import cv2
import gradio as gr
from transformers import pipeline

# Load YOLOv8 model and suspicious activity classification model
pose_detection = pipeline("object-detection", model="yolov8-pose")  # Correct path if it's inside same folder.
suspicious_activity_detection = pipeline("text-classification", model="suspicious_activity_model")

def process_frame(frame):
    results = pose_detection(frame)

    for person in results:
        if person['label'] == 'person':
            x1, y1, x2, y2 = map(int, person['box'].values())
            cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)
            cv2.putText(frame, 'Detected', (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
    return frame

def live_detection(frame):
    frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
    processed_frame = process_frame(frame)
    return processed_frame

interface = gr.Interface(
    fn=live_detection,
    inputs=gr.Image(source="webcam", tool="editor", type="numpy"),
    outputs=gr.Image(type="numpy"),
    live=True
)

if __name__ == "__main__":
    interface.launch(server_name="0.0.0.0", server_port=7860)