demo.py

# 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

from yunet import YuNet

def str2bool(v):
    if v.lower() in ['on', 'yes', 'true', 'y', 't']:
        return True
    elif v.lower() in ['off', 'no', 'false', 'n', 'f']:
        return False
    else:
        raise NotImplementedError

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='Path to the input image. Omit for using default camera.')
parser.add_argument('--model', '-m', type=str, default='face_detection_yunet_2021sep.onnx', help='Path to the model.')
parser.add_argument('--conf_threshold', type=float, default=0.9, help='Filter out faces of confidence < conf_threshold.')
parser.add_argument('--nms_threshold', type=float, default=0.3, help='Suppress bounding boxes of iou >= nms_threshold.')
parser.add_argument('--top_k', type=int, default=5000, help='Keep top_k bounding boxes before NMS.')
parser.add_argument('--save', '-s', type=str, default=False, help='Set true to save results. This flag is invalid when using camera.')
parser.add_argument('--vis', '-v', type=str2bool, default=True, help='Set true to open a window for result visualization. This flag is invalid when using camera.')
args = parser.parse_args()

def visualize(image, results, box_color=(0, 255, 0), text_color=(0, 0, 255), fps=None):
    output = image.copy()
    landmark_color = [
        (255,   0,   0), # 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), (0, 15), cv.FONT_HERSHEY_SIMPLEX, 0.5, 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]+12), cv.FONT_HERSHEY_DUPLEX, 0.5, text_color)

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

    return output

if __name__ == '__main__':
    # Instantiate YuNet
    model = YuNet(modelPath=args.model,
                  inputSize=[320, 320],
                  confThreshold=args.conf_threshold,
                  nmsThreshold=args.nms_threshold,
                  topK=args.top_k)

    # 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 = 0
        cap = cv.VideoCapture(deviceId)
        w = int(cap.get(cv.CAP_PROP_FRAME_WIDTH))
        h = int(cap.get(cv.CAP_PROP_FRAME_HEIGHT))
        model.setInputSize([w, h])

        tm = cv.TickMeter()
        while cv.waitKey(1) < 0:
            hasFrame, frame = cap.read()
            if not hasFrame:
                print('No frames grabbed!')
                break

            # Inference
            tm.start()
            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 Demo', frame)

            tm.reset()