- added eyeFeature_kalibrierung

- added documentation for eyeTracking data

dataset_creation/camera_handling/eyeFeature_kalibrierung.py

@@ -0,0 +1,174 @@
+import cv2
+import mediapipe as mp
+import numpy as np
+import pyautogui
+import pandas as pd
+import time
+from sklearn.pipeline import make_pipeline
+from sklearn.preprocessing import PolynomialFeatures
+from sklearn.linear_model import LinearRegression
+
+# Bildschirmgröße
+screen_w, screen_h = pyautogui.size()
+
+# MediaPipe Setup
+mp_face_mesh = mp.solutions.face_mesh
+face_mesh = mp_face_mesh.FaceMesh(refine_landmarks=True)
+cap = cv2.VideoCapture(0)
+
+# Iris Landmark Indizes
+LEFT_IRIS = [468, 469, 470, 471, 472]
+RIGHT_IRIS = [473, 474, 475, 476, 477]
+
+def get_iris_center(landmarks, indices):
+    points = np.array([[landmarks[i].x, landmarks[i].y] for i in indices])
+    return np.mean(points, axis=0)
+
+# Kalibrierpunkte
+calibration_points = [
+    (0.1,0.1),(0.5,0.1),(0.9,0.1),
+    (0.1,0.5),(0.5,0.5),(0.9,0.5),
+    (0.1,0.9),(0.5,0.9),(0.9,0.9)
+]
+
+left_data = []
+right_data = []
+
+print("Kalibrierung startet...")
+
+for idx, (px, py) in enumerate(calibration_points):
+
+    screen = np.zeros((screen_h, screen_w, 3), dtype=np.uint8)
+
+    for j, (cpx, cpy) in enumerate(calibration_points):
+        cx = int(cpx * screen_w)
+        cy = int(cpy * screen_h)
+
+        if j == idx:
+            color = (0, 0, 255)   
+            radius = 25
+        else:
+            color = (255, 255, 255)   
+            radius = 15
+
+        cv2.circle(screen, (cx, cy), radius, color, -1)
+
+    # Fenster vorbereiten
+    cv2.namedWindow("Calibration", cv2.WINDOW_NORMAL)
+    cv2.imshow("Calibration", screen)
+    cv2.waitKey(1000)
+
+    samples_left = []
+    samples_right = []
+
+    start = time.time()
+    while time.time() - start < 2:
+        ret, frame = cap.read()
+        frame = cv2.flip(frame, 1)
+        rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+        results = face_mesh.process(rgb)
+
+        if results.multi_face_landmarks:
+            mesh = results.multi_face_landmarks[0].landmark
+
+            left_center = get_iris_center(mesh, LEFT_IRIS)
+            right_center = get_iris_center(mesh, RIGHT_IRIS)
+
+            samples_left.append(left_center)
+            samples_right.append(right_center)
+
+    avg_left = np.mean(samples_left, axis=0)
+    avg_right = np.mean(samples_right, axis=0)
+
+    target_x = int(px * screen_w)
+    target_y = int(py * screen_h)
+
+    left_data.append([avg_left[0], avg_left[1], target_x, target_y])
+    right_data.append([avg_right[0], avg_right[1], target_x, target_y])
+
+cv2.destroyWindow("Calibration")
+
+# Training
+def train_model(data):
+    data = np.array(data)
+    X = data[:, :2]
+    yx = data[:, 2]
+    yy = data[:, 3]
+
+    model_x = make_pipeline(PolynomialFeatures(2), LinearRegression())
+    model_y = make_pipeline(PolynomialFeatures(2), LinearRegression())
+
+    model_x.fit(X, yx)
+    model_y.fit(X, yy)
+
+    return model_x, model_y
+
+model_lx, model_ly = train_model(left_data)
+model_rx, model_ry = train_model(right_data)
+
+print("Kalibrierung abgeschlossen. Tracking startet...")
+
+# Datenaufzeichnung
+records = []
+
+while True:
+    ret, frame = cap.read()
+    frame = cv2.flip(frame, 1)
+    rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+    results = face_mesh.process(rgb)
+
+    if results.multi_face_landmarks:
+        mesh = results.multi_face_landmarks[0].landmark
+
+        left_center = get_iris_center(mesh, LEFT_IRIS)
+        right_center = get_iris_center(mesh, RIGHT_IRIS)
+
+        left_input = np.array([left_center])
+        right_input = np.array([right_center])
+
+        lx = model_lx.predict(left_input)[0]
+        ly = model_ly.predict(left_input)[0]
+
+        rx = model_rx.predict(right_input)[0]
+        ry = model_ry.predict(right_input)[0]
+
+        # Pixel-Koordinaten begrenzen
+        lx = np.clip(lx, 0, screen_w)
+        ly = np.clip(ly, 0, screen_h)
+        rx = np.clip(rx, 0, screen_w)
+        ry = np.clip(ry, 0, screen_h)
+
+        # Normierung 0–1
+        lx_norm = lx / screen_w
+        ly_norm = ly / screen_h
+        rx_norm = rx / screen_w
+        ry_norm = ry / screen_h
+
+        records.append([
+            lx_norm, ly_norm,
+            rx_norm, ry_norm
+        ])
+
+        print("L:", int(lx), int(ly), " | R:", int(rx), int(ry))
+
+    cv2.imshow("Tracking", frame)
+
+    key = cv2.waitKey(1) & 0xFF
+    if key == ord('q'):
+        print("q gedrückt – beende Tracking")
+        break
+
+cap.release()
+cv2.destroyAllWindows()
+
+# CSV speichern
+df = pd.DataFrame(records, columns=[
+    "EYE_LEFT_GAZE_POINT_ON_DISPLAY_AREA_X",
+    "EYE_LEFT_GAZE_POINT_ON_DISPLAY_AREA_Y",
+    "EYE_RIGHT_GAZE_POINT_ON_DISPLAY_AREA_X",
+    "EYE_RIGHT_GAZE_POINT_ON_DISPLAY_AREA_Y"
+])
+
+df.to_csv("gaze_data1.csv", index=False)
+
+print("Daten gespeichert als gaze_data1.csv")

