Update app.py

app.py

@@ -72,28 +72,41 @@ def process_video(video_path, target, progress=gr.Progress()):
 
                 boxes, scores, labels = result["boxes"], result["scores"], result["labels"]
 
+                # Inside the loop where bounding boxes are drawn
                 for box, score, label in zip(boxes, scores, labels):
                     if score.item() >= 0.5:
                         box = [round(i, 2) for i in box.tolist()]
                         object_label = target
                         confidence = round(score.item(), 3)
                         annotation = f"{object_label}: {confidence}"
-
+                
                         # Increase line width for the bounding box
                         draw.rectangle(box, outline="red", width=3)
-
-                        # Increase font size and change color to red
-                        font_size = 100
+                
+                        # Calculate font size based on image dimensions
+                        img_width, img_height = pil_img.size
+                        font_size = int(min(img_width, img_height) * 0.03)  # 3% of the smaller dimension
                         try:
                             font = ImageFont.truetype("arial.ttf", font_size)
                         except IOError:
                             font = ImageFont.load_default()
-
-                        text_position = (box[0], box[1] - font_size - 5)
-
+                
+                        # Calculate text size
+                        text_bbox = draw.textbbox((0, 0), annotation, font=font)
+                        text_width = text_bbox[2] - text_bbox[0]
+                        text_height = text_bbox[3] - text_bbox[1]
+                
+                        # Position text inside the top of the bounding box
+                        text_position = (box[0], box[1])
+                
+                        # Draw semi-transparent background for text
+                        draw.rectangle([text_position[0], text_position[1], 
+                                        text_position[0] + text_width, text_position[1] + text_height], 
+                                       fill=(0, 0, 0, 128))
+                
                         # Draw text in red
                         draw.text(text_position, annotation, fill="red", font=font)
-
+                
                         max_score = max(max_score, confidence)
 
                 frame_path = os.path.join(temp_dir, f"frame_{batch_indices[idx]:04d}.png")