English  |  正體中文  |  简体中文  |  全文筆數/總筆數 : 56557/90363 (63%)
造訪人次 : 11846983      線上人數 : 117
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/987654321/92585

    題名: Robot Simultaneous Localization and Mapping Using Speeded-Up Robust Features
    作者: Wang, Yin-tien;Chi, Chen-tung;Feng, Ying-chieh
    貢獻者: 淡江大學機械與機電工程學系
    關鍵詞: Robot Mapping;Speeded-Up Robust Features (SURF);EKF-SLAM
    日期: 2013-01-01
    上傳時間: 2013-10-19 12:09:06 (UTC+8)
    出版者: Stafa-Zurich: Trans Tech Publications Ltd.
    摘要: An algorithm for robot mapping is proposed in this paper using the method of speeded-up robust features (SURF). Since SURFs are scale- and orientation-invariant features, they have higher repeatability than that of the features obtained by other detection methods. Even in the cases of using moving camera, the SURF method can robustly extract the features from image sequences. Therefore, SURFs are suitable to be utilized as the map features in visual simultaneous localization and mapping (SLAM). In this article, the procedures of detection and matching of the SURF method are modified to improve the image processing speed and feature recognition rate. The sparse representation of SURF is also utilized to describe the environmental map in SLAM tasks. The purpose is to reduce the computation complexity in state estimation using extended Kalman filter (EKF). The EKF SLAM with SURF-based map is developed and implemented on a binocular vision system. The integrated system has been successfully validated to fulfill the basic capabilities of SLAM system.
    關聯: Applied Mechanics and Materials 284-287, pp.2142-2146
    DOI: 10.4028/www.scientific.net/AMM.284-287.2142
    顯示於類別:[機械與機電工程學系暨研究所] 期刊論文


    檔案 描述 大小格式瀏覽次數
    AMM.284-287.2142.pdf328KbAdobe PDF707檢視/開啟



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