project_report.md

@@ -68,6 +68,24 @@ Runtime behavior:
 Operational note:
 - `DB_PATH` and other paths are currently code-configured and must be adapted per deployment.
 
+### 2.4 Two Approaches to Eye-Tracking Data Collection
+
+Eye-tracking can be implemented using two main approaches:
+
+Used Approach: Relative Iris Position
+- Tracks the position of the pupil within the eye region
+- The position is normalized relative to the eye itself
+- No reference to the screen or physical environment is required
+
+Not Used Approach: Screen Calibration
+- Requires the user to look at 9 predefined points on the screen
+- A mapping model is trained based on these points
+- Establishes a relationship between eye movement and screen coordinates
+
+Important Considerations (for both methods)
+- Keep the head as still as possible
+- Ensure consistent and even lighting conditions
+
 ## 3) EDA
 The directory EDA provides several files to get insights into both the raw data from AdaBase and your own dataset.
 
@@ -317,6 +335,7 @@ Otherwise, as described in `readme.md: Setup`, you can use `prediction_env.yaml`
 - `dataset_creation/camera_handling/eyeFeature_new.py` - eye-feature extraction from gaze parquet
 - `dataset_creation/camera_handling/db_helper.py` - SQLite helper functions (camera pipeline)
 - `dataset_creation/camera_handling/camera_stream.py` - baseline camera streaming script
+- `dataset_creation/camera_handling/eyeFeature_kalibrierung.py` - eye-feature extraction with calibration
 - `dataset_creation/camera_handling/db_test.py` - DB test utility
 
 ### EDA
@@ -387,4 +406,3 @@ Otherwise, as described in `readme.md: Setup`, you can use `prediction_env.yaml`
 
 - Several paths are hardcoded on purpose to ensure compability with the jetsonboard at the OHM-UX driving simulator.
 - Camera and AU processing are resource-intensive; version pinning and hardware validation are recommended.
-

readme.md

@@ -7,9 +7,9 @@ For full documentation, see [project_report.md](project_report.md).
 ## Quickstart
 
 ### 1) Setup
-Activate the conda-repository "". 
+Activate the conda-repository "camera_stream_AU_ET_test". 
 ```bash
-    conda activate
+    conda activate camera_stream_AU_ET_test
 ```
 **Make sure, another environment that fulfills prediction_env.yaml is available**, matching with predict_pipeline/predict.service 
 See `predict_pipeline/predict_service_timer_documentation.md`