教師資料查詢 | 類別: 期刊論文 | 教師: 王銀添 Wang Yin-tien (瀏覽個人網頁)

標題:Image Feature Initialization for SLAM and Moving Object Detection
學年98
學期1
出版(發表)日期2009/09/01
作品名稱Image Feature Initialization for SLAM and Moving Object Detection
作品名稱(其他語言)
著者Wang, Yin-Tien; Ju, Rukg-Chi; Huang, Yu-Wen; Lin, Ming-Chun
單位淡江大學機械與機電工程學系
出版者Japan: ICIC International
著錄名稱、卷期、頁數ICIC Express Letters 3(3)pt.A, pp.477-482
摘要For robot visual Simultaneous Localization and Mapping (vSLAM), the first task is to initialize the image features. We present an improved feature initialization algorithm for robot SLAM, including detection of image features, selection of good features, calculation of image depth, and update of feature locations. Meanwhile, we extend the usage of the feature initialization algorithm to mapping and detection of features on a moving object. Experimentation is performed with real platform and the results show that the performance of the proposed feature initialization algorithm is efficient for visual SLAM and moving object detection.
關鍵字Image feature initialization;Speeded up robust features (SURF);Simnltaneons localization and mapping(SLAM);Moving object detection
語言英文
ISSN1881-803X
期刊性質國外
收錄於EI
產學合作
通訊作者Wang, Yin-Tien
審稿制度
國別日本
公開徵稿
出版型式紙本
相關連結
Google+ 推薦功能,讓全世界都能看到您的推薦!