Ranga Raju Vatsavai, E. Bright, V. Chandola, B. Bhaduri, A. Cheriyadat, J. Graesser
The proliferation of several machine learning approaches makes it difficult to identify a suitable classification technique for analyzing high-resolution remote sensing images. In this study, ten classification techniques were compared from five broad machine learning categories. Surprisingly, the performance of simple statistical classification schemes like maximum likelihood and Logistic regression over complex and recent techniques is very close. Given that these two classifiers require little input from the user, they should still be considered for most classification tasks. Multiple classifier systems is a good choice if the resources permit.
{"title":"Machine learning approaches for high-resolution urban land cover classification: a comparative study","authors":"Ranga Raju Vatsavai, E. Bright, V. Chandola, B. Bhaduri, A. Cheriyadat, J. Graesser","doi":"10.1145/1999320.1999331","DOIUrl":"https://doi.org/10.1145/1999320.1999331","url":null,"abstract":"The proliferation of several machine learning approaches makes it difficult to identify a suitable classification technique for analyzing high-resolution remote sensing images. In this study, ten classification techniques were compared from five broad machine learning categories. Surprisingly, the performance of simple statistical classification schemes like maximum likelihood and Logistic regression over complex and recent techniques is very close. Given that these two classifiers require little input from the user, they should still be considered for most classification tasks. Multiple classifier systems is a good choice if the resources permit.","PeriodicalId":400763,"journal":{"name":"International Conference and Exhibition on Computing for Geospatial Research & Application","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134380378","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Skyhook Wireless provides hybrid positioning to millions of mobile devices around the world. Using an approach that integrates cell, WiFi, and GPS signals, the system services over 500 million location requests daily. This results in a massive and perpetually growing artifact of device locations anchored in time and place. Using this time-stamped location data, we are able to measure aggregated mobile device activity with extreme local accuracy, to any required resolution, across thousands of cites worldwide. Providing location services to such a large population of devices allows Skyhook to continuously improve positioning quality by reconciling signal maps returned from adjacent requests. It also provides an unparalleled tool for quantifying social behavior in space and time. We describe one analytical output of these data -- SpotRank - which presents a normalized week of discrete, measured hours across the entire global Skyhook service area. SpotRank provides a method to compare and analyze locations aggregated to .001 decimal degree tiles (approximately 1 hectare at mid latitudes) in 1-hour increments. The SpotRank "canonical week" provides an averaged measure of activity for each tile-hour: 168 hours across more than 10 million tiles. This architecture permits many creative comparisons, such as how a typical activity level varies between Monday at 9AM and Friday at 9AM for any tile in our coverage area. These normalized data may also be compared using tiles in disparate cities or countries. With these data as the baseline, many predictive and anomalous behavior analyses are possible, using SpotRank standalone metric or in concert with local data sources.
{"title":"What to do with 500M location requests a day?","authors":"K. Jones, Richard Sutton","doi":"10.1145/1999320.1999390","DOIUrl":"https://doi.org/10.1145/1999320.1999390","url":null,"abstract":"Skyhook Wireless provides hybrid positioning to millions of mobile devices around the world. Using an approach that integrates cell, WiFi, and GPS signals, the system services over 500 million location requests daily. This results in a massive and perpetually growing artifact of device locations anchored in time and place. Using this time-stamped location data, we are able to measure aggregated mobile device activity with extreme local accuracy, to any required resolution, across thousands of cites worldwide.\u0000 Providing location services to such a large population of devices allows Skyhook to continuously improve positioning quality by reconciling signal maps returned from adjacent requests. It also provides an unparalleled tool for quantifying social behavior in space and time. We describe one analytical output of these data -- SpotRank - which presents a normalized week of discrete, measured hours across the entire global Skyhook service area.\u0000 SpotRank provides a method to compare and analyze locations aggregated to .001 decimal degree tiles (approximately 1 hectare at mid latitudes) in 1-hour increments. The SpotRank \"canonical week\" provides an averaged measure of activity for each tile-hour: 168 hours across more than 10 million tiles. This architecture permits many creative comparisons, such as how a typical activity level varies between Monday at 9AM and Friday at 9AM for any tile in our coverage area. These normalized data may also be compared using tiles in disparate cities or countries. With these data as the baseline, many predictive and anomalous behavior analyses are possible, using SpotRank standalone metric or in concert with local data sources.","PeriodicalId":400763,"journal":{"name":"International Conference and Exhibition on Computing for Geospatial Research & Application","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115360422","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The ability to integrate and process volumetric information has recently become increasingly desirable in traditional Geographic Information Systems (GIS). Volumetric GIS (VGIS) is a new, challenging, and promising field. However, due to the lack of the volumetric data source, many research activities in volumetric GIS have not been further carried out deeply. This paper proposes a Graphics Processor Unit (GPU) based fast volumetric terrain modeling technique using standard graphics hardware. Using this technique can generate the volumetric terrain data from traditional geometric terrain data, such as Triangulated Irregular Network (TIN) or Digital Elevation Model (DEM), at interactive time or even in real time. To achieve fast volumetric terrain modeling, this algorithm makes use of standard OpenGL features to apply GPU acceleration to solid terrain slicing and other graphics operations. Some experimental volumetric terrain results based on USGS DEM data are shown in the paper. The conclusions and further works are described in the end.
