new

app.py

@@ -135,6 +135,10 @@ def process_webcam(state):
         if not cap.isOpened():
             return None, "Error: Could not open webcam.", None
         
+        # Try to set webcam properties for better performance
+        cap.set(cv2.CAP_PROP_FRAME_WIDTH, 640)
+        cap.set(cv2.CAP_PROP_FRAME_HEIGHT, 480)
+        
         GAZE_STABILITY_THRESHOLD = 0.5
         TIME_THRESHOLD = 15
         BLINK_RATE_THRESHOLD = 1
@@ -172,6 +176,7 @@ def process_webcam(state):
             "HEAD_STABILITY_THRESHOLD": HEAD_STABILITY_THRESHOLD,
             "log_output": log_output
         }
+        return state, "Initializing webcam...", None
     
     # Extract state variables
     cap = state["cap"]
@@ -184,105 +189,118 @@ def process_webcam(state):
     
     # Capture frame
     ret, frame = cap.read()
-    if not ret:
-        return state, log_output + "\nError: Could not read from webcam.", None
+    if not ret or frame is None:
+        # Try to reinitialize the camera if frame capture fails
+        cap.release()
+        cap = cv2.VideoCapture(0)
+        if not cap.isOpened():
+            return state, log_output + "\nError: Could not read from webcam.", None
+        state["cap"] = cap
+        ret, frame = cap.read()
+        if not ret or frame is None:
+            return state, log_output + "\nError: Failed to capture frame after reinitialization.", None
     
