eye_blink_detect.py

"""Eye blink detection using dlib."""
# USAGE
# python eye_blink_detect.py --shape-predictor shape_predictor_68_face_landmarks.dat

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

def eye_aspect_ratio(eye):
    """Return the eye aspect ratio (EAR) proposed by Soukupová and Čech paper"""
    A = dist.euclidean(eye[1], eye[5])
    B = dist.euclidean(eye[2], eye[4])
    C = dist.euclidean(eye[0], eye[3])

    ear = (A + B) / (2.0 * C)

    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")
args = vars(ap.parse_args())

# EAR threshold
EYE_AR_THRESH = 0.2

# Number of consecutive frames the eye must be below the threshold
EYE_AR_CONSEC_FRAMES = 3

# Frame counter
COUNTER = 0

# Total number of blinks
TOTAL = 0

# init dlib's HOG face detector and the facial landmarks predictor
print("[INFO] loading facial landmark predictor...")
face_hog_detector = dlib.get_frontal_face_detector()
landmark_predictor = dlib.shape_predictor(args["shape_predictor"])

# grab the indexes of the facial landmarks for the left and right eye, respectively
(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 = VideoStream(src=0).start()
time.sleep(1.0)

while True:
    frame = vs.read()
    frame = imutils.resize(frame, width=600)
    gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)

    # detect faces in the grayscale frame
    rects = face_hog_detector(gray, 0)

    for rect in rects:
        shape = landmark_predictor(gray, rect)
        shape = face_utils.shape_to_np(shape)

        leftEye = shape[lStart:lEnd]
        rightEye = shape[rStart:rEnd]
        leftEAR = eye_aspect_ratio(leftEye)
        rightEAR = eye_aspect_ratio(rightEye)

        # average for both eyes
        ear = (leftEAR + rightEAR) / 2.0

        # compute the convex hull for eyes, then visualize each of the eyes
        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)

        # check EAR to count blink
        if ear < EYE_AR_THRESH:
            COUNTER += 1    # increment the blink frame counter 
        else:
            if COUNTER >= EYE_AR_CONSEC_FRAMES:
                TOTAL += 1

            # reset the eye frame counter
            COUNTER = 0

        # draw results
        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)
    key = cv2.waitKey(1) & 0xFF
 
    # if the `q` key was pressed, break from the loop
    if key == ord("q"):
        break
# do a bit of cleanup
cv2.destroyAllWindows()
vs.stop()