文章目录
*
– 流程图
– 相机标定
– 立体匹配
– 效果
–
+ 1.原图像
+ 2.深度图
+ 3.代码链接
流程图
; 相机标定
参考链接：【开源 |教程 | 双目测距】双目相机的标定_哔哩哔哩_bilibili
自制的标定数据集，必须用自己相机拍摄照片制作数据集
标定板下载：pattern.png (1830×1330) (opencv.org)
import cv2
import numpy as np
left_camera_matrix = np.array([[516.5066236,-1.444673028,320.2950423],[0,516.5816117,270.7881873],[0.,0.,1.]])
right_camera_matrix = np.array([[511.8428182,1.295112628,317.310253],[0,513.0748795,269.5885026],[0.,0.,1.]])
left_distortion = np.array([[-0.046645194,0.077595167, 0.012476819,-0.000711358,0]])
right_distortion = np.array([[-0.061588946,0.122384376,0.011081232,-0.000750439,0]])
R = np.array([[0.999911333,-0.004351508,0.012585312],
[0.004184066,0.999902792,0.013300386],
[-0.012641965,-0.013246549,0.999832341]])
T = np.array([-120.3559901,-0.188953775,-0.662073075])
size = (640, 480)
R1, R2, P1, P2, Q, validPixROI1, validPixROI2 = cv2.stereoRectify(left_camera_matrix, left_distortion,
right_camera_matrix, right_distortion, size, R,
T)
left_map1, left_map2 = cv2.initUndistortRectifyMap(left_camera_matrix, left_distortion, R1, P1, size, cv2.CV_16SC2)
right_map1, right_map2 = cv2.initUndistortRectifyMap(right_camera_matrix, right_distortion, R2, P2, size, cv2.CV_16SC2)
print(Q)
cv2.stereoRectify（）函数
- 示例：
R1, R2, P1, P2, Q, validPixROI1, validPixROI2 = cv2.stereoRectify(left_camera_matrix, left_distortion,right_camera_matrix, right_distortion, size, R, T) - 作用：为每个摄像头计算立体校正的映射矩阵R1, R2, P1, P2
- 参数：
- left_camera_matrix：左相机内参
- left_distortion：左相机畸变系数
- right_camera_matrix：右相机内参
- right_distortion：右相机畸变系数
- size：单边相机的图片分辨率
- R：旋转矩阵
- T：平移矩阵
- 返回值：
- R1, R2：R1-输出矩阵，第一个摄像机的校正变换矩阵（旋转变换）；R2-输出矩阵，第二个摄像机的校正变换矩阵（旋转变换）
- P1, P2：P1-输出矩阵，第一个摄像机在新坐标系下的投影矩阵；P2-输出矩阵，第二个摄像机在新坐标系下的投影矩阵
立体匹配
import numpy as np
import cv2
import random
import math
capture = cv2.VideoCapture("./car.avi")
WIN_NAME = 'Deep disp'
cv2.namedWindow(WIN_NAME, cv2.WINDOW_AUTOSIZE)
fps = 0.0
ret, frame = capture.read()
while ret:
t1 = time.time()
ret, frame = capture.read()
frame1 = frame[0:480, 0:640]
frame2 = frame[0:480, 640:1280]
imgL = cv2.cvtColor(frame1, cv2.COLOR_BGR2GRAY)
imgR = cv2.cvtColor(frame2, cv2.COLOR_BGR2GRAY)
img1_rectified = cv2.remap(imgL, left_map1, left_map2, cv2.INTER_LINEAR)
img2_rectified = cv2.remap(imgR, right_map1, right_map2, cv2.INTER_LINEAR)
imageL = cv2.cvtColor(img1_rectified, cv2.COLOR_GRAY2BGR)
imageR = cv2.cvtColor(img2_rectified, cv2.COLOR_GRAY2BGR)
blockSize = 8
img_channels = 3
stereo = cv2.StereoSGBM_create(minDisparity=1,
numDisparities=64,
blockSize=blockSize,
P1=8 * img_channels * blockSize * blockSize,
P2=32 * img_channels * blockSize * blockSize,
disp12MaxDiff=-1,
preFilterCap=1,
uniquenessRatio=10,
speckleWindowSize=100,
speckleRange=100,
mode=cv2.STEREO_SGBM_MODE_HH)
disparity = stereo.compute(img1_rectified, img2_rectified)
disp = cv2.normalize(disparity, disparity, alpha=0, beta=255, norm_type=cv2.NORM_MINMAX, dtype=cv2.CV_8U)
dis_color = disparity
dis_color = cv2.normalize(dis_color, None, alpha=0, beta=255, norm_type=cv2.NORM_MINMAX, dtype=cv2.CV_8U)
dis_color = cv2.applyColorMap(dis_color, 2)
threeD = cv2.reprojectImageTo3D(disparity, Q, handleMissingValues=True)
threeD = threeD * 16
cv2.setMouseCallback("depth", onmouse_pick_points, threeD)
fps = (fps + (1. / (time.time() - t1))) / 2
frame = cv2.putText(frame, "fps= %.2f" % (fps), (0, 40), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
cv2.imshow("depth", dis_color)
cv2.imshow("left", frame1)
cv2.imshow(WIN_NAME, disp)
if cv2.waitKey(20) & 0xff == ord('q'):
break
capture.release()
cv2.destroyAllWindows()
img1_rectified = cv2.remap(imgL, left_map1, left_map2, cv2.INTER_LINEAR)：重映射，即把一幅图像内的像素点放置到另外一幅图像内的指定位置，俗称”拼接” 我们可以通过cv.remap()函数来将img2映射到img1对应位置上并合成
cv2.StereoSGBM_create()函数为opencv集成的算法；我们只需关注blockSize。 使用方法为：
其中，调小 numDisparities会降低精度，但提高速度。注意：numDisparities需能被16整除mode可以设置为STEREO_SGBM_MODE_SGBM_3WAY,STEREO_SGBM_MODE_HH,STEREO_SGBM_MODE_SGBM,STEREO_SGBM_MODE_HH4四种模式，它们的精度和速度呈反比，可根据情况来选择不同的模式.STEREO_SGBM_MODE_HH4的速度最快，STEREO_SGBM_MODE_HH的精度最好
效果
1.原图像
; 2.深度图
3.代码链接
https://github.com/yzfzzz/Stereo-Detection
Original: https://blog.csdn.net/henghuizan2771/article/details/126463140
Author: 什么都只会一点
Title: 【双目视觉】 SGBM算法应用（Python版）
原创文章受到原创版权保护。转载请注明出处：https://www.johngo689.com/646439/
转载文章受原作者版权保护。转载请注明原作者出处！