相關(guān)鏈接
1. YOLOV7 + 單目測(cè)距（python）
2. YOLOV5 + 單目跟蹤（python）
3. YOLOV7 + 單目跟蹤（python）
4. YOLOV5 + 雙目測(cè)距（python）
5. YOLOV7 + 雙目測(cè)距（python）
6. 具體實(shí)現(xiàn)效果已在Bilibili發(fā)布，點(diǎn)擊跳轉(zhuǎn)
本篇博文工程源碼下載
鏈接1：https://download.csdn.net/download/qq_45077760/87708260
鏈接2：https://github.com/up-up-up-up/yolov5_Monocular_ranging
更多有關(guān)單目（尺寸測(cè)量，跟蹤、碰撞檢測(cè)等）的文章請(qǐng)見：https://blog.csdn.net/qq_45077760/category_12312107.html文章來源地址http://www.zghlxwxcb.cn/news/detail-453784.html
1. 相關(guān)配置
系統(tǒng)：win 10
YOLO版本：yolov5 6.1
拍攝視頻設(shè)備：安卓手機(jī)
電腦顯卡：NVIDIA 2080Ti（CPU也可以跑，GPU只是起到加速推理效果）
2. 測(cè)距原理
單目測(cè)距原理相較于雙目十分簡(jiǎn)單，無需進(jìn)行立體匹配，僅需利用下邊公式線性轉(zhuǎn)換即可：
D = (F*W)/P
其中D是目標(biāo)到攝像機(jī)的距離, Ｆ是攝像機(jī)焦距（焦距需要自己進(jìn)行標(biāo)定獲?。? W是目標(biāo)的寬度或者高度（行人檢測(cè)一般以人的身高為基準(zhǔn)）, P是指目標(biāo)在圖像中所占據(jù)的像素
了解基本原理后，下邊就進(jìn)行實(shí)操階段
3. 相機(jī)標(biāo)定
3.1：標(biāo)定方法1
可以參考張學(xué)友標(biāo)定法獲取相機(jī)的焦距
3.2：標(biāo)定方法2
直接使用代碼獲得焦距，需要提前拍攝一個(gè)矩形物體，拍攝時(shí)候相機(jī)固定，距離被拍攝物體自行設(shè)定，并一直保持此距離，背景為純色，不要出現(xiàn)雜物；最后將拍攝的視頻用以下代碼檢測(cè)：
import cv2
win_width = 1920
win_height = 1080
mid_width = int(win_width / 2)
mid_height = int(win_height / 2)
foc = 1990.0 # 根據(jù)教程調(diào)試相機(jī)焦距
real_wid = 9.05 # A4紙橫著的時(shí)候的寬度，視頻拍攝A4紙要橫拍，鏡頭橫，A4紙也橫
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) # 掃描不到紙張輪廓時(shí)，要更改閾值，直到方框緊密框住紙張
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) # 查看所檢測(cè)到的輪框
for c in contours:
if cv2.contourArea(c) < 1000: # 對(duì)于矩形區(qū)域，只顯示大于給定閾值的輪廓，所以一些微小的變化不會(huì)顯示。對(duì)于光照不變和噪聲低的攝像頭可不設(shè)定輪廓最小尺寸的閾值
continue
x, y, w, h = cv2.boundingRect(c) # 該函數(shù)計(jì)算矩形的邊界框
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: # 按退出鍵esc關(guān)閉窗口
break
cv2.destroyAllWindows()
反復(fù)調(diào)節(jié) ret, binary = cv2.threshold(gray, 140, 200, 60)這一行里邊的三個(gè)參數(shù)，直到線條緊緊包裹住你所拍攝視頻的物體，然后調(diào)整相機(jī)焦距直到左上角距離和你拍攝視頻時(shí)相機(jī)到物體的距離接近為止
然后將相機(jī)焦距寫進(jìn)測(cè)距代碼distance.py文件里，這里行人用高度表示，根據(jù)公式 D = (F*W)/P，知道相機(jī)焦距F、行人的高度66.9（單位英寸→170cm/2.54）、像素點(diǎn)距離 h，即可求出相機(jī)到物體距離D。 這里用到h-2是因?yàn)榭虻纳舷逻吔缦袼攸c(diǎn)不接觸物體
foc = 1990.0 # 鏡頭焦距
real_hight_person = 66.9 # 行人高度
real_hight_car = 57.08 # 轎車高度
# 自定義函數(shù)，單目測(cè)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
4. 相機(jī)測(cè)距
4.1 測(cè)距添加
主要是把測(cè)距部分加在了畫框附近，首先提取邊框的像素點(diǎn)坐標(biāo)，然后計(jì)算邊框像素點(diǎn)高度，在根據(jù) 公式 D = (F*W)/P 計(jì)算目標(biāo)距離
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]) #獲取四個(gè)邊框坐標(biāo)
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 整數(shù)類 1111111111
label = None if hide_labels else (
names[c] if hide_conf else f'{names[c]} {conf:.2f}') # 111
dis_m = person_distance(h) # 調(diào)用函數(shù)，計(jì)算行人實(shí)際高度
label += f' {dis_m}m' # 將行人距離顯示寫在標(biāo)簽后
txt = '{0}'.format(label)
annotator.box_label(xyxy, txt, color=colors(c, True))
if names[int(cls)] == "car":
c = int(cls) # integer class 整數(shù)類 1111111111
label = None if hide_labels else (
names[c] if hide_conf else f'{names[c]} {conf:.2f}') # 111
dis_m = car_distance(h) # 調(diào)用函數(shù)，計(jì)算汽車實(shí)際高度
label += f' {dis_m}m' # 將汽車距離顯示寫在標(biāo)簽后
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 細(xì)節(jié)修改（可忽略）
