Update app.py

app.py

@@ -17,123 +17,205 @@ workspace = os.getenv("ROBOFLOW_WORKSPACE")
 project_name = os.getenv("ROBOFLOW_PROJECT")
 model_version = int(os.getenv("ROBOFLOW_MODEL_VERSION"))
 
-# CountGD Config
+# CountGD Config (Replace DINO-X)
+# Set your CountGD API key in your .env file (e.g., COUNTGD_API_KEY=YourEncodedAPIKey)
 COUNTGD_API_KEY = os.getenv("COUNTGD_API_KEY")
 
-# Inisialisasi YOLO Model dari Roboflow
+# Inisialisasi YOLO Model from Roboflow
 rf = Roboflow(api_key=rf_api_key)
 project = rf.workspace(workspace).project(project_name)
 yolo_model = project.version(model_version).model
 
-# ========== Fungsi untuk Menghitung IoU ==========
-def iou(boxA, boxB):
-    xA = max(boxA[0], boxB[0])
-    yA = max(boxA[1], boxB[1])
-    xB = min(boxA[2], boxB[2])
-    yB = min(boxA[3], boxB[3])
-
-    interArea = max(0, xB - xA) * max(0, yB - yA)
-    boxAArea = (boxA[2] - boxA[0]) * (boxA[3] - boxA[1])
-    boxBArea = (boxB[2] - boxB[0]) * (boxB[3] - boxB[1])
-
-    return interArea / float(boxAArea + boxBArea - interArea) if (boxAArea + boxBArea - interArea) > 0 else 0
-
-# ========== Fungsi Deteksi Kombinasi ==========
+# ========== Function to Check Overlap ==========
+def is_overlap(box1, boxes2, threshold=0.3):
+    """
+    Checks if box1 (format: (x_min, y_min, x_max, y_max)) overlaps with any boxes in boxes2.
+    boxes2 is a list of YOLO bounding boxes in the format (x_center, y_center, width, height).
+    Returns True if the overlap ratio of box1 is greater than the threshold.
+    """
+    x1_min, y1_min, x1_max, y1_max = box1
+    for b2 in boxes2:
+        x_center, y_center, w2, h2 = b2
+        x2_min = x_center - w2 / 2
+        x2_max = x_center + w2 / 2
+        y2_min = y_center - h2 / 2
+        y2_max = y_center + h2 / 2
+
+        # Calculate overlap area
+        dx = min(x1_max, x2_max) - max(x1_min, x2_min)
+        dy = min(y1_max, y2_max) - max(y1_min, y2_min)
+        if dx > 0 and dy > 0:
+            area_overlap = dx * dy
+            area_box1 = (x1_max - x1_min) * (y1_max - y1_min)
+            if area_box1 > 0 and (area_overlap / area_box1) > threshold:
+                return True
+    return False
+
+# ========== Combined Object Detection Function ==========
 def detect_combined(image):
     with tempfile.NamedTemporaryFile(delete=False, suffix=".jpg") as temp_file:
         image.save(temp_file, format="JPEG")
         temp_path = temp_file.name
-
+    
     try:
-        # YOLO Detection (Produk Nestlé)
+        # ===== YOLO Detection (Nestlé products) =====
         yolo_pred = yolo_model.predict(temp_path, confidence=50, overlap=80).json()
         nestle_class_count = {}
-        nestle_boxes = []  # (x_center, y_center, width, height)
+        nestle_boxes = []  # List to hold YOLO bounding boxes (format: x_center, y_center, width, height)
         for pred in yolo_pred['predictions']:
             class_name = pred['class']
             nestle_class_count[class_name] = nestle_class_count.get(class_name, 0) + 1
             nestle_boxes.append((pred['x'], pred['y'], pred['width'], pred['height']))
-
         total_nestle = sum(nestle_class_count.values())
-
-        # CountGD Detection (Produk Kompetitor)
+        
+        # ===== CountGD Detection (Competitor products) =====
         url = "https://api.landing.ai/v1/tools/text-to-object-detection"
-        competitor_class_count = {}
-        competitor_boxes = []
-        COUNTGD_PROMPTS = ["cans", "bottle", "mixed box"]
+        files = {"image": open(temp_path, "rb")}
+        data = {"prompts": ["mixed box"], "model": "countgd"}
         headers = {"Authorization": f"Basic {COUNTGD_API_KEY}"}
-
-        for prompt in COUNTGD_PROMPTS:
-            with open(temp_path, "rb") as f:
-                files = {"image": f}
-                data = {"prompts": [prompt], "model": "countgd"}
-                response = requests.post(url, files=files, data=data, headers=headers)
-            result = response.json()
-
-            if 'data' in result and result['data']:
-                detections = result['data'][0]
-                detections_sorted = sorted(detections, key=lambda obj: obj.get('confidence', 0), reverse=True)
-
-                for obj in detections_sorted:
