相关链接
1. YOLOV7 + 单目测距（python）
2. YOLOV5 + 单目跟踪（python）
3. YOLOV7 + 单目跟踪（python）
4. YOLOV5 + 双目测距（python）
5. YOLOV7 + 双目测距（python）
6. 具体实现效果已在Bilibili发布，点击跳转

本篇博文工程源码下载
链接1：https://download.csdn.net/download/qq_45077760/87708260
链接2：https://github.com/up-up-up-up/yolov5_Monocular_ranging

更多有关单目（尺寸测量，跟踪、碰撞检测等）的文章请见：https://blog.csdn.net/qq_45077760/category_12312107.html

1. 相关配置

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）

2. 测距原理

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

3. 相机标定

3.1：标定方法1

可以参考张学友标定法获取相机的焦距

3.2：标定方法2

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 cv2win_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 = 1capture = 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:breakgray = 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continuex, 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:continueif (x + w) < mid_width or (y + h) < mid_height:continueif h > w:continueif x == 0 or y == 0:continueif x == win_width or y == win_height:continuew_ok = wcv2.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breakcv2.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 * 2.54dis_cm = int(dis_cm)dis_m = dis_cm/100return dis_mdef car_distance(h):dis_inch = (real_hight_car * foc) / (h - 2)dis_cm = dis_inch * 2.54dis_cm = int(dis_cm)dis_m = dis_cm/100return dis_m

4. 相机测距

4.1 测距添加

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 filexywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()  # normalized xywhline = (cls, *xywh, conf) if save_conf else (cls, *xywh)  # label formatwith 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 imagex1 = 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-y1if names[int(cls)] == "person":c = int(cls)  # integer class  整数类 1111111111label = None if hide_labels else (names[c] if hide_conf else f'{names[c]} {conf:.2f}')  # 111dis_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 1111111111label = None if hide_labels else (names[c] if hide_conf else f'{names[c]} {conf:.2f}')  # 111dis_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)

4.2 细节修改（可忽略）

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)

