Update app.py

app.py

@@ -7,51 +7,54 @@ from scipy.interpolate import interp1d
 import plotly.graph_objects as go
 import uuid
 import os
+import tempfile
 
-# Load the trained YOLOv8n model with optimizations
+# Load YOLOv8 model and resolve class index
 model = YOLO("best.pt")
-model.to('cuda' if torch.cuda.is_available() else 'cpu')  # Use GPU if available
-
-# Constants for LBW decision and video processing
-STUMPS_WIDTH = 0.2286  # meters (width of stumps)
-BALL_DIAMETER = 0.073  # meters (approx. cricket ball diameter)
-FRAME_RATE = 20  # Input video frame rate
-SLOW_MOTION_FACTOR = 3  # For very slow motion (3x slower)
-CONF_THRESHOLD = 0.2  # Confidence threshold
-IMPACT_ZONE_Y = 0.85  # Fraction of frame height where impact is likely
-IMPACT_DELTA_Y = 50  # Pixels for detecting sudden y-position change
-PITCH_LENGTH = 20.12  # meters (standard cricket pitch length)
-STUMPS_HEIGHT = 0.71  # meters (stumps height)
-CAMERA_HEIGHT = 2.0  # meters (assumed camera height)
-CAMERA_DISTANCE = 10.0  # meters (assumed camera distance from pitch)
-MAX_POSITION_JUMP = 30  # Pixels, tightened for continuous trajectory
+model.to('cuda' if torch.cuda.is_available() else 'cpu')
+
+# Dynamically resolve ball class index
+ball_class_index = None
+for k, v in model.names.items():
+    if v.lower() == "cricketball":
+        ball_class_index = k
+        break
+if ball_class_index is None:
+    raise ValueError("Class 'cricketBall' not found in model.names")
+
+# Constants
+STUMPS_WIDTH = 0.2286
+BALL_DIAMETER = 0.073
+FRAME_RATE = 20
+SLOW_MOTION_FACTOR = 3
+CONF_THRESHOLD = 0.2
+IMPACT_ZONE_Y = 0.85
+IMPACT_DELTA_Y = 50
+PITCH_LENGTH = 20.12
+STUMPS_HEIGHT = 0.71
+MAX_POSITION_JUMP = 30
 
 def process_video(video_path):
     if not os.path.exists(video_path):
         return [], [], [], "Error: Video file not found"
     cap = cv2.VideoCapture(video_path)
-    # Get native video resolution
     frame_width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
     frame_height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
-    frames = []
-    ball_positions = []
-    detection_frames = []
-    debug_log = []
-
+    frames, ball_positions, detection_frames, debug_log = [], [], [], []
     frame_count = 0
+
     while cap.isOpened():
         ret, frame = cap.read()
         if not ret:
             break
         frame_count += 1
         frames.append(frame.copy())
-        # Use native resolution for inference
         results = model.predict(frame, conf=CONF_THRESHOLD, imgsz=(frame_height, frame_width), iou=0.5, max_det=1)
         detections = 0
         for detection in results[0].boxes:
-            if detection.cls == 0:  # Class 0 is the ball
+            if int(detection.cls) == ball_class_index:
                 detections += 1
-                if detections == 1:  # Only consider frames with exactly one detection
+                if detections == 1:
                     x1, y1, x2, y2 = detection.xyxy[0].cpu().numpy()
                     ball_positions.append([(x1 + x2) / 2, (y1 + y2) / 2])
                     detection_frames.append(frame_count - 1)
@@ -68,258 +71,140 @@ def process_video(video_path):
 
     return frames, ball_positions, detection_frames, "\n".join(debug_log)
 
