Update app.py

app.py

@@ -3,10 +3,9 @@ from dotenv import load_dotenv
 from roboflow import Roboflow
 import tempfile
 import os
-import requests
 import cv2
 import numpy as np
-import subprocess
+import vision_agent.tools as T
 
 # ========== Konfigurasi ==========
 load_dotenv()
@@ -18,10 +17,9 @@ project_name = os.getenv("ROBOFLOW_PROJECT")
 model_version = int(os.getenv("ROBOFLOW_MODEL_VERSION"))
 
 # CountGD Config
-# Prompt yang digunakan untuk mendeteksi objek kompetitor
-COUNTGD_PROMPT = "beverage . bottle . cans . mixed box"
+COUNTGD_PROMPT = "cans . bottle"  # Customize sesuai kebutuhan
 
-# Inisialisasi Model YOLO dari Roboflow
+# Inisialisasi Model
 rf = Roboflow(api_key=rf_api_key)
 project = rf.workspace(workspace).project(project_name)
 yolo_model = project.version(model_version).model
@@ -33,10 +31,10 @@ def detect_combined(image):
         temp_path = temp_file.name
 
     try:
-        # ========== [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))
+        # ========== [1] YOLO: Deteksi Produk Nestlé ==========
+        yolo_pred = yolo_model.predict(temp_path, confidence=60, overlap=80).json()
+        
+        # Hitung per class Nestlé
         nestle_class_count = {}
         nestle_boxes = []
         for pred in yolo_pred['predictions']:
@@ -46,32 +44,28 @@ def detect_combined(image):
 
         total_nestle = sum(nestle_class_count.values())
 
-        # ========== [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()
-
+        # ========== [2] CountGD: Deteksi Kompetitor ==========
+        img = cv2.imread(temp_path)
+        prompts = [p.strip() for p in COUNTGD_PROMPT.split('.') if p.strip()]
+        
+        competitor_detections = []
+        for prompt in prompts:
+            dets = T.countgd_object_detection(prompt, img)
+            competitor_detections.extend(dets)
+
+        # Filter & Hitung Kompetitor
         competitor_class_count = {}
         competitor_boxes = []
-        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()
+        for det in competitor_detections:
+            bbox = det['bbox']
+            class_name = det['class_name']
+            
+            if not is_overlap(bbox, nestle_boxes):
                 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"]
+                    "box": bbox,
+                    "confidence": det['score']
                 })
 
         total_competitor = sum(competitor_class_count.values())
@@ -80,31 +74,30 @@ def detect_combined(image):
         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 Nestle: {total_nestle}\n\n"
+        result_text += f"\nTotal Product Nestle: {total_nestle}\n\n"
 
+        result_text += "Competitor Products\n\n"
         if competitor_class_count:
-            result_text += f"Total Unclassified Products: {total_competitor}\n"
+            for class_name, count in competitor_class_count.items():
+                result_text += f"{class_name}: {count}\n"
         else:
-            result_text += "No Unclassified Products detected\n"
+            result_text += "No competitors detected\n"
+        result_text += f"\nTotal Competitor: {total_competitor}"
 
         # ========== [4] Visualisasi ==========
-        img = cv2.imread(temp_path)
-
-        # Tandai deteksi produk Nestlé (Hijau)
+        # Gambar bounding box 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, 1.0, (0, 255, 0), 3)
+            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)
 
-        # Tandai deteksi kompetitor (Merah), dengan pengecekan untuk merubah nama kelas menjadi 'unclassified'
+        # Gambar bounding box Kompetitor (Merah)
         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"{display_name} {comp['confidence']:.2f}",
-                        (int(x1), int(y1 - 10)), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (0, 0, 255), 3)
+            x1, y1, x2, y2 = map(int, comp['box'])
+            cv2.rectangle(img, (x1, y1), (x2, y2), (0,0,255), 2)
+            cv2.putText(img, f"{comp['class']} {comp['confidence']:.2f}", 
+                       (x1, y1-10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0,0,255), 2)
 
         output_path = "/tmp/combined_output.jpg"
         cv2.imwrite(output_path, img)
@@ -116,121 +109,151 @@ def detect_combined(image):
     finally:
         os.remove(temp_path)
 
