Update app.py

app.py

@@ -8,7 +8,7 @@ import cv2
 import numpy as np
 import subprocess
 
-# ========== Konfigurasi ========== 
+# ========== Konfigurasi ==========
 load_dotenv()
 
 # Roboflow Config
@@ -17,95 +17,205 @@ workspace = os.getenv("ROBOFLOW_WORKSPACE")
 project_name = os.getenv("ROBOFLOW_PROJECT")
 model_version = int(os.getenv("ROBOFLOW_MODEL_VERSION"))
 
-# Landing AI CountGD Config
-COUNTGD_API_KEY = os.getenv("COUNTGD_API_KEY")
-COUNTGD_URL = "https://api.landing.ai/v1/tools/text-to-object-detection"
-COUNTGD_PROMPT = ["beverage", "bottle", "cans", "mixed box"]  # Sesuaikan prompt
+# CountGD Config
+# Prompt yang digunakan untuk mendeteksi objek kompetitor
+COUNTGD_PROMPT = "beverage . bottle . cans . mixed box"
 
-# Inisialisasi Model
+# Inisialisasi Model YOLO dari Roboflow
 rf = Roboflow(api_key=rf_api_key)
 project = rf.workspace(workspace).project(project_name)
 yolo_model = project.version(model_version).model
 
-# ========== Fungsi Deteksi Kombinasi ========== 
+# ========== Fungsi Deteksi Kombinasi ==========
 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:
-        # ========== [1] YOLO: Deteksi Produk Nestlé ========== 
+        # ========== [1] YOLO: Deteksi Produk Nestlé (Per Class) ==========
         yolo_pred = yolo_model.predict(temp_path, confidence=50, overlap=80).json()
-        
+
+        # Hitung per class Nestlé dan simpan bounding box (format: (x_center, y_center, width, height))
         nestle_class_count = {}
         nestle_boxes = []
         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())
-        
-        # ========== [2] CountGD: Deteksi Kompetitor ========== 
-        with open(temp_path, 'rb') as img_file:
-            files = {"image": img_file}
-            data = {"prompts": COUNTGD_PROMPT, "model": "countgd"}
-            headers = {"Authorization": f"Basic {COUNTGD_API_KEY}"}
-            response = requests.post(COUNTGD_URL, files=files, data=data, headers=headers)
-            countgd_pred = response.json()
-        
+
+        # ========== [2] COUNTGD: Deteksi Kompetitor ==========
+        # Mengirimkan request ke endpoint CountGD sesuai dokumentasi:
+        # https://va.landing.ai/demo/api/Countgd%20Counting
+        countgd_url = "https://api.landing.ai/v1/tools/text-to-object-detection"
+        with open(temp_path, "rb") as image_file:
+            files = {"image": image_file}
+            data = {
+                "prompts": [COUNTGD_PROMPT],
+                "model": "countgd"
+            }
+            response = requests.post(countgd_url, files=files, data=data)
+        # Asumsikan respons JSON mengandung key "predictions" dengan daftar objek
+        countgd_pred = response.json()
+
         competitor_class_count = {}
         competitor_boxes = []
-        for obj in countgd_pred.get("objects", []):
-            class_name = obj['category'].strip().lower()
-            competitor_class_count[class_name] = competitor_class_count.get(class_name, 0) + 1
-            competitor_boxes.append({
-                "class": class_name,
-                "box": obj['bbox'],
-                "confidence": obj['score']
-            })
-        
+        for obj in countgd_pred.get("predictions", []):
+            countgd_box = obj["bbox"]  # Format: [x1, y1, x2, y2]
+            # Filter objek yang sudah terdeteksi oleh YOLO (menghindari duplikasi deteksi)
+            if not is_overlap(countgd_box, nestle_boxes):
+                class_name = obj["class"].strip().lower()
+                competitor_class_count[class_name] = competitor_class_count.get(class_name, 0) + 1
+                competitor_boxes.append({
+                    "class": class_name,
+                    "box": countgd_box,
+                    "confidence": obj["score"]
+                })
+
         total_competitor = sum(competitor_class_count.values())
-        
-        # ========== [3] Format Output ========== 
-        result_text = "Product Nestlé\n\n"
+
+        # ========== [3] Format Output ==========
+        result_text = "Product Nestle\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"
-        
+        result_text += f"\nTotal Products Nestle: {total_nestle}\n\n"
+
         if competitor_class_count:
             result_text += f"Total Unclassified Products: {total_competitor}\n"
         else:
             result_text += "No Unclassified Products detected\n"
-        
-        # ========== [4] Visualisasi ========== 
+
+        # ========== [4] Visualisasi ==========
         img = cv2.imread(temp_path)
-        
-        # Nestlé (Hijau)
+
+        # Tandai deteksi produk Nestlé (Hijau)
         for pred in yolo_pred['predictions']:
             x, y, w, h = pred['x'], pred['y'], pred['width'], pred['height']
-            cv2.rectangle(img, (int(x-w/2), int(y-h/2)), (int(x+w/2), int(y+h/2)), (0,255,0), 2)
-            cv2.putText(img, pred['class'], (int(x-w/2), int(y-h/2-10)), 
-                        cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0,255,0), 2)
-        
-        # Kompetitor (Merah)
+            cv2.rectangle(img, (int(x - w/2), int(y - h/2)), (int(x + w/2), int(y + h/2)), (0, 255, 0), 2)
+            cv2.putText(img, pred['class'], (int(x - w/2), int(y - h/2 - 10)),
+                        cv2.FONT_HERSHEY_SIMPLEX, 1.0, (0, 255, 0), 3)
+
+        # Tandai deteksi kompetitor (Merah), dengan pengecekan untuk merubah nama kelas menjadi 'unclassified'
         for comp in competitor_boxes:
             x1, y1, x2, y2 = comp['box']
+            unclassified_classes = ["beverage", "cans", "bottle", "mixed box"]
+            display_name = "unclassified" if any(c in comp['class'].lower() for c in unclassified_classes) else comp['class']
             cv2.rectangle(img, (int(x1), int(y1)), (int(x2), int(y2)), (0, 0, 255), 2)
-            cv2.putText(img, f"{comp['class']} {comp['confidence']:.2f}",
-                        (int(x1), int(y1-10)), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 255), 2)
-        
+            cv2.putText(img, f"{display_name} {comp['confidence']:.2f}",
+                        (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:
         os.remove(temp_path)
 
