YOLOV5 + 双目相机实现三维测距（新版本）

本文主要是对此篇文章做一些改进，以及解释读者在复现过程中遇到的问题，完整代码在文章末尾

1. 项目流程

1. YOLOv5检测目标并提取其中心像素点坐标
2. 双目相机经过系列操作将像素点坐标转为深度三维坐标
3. 根据三维坐标计算距离
4. 将深度信息画图显示

2. 测距原理

如果想了解双目测距原理，请移步该文章 双目三维测距（python）

3. 操作步骤和代码解析

下载 yolov5 6.1版本源码 ，之前用的是5.0源码，代码太旧出现了不少问题，故更新了一下，创建一个detect-01.py文件，文件里部分代码解析如下：

双目相机参数stereoconfig.py
双目相机标定误差越小越好，我这里误差为0.1，尽量使误差在0.2以下

import numpy as np
# 双目相机参数
class stereoCamera(object):
    def __init__(self):

        self.cam_matrix_left = np.array([[1101.89299, 0, 1119.89634],
                                         [0, 1100.75252, 636.75282],
                                         [0, 0, 1]])
        self.cam_matrix_right = np.array([[1091.11026, 0, 1117.16592],
                                          [0, 1090.53772, 633.28256],
                                          [0, 0, 1]])

        self.distortion_l = np.array([[-0.08369, 0.05367, -0.00138, -0.0009, 0]])
        self.distortion_r = np.array([[-0.09585, 0.07391, -0.00065, -0.00083, 0]])

        self.R = np.array([[1.0000, -0.000603116945856524, 0.00377055351856816],
                           [0.000608108737333211, 1.0000, -0.00132288199083992],
                           [-0.00376975166958581, 0.00132516525298933, 1.0000]])

        self.T = np.array([[-119.99423], [-0.22807], [0.18540]])
        self.baseline = 119.99423  

测距代码部分解析

这一部分我直接计算了目标检测框中心点的深度值，把中心点的深度值当作了距离。你也可以写个循环，计算平均值或者中位数，把他们当作深度值

if (accel_frame % fps_set == 0):
    t3 = time.time()  
    thread.join()
    points_3d = thread.get_result()
    t4 = time.time()  
    a = points_3d[int(y_0), int(x_0), 0] / 1000
    b = points_3d[int(y_0), int(x_0), 1] / 1000
    c = points_3d[int(y_0), int(x_0), 2] / 1000
    dis = ((a**2+b**2+c**2)**0.5)

主代码detect-01.py
加入了多线程处理，加快处理速度

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 stereo.dianyuntu_yolo import preprocess, undistortion, getRectifyTransform, draw_line, rectifyImage, \
    stereoMatchSGBM
from stereo import stereoconfig_040_2
from stereo.stereo import stereo_threading, MyThread

@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

    config = stereoconfig_040_2.stereoCamera()
    # 立体校正
    map1x, map1y, map2x, map2y, Q = getRectifyTransform(720, 1280, config)
    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)
################################################ start ##############################################
            thread = MyThread(stereo_threading, args=(config, im0, map1x, map1y, map2x, map2y, Q))
            thread.start()

            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 (0 < xyxy[2] < 1280):
                        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
                        x_center = (xyxy[0] + xyxy[2]) / 2
                        y_center = (xyxy[1] + xyxy[3]) / 2
                        x_0 = int(x_center)
                        y_0 = int(y_center)
                        if (0 < x_0 < 1280):
                            x1 = xyxy[0]
                            x2 = xyxy[2]
                            y1 = xyxy[1]
                            y2 = xyxy[3]
                            thread.join()
                            points_3d = thread.get_result()
                            a = points_3d[int(y_0), int(x_0), 0] / 1000
                            b = points_3d[int(y_0), int(x_0), 1] / 1000
                            c = points_3d[int(y_0), int(x_0), 2] / 1000
                            distance = ((a ** 2 + b ** 2 + c ** 2) ** 0.5)

                            if (distance != 0):  ## Add bbox to image
                                c = int(cls)  # integer class
                                label = None if hide_labels else (names[c] if hide_conf else f'{names[c]} {conf:.2f}')
                                annotator.box_label(xyxy, label, color=colors(c, True))
                                print('点 (%d, %d) 的 %s 距离左摄像头的相对距离为 %0.2f m' % (x_center, y_center, label, distance))
                                text_dis_avg = "dis:%0.2fm" % distance
                                # only put dis on frame
                                cv2.putText(im0, text_dis_avg, (int(x1 + (x2 - x1) + 5), int(y1 + 30)), cv2.FONT_ITALIC,
                                            1.2, (255, 255, 255), 3)
                        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.namedWindow("Webcam", cv2.WINDOW_NORMAL)
                cv2.resizeWindow("Webcam", 1280, 480)
                cv2.moveWindow("Webcam", 0, 100)
                cv2.imshow("Webcam", im0)
                cv2.waitKey(1)
                # cv2.imshow(str(p), im0)
                # cv2.waitKey(1)  # 1 millisecond