-                    if 'bounding_box' in obj:
-                        x1, y1, x2, y2 = obj['bounding_box']
-                        countgd_box = (x1, y1, x2, y2)
-
-                        # Hapus duplikasi dengan deteksi YOLO
-                        if any(iou(countgd_box, yolo_box) > 0.3 for yolo_box in nestle_boxes):
-                            continue
-
-                        # Hapus duplikasi antar deteksi CountGD
-                        if any(iou(countgd_box, existing_box) > 0.3 for existing_box in competitor_boxes):
-                            continue
-
-                        label = obj.get('label', prompt)
-                        
-                        # Hapus "mixed box" jika ada "cans" atau "bottle" yang lebih spesifik
-                        if label == "mixed box" and ("cans" in competitor_class_count or "bottle" in competitor_class_count):
-                            continue
-
-                        competitor_class_count[label] = competitor_class_count.get(label, 0) + 1
+        response = requests.post(url, files=files, data=data, headers=headers)
+        result = response.json()
+        
+        competitor_class_count = {}
+        competitor_boxes = []  # List to hold CountGD bounding boxes (format: x_min, y_min, x_max, y_max)
+        if 'data' in result:
+            for obj in result['data'][0]:
+                if 'bounding_box' in obj:
+                    # CountGD returns bounding_box as [x_min, y_min, x_max, y_max]
+                    x1, y1, x2, y2 = obj['bounding_box']
+                    countgd_box = (x1, y1, x2, y2)
+                    # Only add CountGD detection if it does NOT significantly overlap with any YOLO detection
+                    if not is_overlap(countgd_box, nestle_boxes, threshold=0.3):
+                        class_name = "unclassified"  # Generic label for competitor objects
+                        competitor_class_count[class_name] = competitor_class_count.get(class_name, 0) + 1
                         competitor_boxes.append(countgd_box)
-
         total_competitor = sum(competitor_class_count.values())
-
-        # Format Output Text
+        
+        # ===== Format Output Text =====
         result_text = "Product Nestlé\n\n"
         for class_name, count in nestle_class_count.items():
             result_text += f"{class_name}: {count}\n"
         result_text += f"\nTotal Products Nestlé: {total_nestle}\n\n"
-        
         if total_competitor:
-            result_text += f"\nTotal Unclassified Products: {total_competitor}\n"
+            result_text += f"Total Unclassified Products: {total_competitor}\n"
         else:
             result_text += "No Unclassified Products detected\n"
-
-        # Visualisasi Bounding Box
+        
+        # ===== Visualization =====
         img = cv2.imread(temp_path)
+        # Draw YOLO boxes in green
         for pred in yolo_pred['predictions']:
             x, y, w, h = pred['x'], pred['y'], pred['width'], pred['height']
             pt1 = (int(x - w/2), int(y - h/2))
             pt2 = (int(x + w/2), int(y + h/2))
             cv2.rectangle(img, pt1, pt2, (0, 255, 0), 2)
-            cv2.putText(img, pred['class'], (pt1[0], pt1[1]-10), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (0,255,0), 3)
-
+            cv2.putText(img, pred['class'], (pt1[0], pt1[1]-10),
+                        cv2.FONT_HERSHEY_SIMPLEX, 1.0, (0,255,0), 3)
+        # Draw CountGD boxes in red
         for box in competitor_boxes:
             x1, y1, x2, y2 = box
             cv2.rectangle(img, (int(x1), int(y1)), (int(x2), int(y2)), (0, 0, 255), 2)
-            cv2.putText(img, "unclassified", (int(x1), int(y1)-10), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (0,0,255), 3)
-
+            cv2.putText(img, "unclassified", (int(x1), int(y1)-10),
+                        cv2.FONT_HERSHEY_SIMPLEX, 1.0, (0,0,255), 3)
+        
         output_path = "/tmp/combined_output.jpg"
         cv2.imwrite(output_path, img)
         return output_path, result_text
-
+    
     except Exception as e:
         return temp_path, f"Error: {str(e)}"
-
+    
     finally:
         if os.path.exists(temp_path):
             os.remove(temp_path)
 
