zoukankan      html  css  js  c++  java
  • 深度学习图像配准 Image Registration: From SIFT to Deep Learning


    What is Image Registration?


     

    Traditional Feature-based Approaches

    Keypoint Detection and Feature Description
    复制代码
    import numpy as np
    import cv2 as cv
    
    img = cv.imread('image.jpg')
    gray= cv.cvtColor(img, cv.COLOR_BGR2GRAY)
    
    akaze = cv.AKAZE_create()
    kp, descriptor = akaze.detectAndCompute(gray, None)
    
    img=cv.drawKeypoints(gray, kp, img)
    cv.imwrite('keypoints.jpg', img)
    复制代码

    For more details on feature detection and description, you can check out this OpenCV tutorial.

    Feature Matching

    复制代码
    import numpy as np
    import cv2 as cv
    import matplotlib.pyplot as plt
    
    img1 = cv.imread('image1.jpg', cv.IMREAD_GRAYSCALE)  # referenceImage
    img2 = cv.imread('image2.jpg', cv.IMREAD_GRAYSCALE)  # sensedImage
    
    # Initiate AKAZE detector
    akaze = cv.AKAZE_create()
    # Find the keypoints and descriptors with SIFT
    kp1, des1 = akaze.detectAndCompute(img1, None)
    kp2, des2 = akaze.detectAndCompute(img2, None)
    
    # BFMatcher with default params
    bf = cv.BFMatcher()
    matches = bf.knnMatch(des1, des2, k=2)
    
    # Apply ratio test
    good_matches = []
    for m,n in matches:
        if m.distance < 0.75*n.distance:
            good_matches.append([m])
            
    # Draw matches
    img3 = cv.drawMatchesKnn(img1,kp1,img2,kp2,good_matches,None,flags=cv.DrawMatchesFlags_NOT_DRAW_SINGLE_POINTS)
    cv.imwrite('matches.jpg', img3)
    复制代码

    Image Warping

    复制代码
    # Select good matched keypoints
    ref_matched_kpts = np.float32([kp1[m[0].queryIdx].pt for m in good_matches]).reshape(-1,1,2)
    sensed_matched_kpts = np.float32([kp2[m[0].trainIdx].pt for m in good_matches]).reshape(-1,1,2)
    
    # Compute homography
    H, status = cv.findHomography(ref_matched_kpts, sensed_matched_kpts, cv.RANSAC,5.0)
    
    # Warp image
    warped_image = cv.warpPerspective(img1, H, (img1.shape[1]+img2.shape[1], img1.shape[0]))
                
    cv.imwrite('warped.jpg', warped_image)
    复制代码


    Deep Learning Approaches

    Feature Extraction

    Homography Learning

    Their approach introduces two new network structures: a Tensor Direct Linear Transform and a Spatial Transformation Layer. We will not go into the details of these components here, we can simply consider that these are used to obtain a transformed sensed image using the homography parameter outputs of the CNN model, that we then use to compute the photometric loss.

    Other Approaches


     
    _________________________________________________________________________________________________________________________________________________
    每一个不曾起舞的日子,都是对生命的辜负。
    But it is the same with man as with the tree. The more he seeks to rise into the height and light, the more vigorously do his roots struggle earthward, downward, into the dark, the deep - into evil.
    其实人跟树是一样的,越是向往高处的阳光,它的根就越要伸向黑暗的地底。----尼采
  • 相关阅读:
    [NOI2014]动物园
    [NOI2014]起床困难综合症
    bzoj2688 Green Hackenbush
    luogu P2575 高手过招
    [NOI2015]荷马史诗
    win10系统U盘读取不了怎么解决 三种方法快速解决&quot;文件或目录损坏且无法读取& 发布时间:2020-06-05 09:19:46 作者:佚名 我要评论
    在 Linux 中,最直观、最可见的部分就是 文件系统(file system)
    GB 18030-2000《信息技术信息交换用汉字编码字符集基本集的扩充
    docker 分层 隔离
    DNS和BIND
  • 原文地址:https://www.cnblogs.com/leoking01/p/14611959.html
Copyright © 2011-2022 走看看