mediapipe系列之一脸位置标记

基于mediapipe进行的脸位置标记

采用方法

主要使用google 的 mediapipe 工具包中的face_detection模块和opencv中的显示标识模块

使用事项

文中的1.flv 可以换成其他格式的视频。

代码如下

import cv2
import mediapipe as mp
import time


class poseDetector():
    def __init__(self, min_detection_confidence=0.75):
        self.min_detection_confidence = min_detection_confidence
        self.mpFace = mp.solutions.face_detection
        self.face = self.mpFace.FaceDetection(self.min_detection_confidence)
        self.mpDraw = mp.solutions.drawing_utils

    def findPose(self, img, draw=True):
        imgRGB = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
        self.results = self.face.process(imgRGB)
        bboxs = []
        if self.results.detections:
            for id, detection in enumerate(self.results.detections):
                bboxC = detection.location_data.relative_bounding_box
                ih, iw, ic = img.shape
                bbox = int(bboxC.xmin * iw), int(bboxC.ymin * ih), \
                       int(bboxC.width * iw), int(bboxC.height * ih)
                bboxs.append([id, bbox, detection.score])
                # cv2.rectangle(img, bbox, (255, 0, 255), 2)
                if draw:
                    img = self.fancyDraw(img, bbox)
                cv2.putText(img, f'{int(detection.score[0] * 100)}%',
                            (bbox[0], bbox[1] - 20), cv2.FONT_HERSHEY_PLAIN, 2, (255, 0, 255), 2)

        return img, bboxs

    def fancyDraw(self, img, bbox, l=30, t=5, rt=1):
        x, y, w, h = bbox
        x1, y1 = x + w, y + h

        cv2.rectangle(img, bbox, (255, 0, 255), rt)
        # top left
        cv2.line(img, (x, y), (x + l, y), (255, 0, 255), t)
        cv2.line(img, (x, y), (x, y + l), (255, 0, 255), t)
        cv2.line(img, (x1, y), (x1 - l, y), (255, 0, 255), t)
        cv2.line(img, (x1, y), (x1, y + l), (255, 0, 255), t)
        #
        # # bottom left
        cv2.line(img, (x, y1), (x + l, y1), (255, 0, 255), t)
        cv2.line(img, (x, y1), (x, y1 - l), (255, 0, 255), t)
        cv2.line(img, (x1, y1), (x1 - l, y1), (255, 0, 255), t)
        cv2.line(img, (x1, y1), (x1, y1 - l), (255, 0, 255), t)
        return img


def main():
    pTime = 0
    cap = cv2.VideoCapture('1.flv')
    detector = poseDetector()
    while True:
        success, img = cap.read()
        img, bboxs = detector.findPose(img)

        cTime = time.time()
        fps = 1 / (cTime - pTime)
        pTime = cTime
        cv2.putText(img, f"fps:{int(fps)}", (10, 70), cv2.FONT_HERSHEY_PLAIN, 3, (255, 0, 255), 3)
        cv2.imshow('Image', img)
        cv2.waitKey(1)


if __name__ == '__main__':
    main()