{"title":"GPU-based fast volumetric terrain modeling for volumetric GIS","authors":"Duoduo Liao","doi":"10.1145/1999320.1999348","DOIUrl":"https://doi.org/10.1145/1999320.1999348","url":null,"abstract":"The ability to integrate and process volumetric information has recently become increasingly desirable in traditional Geographic Information Systems (GIS). Volumetric GIS (VGIS) is a new, challenging, and promising field. However, due to the lack of the volumetric data source, many research activities in volumetric GIS have not been further carried out deeply. This paper proposes a Graphics Processor Unit (GPU) based fast volumetric terrain modeling technique using standard graphics hardware. Using this technique can generate the volumetric terrain data from traditional geometric terrain data, such as Triangulated Irregular Network (TIN) or Digital Elevation Model (DEM), at interactive time or even in real time. To achieve fast volumetric terrain modeling, this algorithm makes use of standard OpenGL features to apply GPU acceleration to solid terrain slicing and other graphics operations. Some experimental volumetric terrain results based on USGS DEM data are shown in the paper. The conclusions and further works are described in the end.","PeriodicalId":400763,"journal":{"name":"International Conference and Exhibition on Computing for Geospatial Research & Application","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122911483","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Innovators across the Northwest seek to engage Com-Geo attendees in dialog on groundwork underway in Oregon to leverage Open Source Solutions (OSS) and advance National Spatial Data Infrastructure (NSDI) with a new initiative called SDI-Now (Spatial Data Infrastructure - Northwest). Agencies across Oregon have begun evaluating and testing NASA Word Wind (WW) JAVA SDK as enabling technology for vertical and horizontal data sharing at the local level (complex public works infrastructure with private engineering firms), data sharing at the regional level (county-wide address information, cadastral information, land use information, and political boundaries), data sharing at the state level (state-wide elevation information and hydro systems) and data sharing with federal agencies. Specific business areas include managing local electronic assets (facilities inventories), coordinating data flows between regional consortia that manage the regional land information systems, and serving large dynamic remote sensing data sets such as climate, imagery and elevation (LiDAR). The State's Elevation Framework Implementation Team, the Pacific Northwest Hydro Community, the City of Springfield and many others from government, education, federated tribes and the private sector are evaluating new methods to overcome age-old problems regarding NSDI implementation. The presentation will focus on challenges, user needs and key advances under investigation with empowering OSS such as WW. In short, this talk will be needs based and WW centric -- rich with the nuances of local SDI.
