English  |  正體中文  |  简体中文  |  全文筆數/總筆數 : 58286/91808 (63%)
造訪人次 : 13826879      線上人數 : 83
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU Library IR team.
搜尋範圍 查詢小技巧:
  • 您可在西文檢索詞彙前後加上"雙引號",以獲取較精準的檢索結果
  • 若欲以作者姓名搜尋,建議至進階搜尋限定作者欄位,可獲得較完整資料
  • 進階搜尋
    請使用永久網址來引用或連結此文件: http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/92586

    題名: Data Association and Map Management for Robot SLAM using Local Invariant Features
    作者: Wang, Yin-Tien;Feng, Ying-Chieh
    貢獻者: 淡江大學機械與機電工程學系
    關鍵詞: Robot Mapping;Local Invariant Feature Detectors;Speeded-Up Robust Features (SURF);Simultaneous Localization and Mapping (SLAM)
    日期: 2013-08-04
    上傳時間: 2013-10-19 12:16:46 (UTC+8)
    出版者: New York : IEEE Computer Society, Institute of Electrical and Electronics Engineers
    摘要: To build a persistent map with visual landmarks is one of the most important steps for implementing the visual simultaneous localization and mapping (SLAM). The corner detector is a common method utilized to detect visual landmarks for constructing a map of the environment. However, due to the scalevariant characteristic of corner detection, extensive computational cost is needed to recover the scale and orientation of corner features in SLAM tasks. The purpose of this paper is to build the map using a local invariant feature detector, namely speeded-up robust features (SURF), to detect scale- and orientation-invariant features as well as provide a robust representation of visual landmarks for SLAM. The procedures of detection, description and matching of regular SURF algorithms are modified in this paper in order to provide a robust data-association of visual landmarks in SLAM. Furthermore, the effective method of map management for SURF features in SLAM is also designed to improve the accuracy of robot state estimation.
    關聯: Proceedings of 2013 IEEE International Conference on Mechatronics and Automation (ICMA), pp.1102-1107
    顯示於類別:[機械與機電工程學系暨研究所] 會議論文


    檔案 描述 大小格式瀏覽次數
    Wang2013Proc.IEEEicma.pdf575KbAdobe PDF342檢視/開啟



    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library & TKU Library IR teams. Copyright ©   - 回饋