Update app.py

app.py

@@ -1,38 +1,48 @@
 import torch
+import gradio as gr
 import cv2
 import numpy as np
+from datetime import datetime
 
-# Load your YOLO model
-model = torch.hub.load('ultralytics/yolov5', 'custom', path='best.pt') 
+# Load YOLOv5 model
+model = torch.hub.load('ultralytics/yolov5', 'custom', path='best.pt')
 
-def detect(frame):
-    # Perform inference on the current frame
-    results = model(frame)
-    return results
-
-# Open the video file (or camera)
-cap = cv2.VideoCapture("test_video.mp4")  # replace with your video path or camera index (0 for webcam)
-
-while cap.isOpened():
-    ret, frame = cap.read()
-    if not ret:
-        break
+def detect_video(video):
+    cap = cv2.VideoCapture(video.name)
     
-    # Perform inference on the current frame
-    results = detect(frame)
-
-    # Render predictions on the frame (draw bounding boxes)
-    frame_with_boxes = np.array(results.render()[0])  # render predictions on the frame
-
-    # Convert from RGB to BGR for OpenCV (since OpenCV uses BGR)
-    frame_with_boxes = cv2.cvtColor(frame_with_boxes, cv2.COLOR_RGB2BGR)  
-
-    # Display the frame with results
-    cv2.imshow("Detection", frame_with_boxes)
+    # List to hold results
+    detection_results = []
+    
+    while cap.isOpened():
+        ret, frame = cap.read()
+        if not ret:
+            break
+        
+        # Get timestamp
+        timestamp = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
+        
+        # Perform detection
+        results = model(frame)
+        
+        # Extract bounding boxes and confidence scores
+        for *xyxy, conf, cls in results.xywh[0]:
+            x1, y1, x2, y2 = map(int, xyxy)  # Convert to integers
+            detection_results.append({
+                'timestamp': timestamp,
+                'coordinates': {'x1': x1, 'y1': y1, 'x2': x2, 'y2': y2},
+                'confidence': float(conf)
+            })
+    
+    cap.release()
+    
+    return detection_results
 
-    # Break loop if 'q' is pressed
-    if cv2.waitKey(1) & 0xFF == ord('q'):
-        break
+# Gradio Interface
+interface = gr.Interface(fn=detect_video, 
+                         inputs=gr.inputs.Video(source="upload", type="file"),
+                         outputs="json",
+                         live=True,
+                         title="YOLOv5 Video Object Detection",
+                         description="Upload a video to detect objects and get bounding boxes with timestamps.")
 
-cap.release()
-cv2.destroyAllWindows()
+interface.launch()