python简单用opencv打开摄像头并用yolov5模型进行物体检测

1.GitHub代码
yolov5：https://github.com/ultralytics/yolov5

2.环境准备

pip install -r requirements.txt

3.示例代码

import torch

# Model
model = torch.hub.load('ultralytics/yolov5', 'yolov5s')  # or yolov5m, yolov5l, yolov5x, custom

# Images
img = 'https://ultralytics.com/images/zidane.jpg'  # or file, Path, PIL, OpenCV, numpy, list

# Inference
results = model(img)

# Results
results.print()  # or .show(), .save(), .crop(), .pandas(), etc.

或者
使用命令行

python detect.py --source 0  # webcam
                            #file.jpg  # image 
                            #file.mp4  # video
                            #path/  # directory
                            #path/*.jpg  # glob
                            #'https://youtu.be/NUsoVlDFqZg'  # YouTube
                            #'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP stream

4.个人修改简单代码（直接通过opencv打开摄像头进行识别）

# author：chouti

import sys
from pathlib import Path
import cv2
import torch


FILE = Path(__file__).absolute()
sys.path.append(FILE.parents[0].as_posix())  # add yolov5/ to path

from models.experimental import attempt_load
from utils.general import is_ascii, non_max_suppression, scale_coords, set_logging
from utils.plots import Annotator, colors
from utils.torch_utils import select_device


@torch.no_grad()
def run(weights='yolov5s.pt',  # model.pt path(s)
        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
        classes=None,  # filter by class: --class 0, or --class 0 2 3
        agnostic_nms=False,  # class-agnostic NMS
        line_thickness=3,  # bounding box thickness (pixels)
        half=False,  # use FP16 half-precision inference
        ):

    # Initialize
    set_logging()
    device = select_device(device)
    print(device)
    half &= device.type != 'cpu'  # half precision only supported on CUDA

    model = attempt_load(weights, map_location=device)  # load FP32 model
    names = model.module.names if hasattr(model, 'module') else model.names  # get class names
    ascii = is_ascii(names)  # names are ascii (use PIL for UTF-8)
    capture = cv2.VideoCapture(0)

    while True:
        # 获取一帧
        ret, frame = capture.read()
        
        img = torch.from_numpy(frame).to(device)
        img = img.half() if half else img.float()  # uint8 to fp16/32
        img = img / 255.0  # 0 - 255 to 0.0 - 1.0
        if len(img.shape) == 3:
            img = img[None]  # expand for batch dim
        img = img.transpose(2, 3)
        img = img.transpose(1, 2)

        # Inference
        pred = model(img, augment=False, visualize=False)[0]

        # NMS
        pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)

        # Process predictions
        for i, det in enumerate(pred):  # detections per image
            s = ''
            annotator = Annotator(frame, line_width=line_thickness, pil=not ascii)
            if len(det):
                # Rescale boxes from img_size to im0 size
                det[:, :4] = scale_coords(img.shape[2:], det[:, :4], frame.shape).round()

                # Print results
                for c in det[:, -1].unique():
                    n = (det[:, -1] == c).sum()  # detections per class
                    s += str(n.item()) + ' ' + str(names[int(c)]) + ' '  # add to string

                # Write results
                for *xyxy, conf, cls in reversed(det):
                    c = int(cls)  # integer class
                    label = f'{names[c]} {conf:.2f}'
                    annotator.box_label(xyxy, label, color=colors(c, True))
                    print(xyxy)

            print('result:'+s)

        cv2.imshow('frame', frame)
        if cv2.waitKey(1) == ord('q'):
            break


def main():
    run()


if __name__ == "__main__":
    main()

5.注意事项
①可能需要提前下载好模型
②另外可能需要GPU

中国需要更多的免费开源！