1. 官网地址

https://docs.opencv.org/4.x/df/d20/classcv_1_1FaceDetectorYN.html
FaceDetectorYN是opencv内置的一个人脸检测方法，使用的是yunet。

这是一个DNN-based face detector.模型的下载地址：
https://github.com/opencv/opencv_zoo/tree/master/models/face_detection_yunet

2. 如何使用

2.1.到opencv_zoo下载模型文件和代码

2.2. 下载文件展示

2.3. 修改了demo支持读取视频文件，默认是图片和摄像头

# This file is part of OpenCV Zoo project.
# It is subject to the license terms in the LICENSE file found in the same directory.
#
# Copyright (C) 2021, Shenzhen Institute of Artificial Intelligence and Robotics for Society, all rights reserved.
# Third party copyrights are property of their respective owners.

import argparse

import numpy as np
import cv2 as cv

# Check OpenCV version
opencv_python_version = lambda str_version: tuple(map(int, (str_version.split("."))))
assert opencv_python_version(cv.__version__) >= opencv_python_version("4.10.0"), \
    "Please install latest opencv-python for benchmark: python3 -m pip install --upgrade opencv-python"

from yunet import YuNet

# Valid combinations of backends and targets
backend_target_pairs = [
    [cv.dnn.DNN_BACKEND_OPENCV, cv.dnn.DNN_TARGET_CPU],
    [cv.dnn.DNN_BACKEND_CUDA, cv.dnn.DNN_TARGET_CUDA],
    [cv.dnn.DNN_BACKEND_CUDA, cv.dnn.DNN_TARGET_CUDA_FP16],
    [cv.dnn.DNN_BACKEND_TIMVX, cv.dnn.DNN_TARGET_NPU],
    [cv.dnn.DNN_BACKEND_CANN, cv.dnn.DNN_TARGET_NPU]
]

parser = argparse.ArgumentParser(
    description='YuNet: A Fast and Accurate CNN-based Face Detector (https://github.com/ShiqiYu/libfacedetection).')
parser.add_argument('--input', '-i', type=str,
                    help='Usage: Set input to a certain image, omit if using camera.')
parser.add_argument('--model', '-m', type=str, default='face_detection_yunet_2023mar.onnx',
                    help="Usage: Set model type, defaults to 'face_detection_yunet_2023mar.onnx'.")
parser.add_argument('--backend_target', '-bt', type=int, default=0,
                    help='''Choose one of the backend-target pair to run this demo:
                        {:d}: (default) OpenCV implementation + CPU,
                        {:d}: CUDA + GPU (CUDA),
                        {:d}: CUDA + GPU (CUDA FP16),
                        {:d}: TIM-VX + NPU,
                        {:d}: CANN + NPU
                    '''.format(*[x for x in range(len(backend_target_pairs))]))
parser.add_argument('--conf_threshold', type=float, default=0.7,
                    help='Usage: Set the minimum needed confidence for the model to identify a face, defauts to 0.9. Smaller values may result in faster detection, but will limit accuracy. Filter out faces of confidence < conf_threshold.')
parser.add_argument('--nms_threshold', type=float, default=0.3,
                    help='Usage: Suppress bounding boxes of iou >= nms_threshold. Default = 0.3.')
parser.add_argument('--top_k', type=int, default=5000,
                    help='Usage: Keep top_k bounding boxes before NMS.')
parser.add_argument('--save', '-s', action='store_true',
                    help='Usage: Specify to save file with results (i.e. bounding box, confidence level). Invalid in case of camera input.')
parser.add_argument('--vis', '-v', action='store_true',
                    help='Usage: Specify to open a new window to show results. Invalid in case of camera input.')
parser.add_argument('--camera_or_video', '-c', default='123.mov',
                    help='Usage: Specify to open camera or video')
args = parser.parse_args()


