A coarse-to-fine image registration method based on visual attention model

Abstract

A variable threshold visual sensing and image reconstruction method based on pulse sequence SCIENCE CHINA Information Sciences A progressive remote sensing image registration method based on adaptive scale SCIENTIA SINICA Informationis 41, 55 (2011); A model for visual image-background discrimination by relative movement Science in China Series C-Life Sciences 40, 79 (1997);. RESEARCH PAPER. SCIENCE CHINA Information Sciences

A Novel Algorithm of Water Region Detection in SAR Image Based on Bag of Visual Words and Local Pattern Histogram

“…There are a number of classifying algorithms based on local feature descriptor being applied in image classification and pattern recognition [13,14] . How to select a simple algorithm with good performance of local feature descriptor to characterize the local texture features of image has been a hot research topic for a long time [15] .…”

“…P fa = 1 − P recision (13) where A(M Lab ) is real water region pixels set, A(SM B ) is the set of detected water region pixels based on our algorithm, Recall is recall rate for the detecting ability of water region object, Precision is precision rate for the accuracy of detection, P fa is false alarm probability. Experimental analysis include two aspects: one is how the key parameters of the proposed algorithm impact on the performance, the other is comparing among our algorithm, two other algorithms, and artificial marker.…”

A waterborne salient ship detection method on SAR imagery

“…In recent years, biologically plausible computing methods have been widely utilized in the remote sensing field [5]. It should be noted that the human visual system owns excellent properties that help us for its use in target detection even under clutter background [6].…”

Automatic registration method for medium-resolution remote sensing images of coral reefs with morphological information pairing and constrained iterative fining

“…8,9 Many researchers have attempted to develop automatic registration methods. [10][11][12] Generally, there are four types of automatic registration methods: intensity-based methods, feature-based methods, coarse-to-fine methods, and deep learning-based methods. [13][14][15] Intensity-based methods, such as grayscale matching, match images by comparing reflection differences between pixels within correlation windows in images to be matched.…”