Vehicle detection from high resolution aerial images has been studied for many years. However, a robust and efficient vehicle detection is still challenging. In this paper, a novel and robust method for automatic vehi...
详细信息
Vehicle detection from high resolution aerial images has been studied for many years. However, a robust and efficient vehicle detection is still challenging. In this paper, a novel and robust method for automatic vehicle detection from aerial images was presented. In this method, a GIS road vector map is used to constrain a vehicle detection system to road networks, edge detection and morphological preprocessing method are used to identify candidate vehicle pixels. Different types of vehicle templates are chosen to adaptively solve their relative regular rotation angle to detect the similar vehicles by their correlation coefficient with the same size of the windows of the templates. Experiment is conducted using 0.15 meter resolution aerial images, the result demonstrated that the new method has a excellent detection performance.
To study the cause of frequent drought and rainy-flood disasters in Sichuan province in recent years, a method based on remote sensing (RS), geographic information system (GIS) and global positioning system (GPS) is p...
详细信息
The early procedures and algorithms for national digital orthophoto generation in the National Digital Orthophoto Program (NDOP) were based on earlier USGS mapping operations, such as field control, aerotriangulation ...
详细信息
The early procedures and algorithms for national digital orthophoto generation in the National Digital Orthophoto Program (NDOP) were based on earlier USGS mapping operations, such as field control, aerotriangulation (derived in the early 1920s), the quarter-quadrangle-centered (3.75 minutes of longitude and latitude in geographic extent), 1:40,000 aerial photographs, and 2.5 D digital elevation models. However, large-scale city orthophotos using early procedures have disclosed many shortcomings, e.g., ghost image, occlusion, shadow. Thus, to provide the technical base (algorithms, procedure) and experience needed for city large-scale digital orthophoto creation is essential for the near future national large-scale digital orthophoto deployment and the revision of the Standards for National Large-scale City Digital Orthophoto in National Digital Orthophoto Program (NDOP). This paper will report our initial research results as follows: (1) high-precision 3D city DSM generation through LIDAR dataprocessing, (2) spatial objects/features extraction through surface material information and high-accuracy 3D DSM data, (3) 3D city model development, (4) algorithm development for generation of DTM-based orthophoto, and DBM-based orthophoto, (5) true orthophoto generation by merging DBM-based orthophoto and DTM-based orthophoto, and (6) automatic mosaic by optimizing and combining imagery from many perspectives.
暂无评论