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

# Load the YOLOv5 model
# Use a local clone of YOLOv5
yolo_repo = 'ultralytics/yolov5'
model = torch.hub.load(yolo_repo, 'yolov5s', source='github')

# Load the translation model
translator = pipeline("translation_en_to_ar", model="Helsinki-NLP/opus-mt-en-ar")

# Define a function to detect objects and draw bounding boxes for images
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

        # Update counts for each label
        label = model.names[int(class_id)]
        counts[label] = counts.get(label, 0) + 1

        # Draw the bounding box
        draw.rectangle([(xmin, ymin), (xmax, ymax)], outline="red", width=2)
        draw.text((xmin, ymin), f"{label}: {conf:.2f}", fill="white")

    # Translate counts to Arabic
    translated_counts = translator(list(counts.keys()))

    df = pd.DataFrame({
        'label (English)': list(counts.keys()),
        'label (Arabic)': [t['translation_text'] for t in translated_counts],
        'counts': list(counts.values())
    })

    return input_image, df

# Define a function to detect objects and draw bounding boxes for videos
def detect_and_draw_video(video_path):
    cap = cv2.VideoCapture(video_path)
    frames = []
    frame_shape = None
    overall_counts = {}
    detected_objects = set()  # Set to keep track of unique detections

    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

            # Create a unique identifier for the object based on its bounding box
            identifier = (model.names[int(class_id)], int((xmin + xmax) / 2), int((ymin + ymax) / 2))

            # Count the object only if it hasn't been detected before
            if identifier not in detected_objects:
                detected_objects.add(identifier)
                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"{model.names[int(class_id)]}: {conf:.2f}", (int(xmin), int(ymin) - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.75, (255, 255, 255), 2)

        frames.append(frame)

    cap.release()

    if frame_shape is None:
        return None, None

    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()

    # Translate counts to Arabic
    translated_counts = translator(list(overall_counts.keys()))

    df = pd.DataFrame({
        'label (English)': list(overall_counts.keys()),
        'label (Arabic)': [t['translation_text'] for t in translated_counts],
        'counts': list(overall_counts.values())
    })

    return output_path, df

# Create separate interfaces for images and videos
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 by YOLOv5 with bounding boxes 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 by YOLOv5 with bounding boxes and their counts."
)

# Combine interfaces into a single app
app = gr.TabbedInterface([image_interface, video_interface], ["Image Detection", "Video Detection"])

# Launch the app
app.launch(debug=True)