?
Improve Method Using Spatial Fast Filters and GPU to Detection of Parcels of Land in Satellite Images for Cadaster Purposes
Nowadays, remotely sensed images are used for various purposes in different applications. One of them is the cadastral application using high resolution satellite imagery. The edge detection has an important role in image processing, especially in the detection and the extraction physical features, those which are useful to their enforcement in the analysis of cadasters. An improve methodology is shown for detection of parcels of land in satellite images using GPU and fast filter for improve time process to reduce the noise, dynamic histogram equalization instead classic histogram equalization and Canny edge detection which is the best of others as Sobel, Prewitt, etc, for accelerated time process we used parallel Matlab GPU. Index Terms— satellite image, digital image, Canny edge detector, fast filters, dynamic histogram equalization, SSIM measure, parallel programming, GPU.