visualizer.py

import tkinter as tk
from PIL import Image, ImageTk
import json

class CoordinateVisualizer:
    def __init__(self, master, image_path):
        self.master = master
        self.master.title("Video Area Coordinate Visualizer")

        # Load the background image
        self.original_image = