Update app.py

app.py

@@ -23,7 +23,7 @@ model_version = int(os.getenv("ROBOFLOW_MODEL_VERSION"))
 
 # DINO-X Config
 DINOX_API_KEY = os.getenv("DINO_X_API_KEY")
-DINOX_PROMPT = "cans . bottle"  # Customize sesuai produk kompetitor : food . drink
+DINOX_PROMPT = "beverage . bottle"  # Customize sesuai produk kompetitor : food . drink
 
 # Inisialisasi Model
 rf = Roboflow(api_key=rf_api_key)
@@ -69,7 +69,8 @@ def detect_combined(image):
         competitor_boxes = []
         for obj in dinox_pred:
             dinox_box = obj.bbox
-            if not is_overlap(dinox_box, nestle_boxes):
+            # Filter objek yang sudah terdeteksi oleh YOLO (Overlap detection)
+            if not is_overlap(dinox_box, nestle_boxes):  # Ignore if overlap with YOLO detections
                 class_name = obj.category.strip().lower()  # Normalisasi nama kelas
                 competitor_class_count[class_name] = competitor_class_count.get(class_name, 0) + 1
                 competitor_boxes.append({
@@ -153,6 +154,9 @@ def convert_video_to_mp4(input_path, output_path):
 def detect_objects_in_video(video_path):
     temp_output_path = "/tmp/output_video.mp4"
     temp_frames_dir = tempfile.mkdtemp()
+    all_class_count = {}  # To store cumulative counts for all frames
+    nestle_total = 0  # Total Nestlé count
+    frame_count = 0
 
     try:
         # Convert video to MP4 if necessary
@@ -167,7 +171,6 @@ def detect_objects_in_video(video_path):
         frame_width = int(video.get(cv2.CAP_PROP_FRAME_WIDTH))
         frame_height = int(video.get(cv2.CAP_PROP_FRAME_HEIGHT))
         frame_size = (frame_width, frame_height)
-        frame_count = int(video.get(cv2.CAP_PROP_FRAME_COUNT))
 
         # VideoWriter for output video
         fourcc = cv2.VideoWriter_fourcc(*'mp4v')
@@ -185,11 +188,38 @@ def detect_objects_in_video(video_path):
             # Process predictions for frame
             predictions = yolo_model.predict(frame_path, confidence=60, overlap=80).json()
 
+            # Update class count for this frame
+            frame_class_count = {}
             for prediction in predictions['predictions']:
-                x, y, w, h = prediction['x'], prediction['y'], prediction['width'], prediction['height']
                 class_name = prediction['class']
-                cv2.rectangle(frame, (int(x - w/2), int(y - h/2)), (int(x + w/2), int(y + h/2)), (0, 255, 0), 2)
-                cv2.putText(frame, class_name, (int(x - w/2), int(y - h/2 - 10)), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
+                frame_class_count[class_name] = frame_class_count.get(class_name, 0) + 1
+                cv2.rectangle(frame, (int(prediction['x'] - prediction['width']/2), 
+                                      int(prediction['y'] - prediction['height']/2)),
+                              (int(prediction['x'] + prediction['width']/2), 
+                               int(prediction['y'] + prediction['height']/2)),
+                              (0, 255, 0), 2)
+                cv2.putText(frame, class_name, (int(prediction['x'] - prediction['width']/2),
+                                                int(prediction['y'] - prediction['height']/2 - 10)),
+                            cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
+
+            # Update cumulative count for all frames
+            for class_name, count in frame_class_count.items():
+                all_class_count[class_name] = all_class_count.get(class_name, 0) + count
+
+            # Update total Nestlé products count
+            nestle_total = sum(all_class_count.values())
+
+            # Create a vertical layout for counts (dynamically updated)
+            count_text = "Cumulative Object Counts\n"
+            for class_name, count in all_class_count.items():
+                count_text += f"{class_name}: {count}\n"
+            count_text += f"\nTotal Product Nestlé: {nestle_total}"
+
+            # Overlay the counts text onto the frame
+            y_offset = 20
+            for line in count_text.split("\n"):
+                cv2.putText(frame, line, (10, y_offset), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (255, 255, 255), 2)
+                y_offset += 30  # Move down for next line
 
             # Write processed frame to output video
             output_video.write(frame)
@@ -198,7 +228,7 @@ def detect_objects_in_video(video_path):
         video.release()
         output_video.release()
 
-        return temp_output_path
+        return temp_output_path, count_text
 
     except Exception as e:
         return None, f"An error occurred: {e}"
@@ -226,10 +256,11 @@ with gr.Blocks(theme=gr.themes.Base(primary_hue="teal", secondary_hue="teal", ne
             input_video = gr.Video(label="Input Video")
             detect_video_button = gr.Button("Detect Video")
             output_video = gr.Video(label="Output Video")
+            output_video_text = gr.Textbox(label="Counting Object")
             detect_video_button.click(
                 fn=detect_objects_in_video,
                 inputs=input_video,
-                outputs=[output_video]
+                outputs=[output_video, output_video_text]
             )
 
 iface.launch()