西北地区的创新者寻求与Com-Geo与会者就俄勒冈州正在进行的基础工作进行对话，以利用开源解决方案(OSS)，并通过一项名为SDI-Now(西北地区空间数据基础设施)的新计划推进国家空间数据基础设施(NSDI)。俄勒冈州的机构已经开始评估和测试NASA Word Wind (WW) JAVA SDK，将其作为地方层面(复杂的公共工程基础设施与私人工程公司)的垂直和水平数据共享、区域层面(全国范围的地址信息、地籍信息、土地使用信息和政治边界)的数据共享技术。州一级的数据共享(全州海拔信息和水利系统)以及与联邦机构的数据共享。具体的业务领域包括管理本地电子资产(设施清单)，协调管理区域土地信息系统的区域联盟之间的数据流，以及提供大型动态遥感数据集，如气候、图像和海拔(激光雷达)。州海拔框架实施小组、太平洋西北水电社区、斯普林菲尔德市以及来自政府、教育、联邦部落和私营部门的许多其他机构正在评估新方法，以克服有关NSDI实施的老问题。该演讲将重点关注挑战、用户需求和正在调查的授权OSS(如WW)的关键进展。简而言之，这次演讲将以需求为基础，以WW为中心，丰富当地SDI的细微差别。
{"title":"Spatial data infrastructure-northwest","authors":"Brandt Melick","doi":"10.1145/1999320.1999363","DOIUrl":"https://doi.org/10.1145/1999320.1999363","url":null,"abstract":"Innovators across the Northwest seek to engage Com-Geo attendees in dialog on groundwork underway in Oregon to leverage Open Source Solutions (OSS) and advance National Spatial Data Infrastructure (NSDI) with a new initiative called SDI-Now (Spatial Data Infrastructure - Northwest). Agencies across Oregon have begun evaluating and testing NASA Word Wind (WW) JAVA SDK as enabling technology for vertical and horizontal data sharing at the local level (complex public works infrastructure with private engineering firms), data sharing at the regional level (county-wide address information, cadastral information, land use information, and political boundaries), data sharing at the state level (state-wide elevation information and hydro systems) and data sharing with federal agencies. Specific business areas include managing local electronic assets (facilities inventories), coordinating data flows between regional consortia that manage the regional land information systems, and serving large dynamic remote sensing data sets such as climate, imagery and elevation (LiDAR). The State's Elevation Framework Implementation Team, the Pacific Northwest Hydro Community, the City of Springfield and many others from government, education, federated tribes and the private sector are evaluating new methods to overcome age-old problems regarding NSDI implementation. The presentation will focus on challenges, user needs and key advances under investigation with empowering OSS such as WW. In short, this talk will be needs based and WW centric -- rich with the nuances of local SDI.","PeriodicalId":400763,"journal":{"name":"International Conference and Exhibition on Computing for Geospatial Research & Application","volume":"392 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114913230","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The world has great need for analysis of Earth observation data, be it climate change, carbon monitoring, disaster response, national defense or simply local resource management. To best provide for spatial and time-dependent information analysis, the world benefits from an open standards and open source infrastructure for spatial data. In the spirit of NASA's motto "for the benefit of all" NASA invites the world community to collaboratively advance this core technology. The World Wind infrastructure for spatial data both unites and challenges the world for innovative solutions analyzing spatial data while also allowing absolute command and control over any respective information exchange medium.
{"title":"NASA world wind: infrastructure for spatial data","authors":"P. Hogan","doi":"10.1145/1999320.1999322","DOIUrl":"https://doi.org/10.1145/1999320.1999322","url":null,"abstract":"The world has great need for analysis of Earth observation data, be it climate change, carbon monitoring, disaster response, national defense or simply local resource management. To best provide for spatial and time-dependent information analysis, the world benefits from an open standards and open source infrastructure for spatial data. In the spirit of NASA's motto \"for the benefit of all\" NASA invites the world community to collaboratively advance this core technology. The World Wind infrastructure for spatial data both unites and challenges the world for innovative solutions analyzing spatial data while also allowing absolute command and control over any respective information exchange medium.","PeriodicalId":400763,"journal":{"name":"International Conference and Exhibition on Computing for Geospatial Research & Application","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116944349","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The purpose of this study is to map mineral potential in Gangreung area, Korea. The mineral potential map was made and validated using likelihood ratio, logistic regression and artificial neural network models with a geographic information system (GIS). Moreover integration of the models has applied to get the better accuracy than each model. For this, the factors related to Au-Ag mineral occurrence were compiled in the GIS database. The factors are the geological data of lithology and fault structure, geochemical data. Using these factors, the potential of mineral were analysed using the 3 models. The validation result showed that the likelihood ratio, logistic regression and artificial neural network models had 83.70%, 81.91% and 77.37% accuracies. But the integrated mineral potential map, prediction accuracy was 92.94%. The generated maps could be used to not only predict known areas of Au-Ag occurrence, but also identify areas of potential mineralization where no known deposit occurs.