-def pixel_to_3d(x, y, frame_height, frame_width):
-    """Convert 2D pixel coordinates to 3D real-world coordinates."""
-    x_norm = x / frame_width
-    y_norm = y / frame_height
-    x_3d = (x_norm - 0.5) * 3.0  # Center x at 0 (middle of pitch)
-    y_3d = y_norm * PITCH_LENGTH
-    z_3d = (1 - y_norm) * BALL_DIAMETER * 5  # Scale to approximate ball bounce height
-    return x_3d, y_3d, z_3d
+def find_bounce_point(ball_coords):
+    """
+    Detect bounce point using y-derivative reversal with early-frame suppression.
+    Looks for where y increases then decreases (ball hits ground).
+    """
+    y_coords = [p[1] for p in ball_coords]
+    min_index = None
+
+    for i in range(2, len(y_coords) - 2):
+        dy1 = y_coords[i] - y_coords[i - 1]
+        dy2 = y_coords[i + 1] - y_coords[i]
+        if dy1 > 0 and dy2 < 0:
+            if i > len(y_coords) * 0.2:
+                min_index = i
+                break
+
+    if min_index is not None:
+        return ball_coords[min_index]
+    
+    return ball_coords[len(ball_coords)//2]
+
+def lbw_decision(ball_positions, trajectory, frames, pitch_point, impact_point):
+    if not frames or not trajectory or len(ball_positions) < 2:
+        return "Not enough data", trajectory, pitch_point, impact_point
 
-def estimate_trajectory(ball_positions, frames, detection_frames):
-    if len(ball_positions) < 2:
-        return None, None, None, None, None, None, None, None, None, "Error: Fewer than 2 ball detections for trajectory"
     frame_height, frame_width = frames[0].shape[:2]
+    stumps_x = frame_width / 2
+    stumps_y = frame_height * 0.9
+    stumps_width_pixels = frame_width * (STUMPS_WIDTH / 3.0)
+
+    pitch_x, _ = pitch_point
+    impact_x, impact_y = impact_point
+
+    if pitch_x < stumps_x - stumps_width_pixels / 2 or pitch_x > stumps_x + stumps_width_pixels / 2:
+        return f"Not Out (Pitched outside line)", trajectory, pitch_point, impact_point
+    if impact_x < stumps_x - stumps_width_pixels / 2 or impact_x > stumps_x + stumps_width_pixels / 2:
+        return f"Not Out (Impact outside line)", trajectory, pitch_point, impact_point
+    for x, y in trajectory:
+        if abs(x - stumps_x) < stumps_width_pixels / 2 and abs(y - stumps_y) < frame_height * 0.1:
+            return f"Out (Ball projected to hit stumps)", trajectory, pitch_point, impact_point
+    return f"Not Out (Missing stumps)", trajectory, pitch_point, impact_point
+
+def estimate_trajectory(ball_positions, detection_frames, frame_height, frame_width):
+    if len(ball_positions) < 2:
+        return None, None, None, "Error: Not enough ball detections"
 
-    # Filter out sudden changes in position for continuous trajectory
     filtered_positions = [ball_positions[0]]
     filtered_frames = [detection_frames[0]]
     for i in range(1, len(ball_positions)):
-        prev_pos = filtered_positions[-1]
-        curr_pos = ball_positions[i]
-        distance = np.sqrt((curr_pos[0] - prev_pos[0])**2 + (curr_pos[1] - prev_pos[1])**2)
-        if distance <= MAX_POSITION_JUMP:
-            filtered_positions.append(curr_pos)
+        prev, curr = filtered_positions[-1], ball_positions[i]
+        if np.linalg.norm(np.array(curr) - np.array(prev)) <= MAX_POSITION_JUMP:
+            filtered_positions.append(curr)
             filtered_frames.append(detection_frames[i])
-        else:
-            # Skip sudden jumps to maintain continuity
-            continue
 
     if len(filtered_positions) < 2:
-        return None, None, None, None, None, None, None, None, None, "Error: Fewer than 2 valid ball detections after filtering"
+        return None, None, None, "Error: Filtered detections too few"
 
-    x_coords = [pos[0] for pos in filtered_positions]
-    y_coords = [pos[1] for pos in filtered_positions]
+    x_vals = [p[0] for p in filtered_positions]
+    y_vals = [p[1] for p in filtered_positions]
     times = np.array(filtered_frames) / FRAME_RATE
 