-# ========== Gradio Interface ========== 
+def is_overlap(box1, boxes2, threshold=0.3):
+    # Fungsi untuk mendeteksi overlap antara bounding box
+    x1_min, y1_min, x1_max, y1_max = box1
+    for b2 in boxes2:
+        x2, y2, w2, h2 = b2
+        x2_min = x2 - w2/2
+        x2_max = x2 + w2/2
+        y2_min = y2 - h2/2
+        y2_max = y2 + h2/2
+
+        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_overlap / area_box1 > threshold:
+                return True
+    return False
+
+# ========== Fungsi Deteksi Video (tetap menggunakan YOLO) ==========
+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 = {}
+
+    try:
+        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}"
+
+        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)
+
+        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
+
+            frame_path = os.path.join(temp_frames_dir, f"frame_{frame_count}.jpg")
+            cv2.imwrite(frame_path, frame)
+
+            predictions = yolo_model.predict(frame_path, confidence=50, overlap=80).json()
+
+            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
+
+                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)
+
+            object_counts = {}
+            for detection_id in current_detections.keys():
+                class_name = current_detections[detection_id]
+                object_counts[class_name] = object_counts.get(class_name, 0) + 1
+
+            count_text = ""
+            total_product_count = 0
+            for class_name, count in object_counts.items():
+                count_text += f"{class_name}: {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>""")
     
@@ -117,4 +227,10 @@ with gr.Blocks(theme=gr.themes.Base(primary_hue="teal", secondary_hue="teal", ne
             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()