Application of Projection Learning to the Detection of Urban Areas in SPOT Satellite Images
نویسندگان
چکیده
We introduce a novel learning algorithm for neural networks, with the major feature of being rapid when compared to classical learning algorithms, ooering misclassiication rates of 5% and less after only a few iterations, i.e. 20-30 seconds of learning, depending on the task, if a suitable preprocessing has been done. The algorithm is based on considering a neural network as a base in function space, base onto which the function to be learned is projected. We thus call our algorithm projection learning. We present the algorithm, show the application to the detection of inhabited areas in satellite images, discuss the various preprocessors used, compare to other approaches used, and outline further directions of research Application de l'apprentissage par projection a la d etection de zones urbaines dans les images satellite SPOT R esum e : Nous introduisons un nouvel algorithme d'apprentissage pour r eseaux de neurones, dont la caract eristique principale est d'^ etre rapide en comparaison des al-gorithmes classiques d'apprentissage, avec des taux d'erreur de 5% et moins apr es quelques it erations d'apprentissage, d'une dur ee de 20-30 secondes, en supposant un pr etraitement convenable. Nous consid erons un r eseau neuromim etique comme une base non-orthogonale dans un espace de fonctions, base sur laquelle la fonction a apprendre est projet ee. C'est pourquoi nous appelons notre algorithme Apprentissage par Projection. Nous pr esen-tons l'algorithme, montrons l'application a la d etection de zones urbaines dans des images satellite, discutons les pr etraitements utilis es, comparons a d'autres approches, et indiquons les axes futurs de recherche. Mots-cl e : Apprentissage dans la vision par ordinateur, segmentation et groupe-ment perceptuel, r eseaux de neurones, analyse de texture, classiication bas ee pixel, traitement bas niveau, r eseaux a propagation directe, analyse d'images satellite
منابع مشابه
Investigation of the effects of Covid-19 pandemic on UHI in urban, industrial and green spaces of Tehran
Investigation of the effects of Covid-19 pandemic on UHI in residential, industrial and green spaces of Tehran Abstract Rapid urbanization in recent decades has been a major driver of ecosystems and environmental degradation, including changes in agricultural land use and forests. Urbanization is rapidly transforming ecosystems into buildings that increase heat storage capacity. Loss of ve...
متن کاملSalient regions detection in satellite images using the combination of MSER local features detector and saliency models
Nowadays, due to quality development of satellite images, automatic target detection on these images has been attracted many researchers' attention. Remote-sensing images follow various geospatial targets; these targets are generally man-made and have a distinctive structure from their surrounding areas. Different methods have been developed for automatic target detection. In most of these met...
متن کاملOil spill detection using in Sentinel-1 satellite images based on Deep learning concepts
Awareness of the marine area is very important for crisis management in the event of an accident. Oil spills are one of the main threats to the marine and coastal environments and seriously affect the marine ecosystem and cause political and environmental concerns because it seriously affects the fragile marine and coastal ecosystem. The rate of discharge of pollutants and its related effects o...
متن کاملIntroducing An Efficient Set of High Spatial Resolution Images of Urban Areas to Evaluate Building Detection Algorithms
The present work aims to introduce an efficient set of high spatial resolution (HSR) images in order to more fairly evaluate building detection algorithms. The introduced images are chosen from two recent HSR sensors (QuickBird and GeoEye-1) and based on several challenges of urban areas encountered in building detection such as diversity in building density, building dissociation, building sha...
متن کاملCrop Land Change Monitoring Based on Deep Learning Algorithm Using Multi-temporal Hyperspectral Images
Change detection is done with the purpose of analyzing two or more images of a region that has been obtained at different times which is Generally one of the most important applications of satellite imagery is urban development, environmental inspection, agricultural monitoring, hazard assessment, and natural disaster. The purpose of using deep learning algorithms, in particular, convolutional ...
متن کامل