AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |
Back to Blog
EarthView 5.11.211/11/2023 ![]() ![]() This is a 12-class Google image dataset of SIRI-WHU meant for research purposes. Saikat Basu, Sangram Ganguly, Supratik Mukhopadhyay, Robert Dibiano, Manohar Karki and Ramakrishna Nemani, DeepSat - A Learning framework for Satellite Imagery, ACM SIGSPATIAL 2015.ġ1 scenes, all using high resolution remote sensing images, downloaded from Google Earth 2.6.The training and test labels are 1x4 and 1圆 vectors for SAT-4 and SAT-6 respectively having a single 1 indexing a particular class from 0 through 4 or 6 and 0 values at all other indices. Each sample image is 28x28 pixels and consists of 4 bands - red, green, blue and near infrared. mat files that can be read using the standard load command in MATLAB. Care was taken to avoid interclass overlaps within a selected and labeled image patch. We chose 28x28 as the window size to maintain a significantly bigger context, and at the same time not to make it as big as to drop the relative statistical properties of the target class conditional distributions within the contextual window. ![]() Once labeled, 28x28 non-overlapping sliding window blocks were extracted from the uniform image patch and saved to the dataset with the corresponding label. An image labeling tool developed as part of this study was used to manually label uniform image patches belonging to a particular landcover class. In order to maintain the high variance inherent in the entire NAIP dataset, we sample image patches from a multitude of scenes (a total of 1500 image tiles) covering different landscapes like rural areas, urban areas, densely forested, mountainous terrain, small to large water bodies, agricultural areas, etc. The images consist of 4 bands - red, green, blue and Near Infrared (NIR). The imagery is acquired at a 1-m ground sample distance (GSD) with a horizontal accuracy that lies within six meters of photo-identifiable ground control points. The entire NAIP dataset for CONUS is ~65 terabytes. The average image tiles are ~6000 pixels in width and ~7000 pixels in height, measuring around 200 megabytes each. We used the uncompressed digital Ortho quarter quad tiles (DOQQs) which are GeoTIFF images and the area corresponds to the United States Geological Survey (USGS) topographic quadrangles. The NAIP dataset consists of a total of 330,000 scenes spanning the whole of the Continental United States (CONUS). Images were extracted from the National Agriculture Imagery Program (NAIP) dataset.
0 Comments
Read More
Leave a Reply. |