Aided Image Localization for Pede...

引用

5th IEEE Conference on Ubiquitous Positioning, Indoor Navigation and Location-based Services (UPINLBS)

作者： Liao, Jhen-Kai Chiang, Kai-Wei Chang, Hsiu-Wen Li, Yu-Hua Natl Cheng Kung Univ Dept Geomat Tainan Taiwan

ISBN: (纸本)9781538637555

Recently, indoor navigation has become popular because of the popular smartphone and the growth of Location based Services (LBS). Pedestrian Dead Reckoning (PDR) has the good potential to confront the challenges in environments lacking a Global Navigation Satellite System (GNSS). However, PDR has inherent errors that accumulated step by step. An image-based localization can as an aiding system, because virtually all mobile devices contain a basic camera sensor. However, the image-based localization requires successive and overlapped images for continuously positioning. In addition, the solutions provided by either image-based localization or a PDR are usually in a relative coordinate system. Therefore, this study proposes a system, which uses space resection-aided PDR with georeferenced images of a previously mapped environment. In order to implement the procedure automatically and reduce the image processing, this study further uses markers in the georeferenced images. After that, Artificial Neural Network (ANN) is novel applied to estimate the distance between the marker and camera. Since the marker is also georeferenced, the camera position is updated through the detected georeferenced marker, estimated distance, and orientation from inertial sensor, and then update the PDR result. The indoor mobile mapping system (IMMS) is used for the effective production of georeferenced images. The result shows the proposed system is able to initialize in indoor without manually given initial position and provides long-term accurate navigation.

关键词： indoor navigation pedestrian dead reckoning image-based localization Artifical neural network

来源：评论

学校读者我要写书评

暂无评论

Intensity Filtering and Group Fusion for Accurate Mobile Place Recognition

引用

IEEE ACCESS 2018年 6卷 31088-31098页

作者： Wang, Mao Zhu, En Liu, Qiang Ye, Yongkai Ming, Yuewei Yin, Jianping Natl Univ Def Technol Dept Comp Sci & Technol Changsha 410073 Hunan Peoples R China Dongguan Univ Technol Sch Comp Sci & Network Secur Dongguan 523000 Peoples R China

Mobile place recognition targets at matching query images captured by mobile devices with database images collected from vehicle-mounted cameras, such as Google street view panoramas, which plays an important role in many applications. However, current solutions deriving from image retrieval suffer from the problem of low precision on top results, which significantly challenges their usability. By investigating the state-of-the-art approaches, we find that the bad illumination significantly affects initial results, and these initial results are correlative in both spatial location and visual content, which can be utilized for further improvement. In this paper, we propose an effective approach to rerank initial top-ranked results to improve the recognition recall. First, initial retrieval results with low intensity are filtered as they usually depict irrelevant places with dark background. Second, the correlation between top-ranked results is modeled as a reciprocal neighborhood graph by jointly considering spatial location and visual similarity. With the graph, the initial results are reranked based on voting similarity from the query and reciprocal neighbors. In this way, the underlying structure of initial retrieval results is exploited for refining. Experimental results on the public Tokyo 24/7 and San Francisco landmark datasets demonstrate that the proposed approach can achieve persisting improvement of recognition recall over the state-of-the-art approach.

关键词： Place recognition image-based localization image matching deep feature

来源：评论

学校读者我要写书评

暂无评论

Safe and Robust Mobile Robot Navigation in Uneven Indoor Environments

引用

SENSORS 2019年第13期19卷 2993.-2993.页

作者： Wang, Chaoqun Wang, Jiankun Li, Chenming Ho, Danny Cheng, Jiyu Yan, Tingfang Meng, Lili Meng, Max Q. -H. Chinese Univ Hong Kong Dept Elect Engn Hong Kong Peoples R China Univ British Columbia Comp Sci Dept Vancouver BC V6T 1Z4 Canada

Complex environments pose great challenges for autonomous mobile robot navigation. In this study, we address the problem of autonomous navigation in 3D environments with staircases and slopes. An integrated system for safe mobile robot navigation in 3D complex environments is presented and both the perception and navigation capabilities are incorporated into the modular and reusable framework. Firstly, to distinguish the slope from the staircase in the environment, the robot builds a 3D OctoMap of the environment with a novel Simultaneously localization and Mapping (SLAM) framework using the information of wheel odometry, a 2D laser scanner, and an RGB-D camera. Then, we introduce the traversable map, which is generated by the multi-layer 2D maps extracted from the 3D OctoMap. This traversable map serves as the input for autonomous navigation when the robot faces slopes and staircases. Moreover, to enable robust robot navigation in 3D environments, a novel camera re-localization method based on regression forest towards stable 3D localization is incorporated into this framework. In addition, we utilize a variable step size Rapidly-exploring Random Tree (RRT) method which can adjust the exploring step size automatically without tuning this parameter manually according to the environment, so that the navigation efficiency is improved. The experiments are conducted in different kinds of environments and the output results demonstrate that the proposed system enables the robot to navigate efficiently and robustly in complex 3D environments.

关键词： traversable map regression forest image-based localization path planning and navigation

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：