A Rotation-Invariant Optical and SAR Image Registration Algorithm Based on Deep and Gaussian Features

Autor:	Yi-Hang Huang, Haitao Zhang, Ze-Yi Li
Rok vydání:	2021
Předmět:	Synthetic aperture radar Similarity (geometry) neural network Computer science Science Gaussian 0211 other engineering and technologies Image registration 02 engineering and technology symbols.namesake optical and synthetic aperture radar image registration Gaussian pyramid Histogram 0202 electrical engineering electronic engineering information engineering 021101 geological & geomatics engineering business.industry Deep learning Speckle noise Pattern recognition Computer Science::Computer Vision and Pattern Recognition symbols General Earth and Planetary Sciences 020201 artificial intelligence & image processing Artificial intelligence business Rotation (mathematics)
Zdroj:	Remote Sensing, Vol 13, Iss 2628, p 2628 (2021) Remote Sensing; Volume 13; Issue 13; Pages: 2628
ISSN:	2072-4292
DOI:	10.3390/rs13132628
Popis:	Traditional feature matching methods of optical and synthetic aperture radar (SAR) used gradient are sensitive to non-linear radiation distortions (NRD) and the rotation between two images. To address this problem, this study presents a novel approach to solving the rigid body rotation problem by a two-step process. The first step proposes a deep learning neural network named RotNET to predict the rotation relationship between two images. The second step uses a local feature descriptor based on the Gaussian pyramid named Gaussian pyramid features of oriented gradients (GPOG) to match two images. The RotNET uses a neural network to analyze the gradient histogram of the two images to derive the rotation relationship between optical and SAR images. Subsequently, GPOG is depicted a keypoint by using the histogram of Gaussian pyramid to make one-cell block structure which is simpler and more stable than HOG structure-based descriptors. Finally, this paper designs experiments to prove that the gradient histogram of the optical and SAR images can reflect the rotation relationship and the RotNET can correctly predict them. The similarity map test and the image registration results obtained on experiments show that GPOG descriptor is robust to SAR speckle noise and NRD.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::89b4694fddee9bcc2bd3aecece7aa029 https://doi.org/10.3390/rs13132628 Zobrazit plný text záznamu Plný text ve formátu PDF Plný text ve formátu HTML
Nepřihlášeným uživatelům se plný text nezobrazuje	K zobrazení výsledku je třeba se přihlásit.