DC 欄位 | 值 | 語言 |
dc.contributor | 傅立成 | zh-TW |
dc.contributor | Fu, Li-Chen | en |
dc.contributor | 臺灣大學:資訊工程學研究所 | zh-TW |
dc.contributor.author | 彭禹安 | zh-TW |
dc.contributor.author | Peng, Yu-An | en |
dc.creator | 彭禹安 | zh-TW |
dc.creator | Peng, Yu-An | en |
dc.date | 2008 | en |
dc.date.accessioned | 2010-05-18T10:19:42Z | - |
dc.date.accessioned | 2018-07-05T01:50:00Z | - |
dc.date.available | 2010-05-18T10:19:42Z | - |
dc.date.available | 2018-07-05T01:50:00Z | - |
dc.date.issued | 2008 | - |
dc.identifier.other | U0001-2608200823094200 | en |
dc.identifier.uri | http://ntur.lib.ntu.edu.tw//handle/246246/183664 | - |
dc.description.abstract | 在本論文中,我們提出了一個用影像為行動機器人建立階層式地圖以達到快速定位之目標的系統。上層的地圖為一用圖形(graph)來表式的拓樸式地圖,因為此類地圖較適用於大環境。在這個地圖中,每個節點(vertex)由可以快速辨識其在整個環境中的那個地方(Place)的影像資訊所組成,而邊(edge)代表這些地方(Place)的空間關係。在此之後,我們會在每個節點之內建立一個以座標表示的地圖,其建立方式為影像資訊和由其他感應器得到的座標所成的對應。建完此地圖之後,可用即可利用兩個步驟達到快速定位的目標:首先,找出用來搜尋的影像落在那個地方(Place);再者,比對出此地方(Place)中與用來搜尋的影像最相像的影像,並傳回其所附之座標。 | zh-TW |
dc.description.abstract | In our thesis, we propose a system to make the mobile robot building a vision-based hierarchical map and then quickly localizing itself by this map. In learning stage, each image The top-level map is a topological map which is represented as the graph because of the fitness of the large-scale environments. In this map, the vertices comprise some visual information for efficiently identifying the places of the robot''s environment and the edges denote the spatial relation between these places. Then, we construct a small metric map attached each node of the topological map. After this two steps, the robot can localize itself by this hierarchical map effectively and robustly. | en |
dc.description.tableofcontents | 口試委員審定書 I謝 II要 IIIbstract IVist of Figures VIIIist of Tables XI Introduction 1.1 Motivation 1.2 Literature Review 2.3 Thesis Organization 4.4 Contribution 5 Preliminaries 6.1 System Overview 6.2 Feature Extraction in Computer Vision 7.2.1 Feature Detection 8.2.2 Feature Description 9.3 Scale Invariant Feature Transform (SIFT) 10.3.1 Scale Invariant Feature Detection 11.3.2 Feature Descriptor 13 Visual Information for Place Identification 16.1 Diagram of Clustering 18.2 Image Segmentation 19.3 Segment Encoding 20.3.1 Color Space Traslation 24.3.2 Expand Color Histogram 24.3.3 Measurement of Dissimilarity 25.4 Methodology of Clustering 26 Database Management and Localization 28.1 Diagram of Map Building 29.2 Image Representation 31.2.1 Scale Invariant Fearure Transform 32.2.2 Inverted Index 33.3 Databse Management 35.3.1 Top-level Database 36.3.2 Bottom-level Database 37.4 Robust Localization 38.4.1 The Diagram of Localization 38.4.2 Place Identify 39.4.3 Robust Localization 40 Experiments 42.1 Experimental Settings and Environment 42.1.1 Hardware of the Experimental System(Tour Guide Robot) 42.1.2 Hardware of the Experimental System(Home Robot) 44.1.3 Experimental Environment 45.2 Performance Evaluation 46.2.1 The Performance of Clustering 46.2.2 Performance of Image Recognition 48.2.3 Performance of Global Localization 51 Conclusion and Future Work 54.1 Conclusion 54.2 Future Work 55ibliography 56 | en |
dc.format | application/pdf | en |
dc.format.extent | 2789590 bytes | - |
dc.format.mimetype | application/pdf | - |
dc.language | en | en |
dc.language.iso | en_US | - |
dc.subject | 單眼 | zh-TW |
dc.subject | 視覺 | zh-TW |
dc.subject | 全域定位 | zh-TW |
dc.subject | 室內 | zh-TW |
dc.subject | 階層式 | zh-TW |
dc.subject | monocular | en |
dc.subject | visoin | en |
dc.subject | global localization | en |
dc.subject | indoor | en |
dc.subject | hierarchical | en |
dc.title | 大環境之機器人視覺特徵擷取環境定位 | zh-TW |
dc.title | Vision-based Global Localization of Large-Scale Indoor Environments with Hierarchical Map | en |
dc.type | thesis | en |
dc.identifier.uri.fulltext | http://ntur.lib.ntu.edu.tw/bitstream/246246/183664/1/ntu-97-R95922129-1.pdf | - |
item.fulltext | with fulltext | - |
item.languageiso639-1 | en_US | - |
item.openairecristype | http://purl.org/coar/resource_type/c_46ec | - |
item.cerifentitytype | Publications | - |
item.openairetype | thesis | - |
item.grantfulltext | open | - |
顯示於: | 資訊工程學系
|