到上述步驟就已經(jīng)實(shí)現(xiàn)了單目測(cè)距過程，下邊是一些小細(xì)節(jié)修改，可以不看
為了實(shí)時(shí)顯示畫面，對(duì)運(yùn)行的py文件點(diǎn)擊編輯配置，在形參那里輸入–view-img --save-txt
但實(shí)時(shí)顯示畫面太大，我們對(duì)顯示部分做了修改，這部分也可以不要，具體是把代碼
if view_img:
cv2.imshow(str(p), im0)
cv2.waitKey(1) # 1 millisecond
替換成
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 主代碼
# 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 # webcam
img.jpg # image
vid.mp4 # video
path/ # directory
path/*.jpg # glob
'https://youtu.be/Zgi9g1ksQHc' # YouTube
'rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP stream
Usage - formats:
$ python path/to/detect.py --weights yolov5s.pt # PyTorch
yolov5s.torchscript # TorchScript
yolov5s.onnx # ONNX Runtime or OpenCV DNN with --dnn
yolov5s.xml # OpenVINO
yolov5s.engine # TensorRT
yolov5s.mlmodel # CoreML (MacOS-only)
yolov5s_saved_model # TensorFlow SavedModel
yolov5s.pb # TensorFlow GraphDef
yolov5s.tflite # TensorFlow Lite
yolov5s_edgetpu.tflite # TensorFlow Edge TPU
"""
import argparse
import os
import sys
from pathlib import Path
import cv2
import torch
import torch.backends.cudnn as cudnn
FILE = 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())) # relative
from 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 webcam
data=ROOT / 'data/coco128.yaml', # dataset.yaml path
imgsz=(640, 640), # inference size (height, width)
conf_thres=0.25, # confidence threshold
iou_thres=0.45, # NMS IOU threshold
max_det=1000, # maximum detections per image
device='', # cuda device, i.e. 0 or 0,1,2,3 or cpu
view_img=False, # show results
save_txt=False, # save results to *.txt
save_conf=False, # save confidences in --save-txt labels
save_crop=False, # save cropped prediction boxes
nosave=False, # do not save images/videos
classes=None, # filter by class: --class 0, or --class 0 2 3
agnostic_nms=False, # class-agnostic NMS
augment=False, # augmented inference
visualize=False, # visualize features
update=False, # update all models
project=ROOT / 'runs/detect', # save results to project/name
name='exp', # save results to project/name
exist_ok=False, # existing project/name ok, do not increment
line_thickness=3, # bounding box thickness (pixels)
hide_labels=False, # hide labels
hide_conf=False, # hide confidences
half=False, # use FP16 half-precision inference
dnn=False, # use OpenCV DNN for ONNX inference
):
source = str(source)
save_img = not nosave and not source.endswith('.txt') # save inference images
is_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
# Directories
save_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 model
device = 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.engine
imgsz = check_img_size(imgsz, s=stride) # check image size
# Half
half &= (pt or jit or onnx or engine) and device.type != 'cpu' # FP16 supported on limited backends with CUDA
if pt or jit:
model.model.half() if half else model.model.float()
# Dataloader
if webcam:
view_img = check_imshow()
cudnn.benchmark = True # set True to speed up constant image size inference
dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt)
bs = len(dataset) # batch_size
else:
dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt)
bs = 1 # batch_size
vid_path, vid_writer = [None] * bs, [None] * bs
# Run inference
model.warmup(imgsz=(1 if pt else bs, 3, *imgsz), half=half) # warmup
dt, seen = [0.0, 0.0, 0.0], 0
for 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 fp16/32
im /= 255 # 0 - 255 to 0.0 - 1.0
if len(im.shape) == 3:
im = im[None] # expand for batch dim
t2 = time_sync()
dt[0] += t2 - t1
# Inference
visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
pred = model(im, augment=augment, visualize=visualize)
t3 = time_sync()
dt[1] += t3 - t2
# NMS
pred = 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 predictions
for i, det in enumerate(pred): # per image
seen += 1
if webcam: # batch_size >= 1
p, im0, frame = path[i], im0s[i].copy(), dataset.count
s += f'{i}: '
else:
p, im0, frame = path, im0s.copy(), getattr(dataset, 'frame', 0)
p = Path(p) # to Path
save_path = str(save_dir / p.name) # im.jpg
txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}') # im.txt
s += '%gx%g ' % im.shape[2:] # print string
gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh
imc = im0.copy() if save_crop else im0 # for save_crop
annotator = Annotator(im0, line_width=line_thickness, example=str(names))
if len(det):
# Rescale boxes from img_size to im0 size
det[:, :4] = scale_coords(im.shape[2:], det[:, :4], im0.shape).round()
# Print results
for c in det[:, -1].unique():
n = (det[:, -1] == c).sum() # detections per class
s += f"{n} {names[int(c)]}{'s' * (n > 1)}, " # add to string
# Write results
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])
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 整數(shù)類 1111111111
label = None if hide_labels else (
names[c] if hide_conf else f'{names[c]} {conf:.2f}') # 111
dis_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 整數(shù)類 1111111111
label = None if hide_labels else (
names[c] if hide_conf else f'{names[c]} {conf:.2f}') # 111
dis_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 results
im0 = 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 video
vid_path[i] = save_path
if isinstance(vid_writer[i], cv2.VideoWriter):
vid_writer[i].release() # release previous video writer
if vid_cap: # video
fps = 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: # stream
fps, w, h = 30, im0.shape[1], im0.shape[0]
save_path = str(Path(save_path).with_suffix('.mp4')) # force *.mp4 suffix on results videos
vid_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 results
t = tuple(x / seen * 1E3 for x in dt) # speeds per image
LOGGER.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 # expand
print_args(FILE.stem, opt)
return opt
def main(opt):
check_requirements(exclude=('tensorboard', 'thop'))
run(**vars(opt))
if __name__ == "__main__":
opt = parse_opt()
main(opt)
5. 實(shí)驗(yàn)效果
實(shí)驗(yàn)效果如下
文章來源：http://www.zghlxwxcb.cn/news/detail-453784.html
更多有關(guān)單目（尺寸測(cè)量，跟蹤、碰撞檢測(cè)等）的文章請(qǐng)見：https://blog.csdn.net/qq_45077760/category_12312107.html
到了這里，關(guān)于YOLOv5+單目測(cè)距（python）的文章就介紹完了。如果您還想了解更多內(nèi)容，請(qǐng)?jiān)谟疑辖撬阉鱐OY模板網(wǎng)以前的文章或繼續(xù)瀏覽下面的相關(guān)文章，希望大家以后多多支持TOY模板網(wǎng)！
