基于Python OpenCV和 dlib实现眨眼检测

# import the necessary packages
from scipy.spatial import distance as dist
from imutils.video import FileVideoStream
from imutils.video import VideoStream
from imutils import face_utils
import numpy as np
import argparse
import imutils
import time
import dlib
import cv2

pip install --upgrade imutils 

def eye_aspect_ratio(eye):
	# compute the euclidean distances between the two sets of
	# vertical eye landmarks (x, y)-coordinates
	A = dist.euclidean(eye[1], eye[5])
	B = dist.euclidean(eye[2], eye[4])
	# compute the euclidean distance between the horizontal
	# eye landmark (x, y)-coordinates
	C = dist.euclidean(eye[0], eye[3])
	# compute the eye aspect ratio
	ear = (A + B) / (2.0 * C)
	# return the eye aspect ratio
	return ear

# construct the argument parse and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-p", "--shape-predictor", required=True,
	help="path to facial landmark predictor")
ap.add_argument("-v", "--video", type=str, default="",
	help="path to input video file")
args = vars(ap.parse_args())

# 定义两个常量，一个为眼睛纵横比来表示
# 闪烁然后第二个常量为连续的次数
# 帧眼睛必须低于阈值
EYE_AR_THRESH = 0.3
EYE_AR_CONSEC_FRAMES = 3
# 初始化帧计数器和闪烁总数
COUNTER = 0
TOTAL = 0

# 初始化dlib的人脸检测器（基于HOG）然后创建
# 面部标志预测器
print("[INFO] loading facial landmark predictor...")
detector = dlib.get_frontal_face_detector()
predictor = dlib.shape_predictor(args["shape_predictor"])

# 获取左侧和面部标志的索引
# 右眼，分别 
(lStart, lEnd) = face_utils.FACIAL_LANDMARKS_IDXS["left_eye"]
(rStart, rEnd) = face_utils.FACIAL_LANDMARKS_IDXS["right_eye"]

# start the video stream thread
print("[INFO] starting video stream thread...")
vs = FileVideoStream(args["video"]).start()
fileStream = True
# vs = VideoStream(src=0).start()
# vs = VideoStream(usePiCamera=True).start()
# fileStream = False
time.sleep(1.0)
fps = 30    #保存视频的FPS，可以适当调整
size=(450,800)
videoWriter = cv2.VideoWriter('3.mp4',-1,fps,size)#最后一个是保存图片的尺寸

# loop over frames from the video stream
while True:
	# 如果这是一个文件视频流，那么我们需要检查是否
	# 缓冲区中还有更多帧要处理
	if fileStream and not vs.more():
		break
	frame = vs.read()
	if frame is None:
        break
	frame = imutils.resize(frame, width=450)
	gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
	# 在灰度帧中检测人脸
	rects = detector(gray, 0)

	# loop over the face detections
	for rect in rects:
		# 确定面部区域的面部标志，然后
		# 将面部标志 (x, y) 坐标转换为 NumPy数组
		shape = predictor(gray, rect)
		shape = face_utils.shape_to_np(shape)
		# 提取左右眼坐标，然后使用
		# 坐标来计算双眼的眼睛纵横比
		leftEye = shape[lStart:lEnd]
		rightEye = shape[rStart:rEnd]
		leftEAR = eye_aspect_ratio(leftEye)
		rightEAR = eye_aspect_ratio(rightEye)
		# 平均两只眼睛的眼睛纵横比
		ear = (leftEAR + rightEAR) / 2.0

		# 计算左眼和右眼的凸包，然后
		# 可视化每只眼睛
		leftEyeHull = cv2.convexHull(leftEye)
		rightEyeHull = cv2.convexHull(rightEye)
		cv2.drawContours(frame, [leftEyeHull], -1, (0, 255, 0), 1)
		cv2.drawContours(frame, [rightEyeHull], -1, (0, 255, 0), 1)

		# 检查眼睛的纵横比是否低于眨眼
		# 阈值，如果是，则增加闪烁帧计数器
		if ear < EYE_AR_THRESH:
			COUNTER += 1
		# 否则，眼睛纵横比不低于眨眼
		＃ 临界点
		else:
			# 如果眼睛闭上足够多的次数
			# 然后增加闪烁的总数
			if COUNTER >= EYE_AR_CONSEC_FRAMES:
				TOTAL += 1
			# 重置眼框计数器
			COUNTER = 0

		# 绘制帧上闪烁的总数以及
		# 计算出的帧的眼睛纵横比
		cv2.putText(frame, "Blinks: {}".fORMat(TOTAL), (10, 30),
			cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2)
		cv2.putText(frame, "EAR: {:.2f}".format(ear), (300, 30),
			cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2)
 
	# show the frame
	cv2.imshow("Frame", frame)
	videoWriter.write(frame)
	key = cv2.waiTKEy(1) & 0xFF
 
	# if the `q` key was pressed, break from the loop
	if key == ord("q"):
		break
videoWriter.release()
# do a bit of cleanup
cv2.destroyAllwindows()
vs.stop()

python detect_blinks.py --shape-predictor shape_predictor_68_face_landmarks.dat --video 11.mp4

#vs = FileVideoStream(args["video"]).start()
#fileStream = True
vs = VideoStream(src=0).start()
# vs = VideoStream(usePiCamera=True).start()
fileStream = False

python detect_blinks.py --shape-predictor shape_predictor_68_face_landmarks.dat