def visualize(image, results, box_color=(0, 255, 0), text_color=(0, 255, 255), fps=None):
    output = image.copy()
    landmark_color = [
        (0, 0, 255),  # right eye
        (0, 0, 255),  # left eye
        (0, 255, 0),  # nose tip
        (255, 0, 255),  # right mouth corner
        (0, 255, 255)  # left mouth corner
    ]

    if fps is not None:
        cv.putText(output, 'FPS: {:.2f}'.format(fps), (50, 50), cv.FONT_HERSHEY_SIMPLEX, 1.5, text_color)

    for det in results:
        bbox = det[0:4].astype(np.int32)
        cv.rectangle(output, (bbox[0], bbox[1]), (bbox[0] + bbox[2], bbox[1] + bbox[3]), box_color, 2)

        conf = det[-1]
        cv.putText(output, '{:.4f}'.format(conf), (bbox[0], bbox[1] + bbox[3] // 2), cv.FONT_HERSHEY_DUPLEX, 1.5, text_color)

        landmarks = det[4:14].astype(np.int32).reshape((5, 2))
        for idx, landmark in enumerate(landmarks):
            cv.circle(output, landmark, 4, landmark_color[idx], 10)

    return output


if __name__ == '__main__':
    backend_id = backend_target_pairs[args.backend_target][0]
    target_id = backend_target_pairs[args.backend_target][1]

    # Instantiate YuNet
    model = YuNet(modelPath=args.model,
                  inputSize=[320, 320],
                  confThreshold=args.conf_threshold,
                  nmsThreshold=args.nms_threshold,
                  topK=args.top_k,
                  backendId=backend_id,
                  targetId=target_id)

    # If input is an image
    if args.input is not None:
        image = cv.imread(args.input)
        h, w, _ = image.shape

        # Inference
        model.setInputSize([w, h])
        results = model.infer(image)

        # Print results
        print('{} faces detected.'.format(results.shape[0]))
        for idx, det in enumerate(results):
            print(
                '{}: {:.0f} {:.0f} {:.0f} {:.0f} {:.0f} {:.0f} {:.0f} {:.0f} {:.0f} {:.0f} {:.0f} {:.0f} {:.0f} {:.0f}'.format(
                    idx, *det[:-1])
            )

        # Draw results on the input image
        image = visualize(image, results)

        # Save results if save is true
        if args.save:
            print('Resutls saved to result.jpg\n')
            cv.imwrite('result.jpg', image)

        # Visualize results in a new window
        if args.vis:
            cv.namedWindow(args.input, cv.WINDOW_AUTOSIZE)
            cv.imshow(args.input, image)
            cv.waitKey(0)
    else:  # Omit input to call default camera
        deviceId = args.camera_or_video
        cap = cv.VideoCapture(int(deviceId) if deviceId.isdigit() else deviceId)
        w = int(cap.get(cv.CAP_PROP_FRAME_WIDTH))
        h = int(cap.get(cv.CAP_PROP_FRAME_HEIGHT))
        model.setInputSize([w, h])
        fps = int(cap.get(cv.CAP_PROP_FPS))

        # 定义视频编码器和创建VideoWriter对象
        fourcc = cv.VideoWriter_fourcc(*'mp4v')  # 或者使用 'XVID'
        out = cv.VideoWriter('output.mp4', fourcc, fps, (w, h))


        tm = cv.TickMeter()
        while cv.waitKey(1) < 0:
            # Inference
            tm.start()

            hasFrame, frame = cap.read()
            if not hasFrame:
                print('No frames grabbed!')
                break

            results = model.infer(frame)  # results is a tuple
            tm.stop()

            # Draw results on the input image
            frame = visualize(frame, results, fps=tm.getFPS())

            # Visualize results in a new Window
            cv.imshow('YuNet face detection', frame)
            # tm.reset()
            # 写入视频文件
            out.write(frame)

        out.release()
        cap.release()

cv.destroyAllWindows()

## 2.4 效果展示