Update app.py

app.py

@@ -1,287 +1,174 @@
 import cv2
 import numpy as np
-import pandas as pd
-import plotly.express as px
-import plotly.graph_objects as go
 import torch
+from ultralytics import YOLO
 import gradio as gr
+from scipy.interpolate import interp1d
+import uuid
 import os
-import time
-from scipy.optimize import curve_fit
-import sys
 
-# Add yolov5 directory to sys.path
-sys.path.append(os.path.join(os.path.dirname(__file__), "yolov5"))
+# Load the trained YOLOv8n model from the Space's root directory
+model = YOLO("best.pt")  # Assumes best.pt is in the same directory as app.py
 
-# Import YOLOv5 modules
-from models.experimental import attempt_load
-from utils.general import non_max_suppression, xywh2xyxy
+# 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 = 30  # Input video frame rate
+SLOW_MOTION_FACTOR = 6  # For very slow motion (6x slower)
+CONF_THRESHOLD = 0.3  # Lowered confidence threshold for better detection
 
-# Cricket pitch dimensions (in meters)
-PITCH_LENGTH = 20.12  # Length of cricket pitch (stumps to stumps)
-PITCH_WIDTH = 3.05    # Width of pitch
-STUMP_HEIGHT = 0.71   # Stump height
-STUMP_WIDTH = 0.2286  # Stump width (including bails)
-
-# Model input size (adjust if yolov5s.pt was trained with a different size)
-MODEL_INPUT_SIZE = (640, 640)  # (height, width)
-FRAME_SKIP = 2  # Process every 2nd frame
-MIN_DETECTIONS = 10  # Stop after 10 detections
-BATCH_SIZE = 4  # Process 4 frames at a time
-SLOW_MOTION_FACTOR = 3  # Duplicate each frame 3 times for slow motion
-
-# Load model
-device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-model = attempt_load("best.pt")  # Load yolov5s.pt
-model.to(device).eval()  # Move model to device and set to evaluation mode
-
-# Function to process video and detect ball
 def process_video(video_path):
+    # Initialize video capture
+    if not os.path.exists(video_path):
+        return [], [], "Error: Video file not found"
     cap = cv2.VideoCapture(video_path)
-    frame_rate = cap.get(cv2.CAP_PROP_FPS)
-    frame_width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
-    frame_height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
-    positions = []
-    frame_numbers = []
-    bounce_frame = None
-    bounce_point = None
-    batch_frames = []
-    batch_frame_nums = []
-    frame_count = 0
+    frames = []
+    ball_positions = []
+    debug_log = []
 
