视差求取matlab代码.docxVIP

实用文档 Stereo Vision This example shows how to compute the depth map between two rectified stereo images. See the Image Rectification ExampleImage Rectification Example to learn about the details behind rectification. In this example we use block matching, which is the standard algorithm for high-speed stereo vision in hardware systems [8]. We first explore basic block matching, and then apply dynamic programming to improve accuracy, and image pyramiding to improve speed. Stereo vision is the process of recovering depth from camera images by comparing two or more views of the same scene. Simple, binocular stereo uses only two images, typically taken with parallel cameras that were separated by a horizontal distance known as the baseline. The output of the stereo computation is a disparity map (which is translatable to a range image) which tells how far each point in the physical scene was from the camera. Step 1. Read Stereo Image PairHere we read in the color stereo image pair and convert the images to gray scale for the matching process. Using color images may provide some improvement in accuracy, but it is more efficient to work with only one-channel images. For this we use the ImageDataTypeConverter and the ColorSpaceConverter System objects. Below we show the left camera image and a color composite of both images so that one can easily see the disparity between them. hIdtc = vision.ImageDataTypeConverter; hCsc = vision.ColorSpaceConverter(Conversion,RGB to intensity); leftI3chan = step(hIdtc,imread(vipstereo_hallwayLeft.png)); leftI = step(hCsc,leftI3chan); rightI3chan = step(hIdtc,imread(vipstereo_hallwayRight.png)); rightI = step(hCsc,rightI3chan); figure(1), clf; clf; 用来清除图形的命令。一般在画图之前用。 imshow(rightI3chan), title(Right image); figure(2), clf; imshowpair(rightI,leftI,ColorChannels,red-cyan), axis image; title(Color composite (right=red, left=cyan)); Step 2. Basic Block MatchingNext we perform basic block matching. For every pixel in the right image, we ext