Update app.py

app.py

@@ -13,7 +13,7 @@ from ultralytics import YOLO
 import ultralytics
 import time
 
-# Set YOLO config directory early to avoid warning
+# Set YOLO config directory
 os.environ["YOLO_CONFIG_DIR"] = "/tmp/Ultralytics"
 
 # Set up logging
@@ -38,11 +38,12 @@ detected_issues: List[str] = []
 gps_coordinates: List[List[float]] = []
 last_metrics: Dict[str, Any] = {}
 frame_count: int = 0
+SAVE_IMAGE_INTERVAL = 1  # Save every frame with detections
 
 # Debug: Check environment
 print(f"Torch version: {torch.__version__}")
 print(f"Gradio version: {gr.__version__}")
-print(f"Ultralytics version: {ultralytics.__version__}")  # Fixed: Use ultralytics.__version__
+print(f"Ultralytics version: {ultralytics.__version__}")
 print(f"CUDA available: {torch.cuda.is_available()}")
 
 # Load custom YOLO model
@@ -58,7 +59,7 @@ def generate_map(gps_coords: List[List[float]], items: List[Dict[str, Any]]) ->
     map_path = "map_temp.png"
     plt.figure(figsize=(4, 4))
     plt.scatter([x[1] for x in gps_coords], [x[0] for x in gps_coords], c='blue', label='GPS Points')
-    plt.title("Mock Issue Locations Map")
+    plt.title("Issue Locations Map")
     plt.xlabel("Longitude")
     plt.ylabel("Latitude")
     plt.legend()
@@ -67,7 +68,7 @@ def generate_map(gps_coords: List[List[float]], items: List[Dict[str, Any]]) ->
     return map_path
 
 def send_to_salesforce(data: Dict[str, Any]) -> None:
-    logging.info(f"Mock Salesforce dispatch: {json.dumps(data, indent=2)}")
+    pass  # Minimal mock
 
 def update_metrics(detections: List[Dict[str, Any]]) -> Dict[str, Any]:
     counts = Counter([det["label"] for det in detections])
@@ -129,6 +130,8 @@ def process_video(video, resize_width=320, resize_height=240, frame_skip=5):
 
     processed_frames = 0
     all_detections = []
+    frame_times = []
+    detection_frame_count = 0
 
     while True:
         ret, frame = cap.read()
@@ -138,10 +141,10 @@ def process_video(video, resize_width=320, resize_height=240, frame_skip=5):
         if frame_count % frame_skip != 0:
             continue
         processed_frames += 1
-        print(f"Processing frame {frame_count}/{total_frames}")
+        frame_start = time.time()
 
         frame = cv2.resize(frame, (out_width, out_height))
-        results = model(frame, verbose=False, conf=0.5, iou=0.7)
+        results = model(frame, verbose=False, conf=0.5, iou=0.7)  # Lower thresholds
         annotated_frame = results[0].plot()
 
         frame_detections = []
@@ -155,20 +158,16 @@ def process_video(video, resize_width=320, resize_height=240, frame_skip=5):
             logging.info(f"Frame {frame_count}: Detected {label} with confidence {conf:.2f}")
 
         if frame_detections:
-            captured_frame_path = os.path.join(CAPTURED_FRAMES_DIR, f"detected_{frame_count}.jpg")
-            cv2.imwrite(captured_frame_path, annotated_frame)
-            detected_issues.append(captured_frame_path)
-            if len(detected_issues) > 100:
-                detected_issues.pop(0)
-
-        frame_path = os.path.join(OUTPUT_DIR, f"frame_{frame_count:04d}.jpg")
-        cv2.imwrite(frame_path, annotated_frame)
-
-        gps_coord = [17.385044 + (frame_count * 0.0001), 78.486671 + (frame_count * 0.0001)]
-        gps_coordinates.append(gps_coord)
-        for det in frame_detections:
-            det["gps"] = gps_coord
-        all_detections.extend(frame_detections)
+            detection_frame_count += 1
+            if detection_frame_count % SAVE_IMAGE_INTERVAL == 0:
+                captured_frame_path = os.path.join(CAPTURED_FRAMES_DIR, f"detected_{frame_count}.jpg")
+                if not cv2.imwrite(captured_frame_path, annotated_frame):
+                    log_entries.append(f"Error: Failed to save {captured_frame_path}")
+                    logging.error(f"Failed to save {captured_frame_path}")
+                else:
+                    detected_issues.append(captured_frame_path)
+                    if len(detected_issues) > 100:
+                        detected_issues.pop(0)
 