-    start_time = time.time()
+    frame_count = 0
     while cap.isOpened():
-        frame_num = int(cap.get(cv2.CAP_PROP_POS_FRAMES))
         ret, frame = cap.read()
         if not ret:
             break
-
-        # Skip frames
-        if frame_count % FRAME_SKIP != 0:
-            frame_count += 1
-            continue
-
-        # Resize frame to model input size
-        frame = cv2.resize(frame, MODEL_INPUT_SIZE, interpolation=cv2.INTER_AREA)
-        batch_frames.append(frame)
-        batch_frame_nums.append(frame_num)
         frame_count += 1
-
-        # Process batch when full or at end
-        if len(batch_frames) == BATCH_SIZE or not ret:
-            # Preprocess batch
-            batch = [cv2.cvtColor(f, cv2.COLOR_BGR2RGB) for f in batch_frames]
-            batch = np.stack(batch)  # [batch_size, H, W, 3]
-            batch = torch.from_numpy(batch).to(device).float() / 255.0
-            batch = batch.permute(0, 3, 1, 2)  # [batch_size, 3, H, W]
-
-            # Run inference
-            frame_start_time = time.time()
-            with torch.no_grad():
-                pred = model(batch)[0]
-            pred = non_max_suppression(pred, conf_thres=0.25, iou_thres=0.45)
-            print(f"Batch inference time: {time.time() - frame_start_time:.2f}s for {len(batch_frames)} frames")
-
-            # Process detections
-            for i, det in enumerate(pred):
-                if det is not None and len(det):
-                    det = xywh2xyxy(det)  # Convert to [x1, y1, x2, y2]
-                    for *xyxy, conf, cls in det:
-                        x_center = (xyxy[0] + xyxy[2]) / 2
-                        y_center = (xyxy[1] + xyxy[3]) / 2
-                        # Scale coordinates back to original frame size
-                        x_center = x_center * frame_width / MODEL_INPUT_SIZE[1]
-                        y_center = y_center * frame_height / MODEL_INPUT_SIZE[0]
-                        positions.append((x_center.item(), y_center.item()))
-                        frame_numbers.append(batch_frame_nums[i])
-
-                        # Detect bounce (lowest y_center point)
-                        if bounce_frame is None or y_center > positions[bounce_frame][1]:
-                            bounce_frame = len(frame_numbers) - 1
-                            bounce_point = (x_center.item(), y_center.item())
-
-            batch_frames = []
-            batch_frame_nums = []
-
-            # Early termination
-            if len(positions) >= MIN_DETECTIONS:
-                break
-
+        frames.append(frame.copy())  # Store original frame
+        # Detect ball using the trained YOLOv8n model
+        results = model.predict(frame, conf=CONF_THRESHOLD)
+        detections = 0
+        for detection in results[0].boxes:
+            if detection.cls == 0:  # Assuming class 0 is the ball
+                detections += 1
+                x1, y1, x2, y2 = detection.xyxy[0].cpu().numpy()
+                ball_positions.append([(x1 + x2) / 2, (y1 + y2) / 2])
+                # Draw bounding box on frame for visualization
+                cv2.rectangle(frame, (int(x1), int(y1)), (int(x2), int(y2)), (0, 255, 0), 2)
+        frames[-1] = frame  # Update frame with bounding box
+        debug_log.append(f"Frame {frame_count}: {detections} ball detections")
     cap.release()
-    print(f"Total video processing time: {time.time() - start_time:.2f}s")
-    return positions, frame_numbers, bounce_point, frame_rate, frame_width, frame_height
 
-# Polynomial function for trajectory fitting
-def poly_func(x, a, b, c):
-    return a * x**2 + b * x + c
+    if not ball_positions:
+        debug_log.append("No balls detected in any frame")
+    else:
+        debug_log.append(f"Total ball detections: {len(ball_positions)}")
 
-# Predict trajectory and wicket inline path
-def predict_trajectory(positions, frame_numbers, frame_width, frame_height):
-    if len(positions) < 3:
-        return None, None, "Insufficient detections for trajectory prediction"
+    return frames, ball_positions, "\n".join(debug_log)
 
-    x_coords = [p[0] for p in positions]
-    y_coords = [p[1] for p in positions]
-    frames = np.array(frame_numbers)
+def estimate_trajectory(ball_positions, frames):
+    # Simplified physics-based trajectory projection
+    if len(ball_positions) < 2:
+        return None, None, "Error: Fewer than 2 ball detections for trajectory"
+    # Extract x, y coordinates
+    x_coords = [pos[0] for pos in ball_positions]
+    y_coords = [pos[1] for pos in ball_positions]
+    times = np.arange(len(ball_positions)) / FRAME_RATE
 
