Remove dlib components (assume user can provide landmarks)

example.py

@@ -1,41 +0,0 @@
-"""
-Demonstration of the GazeTracking library.
-Check the README.md for complete documentation.
-"""
-
-import cv2
-from gaze_tracking import GazeTracking
-
-gaze = GazeTracking()
-webcam = cv2.VideoCapture(0)
-
-while True:
-    # We get a new frame from the webcam
-    _, frame = webcam.read()
-
-    # We send this frame to GazeTracking to analyze it
-    gaze.refresh(frame)
-
-    frame = gaze.annotated_frame()
-    text = ""
-
-    if gaze.is_blinking():
-        text = "Blinking"
-    elif gaze.is_right():
-        text = "Looking right"
-    elif gaze.is_left():
-        text = "Looking left"
-    elif gaze.is_center():
-        text = "Looking center"
-
-    cv2.putText(frame, text, (90, 60), cv2.FONT_HERSHEY_DUPLEX, 1.6, (147, 58, 31), 2)
-
-    left_pupil = gaze.pupil_left_coords()
-    right_pupil = gaze.pupil_right_coords()
-    cv2.putText(frame, "Left pupil:  " + str(left_pupil), (90, 130), cv2.FONT_HERSHEY_DUPLEX, 0.9, (147, 58, 31), 1)
-    cv2.putText(frame, "Right pupil: " + str(right_pupil), (90, 165), cv2.FONT_HERSHEY_DUPLEX, 0.9, (147, 58, 31), 1)
-
-    cv2.imshow("Demo", frame)
-
-    if cv2.waitKey(1) == 27:
-        break

gaze_tracking/__init__.py

@@ -1 +1 @@
-from .gaze_tracking import GazeTracking
+

gaze_tracking/eye.py

@@ -13,37 +13,24 @@ class Eye(object):
     LEFT_EYE_POINTS = [36, 37, 38, 39, 40, 41]
     RIGHT_EYE_POINTS = [42, 43, 44, 45, 46, 47]
 
-    def __init__(self, original_frame, landmarks, side, calibration):
+    def __init__(self, original_frame, landmarks, margin, side, calibration):
         self.frame = None
         self.origin = None
         self.center = None
         self.pupil = None
+        self.margin = margin
 
         self._analyze(original_frame, landmarks, side, calibration)
 
-    @staticmethod
-    def _middle_point(p1, p2):
-        """Returns the middle point (x,y) between two points
-
-        Arguments:
-            p1 (dlib.point): First point
-            p2 (dlib.point): Second point
-        """
-        x = int((p1.x + p2.x) / 2)
-        y = int((p1.y + p2.y) / 2)
-        return (x, y)
-
     def _isolate(self, frame, landmarks, points):
         """Isolate an eye, to have a frame without other part of the face.
 
         Arguments:
             frame (numpy.ndarray): Frame containing the face
-            landmarks (dlib.full_object_detection): Facial landmarks for the face region
+            landmarks (numpy.ndarray): Facial landmarks for the face region
             points (list): Points of an eye (from the 68 Multi-PIE landmarks)
         """
-        region = np.array([(landmarks.part(point).x, landmarks.part(point).y) for point in points])
-        region = region.astype(np.int32)
-
+        region = landmarks[points].astype(np.int32)
         # Applying a mask to get only the eye
         height, width = frame.shape[:2]
         black_frame = np.zeros((height, width), np.uint8)
@@ -52,11 +39,10 @@ class Eye(object):
         eye = cv2.bitwise_not(black_frame, frame.copy(), mask=mask)
 
         # Cropping on the eye
-        margin = 5
-        min_x = np.min(region[:, 0]) - margin
-        max_x = np.max(region[:, 0]) + margin
-        min_y = np.min(region[:, 1]) - margin
-        max_y = np.max(region[:, 1]) + margin
+        min_x = np.min(region[:, 0]) - self.margin
+        max_x = np.max(region[:, 0]) + self.margin
+        min_y = np.min(region[:, 1]) - self.margin
+        max_y = np.max(region[:, 1]) + self.margin
 
         self.frame = eye[min_y:max_y, min_x:max_x]
         self.origin = (min_x, min_y)
@@ -69,16 +55,16 @@ class Eye(object):
         It's the division of the width of the eye, by its height.
 
         Arguments:
-            landmarks (dlib.full_object_detection): Facial landmarks for the face region
+            landmarks (numpy.ndarray): Facial landmarks for the face region
             points (list): Points of an eye (from the 68 Multi-PIE landmarks)
 
         Returns:
             The computed ratio
         """
-        left = (landmarks.part(points[0]).x, landmarks.part(points[0]).y)
-        right = (landmarks.part(points[3]).x, landmarks.part(points[3]).y)
-        top = self._middle_point(landmarks.part(points[1]), landmarks.part(points[2]))
-        bottom = self._middle_point(landmarks.part(points[5]), landmarks.part(points[4]))
+        left = landmarks[points[0]]
+        right = landmarks[points[3]]
+        top = np.mean(landmarks[points[1:3]], axis=0)
+        bottom = np.mean(landmarks[points[4:6]], axis=0)
 
         eye_width = math.hypot((left[0] - right[0]), (left[1] - right[1]))
         eye_height = math.hypot((top[0] - bottom[0]), (top[1] - bottom[1]))

gaze_tracking/gaze_tracking.py

@@ -1,7 +1,6 @@
 from __future__ import division
 import os
 import cv2
-import dlib
 from .eye import Eye
 from .calibration import Calibration
 
@@ -19,14 +18,6 @@ class GazeTracking(object):
         self.eye_right = None
         self.calibration = Calibration()
 
-        # _face_detector is used to detect faces
-        self._face_detector = dlib.get_frontal_face_detector()
-
-        # _predictor is used to get facial landmarks of a given face
-        cwd = os.path.abspath(os.path.dirname(__file__))
-        model_path = os.path.abspath(os.path.join(cwd, "trained_models/shape_predictor_68_face_landmarks.dat"))
-        self._predictor = dlib.shape_predictor(model_path)
-
     @property
     def pupils_located(self):
         """Check that the pupils have been located"""
@@ -40,26 +31,26 @@ class GazeTracking(object):
             return False
 
     def _analyze(self):
-        """Detects the face and initialize Eye objects"""
+        """Initialize Eye objects"""
         frame = cv2.cvtColor(self.frame, cv2.COLOR_BGR2GRAY)
-        faces = self._face_detector(frame)
 
         try:
-            landmarks = self._predictor(frame, faces[0])
-            self.eye_left = Eye(frame, landmarks, 0, self.calibration)
-            self.eye_right = Eye(frame, landmarks, 1, self.calibration)
+            self.eye_left = Eye(frame, self.landmarks, 0, self.calibration)
+            self.eye_right = Eye(frame, self.landmarks, 1, self.calibration)
 
         except IndexError:
             self.eye_left = None
             self.eye_right = None
 
-    def refresh(self, frame):
+    def refresh(self, frame, landmarks):
         """Refreshes the frame and analyzes it.
 
         Arguments:
             frame (numpy.ndarray): The frame to analyze
+            landmarks (numpy.ndarray): A full set of 68 face landmarks
         """
         self.frame = frame
+        self.landmarks = landmarks
         self._analyze()
 
     def pupil_left_coords(self):

requirements.txt

@@ -1,3 +1,2 @@
 numpy == 1.16.1
 opencv_python == 3.4.5.20
-dlib == 19.16.0