Update app.py

app.py

@@ -95,27 +95,34 @@ def detect_objects(image):
         # Get color for this class
         color = colors[class_id].tolist()
         
-        # Draw bounding box
-        cv2.rectangle(output_image, (x1, y1), (x2, y2), color, 2)
+        cv2.rectangle(output_image, (x1, y1), (x2, y2), color, 4)
         
         # Create label with class name and confidence score
         label = f"{model.names[class_id]} {conf:.2f}"
         
-        # Calculate text size for background rectangle
-        (w, h), _ = cv2.getTextSize(label, cv2.FONT_HERSHEY_SIMPLEX, 0.5, 1)
+        font_scale = 0.8
+        font_thickness = 2
         
-        # Draw label background
-        cv2.rectangle(output_image, (x1, y1 - 20), (x1 + w, y1), color, -1)
+        (w, h), _ = cv2.getTextSize(label, cv2.FONT_HERSHEY_SIMPLEX, font_scale, font_thickness)
+  
+        cv2.rectangle(output_image, (x1, y1 - h - 10), (x1 + w + 10, y1), color, -1)
         
-        # Draw label text
-        cv2.putText(output_image, label, (x1, y1 - 5),
-                    cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 255, 255), 1)
+        cv2.putText(output_image, label, (x1 + 5, y1 - 5),
+                    cv2.FONT_HERSHEY_SIMPLEX, font_scale, (0, 0, 0), font_thickness + 1)
+        cv2.putText(output_image, label, (x1 + 5, y1 - 5),
+                    cv2.FONT_HERSHEY_SIMPLEX, font_scale, (255, 255, 255), font_thickness)
     
     # Calculate FPS
     fps = 1 / inference_time
     
-    # Add FPS counter to the image
-    cv2.putText(output_image, f"FPS: {fps:.2f}", (10, 30),
+    fps_overlay = output_image.copy()
+    cv2.rectangle(fps_overlay, (5, 5), (250, 80), (0, 0, 0), -1)
+    # Apply the overlay with transparency
+    alpha = 0.7
+    output_image = cv2.addWeighted(fps_overlay, alpha, output_image, 1 - alpha, 0)
+    
+    # Display FPS with larger font
+    cv2.putText(output_image, f"FPS: {fps:.2f}", (10, 35),
                 cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
     cv2.putText(output_image, f"Avg FPS: {1/avg_inference_time:.2f}", (10, 70),
                 cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
@@ -142,16 +149,15 @@ with gr.Blocks(title="Optimized YOLOv5 Object Detection") as demo:
     - Processing speed: Optimized for 30+ FPS at 640x640 resolution
     - Confidence threshold: 0.3
     - IoU threshold: 0.3
-    - Real-time FPS display
     
-    Simply upload an image or take a photo with your camera to see the detections!
+    Simply upload an image and click Submit to see the detections!
     """)
     
     with gr.Row():
         with gr.Column(scale=1):
             input_image = gr.Image(label="Input Image", type="numpy")
             with gr.Row():
-                camera_button = gr.Button("Take Photo from Camera")
+                submit_button = gr.Button("Submit", variant="primary")
                 clear_button = gr.Button("Clear")
                 
         with gr.Column(scale=1):
@@ -166,12 +172,10 @@ with gr.Blocks(title="Optimized YOLOv5 Object Detection") as demo:
         cache_examples=True  # Cache for faster response
     )
     
-    # Set up the inference call
-    input_image.change(fn=detect_objects, inputs=input_image, outputs=output_image)
-    
-    # Event listeners for buttons
-    camera_button.click(lambda: None, None, input_image, js="() => {document.querySelector('button.webcam').click(); return null}")
+    # Set up button event handlers
+    submit_button.click(fn=detect_objects, inputs=input_image, outputs=output_image)
     clear_button.click(lambda: None, None, [input_image, output_image])
+    
 
 # Launch for Hugging Face Spaces
 demo.launch()