《实时畸变校正》

本文主要是介绍《实时畸变校正》，希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！

摄像头畸变

​ 由于摄像头制造的不足以及成像过程中的噪声影响，摄像头成像往往不满足针孔模型，这种成像模型称为非线性模型。非线性模型中畸变主要有三种，包括径向畸变、切向畸变和薄棱镜畸变。假设理想的成像点坐标 ，畸变后的实际成像点坐标 ，则非线性畸变模型如下
$$\{\begin{array}{l}{x}_d=x_u+{\delta }_x\\ y_d=y_u+{\delta }_y\end{array}$$

• a) 径向畸变

图像的径向畸变是指像点相对理想位置发生向内或者向外的偏移，即像点在径向上出现误差。
$$\{\begin{array}{l}{\delta }_x=x_u(k_1{r}_u^2+k_2{r}_u^4+k_3{r}_u^6+...)\\ {\delta }_y=y_u(k_1{r}_u^2+k_2{r}_u^4+k_3{r}_u^6+...)\end{array}$$

式中, $r_u^2=x_u^2+y_u^2$， $k_1,k_2,k_3$为径向畸变系数。

• b) 切向畸变

图像的切向畸变是指由于光学系统的光学镜头装配产生误差，光轴不可能完全共线，即像点在切向上出现了偏差。
$$\{\begin{array}{l}{\delta }_x=p_1(3x_u^2+y_u^2)+2p_2{x}_u{y}_u\\ {\delta }_y=p_2(3y_u^2+x_u^2)+2p_1{x}_u{y}_u\end{array}$$
式中， $p_1,p_2$为切向畸变系数。

• c) 薄棱镜畸变

图像的薄棱镜畸变是指由光学镜头制造误差和成像敏感阵列制造误差引起的图像变形。
$$\{\begin{array}{l}{\delta }_x=s_1(x_u^2+y_u^2)\\ {\delta }_y=s_1(x_u^2+y_u^2)\end{array}$$
式中， $s_1,s_2$为薄棱镜畸变系数。

• 畸变参数

  • 径向畸变 $ k_1, k_2, k_3$

  • 切向畸变 $ p_1, p_2$

  • 薄棱镜畸变 $s_1,s_2$

• (一般考虑OpenCV前五个参数, $k_1,k_2,p_1,p_2,k_3$)镜头畸变中径向畸变（主要是前两阶的）和切向畸变影响较

大，占畸变的95%，而薄棱镜畸变会造成额外的径向畸变和切向畸变，影响较小。一般情况下，只需考虑径向畸变和切向畸变，薄棱镜畸往往忽略不计。

手眼标定

• 视频取流
• 按’S’交互保存标定板图片
• 标定图片到一定数量后，按’C’标定
• 按’Q’退出

def grab_web_cam(rtsp, path_img):VideoCapture = cv2.VideoCapture(rtsp)cv2.namedWindow(wnd_name, cv2.WINDOW_NORMAL)if not VideoCapture.isOpened():print("Error open video!")exit()save_num = 0while VideoCapture.isOpened():ret, frame = VideoCapture.read()if not ret:breakk = show_image("frame", frame, 1)if cv2.waitKey(1) & 0xFF == ord('q'):breakelif cv2.waitKey(1) & 0xFF == ord("s"):cv2.imencode(".jpg", frame)[1].tofile(os.path.join(path_img, "img_%04d.jpg" % save_num))save_num += 1print("save image:[%d]" % save_num)elif cv2.waitKey(1) & 0xFF == ord("c"):calib.calib(path_img, path_cfg)VideoCapture.release()

实时畸变校正

cv2.undistort & cv2.initUndistortRectifyMap + cv2.remap

• mtx, dist, new_mtx分别为内参数，畸变系数，优化后的畸变系数

• (1) 直接校正

  frame_rect = cv2.undistort(frame, mtx, dist, None, new_mtx)
  

• (2) 先计算映射关系，再校正

  mapx, mapy = cv2.initUndistortRectifyMap(mtx, dist, None, new_mtx, (int(frame_width), int(frame_height)), 5)
  img_dst = cv2.remap(frame, mapx, mapy, interpolation=cv2.INTER_NEAREST, dst=None,borderMode=cv2.BORDER_CONSTANT, borderValue=(0, 0, 0))
  

• 单独使用几次时，差别不大
• 当多次图片畸变校正时，建议使用一次initUndistortRectifyMap，获取映射矩阵mapx和mapy后，作为remap输入，再使用多次的remap校正
• 实时畸变校正，帧率差距明显

显示区域

• newcameramtx, roi = cv2.getOptimalNewCameraMatrix(mtx, dist, (img_gray.shape[1], img_gray.shape[0]), alpha, (width, height))

  • 优化相机内参（camera matrix）,可选，提高精度
  • alpha= 1, 所有像素都保留，有黑色像素混入
  • alpha=0, 尽可能裁剪不想要的像素，都是有效，这是个scale

• 边界填充

  • 畸变导致矫正后的图像边缘空缺

  • 可以通过remap里的borderMode来设置不同的填充效果

• 有效区域裁剪

  • getOptimalNewCameraMatrix计算ROI
  • 矫正后的区域裁剪

Error:[h264 @ 000001bf04177660] error while decoding MB 11 84, bytestream -17

• RTSP取流后，偶尔报错：

  [h264 @ 000001bf04177660] error while decoding MB 11 84, bytestream -17
  

• 问题分析：H264除了使用帧内压缩之外，采用了独特的I帧、P帧和B帧策略来实现连续帧之间的压缩。在解码的时候如果不能有H264压缩时候需要的帧，就不能正确解码

