赞
踩
系统:win 10
YOLO版本:yolov5 6.1
拍摄视频设备:安卓手机
电脑显卡:NVIDIA 2080Ti(CPU也可以跑,GPU只是起到加速推理效果)
单目测距原理相较于双目十分简单,无需进行立体匹配,仅需利用下边公式线性转换即可:
D = (F\*W)/P
其中D是目标到摄像机的距离, F是摄像机焦距(焦距需要自己进行标定获取), W是目标的宽度或者高度(行人检测一般以人的身高为基准), P是指目标在图像中所占据的像素
了解基本原理后,下边就进行实操阶段
可以参考张友正标定法获取相机的焦距
直接使用代码获得焦距,需要提前拍摄一个矩形物体,拍摄时候相机固定,距离被拍摄物体自行设定,并一直保持此距离,背景为纯色,不要出现杂物;最后将拍摄的视频用以下代码检测:
import cv2 win_width = 1920 win_height = 1080 mid_width = int(win_width / 2) mid_height = int(win_height / 2) foc = 1990.0 # 根据教程调试相机焦距 real_wid = 9.05 # A4纸横着的时候的宽度,视频拍摄A4纸要横拍,镜头横,A4纸也横 font = cv2.FONT_HERSHEY_SIMPLEX w_ok = 1 capture = cv2.VideoCapture('5.mp4') capture.set(3, win_width) capture.set(4, win_height) while (True): ret, frame = capture.read() # frame = cv2.flip(frame, 1) if ret == False: break gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY) gray = cv2.GaussianBlur(gray, (5, 5), 0) ret, binary = cv2.threshold(gray, 140, 200, 60) # 扫描不到纸张轮廓时,要更改阈值,直到方框紧密框住纸张 kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3, 3)) binary = cv2.dilate(binary, kernel, iterations=2) contours, hierarchy = cv2.findContours(binary, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE) # cv2.drawContours(frame, contours, -1, (0, 255, 0), 2) # 查看所检测到的轮框 for c in contours: if cv2.contourArea(c) < 1000: # 对于矩形区域,只显示大于给定阈值的轮廓,所以一些微小的变化不会显示。对于光照不变和噪声低的摄像头可不设定轮廓最小尺寸的阈值 continue x, y, w, h = cv2.boundingRect(c) # 该函数计算矩形的边界框 if x > mid_width or y > mid_height: continue if (x + w) < mid_width or (y + h) < mid_height: continue if h > w: continue if x == 0 or y == 0: continue if x == win_width or y == win_height: continue w_ok = w cv2.rectangle(frame, (x + 1, y + 1), (x + w_ok - 1, y + h - 1), (0, 255, 0), 2) dis_inch = (real_wid \* foc) / (w_ok - 2) dis_cm = dis_inch \* 2.54 # os.system("cls") # print("Distance : ", dis\_cm, "cm") frame = cv2.putText(frame, "%.2fcm" % (dis_cm), (5, 25), font, 0.8, (0, 255, 0), 2) frame = cv2.putText(frame, "+", (mid_width, mid_height), font, 1.0, (0, 255, 0), 2) cv2.namedWindow('res', 0) cv2.namedWindow('gray', 0) cv2.resizeWindow('res', win_width, win_height) cv2.resizeWindow('gray', win_width, win_height) cv2.imshow('res', frame) cv2.imshow('gray', binary) c = cv2.waitKey(40) if c == 27: # 按退出键esc关闭窗口 break cv2.destroyAllWindows()
反复调节 ret, binary = cv2.threshold(gray, 140, 200, 60)这一行里边的三个参数,直到线条紧紧包裹住你所拍摄视频的物体,然后调整相机焦距直到左上角距离和你拍摄视频时相机到物体的距离接近为止
然后将相机焦距写进测距代码distance.py文件里,这里行人用高度表示,根据公式 D = (F*W)/P,知道相机焦距F、行人的高度66.9(单位英寸→170cm/2.54)、像素点距离 h,即可求出相机到物体距离D。 这里用到h-2是因为框的上下边界像素点不接触物体
foc = 1990.0 # 镜头焦距 real_hight_person = 66.9 # 行人高度 real_hight_car = 57.08 # 轿车高度 # 自定义函数,单目测距 def person\_distance(h): dis_inch = (real_hight_person \* foc) / (h - 2) dis_cm = dis_inch \* 2.54 dis_cm = int(dis_cm) dis_m = dis_cm/100 return dis_m def car\_distance(h): dis_inch = (real_hight_car \* foc) / (h - 2) dis_cm = dis_inch \* 2.54 dis_cm = int(dis_cm) dis_m = dis_cm/100 return dis_m
主要是把测距部分加在了画框附近,首先提取边框的像素点坐标,然后计算边框像素点高度,在根据 公式 D = (F*W)/P 计算目标距离
for \*xyxy, conf, cls in reversed(det): if save_txt: # Write to file xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh line = (cls, \*xywh, conf) if save_conf else (cls, \*xywh) # label format with open(txt_path + '.txt', 'a') as f: f.write(('%g ' \* len(line)).rstrip() % line + '\n') if save_img or save_crop or view_img: # Add bbox to image x1 = int(xyxy[0]) #获取四个边框坐标 y1 = int(xyxy[1]) x2 = int(xyxy[2]) y2 = int(xyxy[3]) h = y2-y1 if names[int(cls)] == "person": c = int(cls) # integer class 整数类 1111111111 label = None if hide_labels else ( names[c] if hide_conf else f'{names[c]} {conf:.2f}') # 111 dis_m = person_distance(h) # 调用函数,计算行人实际高度 label += f' {dis\_m}m' # 将行人距离显示写在标签后 txt = '{0}'.format(label) annotator.box_label(xyxy, txt, color=colors(c, True)) if names[int(cls)] == "car": c = int(cls) # integer class 整数类 1111111111 label = None if hide_labels else ( names[c] if hide_conf else f'{names[c]} {conf:.2f}') # 111 dis_m = car_distance(h) # 调用函数,计算汽车实际高度 label += f' {dis\_m}m' # 将汽车距离显示写在标签后 txt = '{0}'.format(label) annotator.box_label(xyxy, txt, color=colors(c, True)) if save_crop: save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True)
到上述步骤就已经实现了单目测距过程,下边是一些小细节修改,可以不看
为了实时显示画面,对运行的py文件点击编辑配置,在形参那里输入–view-img --save-txt
但实时显示画面太大,我们对显示部分做了修改,这部分也可以不要,具体是把代码
if view_img:
cv2.imshow(str(p), im0)
cv2.waitKey(1) # 1 millisecond
替换成
if view_img:
cv2.namedWindow("Webcam", cv2.WINDOW_NORMAL)
cv2.resizeWindow("Webcam", 1280, 720)
cv2.moveWindow("Webcam", 0, 100)
cv2.imshow("Webcam", im0)
cv2.waitKey(1)
# YOLOv5 声明:本文内容由网友自发贡献,不代表【wpsshop博客】立场,版权归原作者所有,本站不承担相应法律责任。如您发现有侵权的内容,请联系我们。转载请注明出处:https://www.wpsshop.cn/w/小舞很执着/article/detail/818297
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。