{"title":"Integration of mineral potential maps from various geospatial models","authors":"Saro Lee","doi":"10.1145/1999320.1999373","DOIUrl":"https://doi.org/10.1145/1999320.1999373","url":null,"abstract":"The purpose of this study is to map mineral potential in Gangreung area, Korea. The mineral potential map was made and validated using likelihood ratio, logistic regression and artificial neural network models with a geographic information system (GIS). Moreover integration of the models has applied to get the better accuracy than each model. For this, the factors related to Au-Ag mineral occurrence were compiled in the GIS database. The factors are the geological data of lithology and fault structure, geochemical data. Using these factors, the potential of mineral were analysed using the 3 models. The validation result showed that the likelihood ratio, logistic regression and artificial neural network models had 83.70%, 81.91% and 77.37% accuracies. But the integrated mineral potential map, prediction accuracy was 92.94%. The generated maps could be used to not only predict known areas of Au-Ag occurrence, but also identify areas of potential mineralization where no known deposit occurs.","PeriodicalId":400763,"journal":{"name":"International Conference and Exhibition on Computing for Geospatial Research & Application","volume":"516 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123085393","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
S. Krishnan, C. Crosby, V. Nandigam, M. Phan, C. Cowart, C. Baru, R. Arrowsmith
High-resolution topography data acquired with LIDAR (Light Detection and Ranging) remote sensing technology have emerged as a fundamental tool for Earth science research. Because these acquisitions are often undertaken with federal and state funds at significant cost, it is important to maximize the impact of these geospatial data by providing online access to a range of potential users. The National Science Foundation-funded OpenTopography Facility hosted at the San Diego Supercomputer Center (SDSC), has developed a Geospatial Cyberinfrastructure (GCI) to enable online access to Earth science-oriented high-resolution LIDAR topography data, online processing tools, and derivative products. Leveraging high performance computational and data storage resources available at SDSC, OpenTopography provides access to terabytes of point cloud data, standard digital elevation models, and Google Earth image data, all co-located with computational resources for higher-level data processing. This paper describes the motivation, goals, and the technical details of the Services Oriented Architecture (SOA) and underlying cyberinfrastructure platform implemented by OpenTopography. The use of an SOA, and the co-location of processing and data resources are unique to the field of LIDAR topography data processing, and lays a foundation for providing an open system for hosting and providing access to data and computational tools for these important scientific data, and is an exemplar for similar large geospatial data and processing community-oriented cyberinfrastructure systems.
{"title":"OpenTopography: a services oriented architecture for community access to LIDAR topography","authors":"S. Krishnan, C. Crosby, V. Nandigam, M. Phan, C. Cowart, C. Baru, R. Arrowsmith","doi":"10.1145/1999320.1999327","DOIUrl":"https://doi.org/10.1145/1999320.1999327","url":null,"abstract":"High-resolution topography data acquired with LIDAR (Light Detection and Ranging) remote sensing technology have emerged as a fundamental tool for Earth science research. Because these acquisitions are often undertaken with federal and state funds at significant cost, it is important to maximize the impact of these geospatial data by providing online access to a range of potential users. The National Science Foundation-funded OpenTopography Facility hosted at the San Diego Supercomputer Center (SDSC), has developed a Geospatial Cyberinfrastructure (GCI) to enable online access to Earth science-oriented high-resolution LIDAR topography data, online processing tools, and derivative products. Leveraging high performance computational and data storage resources available at SDSC, OpenTopography provides access to terabytes of point cloud data, standard digital elevation models, and Google Earth image data, all co-located with computational resources for higher-level data processing. This paper describes the motivation, goals, and the technical details of the Services Oriented Architecture (SOA) and underlying cyberinfrastructure platform implemented by OpenTopography. The use of an SOA, and the co-location of processing and data resources are unique to the field of LIDAR topography data processing, and lays a foundation for providing an open system for hosting and providing access