-    pitch_point = filtered_positions[0]
-    pitch_frame = filtered_frames[0]
-
-    # Prioritize sudden y-change for impact detection
-    impact_idx = None
-    impact_frame = None
-    for i in range(1, len(y_coords)):
-        delta_y = abs(y_coords[i] - y_coords[i-1])
-        if delta_y > IMPACT_DELTA_Y:
-            impact_idx = i
-            impact_frame = filtered_frames[i]
-            break
-        elif y_coords[i] > frame_height * IMPACT_ZONE_Y:
-            impact_idx = i
-            impact_frame = filtered_frames[i]
-            break
-    if impact_idx is None:
-        impact_idx = len(filtered_positions) - 1
-        impact_frame = filtered_frames[-1]
-    impact_point = filtered_positions[impact_idx]
-
     try:
-        # Use cubic interpolation for smoother trajectory
-        fx = interp1d(times[:impact_idx + 1], x_coords[:impact_idx + 1], kind='cubic', fill_value="extrapolate")
-        fy = interp1d(times[:impact_idx + 1], y_coords[:impact_idx + 1], kind='cubic', fill_value="extrapolate")
+        fx = interp1d(times, x_vals, kind='cubic', fill_value="extrapolate")
+        fy = interp1d(times, y_vals, kind='cubic', fill_value="extrapolate")
     except Exception as e:
-        return None, None, None, None, None, None, None, None, None, f"Error in trajectory interpolation: {str(e)}"
+        return None, None, None, f"Interpolation error: {str(e)}"
 
