透视变换不能在Matlab中计算场景中的正确线 [英] Perspective transform not calculating proper lines on scene in Matlab
问题描述
因此，我试图为单应性写入等效代码 OpenCV中给出的示例。代码很长，但非常简洁，首先它计算一个对象和一个场景（通过webcam）的检测器和描述符。然后，它使用 BruteForce Matcher 进行比较。然后选择最佳匹配并使用它来计算对象和场景的单应性和之后透视变换。现在我的问题是透视变换没有给我一个好的结果。通过透视变换获得的坐标似乎挂在（0,0）坐标上。我有一个类似的代码运行在纯OpenCV在eclipse，从中我看到第一个坐标变化时，我移动相机，它不发生。还要注意，计算的单应性值略有不同。然而，对我来说，代码的逻辑没有问题。但是，矩形区域没有在场景中正确显示。我可以看到不同的线被绘制在场景上，但他们不适合的图像，以及它应该的。也许我需要一组不同的眼睛。感谢。
So , I have trying to write equivalent code for homography example given in OpenCV . The code is pretty long but is very concise , at first it calculates the detectors and descriptors of an object and a scene(via webcam) . It then makes comparison between them using BruteForce Matcher . It then chooses the best matches and use that to calculate the homography and afterwards perspective transform of the object and the scene . Now my problem is that the perspective transform is not giving me a good result . On of the coordinates obtained by perspective transform seems to hang around the (0,0) coordinates . I have a similar code running in pure OpenCV in eclipse , from which I saw that the first coordinate change when I move around the camera , its not happening . Also to note that the homography value calculated is slightly different . However , to me there is no problem with the logic of the code .But , the rectangular region is not properly shown in the scene. I can see different lines being drawn on the scene,but they are not fitting the image , as well as it should .Perhaps I need a different set of eyes . Thanks.
function hello
disp('Feature matching demo. Press any key when done.');
% Set up camera
camera = cv.VideoCapture;
pause(3); % Necessary in some environment. See help cv.VideoCapture
% Set up display window
window = figure('KeyPressFcn',@(obj,evt)setappdata(obj,'flag',true));
setappdata(window,'flag',false);
object = imread('D:/match.jpg');
%Conversion from color to gray
object = cv.cvtColor(object,'RGB2GRAY');
%Declaring detector and extractor
detector = cv.FeatureDetector('SURF');
extractor = cv.DescriptorExtractor('SURF');
%Calculating object keypoints
objKeypoints = detector.detect(object);
%Calculating object descriptors
objDescriptors = extractor.compute(object,objKeypoints);
% Start main loop
while true
% Grab and preprocess an image
im = camera.read;
%im = cv.resize(im,1);
scene = cv.cvtColor(im,'RGB2GRAY');
sceneKeypoints = detector.detect(scene);
%Checking for empty keypoints
if isempty(sceneKeypoints)
continue
end;
sceneDescriptors = extractor.compute(scene,sceneKeypoints);
matcher = cv.DescriptorMatcher('BruteForce');
matches = matcher.match(objDescriptors,sceneDescriptors);
objDescriptRow = size(objDescriptors,1);
dist_arr = zeros(1,objDescriptRow);
for i=1:objDescriptRow
dist_arr(i) = matches(i).distance;
end;
min_dist = min(dist_arr);
N = 10000;
good_matches = repmat(struct('distance',0,'imgIdx',0,'queryIdx',0,'trainIdx',0), N, 1 );
goodmatchesSize = 0;
for i=1:objDescriptRow
if matches(i).distance < 3 * min_dist
good_matches(i).distance = matches(i).distance;
good_matches(i).imgIdx = matches(i).imgIdx;
good_matches(i).queryIdx = matches(i).queryIdx;
good_matches(i).trainIdx = matches(i).trainIdx;
%Recording the number of good matches
goodmatchesSize = goodmatchesSize +1;
end
end
im_matches = cv.drawMatches(object, objKeypoints, scene, sceneKeypoints,good_matches);
objPoints = [];
scnPoints = [];
%Finding the good matches
for i=1:goodmatchesSize
qryIdx = good_matches(i).queryIdx;
trnIdx = good_matches(i).trainIdx;
if qryIdx == 0
continue
end;
if trnIdx == 0
continue
end;
first_point = objKeypoints(qryIdx).pt;
second_point = sceneKeypoints(trnIdx).pt;
objPoints(i,:)= (first_point);
scnPoints(i,:) = (second_point);
end
%Error checking
if length(scnPoints) <=4
continue
end;
if length(scnPoints)~= length(objPoints)
continue
end;
% Finding homography of arrays of two sets of points
H = cv.findHomography(objPoints,scnPoints);
objectCorners = [];
sceneCorners =[];
objectCorners(1,1) = 0.1;
objectCorners(1,2) = 0.1;
objectCorners(2,1) = size(object,2);
objectCorners(2,2) = 0.1;
objectCorners(3,1) = size(object,2);
objectCorners(3,2) = size(object,1);
objectCorners(4,1) = 0.1;
objectCorners(4,2) = size(object,1);
%Transposing the object corners for perpective transform to work
newObj = shiftdim(objectCorners,-1);
%Calculating the perspective tranform
foo =cv.perspectiveTransform(newObj,H);
sceneCorners = shiftdim(foo,1);
offset = [];
offset(1,1) = size(object,2);
offset(1,2)= 0;
outimg = cv.line(im_matches,sceneCorners(1,:)+offset,sceneCorners(2,:)+offset);
outimg = cv.line(outimg,sceneCorners(2,:)+offset,sceneCorners(3,:)+offset);
outimg = cv.line(outimg,sceneCorners(3,:)+offset,sceneCorners(4,:)+offset);
outimg = cv.line(outimg,sceneCorners(4,:)+offset,sceneCorners(1,:)+offset);
imshow(outimg);
% Terminate if any user input
flag = getappdata(window,'flag');
if isempty(flag)||flag, break; end
pause(0.000000001);
end
% Close
close(window);
end
推荐答案
需要一个完整的单应性？对于该应用，仿射或甚至相似变换（dx，dy，scale和rotation）可能就足够了。更有约束的转换在噪声的存在下会更好。
Do you need a full homography? For this application an affine or even a similarity transformation (dx, dy, scale, and rotation) may be sufficient. A more constrained transformation will work better in the presence of noise.
这篇关于透视变换不能在Matlab中计算场景中的正确线的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！