            # 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/a1.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)

执行detect-01.py，检测结果如下：

4. 实时检测

（1）如想要调用摄像头检测，直接把detect-01.py里的

parser.add_argument('--source', type=str, default=ROOT / 'data/images/a1.mp4', help='file/dir/URL/glob, 0 for webcam')

改为

parser.add_argument('--source', type=str, default=ROOT / '0')

（2）需要注意的是，代码设置的是检测分辨率为2560x720大小的图或者视频，直接调用摄像头，摄像头分辨率不一定为2560x720，因此需要设定一下打开摄像头默认分辨率

打开utils/dataset.py文件，找到class LoadStreams:这个类
将

for i, s in enumerate(sources):  # index, source
    # Start thread to read frames from video stream
    st = f'{i + 1}/{n}: {s}... '
    if 'youtube.com/' in s or 'youtu.be/' in s:  # if source is YouTube video
        check_requirements(('pafy', 'youtube_dl==2020.12.2'))
        import pafy
        s = pafy.new(s).getbest(preftype="mp4").url  # YouTube URL
    s = eval(s) if s.isnumeric() else s  # i.e. s = '0' local webcam
    cap = cv2.VideoCapture(s)
    assert cap.isOpened(), f'{st}Failed to open {s}'
    w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
    h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
    fps = cap.get(cv2.CAP_PROP_FPS)  # warning: may return 0 or nan
    self.frames[i] = max(int(cap.get(cv2.CAP_PROP_FRAME_COUNT)), 0) or float('inf')  # infinite stream fallback
    self.fps[i] = max((fps if math.isfinite(fps) else 0) % 100, 0) or 30  # 30 FPS fallback

    _, self.imgs[i] = cap.read()  # guarantee first frame
    self.threads[i] = Thread(target=self.update, args=([i, cap, s]), daemon=True)
    LOGGER.info(f"{st} Success ({self.frames[i]} frames {w}x{h} at {self.fps[i]:.2f} FPS)")
    self.threads[i].start()
LOGGER.info('')  # newline

改为

for i, s in enumerate(sources):
     # Start the thread to read frames from the video stream
     print(f'{i + 1}/{n}: {s}... ', end='')
     cap = cv2.VideoCapture(eval(s) if s.isnumeric() else s)
     ####################################################################################################
     imageWidth = 2560
     imageHeight = 720
     cap.set(cv2.CAP_PROP_FRAME_WIDTH, imageWidth)
     cap.set(cv2.CAP_PROP_FRAME_HEIGHT, imageHeight)
     assert cap.isOpened(), f'Failed to open {s}'
     w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
     h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
     fps = 24#cap.get(cv2.CAP_PROP_FPS) % 100
     _, self.imgs[i] = cap.read()  # guarantee first frame
     thread = Thread(target=self.update, args=([i, cap]), daemon=True)
     print(f' success ({w}x{h} at {fps:.2f} FPS).')
     thread.start()
 print('')  # newline

这样就设置好了

5. 训练

数据集采用YOLO格式，目录如下：

dataset
    |
     coco
         |
          images
                |
                train2017
                         |
                         1.jpg
                         2.jpg
                val2017
                       |
                         11.jpg
                         22.jpg
           labels
                |
                train2017
                         |
                         1.txt
                         2.txt
                val2017
                       |
                         11.txt
                         22.txt

打开data/coco.yaml文件，把里边的内容修改如下(这里训练两个类别)

# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
# COCO128 dataset https://www.kaggle.com/ultralytics/coco128 (first 128 images from COCO train2017) by Ultralytics
# Example usage: python train.py --data coco128.yaml
# parent
# ├── yolov5
# └── datasets
#     └── coco128  ← downloads here
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: ./dataset/coco  # dataset root dir
train: images/train2017  # train images (relative to 'path') 128 images
val: images/train2017  # val images (relative to 'path') 128 images
test:  # test images (optional)

# Classes
nc: 2  # number of classes
names: ['person', 'bicycle']  # class names

同时把训练用的model/yolov5s.yaml文件的类别改成与上边对应的类别数，接下来运行train.py即可

6. 源码下载

下载链接：https://download.csdn.net/download/qq_45077760/89136394