-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
+def is_overlap(countgd_bbox, yolo_boxes, iou_threshold=0.3):
+    """
+    Deteksi overlap menggunakan Intersection over Union (IoU)
+    Format bbox:
+    - CountGD: [x1, y1, x2, y2]
+    - YOLO: (x_center, y_center, width, height)
+    """
+    # Convert YOLO boxes to [x1,y1,x2,y2]
+    yolo_boxes_converted = []
+    for yb in yolo_boxes:
+        x_center, y_center, width, height = yb
+        x1 = x_center - width/2
+        y1 = y_center - height/2
+        x2 = x_center + width/2
+        y2 = y_center + height/2
+        yolo_boxes_converted.append((x1, y1, x2, y2))
+    
+    # Convert CountGD bbox to [x1,y1,x2,y2]
+    countgd_x1, countgd_y1, countgd_x2, countgd_y2 = countgd_bbox
+    
+    # Hitung IoU dengan semua YOLO boxes
+    for yolo_bbox in yolo_boxes_converted:
+        yolo_x1, yolo_y1, yolo_x2, yolo_y2 = yolo_bbox
+        
+        # Hitung area intersection
+        x_left = max(countgd_x1, yolo_x1)
+        y_top = max(countgd_y1, yolo_y1)
+        x_right = min(countgd_x2, yolo_x2)
+        y_bottom = min(countgd_y2, yolo_y2)
+        
+        if x_right < x_left or y_bottom < y_top:
+            continue
+            
+        intersection_area = (x_right - x_left) * (y_bottom - y_top)
+        
+        # Hitung area union
+        countgd_area = (countgd_x2 - countgd_x1) * (countgd_y2 - countgd_y1)
+        yolo_area = (yolo_x2 - yolo_x1) * (yolo_y2 - yolo_y1)
+        union_area = countgd_area + yolo_area - intersection_area
+        
+        iou = intersection_area / union_area if union_area > 0 else 0
+        
+        if iou > iou_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}"
-
+# ========== Fungsi untuk Deteksi Video ==========
 def detect_objects_in_video(video_path):
-    temp_output_path = "/tmp/output_video.mp4"
-    temp_frames_dir = tempfile.mkdtemp()
-    frame_count = 0
-    previous_detections = {}
-
+    temp_output = "/tmp/output_video.mp4"
+    temp_dir = tempfile.mkdtemp()
+    
     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)
-
+        cap = cv2.VideoCapture(video_path)
+        fps = int(cap.get(cv2.CAP_PROP_FPS))
+        width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+        height = int(cap.get(cv2.CAP_PROP_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()
+        out = cv2.VideoWriter(temp_output, fourcc, fps, (width, height))
+        
+        total_counts = {}
+        frame_idx = 0
+        
+        while cap.isOpened():
+            ret, frame = cap.read()
             if not ret:
                 break
-
-            frame_path = os.path.join(temp_frames_dir, f"frame_{frame_count}.jpg")
+                
+            frame_path = os.path.join(temp_dir, f"frame_{frame_idx}.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
-
+            
+            # Deteksi dengan YOLO
+            predictions = yolo_model.predict(frame_path, confidence=60, overlap=80).json()
+            
+            # Update counts dan gambar bounding box
+            class_count = {}
+            for pred in predictions['predictions']:
+                class_name = pred['class']
+                class_count[class_name] = class_count.get(class_name, 0) + 1
+                total_counts[class_name] = total_counts.get(class_name, 0) + 1
+                
+                x, y, w, h = pred['x'], pred['y'], pred['width'], pred['height']
+                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)
+            
+            # Tampilkan counter
+            y_pos = 30
+            for cls, cnt in class_count.items():
+                cv2.putText(frame, f"{cls}: {cnt}", (10, y_pos), 
+                          cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0,0,255), 2)
+                y_pos += 30
+            
+            out.write(frame)
+            frame_idx += 1
+            
+        cap.release()
+        out.release()
+        
+        # Generate report
+        result_text = "Final Counts\n\n"
+        for cls, cnt in total_counts.items():
+            result_text += f"{cls}: {cnt}\n"
+        result_text += f"\nTotal: {sum(total_counts.values())}"
+        
+        return temp_output, result_text
+        
     except Exception as e:
-        return None, f"An error occurred: {e}"
+        return None, f"Error: {str(e)}"
+    finally:
+        for f in os.listdir(temp_dir):
+            os.remove(os.path.join(temp_dir, f))
+        os.rmdir(temp_dir)
 
 # ========== 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>""")
-    
+    gr.Markdown("""
+    <div style="text-align: center;">
+        <h1>NESTLE - STOCK COUNTING</h1>
+    </div>
+    """)
     with gr.Row():
         with gr.Column():
             input_image = gr.Image(type="pil", label="Input Image")
             detect_image_button = gr.Button("Detect Image")
-            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])
-
+            output_image = gr.Image(label="Detection Result")
+            
         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])
+            output_video = gr.Video(label="Video Result")
+            
+        with gr.Column():
+            output_text = gr.Textbox(label="Counting Results")
+
+    detect_image_button.click(
+        fn=detect_combined,
+        inputs=input_image,
+        outputs=[output_image, output_text]
+    )
+    
+    detect_video_button.click(
+        fn=detect_objects_in_video,
+        inputs=input_video,
+        outputs=[output_video, output_text]
+    )
 
-iface.launch()
+iface.launch()