Paper Info
Title
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 -shape (WSH) local invariant features are tolerant to image rotation, scale change, affine deformation, illumination change, and blurring. However, since the number of WSH features is small, it is difficult to get enough matches to estimate the satisfactory homography matrix or fundamental matrix. In addition, the WSH detector is extremely sensitive to image noise because it is built on sampled edges. Considering the shortcomings of the WSH detector, this paper improves the WSH feature matching method based on the 2D discrete wavelet transform (2D-DWT). The method firstly performs 2D-DWT on the image, and then detects WSH features on the transformed images. According to the methods of descriptor construction for WSH features, three matching methods on the basis of wavelet transform WSH features (WWF), improved wavelet transform WSH 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 WSH. 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, WSH, DWT-WSH, KAZE, WWF, and LIWWF.
Year
DOI
Venue
2018
10.3390/s18103494
SENSORS
Keywords
Field
DocType
stereo remote sensing image,feature matching,2D-DWT,WSH,MSER,image deformation
Computer vision,Electronic engineering,Feature matching,Artificial intelligence,Engineering
Journal
Volume
Issue
Citations 
18
10
0
PageRank 
References 
Authors
0.34
12
4
Name
Order
Citations
PageRank
Mei Yu1132.92
Ka-zhong Deng200.68
Hua-chao Yang3131.70
Changbiao Qin400.34