Changing to use opencv for real time detection

app.py

@@ -1,47 +1,54 @@
-import gradio as gr
 import cv2
+import gradio as gr
 import numpy as np
 from transformers import pipeline
 
-# Load the YOLO model using Hugging Face's pipeline
+# Load YOLO model from Hugging Face's transformers library
 model = pipeline("object-detection", model="hustvl/yolos-tiny")
 
-# Function to run YOLO on each video frame
-def detect_objects(frame):
-    # Convert frame to RGB as required by the model
-    rgb_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+# Function to capture and process video frames in real time
+def capture_and_detect():
+    cap = cv2.VideoCapture(0)  # OpenCV video capture from webcam
+
+    while True:
+        ret, frame = cap.read()
+        if not ret:
+            break
 
-    # Run object detection
-    results = model(rgb_frame)
+        # Convert frame to RGB as required by YOLO model
+        rgb_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
 
-    # Draw bounding boxes and labels
-    for result in results:
-        # Extract details
-        label = result['label']
-        score = result['score']
-        box = result['box']
-        x1, y1, x2, y2 = int(box['xmin']), int(box['ymin']), int(box['xmax']), int(box['ymax'])
+        # Perform object detection on the frame
+        results = model(rgb_frame)
 
-        # Draw rectangle and label on the frame
-        cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)
-        text = f"{label}: {score:.2f}"
-        cv2.putText(frame, text, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
+        # Draw bounding boxes and labels on the frame
+        for result in results:
+            label = result['label']
+            score = result['score']
+            box = result['box']
+            x1, y1, x2, y2 = int(box['xmin']), int(box['ymin']), int(box['xmax']), int(box['ymax'])
 
-    return cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)  # Convert back to RGB for Gradio
+            # Draw bounding box and label
+            cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)
+            text = f"{label}: {score:.2f}"
+            cv2.putText(frame, text, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
 
-# Gradio interface to capture video frames
-def video_stream(frame):
-    # Run object detection on the frame
-    annotated_frame = detect_objects(frame)
-    return annotated_frame
+        # Convert BGR back to RGB for Gradio display
+        yield cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+
+    cap.release()
+
+# Gradio Interface using real-time video capture and object detection
+def video_stream():
+    return capture_and_detect()
 
 # Create Gradio interface
 webcam_interface = gr.Interface(
     fn=video_stream,
-    inputs=gr.Video(format="mp4", streaming=True),
+    inputs=None,
     outputs=gr.Image(),
     live=True,
-    description="Real-Time Object Detection with YOLO on Hugging Face"
+    description="Real-Time Object Detection with YOLO and Gradio"
 )
 
 # Launch Gradio app
@@ -49,3 +56,4 @@ if __name__ == "__main__":
     webcam_interface.launch()
 
 
+