-    # Fit polynomial to x and y coordinates
+    # Interpolate to smooth trajectory
     try:
-        popt_x, _ = curve_fit(poly_func, frames, x_coords)
-        popt_y, _ = curve_fit(poly_func, frames, y_coords)
-    except:
-        return None, None, "Failed to fit trajectory"
-
-    # Extrapolate to stumps
-    frame_max = max(frames) + 10
-    future_frames = np.linspace(min(frames), frame_max, 100)
-    x_pred = poly_func(future_frames, *popt_x)
-    y_pred = poly_func(future_frames, *popt_y)
-
-    # Wicket inline path (center line toward stumps)
-    stump_x = frame_width / 2
-    stump_y = frame_height
-    inline_x = np.linspace(min(x_coords), stump_x, 100)
-    inline_y = np.interp(inline_x, x_pred, y_pred)
-
-    # Check if trajectory hits stumps
-    stump_hit = False
-    for x, y in zip(x_pred, y_pred):
-        if abs(y - stump_y) < 50 and abs(x - stump_x) < STUMP_WIDTH * frame_width / PITCH_WIDTH:
-            stump_hit = True
-            break
-
-    lbw_decision = "OUT" if stump_hit else "NOT OUT"
-    return list(zip(future_frames, x_pred, y_pred)), list(zip(inline_x, inline_y)), lbw_decision
-
-# Map pitch location
-def map_pitch(bounce_point, frame_width, frame_height):
-    if bounce_point is None:
-        return None, "No bounce detected"
-
-    x, y = bounce_point
-    pitch_x = (x / frame_width) * PITCH_WIDTH - PITCH_WIDTH / 2
-    pitch_y = (1 - y / frame_height) * PITCH_LENGTH
-    return pitch_x, pitch_y
-
-# Estimate ball speed
-def estimate_speed(positions, frame_numbers, frame_rate, frame_width):
-    if len(positions) < 2:
-        return None, "Insufficient detections for speed estimation"
-
-    distances = []
-    for i in range(1, len(positions)):
-        x1, y1 = positions[i-1]
-        x2, y2 = positions[i]
-        pixel_dist = np.sqrt((x2 - x1)**2 + (y2 - y1)**2)
-        distances.append(pixel_dist)
-
-    pixel_to_meter = PITCH_LENGTH / frame_width
-    distances_m = [d * pixel_to_meter for d in distances]
-    time_interval = 1 / frame_rate
-    speeds = [d / time_interval for d in distances_m]
-    avg_speed_kmh = np.mean(speeds) * 3.6
-    return avg_speed_kmh, "Speed calculated successfully"
-
-# Main Gradio function with video overlay and slow motion
-def drs_analysis(video):
-    # Video is a file path (string) in Hugging Face Spaces
-    video_path = video if isinstance(video, str) else "temp_video.mp4"
-    if not isinstance(video, str):
-        with open(video_path, "wb") as f:
-            f.write(video.read())
-
-    # Process video for detections
-    positions, frame_numbers, bounce_point, frame_rate, frame_width, frame_height = process_video(video_path)
-    if not positions:
-        return None, None, "No ball detected in video", None
-
-    # Predict trajectory and wicket path
-    trajectory, inline_path, lbw_decision = predict_trajectory(positions, frame_numbers, frame_width, frame_height)
-    if trajectory is None:
-        return None, None, lbw_decision, None
-
-    pitch_x, pitch_y = map_pitch(bounce_point, frame_width, frame_height)
-    speed_kmh, speed_status = estimate_speed(positions, frame_numbers, frame_rate, frame_width)
-
-    # Create output video with overlays and slow motion
-    output_path = "output_video.mp4"
-    cap = cv2.VideoCapture(video_path)
+        fx = interp1d(times, x_coords, kind='linear', fill_value="extrapolate")
+        fy = interp1d(times, y_coords, kind='quadratic', fill_value="extrapolate")
+    except Exception as e:
+        return None, None, f"Error in trajectory interpolation: {str(e)}"
+
+    # Project trajectory forward (0.5 seconds post-impact)
+    t_future = np.linspace(times[-1], times[-1] + 0.5, 10)
+    x_future = fx(t_future)
+    y_future = fy(t_future)
+
+    return list(zip(x_future, y_future)), t_future, "Trajectory estimated successfully"
+
+def lbw_decision(ball_positions, trajectory, frames):
+    # Simplified LBW logic
+    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
+
+    # Assume stumps are at the bottom center of the frame (calibration needed)
+    frame_height, frame_width = frames[0].shape[:2]
+    stumps_x = frame_width / 2
+    stumps_y = frame_height * 0.9  # Approximate stumps position
+    stumps_width_pixels = frame_width * (STUMPS_WIDTH / 3.0)  # Assume 3m pitch width
+
+    # Store pitch and impact points
+    pitch_point = ball_positions[0]
+    impact_point = ball_positions[-1]
+
+    # Check pitching point
+    pitch_x, pitch_y = pitch_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 at x: {pitch_x:.1f}, y: {pitch_y:.1f})", trajectory, pitch_point, impact_point
+
+    # Check impact point
+    impact_x, impact_y = 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
+
+    # Check trajectory hitting stumps
+    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
+
+def generate_slow_motion(frames, trajectory, pitch_point, impact_point, output_path):
+    # Generate very slow-motion video with ball detection, trajectory, and pitch/impact points
+    if not frames:
+        return None
     fourcc = cv2.VideoWriter_fourcc(*'mp4v')
-    out = cv2.VideoWriter(output_path, fourcc, frame_rate, (frame_width, frame_height))
-
-    frame_count = 0
-    positions_dict = dict(zip(frame_numbers, positions))
+    out = cv2.VideoWriter(output_path, fourcc, FRAME_RATE / SLOW_MOTION_FACTOR, (frames[0].shape[1], frames[0].shape[0]))
 
