Python+OpenCV实现实时眼动追踪的示例代码

使用Python+OpenCV实现实时眼动追踪，不需要高端硬件简单摄像头即可实现，效果图如下所示。

项目演示参见：https://www.bilibili.com/video/av75181965/

项目主程序如下：

import sys
import cv2
import numpy as np
import process
from PyQt5.QtCore import QTimer
from PyQt5.QtWidgets import QApplication, QMainWindow
from PyQt5.uic import loadUi
from PyQt5.QtGui import QPixmap, QImage

class Window(QMainWindow):
  def __init__(self):
    super(Window, self).__init__()
    loadUi('GUImain.ui', self)
    with open("style.css", "r") as css:
      self.setStyleSheet(css.read())
    self.face_decector, self.eye_detector, self.detector = process.init_cv()
    self.startButton.clicked.connect(self.start_webcam)
    self.stopButton.clicked.connect(self.stop_webcam)
    self.camera_is_running = False
    self.previous_right_keypoints = None
    self.previous_left_keypoints = None
    self.previous_right_blob_area = None
    self.previous_left_blob_area = None

  def start_webcam(self):
    if not self.camera_is_running:
      self.capture = cv2.VideoCapture(cv2.CAP_DSHOW) # VideoCapture(0) sometimes drops error #-1072875772
      if self.capture is None:
        self.capture = cv2.VideoCapture(0)
      self.camera_is_running = True
      self.timer = QTimer(self)
      self.timer.timeout.connect(self.update_frame)
      self.timer.start(2)

  def stop_webcam(self):
    if self.camera_is_running:
      self.capture.release()
      self.timer.stop()
      self.camera_is_running = not self.camera_is_running

  def update_frame(self): # logic of the main loop

    _, base_image = self.capture.read()
    self.display_image(base_image)

    processed_image = cv2.cvtColor(base_image, cv2.COLOR_RGB2GRAY)

    face_frame, face_frame_gray, left_eye_estimated_position, right_eye_estimated_position, _, _ = process.detect_face(
      base_image, processed_image, self.face_decector)

    if face_frame is not None:
      left_eye_frame, right_eye_frame, left_eye_frame_gray, right_eye_frame_gray = process.detect_eyes(face_frame,
                                                       face_frame_gray,
                                                       left_eye_estimated_position,
                                                       right_eye_estimated_position,
                                                       self.eye_detector)

      if right_eye_frame is not None:
        if self.rightEyeCheckbox.isChecked():
          right_eye_threshold = self.rightEyeThreshold.value()
          right_keypoints, self.previous_right_keypoints, self.previous_right_blob_area = self.get_keypoints(
            right_eye_frame, right_eye_frame_gray, right_eye_threshold,
            previous_area=self.previous_right_blob_area,
            previous_keypoint=self.previous_right_keypoints)
          process.draw_blobs(right_eye_frame, right_keypoints)

        right_eye_frame = np.require(right_eye_frame, np.uint8, 'C')
        self.display_image(right_eye_frame, window='right')

      if left_eye_frame is not None:
        if self.leftEyeCheckbox.isChecked():
          left_eye_threshold = self.leftEyeThreshold.value()
          left_keypoints, self.previous_left_keypoints, self.previous_left_blob_area = self.get_keypoints(
            left_eye_frame, left_eye_frame_gray, left_eye_threshold,
            previous_area=self.previous_left_blob_area,
            previous_keypoint=self.previous_left_keypoints)
          process.draw_blobs(left_eye_frame, left_keypoints)

        left_eye_frame = np.require(left_eye_frame, np.uint8, 'C')
        self.display_image(left_eye_frame, window='left')

    if self.pupilsCheckbox.isChecked(): # draws keypoints on pupils on main window
      self.display_image(base_image)

  def get_keypoints(self, frame, frame_gray, threshold, previous_keypoint, previous_area):

    keypoints = process.process_eye(frame_gray, threshold, self.detector,
                    prevArea=previous_area)
    if keypoints:
      previous_keypoint = keypoints
      previous_area = keypoints[0].size
    else:
      keypoints = previous_keypoint
    return keypoints, previous_keypoint, previous_area

  def display_image(self, img, window='main'):
    # Makes OpenCV images displayable on PyQT, displays them
    qformat = QImage.Format_Indexed8
    if len(img.shape) == 3:
      if img.shape[2] == 4: # RGBA
        qformat = QImage.Format_RGBA8888
      else: # RGB
        qformat = QImage.Format_RGB888

    out_image = QImage(img, img.shape[1], img.shape[0], img.strides[0], qformat) # BGR to RGB
    out_image = out_image.rgbSwapped()
    if window == 'main': # main window
      self.baseImage.setPixmap(QPixmap.fromImage(out_image))
      self.baseImage.setScaledContents(True)
    if window == 'left': # left eye window
      self.leftEyeBox.setPixmap(QPixmap.fromImage(out_image))
      self.leftEyeBox.setScaledContents(True)
    if window == 'right': # right eye window
      self.rightEyeBox.setPixmap(QPixmap.fromImage(out_image))
      self.rightEyeBox.setScaledContents(True)

if __name__ == "__main__":
  app = QApplication(sys.argv)
  window = Window()
  window.setWindowTitle("GUI")
  window.show()
  sys.exit(app.exec_())