-    # Generate dense points for all frames between first and last detection
-    total_frames = max(detection_frames) - min(detection_frames) + 1
-    t_full = np.linspace(times[0], times[-1], total_frames * SLOW_MOTION_FACTOR)
+    total_frames = max(filtered_frames) - min(filtered_frames) + 1
+    t_full = np.linspace(times[0], times[-1], max(5, total_frames * SLOW_MOTION_FACTOR))
     x_full = fx(t_full)
     y_full = fy(t_full)
-    trajectory_2d = list(zip(x_full, y_full))
-
-    trajectory_3d = [pixel_to_3d(x, y, frame_height, frame_width) for x, y in trajectory_2d]
-    detections_3d = [pixel_to_3d(x, y, frame_height, frame_width) for x, y in filtered_positions]
-    pitch_point_3d = pixel_to_3d(pitch_point[0], pitch_point[1], frame_height, frame_width)
-    impact_point_3d = pixel_to_3d(impact_point[0], impact_point[1], frame_height, frame_width)
-
-    debug_log = (
-        f"Trajectory estimated successfully\n"
-        f"Pitch point at frame {pitch_frame + 1}: ({pitch_point[0]:.1f}, {pitch_point[1]:.1f})\n"
-        f"Impact point at frame {impact_frame + 1}: ({impact_point[0]:.1f}, {impact_point[1]:.1f})\n"
-        f"Detections in frames: {filtered_frames}"
-    )
-    return trajectory_2d, pitch_point, impact_point, pitch_frame, impact_frame, detections_3d, trajectory_3d, pitch_point_3d, impact_point_3d, debug_log
-
-def create_3d_plot(detections_3d, trajectory_3d, pitch_point_3d, impact_point_3d, plot_type="detections"):
-    """Create 3D Plotly visualization for detections or trajectory using single-detection frames."""
-    stump_x = [-STUMPS_WIDTH/2, STUMPS_WIDTH/2, 0]
-    stump_y = [PITCH_LENGTH, PITCH_LENGTH, PITCH_LENGTH]
-    stump_z = [0, 0, 0]
-    stump_top_z = [STUMPS_HEIGHT, STUMPS_HEIGHT, STUMPS_HEIGHT]
-    bail_x = [-STUMPS_WIDTH/2, STUMPS_WIDTH/2]
-    bail_y = [PITCH_LENGTH, PITCH_LENGTH]
-    bail_z = [STUMPS_HEIGHT, STUMPS_HEIGHT]
-
-    stump_traces = []
-    for i in range(3):
-        stump_traces.append(go.Scatter3d(
-            x=[stump_x[i], stump_x[i]], y=[stump_y[i], stump_y[i]], z=[stump_z[i], stump_top_z[i]],
-            mode='lines', line=dict(color='black', width=5), name=f'Stump {i+1}'
-        ))
-    bail_traces = [
-        go.Scatter3d(
-            x=bail_x, y=bail_y, z=bail_z,
-            mode='lines', line=dict(color='black', width=5), name='Bail'
-        )
-    ]
-
-    pitch_scatter = go.Scatter3d(
-        x=[pitch_point_3d[0]] if pitch_point_3d else [], 
-        y=[pitch_point_3d[1]] if pitch_point_3d else [], 
-        z=[pitch_point_3d[2]] if pitch_point_3d else [],
-        mode='markers', marker=dict(size=8, color='red'), name='Pitch Point'
-    )
-    impact_scatter = go.Scatter3d(
-        x=[impact_point_3d[0]] if impact_point_3d else [], 
-        y=[impact_point_3d[1]] if impact_point_3d else [], 
-        z=[impact_point_3d[2]] if impact_point_3d else [],
-        mode='markers', marker=dict(size=8, color='yellow'), name='Impact Point'
-    )
-
-    if plot_type == "detections":
-        x, y, z = zip(*detections_3d) if detections_3d else ([], [], [])
-        scatter = go.Scatter3d(
-            x=x, y=y, z=z, mode='markers',
-            marker=dict(size=5, color='green'), name='Single Ball Detections'
-        )
-        data = [scatter, pitch_scatter, impact_scatter] + stump_traces + bail_traces
-        title = "3D Single Ball Detections"
-    else:
-        x, y, z = zip(*trajectory_3d) if trajectory_3d else ([], [], [])
-        trajectory_line = go.Scatter3d(
-            x=x, y=y, z=z, mode='lines',
-            line=dict(color='blue', width=4), name='Ball Trajectory (Single Detections)'
-        )
-        data = [trajectory_line, pitch_scatter, impact_scatter] + stump_traces + bail_traces
-        title = "3D Ball Trajectory (Single Detections)"
-
-    layout = go.Layout(
-        title=title,
-        scene=dict(
-            xaxis_title='X (meters)', yaxis_title='Y (meters)', zaxis_title='Z (meters)',
-            xaxis=dict(range=[-1.5, 1.5]), yaxis=dict(range=[0, PITCH_LENGTH]),
-            zaxis=dict(range=[0, STUMPS_HEIGHT * 2]), aspectmode='manual',
-            aspectratio=dict(x=1, y=4, z=0.5)
-        ),
-        showlegend=True
-    )
-    fig = go.Figure(data=data, layout=layout)
-    return fig
+    trajectory = list(zip(x_full, y_full))
 
-def lbw_decision(ball_positions, trajectory, frames, pitch_point, impact_point):
-    if not frames:
-        return "Error: No frames processed", None, None, None
-    if not trajectory or len(ball_positions) < 2:
-        return "Not enough data (insufficient ball detections)", None, None, None
+    pitch_point = find_bounce_point(filtered_positions)
+    impact_point = filtered_positions[-1]
 
-    frame_height, frame_width = frames[0].shape[:2]
-    stumps_x = frame_width / 2
-    stumps_y = frame_height * 0.9
-    stumps_width_pixels = frame_width * (STUMPS_WIDTH / 3.0)
+    return trajectory, pitch_point, impact_point, "Trajectory estimated successfully"
 
-    pitch_x, pitch_y = pitch_point
-    impact_x, impact_y = impact_point
+def generate_replay(frames, trajectory, pitch_point, impact_point, detection_frames):
+    if not frames or not trajectory:
+        return None
 