     # Process frame
-    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)
-    
-    # Update display and logs
-    current_time = time.time()
-    logs = []
-    
-    if ear is None:
-        cv2.putText(frame, "No face detected", (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2)
-        smoothed_head = smooth_values(head_history, None)
-        smoothed_ear = smooth_values(ear_history, None)
-        logs.append("No face detected")
-    else:
-        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)
-    
-    # Add metrics to frame
-    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)
-    
-    # Check for gaze stability
-    if len(gaze_history) > 1:
-        gaze_diff = np.sqrt(np.sum((smoothed_gaze - gaze_history[-2])**2))
-        if gaze_diff < state["GAZE_STABILITY_THRESHOLD"]:
-            if state["stable_gaze_time"] == 0:
-                state["stable_gaze_time"] = current_time
+    try:
+        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)
+        
+        # Update display and logs
+        current_time = time.time()
+        logs = []
+        
+        if ear is None:
+            cv2.putText(frame, "No face detected", (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2)
+            smoothed_head = smooth_values(head_history, None)
+            smoothed_ear = smooth_values(ear_history, None)
+            logs.append("No face detected")
         else:
-            state["stable_gaze_time"] = 0
-    
-    # Check for head stability
-    if len(head_history) > 1 and head_pose is not None:
-        head_diff = abs(smoothed_head - head_history[-2])
-        if head_diff < state["HEAD_STABILITY_THRESHOLD"]:
-            if state["stable_head_time"] == 0:
-                state["stable_head_time"] = current_time
+            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)
+        
+        # Add metrics to frame
+        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)
+        
+        # Check for gaze stability
+        if len(gaze_history) > 1:
+            gaze_diff = np.sqrt(np.sum((smoothed_gaze - gaze_history[-2])**2))
+            if gaze_diff < state["GAZE_STABILITY_THRESHOLD"]:
+                if state["stable_gaze_time"] == 0:
+                    state["stable_gaze_time"] = current_time
+            else:
+                state["stable_gaze_time"] = 0
+        
+        # Check for head stability
+        if len(head_history) > 1 and head_pose is not None:
+            head_diff = abs(smoothed_head - head_history[-2])
+            if head_diff < state["HEAD_STABILITY_THRESHOLD"]:
+                if state["stable_head_time"] == 0:
+                    state["stable_head_time"] = current_time
+            else:
+                state["stable_head_time"] = 0
+        
+        # Check for eye closure
+        if ear is not None and smoothed_ear < blink_detector.EAR_THRESHOLD:
+            if state["eye_closed_time"] == 0:
+                state["eye_closed_time"] = current_time
+            elif current_time - state["eye_closed_time"] > state["EYE_CLOSURE_THRESHOLD"]:
+                cv2.putText(frame, "Eyes Closed", (10, 210), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2)
+                logs.append("Eyes have been closed for an extended period")
         else:
-            state["stable_head_time"] = 0
-    
-    # Check for eye closure
-    if ear is not None and smoothed_ear < blink_detector.EAR_THRESHOLD:
-        if state["eye_closed_time"] == 0:
-            state["eye_closed_time"] = current_time
-        elif current_time - state["eye_closed_time"] > state["EYE_CLOSURE_THRESHOLD"]:
-            cv2.putText(frame, "Eyes Closed", (10, 210), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2)
-            logs.append("Eyes have been closed for an extended period")
-    else:
-        if state["eye_closed_time"] > 0 and current_time - state["eye_closed_time"] < 0.5:
-            state["blink_count"] += 1
-            logs.append("Blink detected")
-        state["eye_closed_time"] = 0
-    
-    elapsed_seconds = current_time - state["start_time"]
-    elapsed_minutes = elapsed_seconds / 60
-    blink_rate = state["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)
-    logs.append(f"Blink rate: {blink_rate:.1f}/min")
-    
-    # Check for unconscious state
-    unconscious_conditions = [
-        state["stable_gaze_time"] > 0 and current_time - state["stable_gaze_time"] > state["TIME_THRESHOLD"],
-        blink_rate < state["BLINK_RATE_THRESHOLD"] and elapsed_minutes > 1,
-        state["eye_closed_time"] > 0 and current_time - state["eye_closed_time"] > state["EYE_CLOSURE_THRESHOLD"],
-        state["stable_head_time"] > 0 and current_time - state["stable_head_time"] > state["TIME_THRESHOLD"]
-    ]
-    
-    if sum(unconscious_conditions) >= 2:
-        cv2.putText(frame, "Unconscious Detected", (10, 270), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2)
-        state["is_unconscious"] = True
-        logs.append("WARNING: Possible unconscious state detected!")
-    else:
-        state["is_unconscious"] = False
-    
-    # Update log output with latest information
-    logs.append(f"Gaze: ({smoothed_gaze[0]:.2f}, {smoothed_gaze[1]:.2f}) | Head: {smoothed_head:.2f} | EAR: {smoothed_ear:.2f}")
-    log_text = "\n".join(logs)
-    
-    # Keep log_output to a reasonable size
-    log_lines = log_output.split("\n") if log_output else []
-    log_lines.append(log_text)
-    if len(log_lines) > 20:  # Keep only last 20 entries
-        log_lines = log_lines[-20:]
-    state["log_output"] = "\n".join(log_lines)
-    
-    # Convert from BGR to RGB for Gradio
-    frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
-    
-    return state, state["log_output"], frame_rgb
+            if state["eye_closed_time"] > 0 and current_time - state["eye_closed_time"] < 0.5:
+                state["blink_count"] += 1
+                logs.append("Blink detected")
+            state["eye_closed_time"] = 0
+        
+        elapsed_seconds = current_time - state["start_time"]
+        elapsed_minutes = elapsed_seconds / 60
+        blink_rate = state["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)
+        logs.append(f"Blink rate: {blink_rate:.1f}/min")
+        
+        # Check for unconscious state
+        unconscious_conditions = [
+            state["stable_gaze_time"] > 0 and current_time - state["stable_gaze_time"] > state["TIME_THRESHOLD"],
+            blink_rate < state["BLINK_RATE_THRESHOLD"] and elapsed_minutes > 1,
+            state["eye_closed_time"] > 0 and current_time - state["eye_closed_time"] > state["EYE_CLOSURE_THRESHOLD"],
+            state["stable_head_time"] > 0 and current_time - state["stable_head_time"] > state["TIME_THRESHOLD"]
+        ]
+        
+        if sum(unconscious_conditions) >= 2:
+            cv2.putText(frame, "Unconscious Detected", (10, 270), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2)
+            state["is_unconscious"] = True
+            logs.append("WARNING: Possible unconscious state detected!")
+        else:
+            state["is_unconscious"] = False
+        
+        # Update log output with latest information
+        logs.append(f"Gaze: ({smoothed_gaze[0]:.2f}, {smoothed_gaze[1]:.2f}) | Head: {smoothed_head:.2f} | EAR: {smoothed_ear:.2f}")
+        log_text = "\n".join(logs)
+        
+        # Keep log_output to a reasonable size
+        log_lines = log_output.split("\n") if log_output else []
+        log_lines.append(log_text)
+        if len(log_lines) > 20:  # Keep only last 20 entries
+            log_lines = log_lines[-20:]
+        state["log_output"] = "\n".join(log_lines)
+        
+        # Convert from BGR to RGB for Gradio
+        frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+        
+        return state, state["log_output"], frame_rgb
+        
+    except Exception as e:
+        error_msg = f"Error processing frame: {str(e)}"
+        return state, log_output + "\n" + error_msg, None
 
 def create_webcam_interface():
     log_output = gr.Textbox(label="Gaze Tracking Log", lines=10)