import sys import os sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '..'))) import cv2 import time import numpy as np from scripts.inference import GazePredictor from utils.ear_utils import BlinkDetector from pygame import mixer def smooth_values(history, current_value, window_size=5): if current_value is not None: history.append(current_value) if len(history) > window_size: history.pop(0) return np.mean(history, axis=0) if isinstance(current_value, np.ndarray) and history else current_value if current_value is not None else 0 def track_gaze(model_path): gaze_predictor = GazePredictor(model_path) blink_detector = BlinkDetector() cap = cv2.VideoCapture(0) if not cap.isOpened(): print("Error: Could not open webcam.") return GAZE_STABILITY_THRESHOLD = 0.5 TIME_THRESHOLD = 15 BLINK_RATE_THRESHOLD = 1 EYE_CLOSURE_THRESHOLD = 10 HEAD_STABILITY_THRESHOLD = 0.05 gaze_history = [] head_history = [] ear_history = [] stable_gaze_time = 0 stable_head_time = 0 eye_closed_time = 0 blink_count = 0 start_time = time.time() is_unconscious = False # Initialize pygame mixer mixer.init() ALARM_PATH = os.path.normpath(os.path.abspath(os.path.join(os.path.dirname(__file__), "..", "sounds", "alarm.wav"))) if not os.path.exists(ALARM_PATH): print(f"Warning: Alarm sound file not found at {ALARM_PATH}. No sound will play.") while True: ret, frame = cap.read() if not ret: print("Failed to capture frame") break head_pose_gaze, gaze_h, gaze_v = gaze_predictor.predict_gaze(frame) current_gaze = np.array([gaze_h, gaze_v]) smoothed_gaze = smooth_values(gaze_history, current_gaze) ear, left_eye, right_eye, head_pose, left_iris, right_iris = blink_detector.detect_blinks(frame) if ear is None: cv2.putText(frame, "No face detected", (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2) print("No face detected") smoothed_head = smooth_values(head_history, None) smoothed_ear = smooth_values(ear_history, None) else: print(f"EAR: {ear:.2f}, Head Pose: {head_pose:.2f}, Gaze: [{smoothed_gaze[0]:.2f}, {smoothed_gaze[1]:.2f}]") smoothed_head = smooth_values(head_history, head_pose) smoothed_ear = smooth_values(ear_history, ear) if smoothed_ear >= blink_detector.EAR_THRESHOLD: cv2.drawMarker(frame, left_iris, (0, 255, 0), markerType=cv2.MARKER_CROSS, markerSize=10, thickness=2) cv2.drawMarker(frame, right_iris, (0, 255, 0), markerType=cv2.MARKER_CROSS, markerSize=10, thickness=2) cv2.putText(frame, f"Gaze H: {smoothed_gaze[0]:.2f}", (10, 60), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2) cv2.putText(frame, f"Gaze V: {smoothed_gaze[1]:.2f}", (10, 90), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2) cv2.putText(frame, f"Head Pose: {smoothed_head:.2f}", (10, 120), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2) cv2.putText(frame, f"EAR: {smoothed_ear:.2f}", (10, 150), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2) if len(gaze_history) > 1: gaze_diff = np.sqrt(np.sum((smoothed_gaze - gaze_history[-2])**2)) print(f"Gaze Diff: {gaze_diff:.2f}") if gaze_diff < GAZE_STABILITY_THRESHOLD: if stable_gaze_time == 0: stable_gaze_time = time.time() elif time.time() - stable_gaze_time > TIME_THRESHOLD: cv2.putText(frame, "Gaze Fixed", (10, 180), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2) else: stable_gaze_time = 0 if len(head_history) > 1 and head_pose is not None: head_diff = abs(smoothed_head - head_history[-2]) print(f"Head Diff: {head_diff:.2f}") if head_diff < HEAD_STABILITY_THRESHOLD: if stable_head_time == 0: stable_head_time = time.time() else: stable_head_time = 0 if ear is not None and smoothed_ear < blink_detector.EAR_THRESHOLD: if eye_closed_time == 0: eye_closed_time = time.time() elif time.time() - eye_closed_time > EYE_CLOSURE_THRESHOLD: cv2.putText(frame, "Eyes Closed", (10, 210), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2) else: if eye_closed_time > 0 and time.time() - eye_closed_time < 0.5: blink_count += 1 eye_closed_time = 0 elapsed_minutes = (time.time() - start_time) / 60 blink_rate = blink_count / elapsed_minutes if elapsed_minutes > 0 else 0 cv2.putText(frame, f"Blink Rate: {blink_rate:.1f}/min", (10, 240), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2) unconscious_conditions = [ stable_gaze_time > 0 and time.time() - stable_gaze_time > TIME_THRESHOLD, blink_rate < BLINK_RATE_THRESHOLD and elapsed_minutes > 1, eye_closed_time > 0 and time.time() - eye_closed_time > EYE_CLOSURE_THRESHOLD, stable_head_time > 0 and time.time() - stable_head_time > TIME_THRESHOLD ] print(f"Conditions: {unconscious_conditions}") if sum(unconscious_conditions) >= 2: if not is_unconscious and os.path.exists(ALARM_PATH): print(f"Attempting to play alarm at {ALARM_PATH}") try: mixer.music.load(ALARM_PATH) mixer.music.play() except Exception as e: print(f"Error playing alarm sound: {e}") print("Unconscious detected!") cv2.putText(frame, "Unconscious Detected", (10, 270), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2) is_unconscious = True else: is_unconscious = False cv2.imshow("Gaze Tracking", frame) if cv2.waitKey(1) & 0xFF == ord('q'): break cap.release() cv2.destroyAllWindows() mixer.quit() if __name__ == "__main__": SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__)) MODEL_PATH = os.path.join(SCRIPT_DIR, "..", "models", "gaze_estimation_model.pth") if not os.path.exists(MODEL_PATH): print(f"Error: Missing model file at {MODEL_PATH}") sys.exit(1) track_gaze(MODEL_PATH)