import cv2
import torch
from PIL import Image, ImageDraw
import gradio as gr
import pandas as pd
from transformers import pipeline

model = torch.hub.load('ultralytics/yolov5', 'yolov5s')
translator = pipeline("translation_en_to_ar", model="Helsinki-NLP/opus-mt-en-ar")

def detect_and_draw_image(input_image):
    results = model(input_image)
    detections = results.xyxy[0].numpy()
    
    draw = ImageDraw.Draw(input_image)
    counts = {}
    for detection in detections:
        xmin, ymin, xmax, ymax, conf, class_id = detection
        label = model.names[int(class_id)]
        counts[label] = counts.get(label, 0) + 1
        
        draw.rectangle([(xmin, ymin), (xmax, ymax)], outline="red", width=2)
        draw.text((xmin, ymin), f"{label}: {conf:.2f}", fill="white")

    translated_labels = translator(list(counts.keys()))
    df = pd.DataFrame({
        'Label (English)': list(counts.keys()),
        'Label (Arabic)': [t['translation_text'] for t in translated_labels],
        'Object Count': list(counts.values())
    })

    return input_image, df

def detect_and_draw_video(video_path):
    cap = cv2.VideoCapture(video_path)
    frames = []
    overall_counts = {}

    while cap.isOpened():
        ret, frame = cap.read()
        if not ret:
            break

        frame = cv2.resize(frame, (640, 480))
        results = model(frame)
        detections = results.xyxy[0].numpy()

        for detection in detections:
            xmin, ymin, xmax, ymax, conf, class_id = detection
            label = model.names[int(class_id)]
            overall_counts[label] = overall_counts.get(label, 0) + 1
            
            cv2.rectangle(frame, (int(xmin), int(ymin)), (int(xmax), int(ymax)), (255, 0, 0), 2)
            cv2.putText(frame, f"{label}: {conf:.2f}", (int(xmin), int(ymin) - 10), 
                        cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 255, 255), 2)

        frames.append(frame)

    cap.release()
    output_path = 'output.mp4'
    out = cv2.VideoWriter(output_path, cv2.VideoWriter_fourcc(*'mp4v'), 20.0, (640, 480))

    for frame in frames:
        out.write(frame)
    out.release()

    translated_labels = translator(list(overall_counts.keys()))
    df = pd.DataFrame({
        'Label (English)': list(overall_counts.keys()),
        'Label (Arabic)': [t['translation_text'] for t in translated_labels],
        'Object Count': list(overall_counts.values())
    })

    return output_path, df

image_interface = gr.Interface(
    fn=detect_and_draw_image,
    inputs=gr.Image(type="pil", label="Upload Image"),
    outputs=[gr.Image(type="pil"), gr.Dataframe(label="Object Counts")],
    title="Object Detection for Images",
    description="Upload an image to see the objects detected and their counts."
)

video_interface = gr.Interface(
    fn=detect_and_draw_video,
    inputs=gr.Video(label="Upload Video"),
    outputs=[gr.Video(label="Processed Video"), gr.Dataframe(label="Object Counts")],
    title="Object Detection for Videos",
    description="Upload a video to see the objects detected and their counts."
)

app = gr.TabbedInterface([image_interface, video_interface], ["Image Detection", "Video Detection"])
app.launch(debug=True)