| 書目名稱 | Discrete Representation of Spatial Objects in Computer Vision | | 編輯 | Longin Jan Latecki | | 視頻video | http://file.papertrans.cn/282/281162/281162.mp4 | | 叢書名稱 | Computational Imaging and Vision | | 圖書封面 |  | | 描述 | One of the most natural representations for modelling spatialobjects in computers is discrete representations in the form of a 2Dsquare raster and a 3D cubic grid, since these are naturally obtainedby segmenting sensor images. However, the main difficulty is thatdiscrete representations are only approximations of the originalobjects, and can only be as accurate as the cell size allows. Ifdigitisation is done by real sensor devices, then there is theadditional difficulty of sensor distortion. To overcome this, digitalshape features must be used that abstract from the inaccuracies ofdigital representation. In order to ensure the correspondence ofcontinuous and digital features, it is necessary to relate shapefeatures of the underlying continuous objects and to determine thenecessary resolution of the digital representation. .This volume gives an overview and a classification of the actualapproaches to describe the relation between continuous and discreteshape features that are based on digital geometric concepts ofdiscrete structures. ..Audience:. This book will be of interest to researchers andgraduate students whose work involves computer vision, imageprocessing, knowledge represen | | 出版日期 | Book 1998 | | 關(guān)鍵詞 | 3D; classification; computer vision; image processing; knowledge; knowledge representation; modeling | | 版次 | 1 | | doi | https://doi.org/10.1007/978-94-015-9002-0 | | isbn_softcover | 978-90-481-4982-7 | | isbn_ebook | 978-94-015-9002-0Series ISSN 1381-6446 | | issn_series | 1381-6446 | | copyright | Springer Science+Business Media Dordrecht 1998 |
The information of publication is updating
|
|
|Archiver|手機(jī)版|小黑屋|
派博傳思國際
( 京公網(wǎng)安備110108008328)
GMT+8, 2025-10-12 05:38
發(fā)表于 2025-3-21 19:54:06