+# ========== Video Detection Functions ==========
+def convert_video_to_mp4(input_path, output_path):
+    try:
+        subprocess.run(['ffmpeg', '-i', input_path, '-vcodec', 'libx264', '-acodec', 'aac', output_path], check=True)
+        return output_path
+    except subprocess.CalledProcessError as e:
+        return None, f"Error converting video: {e}"
+
+def detect_objects_in_video(video_path):
+    temp_output_path = "/tmp/output_video.mp4"
+    temp_frames_dir = tempfile.mkdtemp()
+    frame_count = 0
+    previous_detections = {}  # For storing previous frame's detections
+
+    try:
+        # Convert video to MP4 if necessary
+        if not video_path.endswith(".mp4"):
+            video_path, err = convert_video_to_mp4(video_path, temp_output_path)
+            if not video_path:
+                return None, f"Video conversion error: {err}"
+
+        # Open video for processing
+        video = cv2.VideoCapture(video_path)
+        frame_rate = int(video.get(cv2.CAP_PROP_FPS))
+        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)
+
+        # Setup VideoWriter for output
+        fourcc = cv2.VideoWriter_fourcc(*'mp4v')
+        output_video = cv2.VideoWriter(temp_output_path, fourcc, frame_rate, frame_size)
+
+        while True:
+            ret, frame = video.read()
+            if not ret:
+                break
+
+            # Save frame for YOLO detection
+            frame_path = os.path.join(temp_frames_dir, f"frame_{frame_count}.jpg")
+            cv2.imwrite(frame_path, frame)
+
+            # YOLO detection on the frame
+            predictions = yolo_model.predict(frame_path, confidence=50, overlap=80).json()
+
+            # Draw YOLO detections on the frame
+            current_detections = {}
+            for prediction in predictions['predictions']:
+                class_name = prediction['class']
+                x, y, w, h = prediction['x'], prediction['y'], prediction['width'], prediction['height']
+                object_id = f"{class_name}_{x}_{y}_{w}_{h}"
+                if object_id not in current_detections:
+                    current_detections[object_id] = class_name
+                pt1 = (int(x - w/2), int(y - h/2))
+                pt2 = (int(x + w/2), int(y + h/2))
+                cv2.rectangle(frame, pt1, pt2, (0,255,0), 2)
+                cv2.putText(frame, class_name, (pt1[0], pt1[1]-10),
+                            cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0,255,0), 2)
+
+            # Count objects and overlay text
+            object_counts = {}
+            for detection_id in current_detections:
+                cls = current_detections[detection_id]
+                object_counts[cls] = object_counts.get(cls, 0) + 1
+
+            count_text = ""
+            total_product_count = 0
+            for cls, count in object_counts.items():
+                count_text += f"{cls}: {count}\n"
+                total_product_count += count
+            count_text += f"\nTotal Product: {total_product_count}"
+            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
+
+            output_video.write(frame)
+            frame_count += 1
+            previous_detections = current_detections
+
+        video.release()
+        output_video.release()
+
+        return temp_output_path
+
+    except Exception as e:
+        return None, f"An error occurred: {e}"
+
 # ========== Gradio Interface ==========
 with gr.Blocks(theme=gr.themes.Base(primary_hue="teal", secondary_hue="teal", neutral_hue="slate")) as iface:
     gr.Markdown("""<div style="text-align: center;"><h1>NESTLE - STOCK COUNTING</h1></div>""")
@@ -145,5 +227,10 @@ with gr.Blocks(theme=gr.themes.Base(primary_hue="teal", secondary_hue="teal", ne
             output_image = gr.Image(label="Detect Object")
             output_text = gr.Textbox(label="Counting Object")
             detect_image_button.click(fn=detect_combined, inputs=input_image, outputs=[output_image, output_text])
+        with gr.Column():
+            input_video = gr.Video(label="Input Video")
+            detect_video_button = gr.Button("Detect Video")
+            output_video = gr.Video(label="Output Video")
+            detect_video_button.click(fn=detect_objects_in_video, inputs=input_video, outputs=[output_video])
 
 iface.launch()