-    if pitch_x < stumps_x - stumps_width_pixels / 2 or pitch_x > stumps_x + stumps_width_pixels / 2:
-        return f"Not Out (Pitched outside line at x: {pitch_x:.1f}, y: {pitch_y:.1f})", trajectory, pitch_point, impact_point
-    if impact_x < stumps_x - stumps_width_pixels / 2 or impact_x > stumps_x + stumps_width_pixels / 2:
-        return f"Not Out (Impact outside line at x: {impact_x:.1f}, y: {impact_y:.1f})", trajectory, pitch_point, impact_point
-    for x, y in trajectory:
-        if abs(x - stumps_x) < stumps_width_pixels / 2 and abs(y - stumps_y) < frame_height * 0.1:
-            return f"Out (Ball hits stumps, Pitch at x: {pitch_x:.1f}, y: {pitch_y:.1f}, Impact at x: {impact_x:.1f}, y: {impact_y:.1f})", trajectory, pitch_point, impact_point
-    return f"Not Out (Missing stumps, Pitch at x: {pitch_x:.1f}, y: {pitch_y:.1f}, Impact at x: {impact_x:.1f}, y: {impact_y:.1f})", trajectory, pitch_point, impact_point
+    temp_file = os.path.join(tempfile.gettempdir(), f"drs_output_{uuid.uuid4()}.mp4")
+    height, width = frames[0].shape[:2]
+    out = cv2.VideoWriter(temp_file, cv2.VideoWriter_fourcc(*'mp4v'), FRAME_RATE / SLOW_MOTION_FACTOR, (width, height))
 
-def generate_slow_motion(frames, trajectory, pitch_point, impact_point, detection_frames, pitch_frame, impact_frame, output_path):
-    if not frames:
-        return None
-    frame_height, frame_width = frames[0].shape[:2]
-    fourcc = cv2.VideoWriter_fourcc(*'mp4v')
-    out = cv2.VideoWriter(output_path, fourcc, FRAME_RATE / SLOW_MOTION_FACTOR, (frame_width, frame_height))
-
-    # Map trajectory points to all frames between first and last detection
-    if trajectory and detection_frames:
-        min_frame = min(detection_frames)
-        max_frame = max(detection_frames)
-        total_frames = max_frame - min_frame + 1
-        trajectory_points = np.array(trajectory, dtype=np.int32).reshape((-1, 1, 2))
-        traj_per_frame = len(trajectory) // total_frames
-        trajectory_indices = [i * traj_per_frame for i in range(total_frames)]
-    else:
-        trajectory_points = np.array([], dtype=np.int32)
-        trajectory_indices = []
+    min_frame = min(detection_frames)
+    max_frame = max(detection_frames)
+    total_frames = max_frame - min_frame + 1
+    traj_per_frame = max(1, len(trajectory) // total_frames)
+    indices = [min(i * traj_per_frame, len(trajectory)-1) for i in range(total_frames)]
 
     for i, frame in enumerate(frames):
-        frame_idx = i - min_frame if trajectory_indices else -1
-        if frame_idx >= 0 and frame_idx < total_frames and trajectory_points.size > 0:
-            # Draw trajectory up to current frame
-            end_idx = trajectory_indices[frame_idx] + 1
-            cv2.polylines(frame, [trajectory_points[:end_idx]], False, (255, 0, 0), 2)
-        if pitch_point and i == pitch_frame:
-            x, y = pitch_point
-            cv2.circle(frame, (int(x), int(y)), 8, (0, 0, 255), -1)
-            cv2.putText(frame, "Pitch Point", (int(x) + 10, int(y) - 10), 
-                        cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 255), 2)
-        if impact_point and i == impact_frame:
-            x, y = impact_point
-            cv2.circle(frame, (int(x), int(y)), 8, (0, 255, 255), -1)
-            cv2.putText(frame, "Impact Point", (int(x) + 10, int(y) + 20), 
-                        cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 255, 255), 2)
+        idx = i - min_frame
+        if 0 <= idx < len(indices):
+            end_idx = indices[idx]
+            points = np.array(trajectory[:end_idx+1], dtype=np.int32).reshape((-1, 1, 2))
+            cv2.polylines(frame, [points], False, (255, 0, 0), 2)
+        if pitch_point and i == detection_frames[0]:
+            cv2.circle(frame, tuple(map(int, pitch_point)), 6, (0, 0, 255), -1)
+        if impact_point and i == detection_frames[-1]:
+            cv2.circle(frame, tuple(map(int, impact_point)), 6, (0, 255, 255), -1)
         for _ in range(SLOW_MOTION_FACTOR):
             out.write(frame)
     out.release()
-    return output_path
+    return temp_file
 