4.3 主代码

# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
"""
Run inference on images, videos, directories, streams, etc.Usage - sources:$ python path/to/detect.py --weights yolov5s.pt --source 0              # webcamimg.jpg        # imagevid.mp4        # videopath/          # directorypath/*.jpg     # glob'https://youtu.be/Zgi9g1ksQHc'  # YouTube'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP streamUsage - formats:$ python path/to/detect.py --weights yolov5s.pt                 # PyTorchyolov5s.torchscript        # TorchScriptyolov5s.onnx               # ONNX Runtime or OpenCV DNN with --dnnyolov5s.xml                # OpenVINOyolov5s.engine             # TensorRTyolov5s.mlmodel            # CoreML (MacOS-only)yolov5s_saved_model        # TensorFlow SavedModelyolov5s.pb                 # TensorFlow GraphDefyolov5s.tflite             # TensorFlow Liteyolov5s_edgetpu.tflite     # TensorFlow Edge TPU
"""import argparse
import os
import sys
from pathlib import Pathimport cv2
import torch
import torch.backends.cudnn as cudnnFILE = Path(__file__).resolve()
ROOT = FILE.parents[0]  # YOLOv5 root directory
if str(ROOT) not in sys.path:sys.path.append(str(ROOT))  # add ROOT to PATH
ROOT = Path(os.path.relpath(ROOT, Path.cwd()))  # relativefrom models.common import DetectMultiBackend
from utils.datasets import IMG_FORMATS, VID_FORMATS, LoadImages, LoadStreams
from utils.general import (LOGGER, check_file, check_img_size, check_imshow, check_requirements, colorstr,increment_path, non_max_suppression, print_args, scale_coords, strip_optimizer, xyxy2xywh)
from utils.plots import Annotator, colors, save_one_box
from utils.torch_utils import select_device, time_sync
from distance import person_distance,car_distance@torch.no_grad()
def run(weights=ROOT / 'yolov5s.pt',  # model.pt path(s)source=ROOT / 'data/images',  # file/dir/URL/glob, 0 for webcamdata=ROOT / 'data/coco128.yaml',  # dataset.yaml pathimgsz=(640, 640),  # inference size (height, width)conf_thres=0.25,  # confidence thresholdiou_thres=0.45,  # NMS IOU thresholdmax_det=1000,  # maximum detections per imagedevice='',  # cuda device, i.e. 0 or 0,1,2,3 or cpuview_img=False,  # show resultssave_txt=False,  # save results to *.txtsave_conf=False,  # save confidences in --save-txt labelssave_crop=False,  # save cropped prediction boxesnosave=False,  # do not save images/videosclasses=None,  # filter by class: --class 0, or --class 0 2 3agnostic_nms=False,  # class-agnostic NMSaugment=False,  # augmented inferencevisualize=False,  # visualize featuresupdate=False,  # update all modelsproject=ROOT / 'runs/detect',  # save results to project/namename='exp',  # save results to project/nameexist_ok=False,  # existing project/name ok, do not incrementline_thickness=3,  # bounding box thickness (pixels)hide_labels=False,  # hide labelshide_conf=False,  # hide confidenceshalf=False,  # use FP16 half-precision inferencednn=False,  # use OpenCV DNN for ONNX inference):source = str(source)save_img = not nosave and not source.endswith('.txt')  # save inference imagesis_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))webcam = source.isnumeric() or source.endswith('.txt') or (is_url and not is_file)if is_url and is_file:source = check_file(source)  # download# Directoriessave_dir = increment_path(Path(project) / name, exist_ok=exist_ok)  # increment run(save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)  # make dir# Load modeldevice = select_device(device)model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data)stride, names, pt, jit, onnx, engine = model.stride, model.names, model.pt, model.jit, model.onnx, model.engineimgsz = check_img_size(imgsz, s=stride)  # check image size# Halfhalf &= (pt or jit or onnx or engine) and device.type != 'cpu'  # FP16 supported on limited backends with CUDAif pt or jit:model.model.half() if half else model.model.float()# Dataloaderif webcam:view_img = check_imshow()cudnn.benchmark = True  # set True to speed up constant image size inferencedataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt)bs = len(dataset)  # batch_sizeelse:dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt)bs = 1  # batch_sizevid_path, vid_writer = [None] * bs, [None] * bs# Run inferencemodel.warmup(imgsz=(1 if pt else bs, 3, *imgsz), half=half)  # warmupdt, seen = [0.0, 0.0, 0.0], 0for path, im, im0s, vid_cap, s in dataset:t1 = time_sync()im = torch.from_numpy(im).to(device)im = im.half() if half else im.float()  # uint8 to fp16/32im /= 255  # 0 - 255 to 0.0 - 1.0if len(im.shape) == 3:im = im[None]  # expand for batch dimt2 = time_sync()dt[0] += t2 - t1# Inferencevisualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else Falsepred = model(im, augment=augment, visualize=visualize)t3 = time_sync()dt[1] += t3 - t2# NMSpred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)dt[2] += time_sync() - t3# Second-stage classifier (optional)# pred = utils.general.apply_classifier(pred, classifier_model, im, im0s)# Process predictionsfor i, det in enumerate(pred):  # per imageseen += 1if webcam:  # batch_size >= 1p, im0, frame = path[i], im0s[i].copy(), dataset.counts += f'{i}: 'else:p, im0, frame = path, im0s.copy(), getattr(dataset, 'frame', 0)p = Path(p)  # to Pathsave_path = str(save_dir / p.name)  # im.jpgtxt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}')  # im.txts += '%gx%g ' % im.shape[2:]  # print stringgn = torch.tensor(im0.shape)[[1, 0, 1, 0]]  # normalization gain whwhimc = im0.copy() if save_crop else im0  # for save_cropannotator = Annotator(im0, line_width=line_thickness, example=str(names))if len(det):# Rescale boxes from img_size to im0 sizedet[:, :4] = scale_coords(im.shape[2:], det[:, :4], im0.shape).round()# Print resultsfor c in det[:, -1].unique():n = (det[:, -1] == c).sum()  # detections per classs += f"{n} {names[int(c)]}{'s' * (n > 1)}, "  # add to string# Write resultsfor *xyxy, conf, cls in reversed(det):if save_txt:  # Write to filexywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()  # normalized xywhline = (cls, *xywh, conf) if save_conf else (cls, *xywh)  # label formatwith 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 imagex1 = int(xyxy[0])y1 = int(xyxy[1])x2 = int(xyxy[2])y2 = int(xyxy[3])h = y2-y1if names[int(cls)] == "person":c = int(cls)  # integer class  整数类 1111111111label = None if hide_labels else (names[c] if hide_conf else f'{names[c]} {conf:.2f}')  # 111dis_m = person_distance(h)label += f'  {dis_m}m'txt = '{0}'.format(label)# annotator.box_label(xyxy, txt, color=(255, 0, 255))annotator.box_label(xyxy, txt, color=colors(c, True))if names[int(cls)] == "car":c = int(cls)  # integer class  整数类 1111111111label = None if hide_labels else (names[c] if hide_conf else f'{names[c]} {conf:.2f}')  # 111dis_m = car_distance(h)label += f'  {dis_m}m'txt = '{0}'.format(label)# annotator.box_label(xyxy, txt, color=(255, 0, 255))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)# Stream resultsim0 = annotator.result()'''if view_img:cv2.imshow(str(p), im0)cv2.waitKey(1)  # 1 millisecond'''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)# Save results (image with detections)if save_img:if dataset.mode == 'image':cv2.imwrite(save_path, im0)else:  # 'video' or 'stream'if vid_path[i] != save_path:  # new videovid_path[i] = save_pathif isinstance(vid_writer[i], cv2.VideoWriter):vid_writer[i].release()  # release previous video writerif vid_cap:  # videofps = vid_cap.get(cv2.CAP_PROP_FPS)w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))else:  # streamfps, w, h = 30, im0.shape[1], im0.shape[0]save_path = str(Path(save_path).with_suffix('.mp4'))  # force *.mp4 suffix on results videosvid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))vid_writer[i].write(im0)# Print time (inference-only)LOGGER.info(f'{s}Done. ({t3 - t2:.3f}s)')# Print resultst = tuple(x / seen * 1E3 for x in dt)  # speeds per imageLOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}' % t)if save_txt or save_img:s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}")if update:strip_optimizer(weights)  # update model (to fix SourceChangeWarning)def parse_opt():parser = argparse.ArgumentParser()parser.add_argument('--weights', nargs='+', type=str, default=ROOT / 'yolov5s.pt', help='model path(s)')parser.add_argument('--source', type=str, default=ROOT / 'data/images/1.mp4', help='file/dir/URL/glob, 0 for webcam')parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='(optional) dataset.yaml path')parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640], help='inference size h,w')parser.add_argument('--conf-thres', type=float, default=0.25, help='confidence threshold')parser.add_argument('--iou-thres', type=float, default=0.45, help='NMS IoU threshold')parser.add_argument('--max-det', type=int, default=1000, help='maximum detections per image')parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')parser.add_argument('--view-img', action='store_true', help='show results')parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')parser.add_argument('--save-crop', action='store_true', help='save cropped prediction boxes')parser.add_argument('--nosave', action='store_true', help='do not save images/videos')parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --classes 0, or --classes 0 2 3')parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS')parser.add_argument('--augment', action='store_true', help='augmented inference')parser.add_argument('--visualize', action='store_true', help='visualize features')parser.add_argument('--update', action='store_true', help='update all models')parser.add_argument('--project', default=ROOT / 'runs/detect', help='save results to project/name')parser.add_argument('--name', default='exp', help='save results to project/name')parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')parser.add_argument('--line-thickness', default=3, type=int, help='bounding box thickness (pixels)')parser.add_argument('--hide-labels', default=False, action='store_true', help='hide labels')parser.add_argument('--hide-conf', default=False, action='store_true', help='hide confidences')parser.add_argument('--half', action='store_true', help='use FP16 half-precision inference')parser.add_argument('--dnn', action='store_true', help='use OpenCV DNN for ONNX inference')opt = parser.parse_args()opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1  # expandprint_args(FILE.stem, opt)return optdef main(opt):check_requirements(exclude=('tensorboard', 'thop'))run(**vars(opt))if __name__ == "__main__":opt = parse_opt()main(opt)

5. 实验效果

实验效果如下

更多有关单目（尺寸测量，跟踪、碰撞检测等）的文章请见：https://blog.csdn.net/qq_45077760/category_12312107.html