Improved WαSH Feature Matching Based on 2D-DWT for Stereo Remote Sensing Images

Abstract

Image matching is an outstanding issue because of the existing of geometric and radiometric distortion in stereo remote sensing images. Weighted α-shape (WαSH) local invariant features are tolerant to image rotation, scale change, affine deformation, illumination change, and blurring. However, since the number of WαSH features is small, it is difficult to get enough matches to estimate the satisfactory homography matrix or fundamental matrix. In addition, the WαSH detector is extremely sensitive to image noise because it is built on sampled edges. Considering the shortcomings of the WαSH detector, this paper improves the WαSH feature matching method based on the 2D discrete wavelet transform (2D-DWT). The method firstly performs 2D-DWT on the image, and then detects WαSH features on the transformed images. According to the methods of descriptor construction for WαSH features, three matching methods on the basis of wavelet transform WαSH features (WWF), improved wavelet transform WαSH features (IWWF), and layered IWWF (LIWWF) are distinguished with respect to the character of the sub-images. The experimental results on the dataset containing affine distortion, scale distortion, illumination change, and noise images, showed that the proposed methods acquired more matches and better stableness than WαSH. Experimentation on remote sensing images with less affine distortion and slight noise showed that the proposed methods obtained the correct matching rate greater than 90%. For images containing severe distortion, KAZE obtained a 35.71% correct matching rate, which is unacceptable for calculating the homography matrix, while IWWF achieved a 71.42% correct matching rate. IWWF was the only method that achieved the correct matching rate of no less than 50% for all four test stereo remote sensing image pairs and was the most stable compared to MSER, DWT-MSER, WαSH, DWT-WαSH, KAZE, WWF, and LIWWF.

Glioma Segmentation and Classification System Based on Proposed Texture Features Extraction Method and Hybrid Ensemble Learning

“…The LL sub-band is the approximation image. The HH sub-band is discarded as it mostly contains noise [31].…”

Brain-Inspired Remote Sensing Interpretation: A Comprehensive Survey

“…As for the disparity estimation in remote sensing [253,254,255]. Among them, Yu et al [253] mainly uses twodimensional discrete wavelet transform (2D-DWT) to enhance the local invariant features of the existing weighted α-shape (WαSH). And it is used in remote sensing images with less affine distortion and less noise.…”

A Robust Method for Automatic Panoramic UAV Image Mosaic

“…On the one hand, the geometrical relationship between UAV images is often complex due to variations in ground relief, changes in imaging viewpoints, and shooting at low altitudes, where image pairs cannot be accurately matched using a parametric transformation model (e.g., affine or homography) as in most existing methods. Image matching is a critical prerequisite of image mosaic, which aims to overlay two images of the same scene geometrically [10,11,12,13]. On the basis of the type of data given, image matching can be divided into rigid and nonrigid.…”