to data and computational tools for these important scientific data, and is an exemplar for similar large geospatial data and processing community-oriented cyberinfrastructure systems.","PeriodicalId":400763,"journal":{"name":"International Conference and Exhibition on Computing for Geospatial Research & Application","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125813642","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Geospatial data accessible on the web has become common place and transformative. The GeoWeb allows us to view geographic information about any location on the planet and to make plans based on this. Planning routes for travel using the GeoWeb has become highly advanced enabled by open standards. Using the GeoWeb for environmental studies is advancing but requires additional standards regarding semantics of the features of the world. The GeoWeb is now moving to mobile internet platforms. Soon, if not already, mobile devices will be the predominant method to access the Internet. This is enabled by dramatic advances in technologies and business models for electronic communications and hand held devices. Smartphones have led the way enabling access on mobile devices similar to fixed internet locations. The initial generation of Location Based Services were defined based on walled gardens. Now we are extending the GeoWeb to the mobile internet and enhancing it based on location context and by access to an Internet of things including sensors. Using mobile GeoWeb devices embedded in the world enables an augmented understanding of our geospatial reality.
{"title":"GeoWeb on mobile internet","authors":"G. Percivall","doi":"10.1145/1999320.1999324","DOIUrl":"https://doi.org/10.1145/1999320.1999324","url":null,"abstract":"Geospatial data accessible on the web has become common place and transformative. The GeoWeb allows us to view geographic information about any location on the planet and to make plans based on this. Planning routes for travel using the GeoWeb has become highly advanced enabled by open standards. Using the GeoWeb for environmental studies is advancing but requires additional standards regarding semantics of the features of the world. The GeoWeb is now moving to mobile internet platforms. Soon, if not already, mobile devices will be the predominant method to access the Internet. This is enabled by dramatic advances in technologies and business models for electronic communications and hand held devices. Smartphones have led the way enabling access on mobile devices similar to fixed internet locations. The initial generation of Location Based Services were defined based on walled gardens. Now we are extending the GeoWeb to the mobile internet and enhancing it based on location context and by access to an Internet of things including sensors. Using mobile GeoWeb devices embedded in the world enables an augmented understanding of our geospatial reality.","PeriodicalId":400763,"journal":{"name":"International Conference and Exhibition on Computing for Geospatial Research & Application","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126841515","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
When mobile robots perform their missions, the self-localization is needed basically. Several past researches established how to obtain their location information from the environment by using a distance sensor or a camera. However, these methods have map-making problem when the environment changes and localization problem while the robot moves from sensing features has typical affine and occlusion characteristics. This paper presents a localizer for mobile robot that travels around indoor environments. Our module uses the only one sensor, a single camera looking up the ceiling. There is no efficient enough SLAM* (Simultaneous Localization And Mapping) algorithm working on embedded system. The initial difficulty of vision based SLAM is computational complexity to acquire reliable feature on their algorithm. To reduce the computational complexity, we use the ceiling segmentation to extract line features of ceiling area. Line features are extracted from the boundaries between the ceiling and walls. The line features have advantages over point features for its robustness to environmental variation and structural information helpful to data association. Extended Kalman Filter is used to estimate the pose of a robot and build the ceiling map with line features. The experiment is practiced in our indoor test bed and the proposed algorithm is proved by the experimental results. *SLAM: Simultaneous localization and mapping is a technique used by robots and autonomous vehicles to build up a map within an unknown environment or to update a map within a known environment while at the same time keeping track of their current location.