         out.write(annotated_frame)
         if frame_skip > 1:
@@ -178,27 +177,34 @@ def process_video(video, resize_width=320, resize_height=240, frame_skip=5):
                     frame_count += 1
 
         detected_counts.append(len(frame_detections))
-        last_metrics = update_metrics(all_detections)
+        gps_coord = [17.385044 + (frame_count * 0.0001), 78.486671 + (frame_count * 0.0001)]
+        gps_coordinates.append(gps_coord)
+        for det in frame_detections:
+            det["gps"] = gps_coord
+        all_detections.extend(frame_detections)
+
+        frame_time = (time.time() - frame_start) * 1000
+        frame_times.append(frame_time)
         detection_summary = {
             "timestamp": datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
             "frame": frame_count,
             "cracks": sum(1 for det in frame_detections if det["label"] == "crack"),
             "potholes": sum(1 for det in frame_detections if det["label"] == "pothole"),
             "gps": gps_coord,
-            "processing_time_ms": (time.time() - start_time) * 1000 / processed_frames if processed_frames else 0
+            "processing_time_ms": frame_time
         }
         log_entries.append(json.dumps(detection_summary, indent=2))
-        logging.info(json.dumps(detection_summary, indent=2))
-        if len(log_entries) > 100:
+        if len(log_entries) > 50:
             log_entries.pop(0)
 
-        send_to_salesforce({
-            "detections": frame_detections,
-            "metrics": last_metrics,
-            "timestamp": detection_summary["timestamp"],
-            "frame_count": frame_count,
-            "gps_coordinates": gps_coord
-        })
+    last_metrics = update_metrics(all_detections)
+    send_to_salesforce({
+        "detections": all_detections,
+        "metrics": last_metrics,
+        "timestamp": detection_summary["timestamp"] if all_detections else datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
+        "frame_count": frame_count,
+        "gps_coordinates": gps_coordinates[-1] if gps_coordinates else [0, 0]
+    })
 
     cap.release()
     out.release()
@@ -209,10 +215,14 @@ def process_video(video, resize_width=320, resize_height=240, frame_skip=5):
     output_duration = output_frames / output_fps
     cap.release()
 
+    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}")
     logging.info(f"Output video: {output_frames} frames, {output_fps} FPS, {output_duration:.2f} seconds")
+    logging.info(f"Total processing time: {total_time:.2f} seconds, Avg frame time: {avg_frame_time:.2f} ms, Detection frames: {detection_frame_count}")
     print(f"Output video: {output_frames} frames, {output_fps} FPS, {output_duration:.2f} seconds")
-    print(f"Processing time: {time.time() - start_time:.2f} seconds")
+    print(f"Total processing time: {total_time:.2f} seconds, Avg frame time: {avg_frame_time:.2f} ms, Detection frames: {detection_frame_count}")
 
     chart_path = generate_line_chart()
     map_path = generate_map(gps_coordinates[-5:], all_detections)
@@ -232,20 +242,20 @@ with gr.Blocks(theme=gr.themes.Soft(primary_hue="orange")) as iface:
     with gr.Row():
         with gr.Column(scale=3):
             video_input = gr.Video(label="Upload Video")
-            width_slider = gr.Slider(320, 1280, value=320, label="Output Width", step=1)
-            height_slider = gr.Slider(240, 720, value=240, label="Output Height", step=1)
+            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)
             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):
-            metrics_output = gr.Textbox(label="Detection Metrics", lines=10, interactive=False)
+            metrics_output = gr.Textbox(label="Detection Metrics", lines=5, interactive=False)
     with gr.Row():
         video_output = gr.Video(label="Processed Video")
-        issue_gallery = gr.Gallery(label="Detected Issues", columns=4, height="auto")
+        issue_gallery = gr.Gallery(label="Detected Issues", columns=4, height="auto", object_fit="contain")
     with gr.Row():
         chart_output = gr.Image(label="Detection Trend")
         map_output = gr.Image(label="Issue Locations Map")
     with gr.Row():
-        logs_output = gr.Textbox(label="Logs", lines=8, interactive=False)
+        logs_output = gr.Textbox(label="Logs", lines=5, interactive=False)
 
     process_btn.click(
         process_video,