-    while cap.isOpened():
-        ret, frame = cap.read()
-        if not ret:
-            break
-
-        # Skip frames for consistency with detection
-        if frame_count % FRAME_SKIP != 0:
-            frame_count += 1
-            continue
-
-        # Overlay ball trajectory (red) and wicket inline path (blue)
-        if frame_count in positions_dict:
-            cv2.circle(frame, (int(positions_dict[frame_count][0]), int(positions_dict[frame_count][1])), 5, (0, 0, 255), -1)  # Red dot
+    for frame in frames:
+        # Draw trajectory
         if trajectory:
-            traj_x = [int(t[1]) for t in trajectory if t[0] >= frame_count]
-            traj_y = [int(t[2]) for t in trajectory if t[0] >= frame_count]
-            if traj_x and traj_y:
-                for i in range(1, len(traj_x)):
-                    cv2.line(frame, (traj_x[i-1], traj_y[i-1]), (traj_x[i], traj_y[i]), (0, 0, 255), 2)  # Red line
-        if inline_path:
-            inline_x = [int(x) for x, _ in inline_path]
-            inline_y = [int(y) for _, y in inline_path]
-            if inline_x and inline_y:
-                for i in range(1, len(inline_x)):
-                    cv2.line(frame, (inline_x[i-1], inline_y[i-1]), (inline_x[i], inline_y[i]), (255, 0, 0), 2)  # Blue line
-
-        # Overlay pitch map in top-right corner
-        if pitch_x is not None and pitch_y is not None:
-            map_width = 200
-            # Cap map_height to 25% of frame height to ensure it fits
-            map_height = min(int(map_width * PITCH_LENGTH / PITCH_WIDTH), frame_height // 4)
-            pitch_map = np.zeros((map_height, map_width, 3), dtype=np.uint8)
-            pitch_map[:] = (0, 255, 0)  # Green pitch
-            cv2.rectangle(pitch_map, (0, map_height-10), (map_width, map_height), (0, 51, 51), -1)  # Brown stumps
-            bounce_x = int((pitch_x + PITCH_WIDTH/2) / PITCH_WIDTH * map_width)
-            bounce_y = int((1 - pitch_y / PITCH_LENGTH) * map_height)
-            cv2.circle(pitch_map, (bounce_x, bounce_y), 5, (0, 0, 255), -1)  # Red bounce point
-            # Ensure overlay fits within frame
-            overlay_region = frame[0:map_height, frame_width-map_width:frame_width]
-            if overlay_region.shape[0] >= map_height and overlay_region.shape[1] >= map_width:
-                frame[0:map_height, frame_width-map_width:frame_width] = cv2.resize(pitch_map, (map_width, map_height))
-
-        # Add text annotations
-        text = f"LBW: {lbw_decision}\nSpeed: {speed_kmh:.2f} km/h"
-        cv2.putText(frame, text, (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 255, 255), 2, cv2.LINE_AA)
-
-        # Write frame multiple times for slow motion
-        for _ in range(SLOW_MOTION_FACTOR):
+            for x, y in trajectory:
+                cv2.circle(frame, (int(x), int(y)), 5, (255, 0, 0), -1)  # Blue dots for trajectory
+
+        # Draw pitch point (red circle with label)
+        if pitch_point:
+            x, y = pitch_point
+            cv2.circle(frame, (int(x), int(y)), 8, (0, 0, 255), -1)  # Red circle
+            cv2.putText(frame, "Pitch Point", (int(x) + 10, int(y) - 10), 
+                       cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 255), 2)
+
+        # Draw impact point (yellow circle with label)
+        if impact_point:
+            x, y = impact_point
+            cv2.circle(frame, (int(x), int(y)), 8, (0, 255, 255), -1)  # Yellow circle
+            cv2.putText(frame, "Impact Point", (int(x) + 10, int(y) + 20), 
+                       cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 255, 255), 2)
+
+        for _ in range(SLOW_MOTION_FACTOR):  # Duplicate frames for very slow motion
             out.write(frame)
-
-        frame_count += 1
-
-    cap.release()
     out.release()
+    return output_path
+
+def drs_review(video):
+    # Process video and generate DRS output
+    frames, ball_positions, debug_log = process_video(video)
+    if not frames:
+        return f"Error: Failed to process video\nDebug Log:\n{debug_log}", None
+    trajectory, _, trajectory_log = estimate_trajectory(ball_positions, frames)
+    decision, trajectory, pitch_point, impact_point = lbw_decision(ball_positions, trajectory, frames)
 