• 解决思路

  • （1）检查网络摄像头读取，失败后重启

        while (VideoCapture.isOpened()):ret, frame = VideoCapture.read()if not ret:VideoCapture = cv2.VideoCapture(rtsp)print("lost, have to reinitialization!")  continue
    

  • （2）取图和校正分开处理，多线程或多进程

多线程实时实时校正

• 取图
• 校正+显示

import cv2, os, time
import numpy as np
import threading, queuedef read_campara(path):with np.load(path) as X:data = [X[i] for i in ('mtx', 'dist', 'new_mtx', 'roi')]mtx, dist, new_mtx, roi = datareturn mtx, dist, new_mtx, roidef show(fps_enable = True, roi_enable=True):x, y, w, h = roicv2.namedWindow('undistort', cv2.WINDOW_NORMAL)while True:if not q.empty():frame = q.get()if fps_enable:timer = cv2.getTickCount()frame_rect = cv2.remap(frame, mapx, mapy, interpolation=cv2.INTER_NEAREST, dst=None,borderMode=cv2.BORDER_CONSTANT, borderValue=(0, 0, 0))if fps_enable:fps = cv2.getTickFrequency() / (cv2.getTickCount() - timer)print("FPS:{}".format(fps))if roi_enable:rect_roi = frame_rect[y:y + h, x:x + w]frame_roi = frame[y:y + h, x:x + w]img_stack = np.hstack([frame_roi, rect_roi])else:img_stack = np.hstack([frame, frame_rect])  # srcif fps_enable:cv2.putText(img_stack, "FPS : " + str(int(fps)), (50, 50), cv2.FONT_HERSHEY_SIMPLEX, 2, (0, 0, 255), 3)cv2.imshow('undistort', img_stack)if cv2.waitKey(1) & 0xFF == ord('q'):breakdef undistort_show_threads(rtsp, path_cfg, interval = 3):VideoCapture = cv2.VideoCapture(rtsp)while (VideoCapture.isOpened()):ret, frame = VideoCapture.read()if not ret:VideoCapture = cv2.VideoCapture(rtsp)print("lost, have to reinitialization!")  continuepos = VideoCapture.get(cv2.CAP_PROP_POS_FRAMES)if pos % interval != 0:continueq.put(frame)VideoCapture.release()if __name__ == "__main__":path_cfg = r"./cfg/cam2.npz"rtsp = 'rtsp://admin:123456@192.168.*.*'frame_width = 2560frame_height = 1440mtx, dist, new_mtx, roi = read_campara(path_cfg)mapx, mapy = cv2.initUndistortRectifyMap(mtx, dist, None, new_mtx, (int(frame_width), int(frame_height)), 5)q = queue.Queue()t1 = threading.Thread(target=undistort_show_threads, args=(rtsp, path_cfg))t2 = threading.Thread(target = show)t1.start()t2.start()t1.join()t2.join()

多进程实时校正

• 取图
• 校正+显示

import cv2, multiprocessing
import numpy as npdef read_campara(path):with np.load(path) as X:data = [X[i] for i in ('mtx', 'dist', 'new_mtx', 'roi')]mtx, dist, new_mtx, roi = datareturn mtx, dist, new_mtx, roidef show(queue, roi, mapx, mapy, fps_enable = True, roi_enable = True):x, y, w, h = roicv2.namedWindow('undistort', cv2.WINDOW_NORMAL)while True:if not queue.empty():frame = queue.get()if fps_enable:timer = cv2.getTickCount()frame_rect = cv2.remap(frame, mapx, mapy, interpolation=cv2.INTER_NEAREST, dst=None,borderMode=cv2.BORDER_CONSTANT, borderValue=(0, 0, 0))if fps_enable:fps = cv2.getTickFrequency() / (cv2.getTickCount() - timer)print("FPS:{}".format(fps))if roi_enable:rect_roi = frame_rect[y:y + h, x:x + w]frame_roi = frame[y:y + h, x:x + w]img_stack = np.hstack([frame_roi, rect_roi])else:img_stack = np.hstack([frame, frame_rect])  # srcif fps_enable:cv2.putText(img_stack, "FPS : " + str(int(fps)), (50, 50), cv2.FONT_HERSHEY_SIMPLEX, 2, (0, 0, 255), 3)cv2.imshow('undistort', img_stack)if cv2.waitKey(1) & 0xFF == ord('q'):breakdef undistort_show_processes(queue, rtsp, path_cfg, interval = 3):VideoCapture = cv2.VideoCapture(rtsp)while (VideoCapture.isOpened()):ret, frame = VideoCapture.read()if not ret:VideoCapture = cv2.VideoCapture(rtsp)print("lost, have to reinitialization!")  continuepos = VideoCapture.get(cv2.CAP_PROP_POS_FRAMES)if pos % interval != 0:continuequeue.put(frame)VideoCapture.release()if __name__ == "__main__":path_cfg = r"./cfg/cam2.npz"rtsp = 'rtsp://admin:123455@192.168.*.*'frame_width = 2560frame_height = 1440mtx, dist, new_mtx, roi = read_campara(path_cfg)mapx, mapy = cv2.initUndistortRectifyMap(mtx, dist, None, new_mtx, (int(frame_width), int(frame_height)), 5)multiprocessing.set_start_method(method='spawn')  # initqueue = multiprocessing.Queue(maxsize=4)processes = []processes.append(multiprocessing.Process(target = undistort_show_processes, args=(queue, rtsp, path_cfg)))processes.append(multiprocessing.Process(target = show, args = (queue, roi, mapx, mapy)))for process in processes:process.daemon = Trueprocess.start()for process in processes:process.join()

参考链接

opencv read error:[h264 @ 0x8f915e0] error while decoding MB 53 20, bytestream -7

这篇关于《实时畸变校正》的文章就介绍到这儿，希望我们推荐的文章对编程师们有所帮助！

---