移动机器人在执行任务时，基本需要进行自定位。过去的一些研究建立了如何通过使用距离传感器或相机从环境中获取它们的位置信息。然而，这些方法存在环境变化时的地图制作问题，以及机器人从具有典型仿射和遮挡特征的传感特征移动时的定位问题。提出了一种适用于室内环境下移动机器人的定位器。我们的模块使用了唯一的传感器，一个指向天花板的摄像头。目前在嵌入式系统上还没有足够高效的SLAM (Simultaneous Localization And Mapping)算法。基于视觉的SLAM算法的初始难点在于其算法获取可靠特征的计算复杂度。为了降低计算复杂度，我们使用天花板分割来提取天花板区域的线特征。从天花板和墙壁之间的边界提取线条特征。线特征对环境变化的鲁棒性和有助于数据关联的结构信息都优于点特征。利用扩展卡尔曼滤波估计机器人的姿态，建立具有线特征的天花板图。在我们的室内实验台上进行了实验，实验结果验证了所提出的算法。SLAM:同步定位和绘图是机器人和自动驾驶汽车使用的一种技术，用于在未知环境中建立地图或在已知环境中更新地图，同时跟踪其当前位置。
{"title":"Ceiling vision based localizer for mobile robot","authors":"Seung-Hun Kim, Changwoo Park, Sewoong Jun","doi":"10.1145/1999320.1999374","DOIUrl":"https://doi.org/10.1145/1999320.1999374","url":null,"abstract":"When mobile robots perform their missions, the self-localization is needed basically. Several past researches established how to obtain their location information from the environment by using a distance sensor or a camera. However, these methods have map-making problem when the environment changes and localization problem while the robot moves from sensing features has typical affine and occlusion characteristics. This paper presents a localizer for mobile robot that travels around indoor environments. Our module uses the only one sensor, a single camera looking up the ceiling. There is no efficient enough SLAM* (Simultaneous Localization And Mapping) algorithm working on embedded system. The initial difficulty of vision based SLAM is computational complexity to acquire reliable feature on their algorithm. To reduce the computational complexity, we use the ceiling segmentation to extract line features of ceiling area. Line features are extracted from the boundaries between the ceiling and walls. The line features have advantages over point features for its robustness to environmental variation and structural information helpful to data association. Extended Kalman Filter is used to estimate the pose of a robot and build the ceiling map with line features. The experiment is practiced in our indoor test bed and the proposed algorithm is proved by the experimental results.\u0000 *SLAM: Simultaneous localization and mapping is a technique used by robots and autonomous vehicles to build up a map within an unknown environment or to update a map within a known environment while at the same time keeping track of their current location.","PeriodicalId":400763,"journal":{"name":"International Conference and Exhibition on Computing for Geospatial Research & Application","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131837249","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Efforts to promote digital, social and environmental inclusions the Central Amazon Region are being made. The Federal Government and some universities plan to induce around 1,400 school teachers and their students to grow as citizens, portraying through their own and unbiased perception the environment from which they emerged. The Rio de Janeiro Federal University (UFRJ) developed a web based system through which school students are able to upload to Internet, after screening procedures, all kinds of data (textual, pictures, videos, files) of their choice, using low cost equipments (GPS, digital cameras and notebooks) and simple system interfaces. During 2010, a pilot project has been applied to 48 high schools of the Santarem Municipality, Pará State, in the Central Amazon Region. The basic structure, procedures and some already obtained results are made available in the present paper, documenting one more example of data processing technology promoting citizenship in an emblematic region of Brazil.
{"title":"Citizenship through data sharing in the Amazon region","authors":"Jorge Xavier da Silva, T. Marino","doi":"10.1145/1999320.1999346","DOIUrl":"https://doi.org/10.1145/1999320.1999346","url":null,"abstract":"Efforts to promote digital, social and environmental inclusions the Central Amazon Region are being made. The Federal Government and some universities plan to induce around 1,400 school teachers and their students to grow as citizens, portraying through their own and unbiased perception the environment from which they emerged. The Rio de Janeiro Federal University (UFRJ) developed a web based system through which school students are able to upload to Internet, after screening procedures, all kinds of data (textual, pictures, videos, files) of their choice, using low cost equipments (GPS, digital cameras and notebooks) and simple system interfaces. During 2010, a pilot project has been applied to 48 high schools of the Santarem Municipality, Pará State, in the Central Amazon Region. The basic structure, procedures and some already obtained results are made available in the present paper, documenting one more example of data processing technology promoting citizenship in an emblematic region of Brazil.","PeriodicalId":400763,"journal":{"name":"International Conference and Exhibition on Computing for Geospatial Research & Application","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131506458","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：