-    if not isinstance(video, str):
-        os.remove(video_path)
+    # Generate slow-motion replay with enhanced annotations
+    output_path = f"output_{uuid.uuid4()}.mp4"
+    slow_motion_path = generate_slow_motion(frames, trajectory, pitch_point, impact_point, output_path)
 
-    return None, None, None, output_path
+    # Combine debug logs for output
+    debug_output = f"{debug_log}\n{trajectory_log}"
+    return f"DRS Decision: {decision}\nDebug Log:\n{debug_output}", slow_motion_path
 
 # Gradio interface
-with gr.Blocks() as demo:
-    gr.Markdown("## Cricket DRS Analysis")
-    video_input = gr.Video(label="Upload Video Clip")
-    btn = gr.Button("Analyze")
-    trajectory_output = gr.Plot(label="Ball Trajectory")
-    pitch_output = gr.Plot(label="Pitch Map")
-    text_output = gr.Textbox(label="Analysis Results")
-    video_output = gr.Video(label="Processed Video")
-    btn.click(drs_analysis, inputs=video_input, outputs=[trajectory_output, pitch_output, text_output, video_output])
+iface = gr.Interface(
+    fn=drs_review,
+    inputs=gr.Video(label="Upload Video Clip"),
+    outputs=[
+        gr.Textbox(label="DRS Decision and Debug Log"),
+        gr.Video(label="Very Slow-Motion Replay with Ball Detection (Green), Trajectory (Blue), Pitch Point (Red), Impact Point (Yellow)")
+    ],
+    title="AI-Powered DRS for LBW in Local Cricket",
+    description="Upload a video clip of a cricket delivery to get an LBW decision and very slow-motion replay showing ball detection (green boxes), trajectory (blue dots), pitch point (red circle), and impact point (yellow circle)."
+)
 
 if __name__ == "__main__":
-    demo.launch()
+    iface.launch()