期刊名称：ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
印刷版ISSN：2194-9042
电子版ISSN：2194-9050
出版年度：2002
卷号：XXXIV Part 2
页码：351-356
出版社：Copernicus Publications
摘要：This paper presents a method for extraction and recognition of trucks from aerial photographs. A new method, mean shift image segmentation, is employed to extract truck shadow and boundary information. After a conversion of the boundaries into vector data, an enclosing minimum area rectangle is fit to each boundary. These rectangles are input as candidates into a designed Hopfield Neural Network. Trucks in the photographs are then recognized by comparison with predefined truck models