 def drs_review(video):
     frames, ball_positions, detection_frames, debug_log = process_video(video)
-    if not frames:
-        return f"Error: Failed to process video\nDebug Log:\n{debug_log}", None, None, None
-
-    trajectory_2d, pitch_point, impact_point, pitch_frame, impact_frame, detections_3d, trajectory_3d, pitch_point_3d, impact_point_3d, trajectory_log = estimate_trajectory(ball_positions, frames, detection_frames)
-    
-    if trajectory_2d is None:
-        return (f"Error: {trajectory_log}\nDebug Log:\n{debug_log}", None, None, None)
+    if not frames or not ball_positions:
+        return "No frames or detections found.", None
 
-    decision, trajectory_2d, pitch_point, impact_point = lbw_decision(ball_positions, trajectory_2d, frames, pitch_point, impact_point)
-
-    output_path = f"output_{uuid.uuid4()}.mp4"
-    slow_motion_path = generate_slow_motion(frames, trajectory_2d, pitch_point, impact_point, detection_frames, pitch_frame, impact_frame, output_path)
+    frame_height, frame_width = frames[0].shape[:2]
+    trajectory, pitch_point, impact_point, log = estimate_trajectory(ball_positions, detection_frames, frame_height, frame_width)
+    if not trajectory:
+        return f"{log}\n{debug_log}", None
 
-    detections_fig = None
-    trajectory_fig = None
-    if detections_3d:
-        detections_fig = create_3d_plot(detections_3d, trajectory_3d, pitch_point_3d, impact_point_3d, "detections")
-        trajectory_fig = create_3d_plot(detections_3d, trajectory_3d, pitch_point_3d, impact_point_3d, "trajectory")
+    decision, _, _, _ = lbw_decision(ball_positions, trajectory, frames, pitch_point, impact_point)
+    replay_path = generate_replay(frames, trajectory, pitch_point, impact_point, detection_frames)
 
-    debug_output = f"{debug_log}\n{trajectory_log}"
-    return (f"DRS Decision: {decision}\nDebug Log:\n{debug_output}", 
-            slow_motion_path, 
-            detections_fig, 
-            trajectory_fig)
+    result_log = f"DRS Decision: {decision}\n\n{log}\n\n{debug_log}"
+    return result_log, replay_path
 
-# Gradio interface
+# Gradio Interface
 iface = gr.Interface(
     fn=drs_review,
-    inputs=gr.Video(label="Upload Video Clip"),
+    inputs=gr.Video(label="Upload Cricket Delivery Video"),
     outputs=[
-        gr.Textbox(label="DRS Decision and Debug Log"),
-        gr.Video(label="Very Slow-Motion Replay with Ball Detection (Green), Trajectory (Blue Line), Pitch Point (Red), Impact Point (Yellow)"),
-        gr.Plot(label="3D Single Ball Detections Plot"),
-        gr.Plot(label="3D Ball Trajectory Plot (Single Detections)")
+        gr.Textbox(label="DRS Result and Debug Info"),
+        gr.Video(label="Replay with Trajectory & Decision")
     ],
-    title="AI-Powered DRS for LBW in Local Cricket",
-    description="Upload a video clip of a cricket delivery to get an LBW decision, a slow-motion replay, and 3D visualizations. The replay shows ball detection (green boxes), trajectory (blue line), pitch point (red circle), and impact point (yellow circle). The 3D plots show single-detection frames (green markers) and trajectory (blue line) with wicket lines (black), pitch point (red), and impact point (yellow)."
+    title="GullyDRS - AI-Powered LBW Review",
+    description="Upload a cricket delivery video. The system will track the ball, estimate trajectory, and return a replay with an OUT/NOT OUT decision."
 )
 
 if __name__ == "__main__":
-    iface.launch()
+    iface.launch()