Update app.py

app.py

@@ -44,8 +44,8 @@ last_metrics: Dict[str, Any] = {}
 frame_count: int = 0
 SAVE_IMAGE_INTERVAL = 1  # Save every frame with detections
 
-# Detection classes (as per original code)
-DETECTION_CLASSES = ["Longitudinal", "Pothole", "Transverse", "Crack"]
+# Detection classes (aligned with model classes, excluding 'Crocodile' and 'Crack')
+DETECTION_CLASSES = ["Longitudinal", "Pothole", "Transverse"]
 
 # Debug: Check environment
 print(f"Torch version: {torch.__version__}")
@@ -106,10 +106,13 @@ def write_flight_log(frame_count: int, gps_coord: List[float], timestamp: str) -
         log_entries.append(f"Error: Failed to write flight log {log_path}: {str(e)}")
         return ""
 
-def check_image_quality(frame: np.ndarray) -> bool:
+def check_image_quality(frame: np.ndarray, input_resolution: int) -> bool:
     height, width, _ = frame.shape
-    if width * height < 12_000_000:  # 12 MP requirement
-        log_entries.append(f"Frame {frame_count}: Resolution below 12MP")
+    frame_resolution = width * height
+    if frame_resolution < 12_000_000:  # NHAI requires 12 MP
+        log_entries.append(f"Frame {frame_count}: Resolution {width}x{height} ({frame_resolution/1e6:.2f}MP) below 12MP, non-compliant")
+    if frame_resolution < input_resolution:  # Ensure output is not below input
+        log_entries.append(f"Frame {frame_count}: Output resolution {width}x{height} below input resolution")
         return False
     return True
 
@@ -136,7 +139,7 @@ def generate_line_chart() -> Optional[str]:
     plt.close()
     return chart_path
 
-def process_video(video, resize_width=320, resize_height=240, frame_skip=5):
+def process_video(video, resize_width=4000, resize_height=3000, frame_skip=5):
     global frame_count, last_metrics, detected_counts, detected_issues, gps_coordinates, log_entries
     frame_count = 0
     detected_counts.clear()
@@ -159,12 +162,13 @@ def process_video(video, resize_width=320, resize_height=240, frame_skip=5):
 
     frame_width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
     frame_height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+    input_resolution = frame_width * frame_height
     fps = cap.get(cv2.CAP_PROP_FPS)
     total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
     expected_duration = total_frames / fps if fps > 0 else 0
-    log_entries.append(f"Input video: {frame_width}x{frame_height}, {fps} FPS, {total_frames} frames, {expected_duration:.2f} seconds")
-    logging.info(f"Input video: {frame_width}x{frame_height}, {fps} FPS, {total_frames} frames, {expected_duration:.2f} seconds")
-    print(f"Input video: {frame_width}x{frame_height}, {fps} FPS, {total_frames} frames, {expected_duration:.2f} seconds")
+    log_entries.append(f"Input video: {frame_width}x{frame_height} ({input_resolution/1e6:.2f}MP), {fps} FPS, {total_frames} frames, {expected_duration:.2f} seconds")
+    logging.info(f"Input video: {frame_width}x{frame_height} ({input_resolution/1e6:.2f}MP), {fps} FPS, {total_frames} frames, {expected_duration:.2f} seconds")
+    print(f"Input video: {frame_width}x{frame_height} ({input_resolution/1e6:.2f}MP), {fps} FPS, {total_frames} frames, {expected_duration:.2f} seconds")
 
     out_width, out_height = resize_width, resize_height
     output_path = os.path.join(OUTPUT_DIR, "processed_output.mp4")
@@ -213,7 +217,7 @@ def process_video(video, resize_width=320, resize_height=240, frame_skip=5):
         frame_start = time.time()
 
         frame = cv2.resize(frame, (out_width, out_height))
-        if not check_image_quality(frame):
+        if not check_image_quality(frame, input_resolution):
             log_entries.append(f"Frame {frame_count}: Skipped due to low resolution")
             continue
 
@@ -232,7 +236,7 @@ def process_video(video, resize_width=320, resize_height=240, frame_skip=5):
             conf = float(detection.conf)
             box = detection.xyxy[0].cpu().numpy().astype(int).tolist()
             label = model.names[cls]
-            if label in DETECTION_CLASSES:  # Only process relevant classes
+            if label in DETECTION_CLASSES:
                 frame_detections.append({
                     "label": label,
                     "box": box,
@@ -327,8 +331,8 @@ def process_video(video, resize_width=320, resize_height=240, frame_skip=5):
     total_time = time.time() - start_time
     avg_frame_time = sum(frame_times) / len(frame_times) if frame_times else 0
     log_entries.append(f"Output video: {output_frames} frames, {output_fps} FPS, {output_duration:.2f} seconds")
-    log_entries.append(f"Total processing time: {total_time:.2f} seconds, Avg frame time: {avg_frame_time:.2f} ms, Detection frames: {detection_frame_count}, Output frames: {output_frame_count}")
     logging.info(f"Output video: {output_frames} frames, {output_fps} FPS, {output_duration:.2f} seconds")
+    log_entries.append(f"Total processing time: {total_time:.2f} seconds, Avg frame time: {avg_frame_time:.2f} ms, Detection frames: {detection_frame_count}, Output frames: {output_frame_count}")
     logging.info(f"Total processing time: {total_time:.2f} seconds, Avg frame time: {avg_frame_time:.2f} ms, Detection frames: {detection_frame_count}, Output frames: {output_frame_count}")
     print(f"Output video: {output_frames} frames, {output_fps} FPS, {output_duration:.2f} seconds")
     print(f"Total processing time: {total_time:.2f} seconds, Avg frame time: {avg_frame_time:.2f} ms, Detection frames: {detection_frame_count}, Output frames: {output_frame_count}")
@@ -350,9 +354,9 @@ with gr.Blocks(theme=gr.themes.Soft(primary_hue="orange")) as iface:
     gr.Markdown("# NHAI Road Defect Detection Dashboard")
     with gr.Row():
         with gr.Column(scale=3):
-            video_input = gr.Video(label="Upload Video")
-            width_slider = gr.Slider(320, 640, value=320, label="Output Width", step=1)
-            height_slider = gr.Slider(240, 480, value=240, label="Output Height", step=1)
+            video_input = gr.Video(label="Upload Video (12MP recommended for NHAI compliance)")
+            width_slider = gr.Slider(320, 4000, value=4000, label="Output Width", step=1)
+            height_slider = gr.Slider(240, 3000, value=3000, label="Output Height", step=1)
             skip_slider = gr.Slider(1, 10, value=5, label="Frame Skip", step=1)
             process_btn = gr.Button("Process Video", variant="primary")
         with gr.Column(scale=1):