人眼检测程序如下：

import os
import cv2
import numpy as np

def init_cv():
  """loads all of cv2 tools"""
  face_detector = cv2.CascadeClassifier(
    os.path.join("Classifiers", "haar", "haarcascade_frontalface_default.xml"))
  eye_detector = cv2.CascadeClassifier(os.path.join("Classifiers", "haar", 'haarcascade_eye.xml'))
  detector_params = cv2.SimpleBlobDetector_Params()
  detector_params.filterByArea = True
  detector_params.maxArea = 1500
  detector = cv2.SimpleBlobDetector_create(detector_params)

  return face_detector, eye_detector, detector

def detect_face(img, img_gray, cascade):
  """
  Detects all faces, if multiple found, works with the biggest. Returns the following parameters:
  1. The face frame
  2. A gray version of the face frame
  2. Estimated left eye coordinates range
  3. Estimated right eye coordinates range
  5. X of the face frame
  6. Y of the face frame
  """
  coords = cascade.detectMultiScale(img, 1.3, 5)

  if len(coords) > 1:
    biggest = (0, 0, 0, 0)
    for i in coords:
      if i[3] > biggest[3]:
        biggest = i
    biggest = np.array([i], np.int32)
  elif len(coords) == 1:
    biggest = coords
  else:
    return None, None, None, None, None, None
  for (x, y, w, h) in biggest:
    frame = img[y:y + h, x:x + w]
    frame_gray = img_gray[y:y + h, x:x + w]
    lest = (int(w * 0.1), int(w * 0.45))
    rest = (int(w * 0.55), int(w * 0.9))
    X = x
    Y = y

  return frame, frame_gray, lest, rest, X, Y

def detect_eyes(img, img_gray, lest, rest, cascade):
  """
  :param img: image frame
  :param img_gray: gray image frame
  :param lest: left eye estimated position, needed to filter out nostril, know what eye is found
  :param rest: right eye estimated position
  :param cascade: Hhaar cascade
  :return: colored and grayscale versions of eye frames
  """
  leftEye = None
  rightEye = None
  leftEyeG = None
  rightEyeG = None
  coords = cascade.detectMultiScale(img_gray, 1.3, 5)

  if coords is None or len(coords) == 0:
    pass
  else:
    for (x, y, w, h) in coords:
      eyecenter = int(float(x) + (float(w) / float(2)))
      if lest[0] < eyecenter and eyecenter < lest[1]:
        leftEye = img[y:y + h, x:x + w]
        leftEyeG = img_gray[y:y + h, x:x + w]
        leftEye, leftEyeG = cut_eyebrows(leftEye, leftEyeG)
      elif rest[0] < eyecenter and eyecenter < rest[1]:
        rightEye = img[y:y + h, x:x + w]
        rightEyeG = img_gray[y:y + h, x:x + w]
        rightEye, rightEye = cut_eyebrows(rightEye, rightEyeG)
      else:
        pass # nostril
  return leftEye, rightEye, leftEyeG, rightEyeG

def process_eye(img, threshold, detector, prevArea=None):
  """
  :param img: eye frame
  :param threshold: threshold value for threshold function
  :param detector: blob detector
  :param prevArea: area of the previous keypoint(used for filtering)
  :return: keypoints
  """
  _, img = cv2.threshold(img, threshold, 255, cv2.THRESH_BINARY)
  img = cv2.erode(img, None, iterations=2)
  img = cv2.dilate(img, None, iterations=4)
  img = cv2.medianBlur(img, 5)
  keypoints = detector.detect(img)
  if keypoints and prevArea and len(keypoints) > 1:
    tmp = 1000
    for keypoint in keypoints: # filter out odd blobs
      if abs(keypoint.size - prevArea) < tmp:
        ans = keypoint
        tmp = abs(keypoint.size - prevArea)
    keypoints = np.array(ans)

  return keypoints

def cut_eyebrows(img, imgG):
  height, width = img.shape[:2]
  img = img[15:height, 0:width] # cut eyebrows out (15 px)
  imgG = imgG[15:height, 0:width]

  return img, imgG

def draw_blobs(img, keypoints):
  """Draws blobs"""
  cv2.drawKeypoints(img, keypoints, img, (0, 0, 255), cv2.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS)

以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持我们。