Update app.py

app.py

@@ -9,10 +9,11 @@ import gradio as gr
 import os
 
 # Import the Sort class from the local 'sort.py' file
+# Pastikan file 'sort.py' ada di direktori yang sama dengan app.py
 from sort import Sort
 
 # --- LOAD MODELS AND TRACKER ONCE (PENTING!) ---
-# This part runs only once when the app starts, so we don't reload the model for every user.
+# Bagian ini hanya berjalan sekali saat aplikasi dimulai.
 print("Loading model and processor...")
 model_checkpoint = "facebook/detr-resnet-50"
 image_processor = AutoImageProcessor.from_pretrained(model_checkpoint)
@@ -26,7 +27,7 @@ print("Model loaded successfully.")
 # ---------------------------------------------------
 
 def iou(boxA, boxB):
-    # Standard IoU calculation
+    # Fungsi untuk menghitung Intersection over Union (IoU)
     xA = max(boxA[0], boxB[0])
     yA = max(boxA[1], boxB[1])
     xB = min(boxA[2], boxB[2])
@@ -37,33 +38,41 @@ def iou(boxA, boxB):
     iou_score = interArea / float(boxAArea + boxBArea - interArea)
     return iou_score
 
-# --- THE MAIN PROCESSING FUNCTION ---
+# --- FUNGSI PEMROSESAN UTAMA ---
 def process_video(input_video_path):
-    # Initialize tracker and counters for each new video
-    tracker = Sort(min_hits=1, iou_threshold=0.3)
+    # Inisialisasi tracker dan penghitung untuk setiap video baru
+    tracker = Sort(min_hits=3, iou_threshold=0.3)
     total_counts = {'person': 0, 'bicycle': 0, 'car': 0, 'motorcycle': 0}
     counted_ids = set()
 
-    # Define the output path for the processed video
+    # Tentukan path output untuk video yang diproses
     output_video_path = "output.mp4"
     
     cap = cv2.VideoCapture(input_video_path)
     if not cap.isOpened():
         raise gr.Error(f"Could not open video file.")
     
-    frame_width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
-    frame_height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
     fps = int(cap.get(cv2.CAP_PROP_FPS))
     
-    # Use 'mp4v' codec which is widely compatible
-    out = cv2.VideoWriter(output_video_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (frame_width, frame_height))
-
+    # --- OPTIMISASI: Atur resolusi baru yang lebih kecil ---
+    new_width = 960
+    new_height = 540
+    
+    # Gunakan codec 'mp4v' yang kompatibel dan resolusi baru
+    out = cv2.VideoWriter(output_video_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (new_width, new_height))
+    
+    frame_number = 0
     while True:
         ret, frame = cap.read()
         if not ret:
             break
         
-        # --- (Logic from our notebook goes here) ---
+        frame_number += 1
+        
+        # --- OPTIMISASI: Ubah ukuran setiap frame sebelum dideteksi ---
+        frame = cv2.resize(frame, (new_width, new_height))
+
+        # 1. Deteksi objek dengan DETR
         pil_image = Image.fromarray(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))
         inputs = image_processor(images=pil_image, return_tensors="pt").to(device)
         with torch.no_grad():
@@ -71,6 +80,7 @@ def process_video(input_video_path):
         target_sizes = torch.tensor([pil_image.size[::-1]])
         results = image_processor.post_process_object_detection(outputs, threshold=0.6, target_sizes=target_sizes)[0]
 
+        # 2. Format deteksi untuk SORT
         detections_for_sort = []
         original_detections = []
         for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
@@ -80,12 +90,15 @@ def process_video(input_video_path):
                 detections_for_sort.append([box_list[0], box_list[1], box_list[2], box_list[3], score.item()])
                 original_detections.append({'box': box_list, 'label': label_name})
 
+        # 3. Update tracker
         tracked_objects_raw = []
         if len(detections_for_sort) > 0:
             tracked_objects_raw = tracker.update(np.array(detections_for_sort))
 
+        # 4. Logika Penghitungan & Visualisasi
         for obj in tracked_objects_raw:
             x1, y1, x2, y2, obj_id = [int(val) for val in obj]
+            
             best_iou = 0
             best_label = None
             for det in original_detections:
@@ -94,6 +107,7 @@ def process_video(input_video_path):
                     best_iou = iou_score
                     best_label = det['label']
 
+            # Hitung objek jika ID-nya baru
             if best_label and obj_id not in counted_ids:
                 total_counts[best_label] += 1
                 counted_ids.add(obj_id)
@@ -102,6 +116,7 @@ def process_video(input_video_path):
                 cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)
                 cv2.putText(frame, f'{best_label} ID: {obj_id}', (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 255, 0), 2)
         
+        # Tampilkan total hitungan kumulatif
         y_offset = 30
         for obj_name, count in total_counts.items():
             text = f'Total {obj_name.capitalize()}: {count}'
@@ -114,40 +129,32 @@ def process_video(input_video_path):
     cap.release()
     out.release()
     
-    # Return the path to the processed video
+    print(f"Video processing finished. Total frames: {frame_number}")
     return output_video_path
 
-# --- GRADIO INTERFACE ---
-
-# Build the layout with gr.Blocks
+# --- ANTARMUKA GRADIO (Dengan Layout Stabil) ---
 with gr.Blocks(css="footer {visibility: hidden}") as demo:
-    # 1. Title and Description (no change)
     gr.Markdown("<h1>Real-Time Object Tracking & Counting with DETR and SORT</h1>")
     gr.Markdown("Upload a video to see object detection and tracking in action. This demo uses Facebook's DETR model for detection and the SORT algorithm to assign unique IDs and count objects.")
 
-    # 2. Main Row for Input and Output
     with gr.Row():
-        # We set a fixed width and height for both video components
-        # to prevent the layout from shifting.
+        # Atur ukuran video yang tetap untuk mencegah layout "melompat"
         input_video = gr.Video(label="Input Video", width=640, height=360)
         output_video = gr.Video(label="Processed Video", width=640, height=360)
 
-    # 3. Submit Button (no change)
     submit_button = gr.Button("Submit", variant="primary")
 
-    # 4. Examples (no change)
     gr.Examples(
         examples=[['5402016-hd_1920_1080_30fps.mp4']],
         inputs=input_video,
         label="Click an example to run"
     )
 
-    # 5. Link button to function (no change)
     submit_button.click(
         fn=process_video,
         inputs=input_video,
         outputs=output_video
     )
 
-# Launch the app
-demo.launch()
+# Jalankan aplikasi
+demo.launch()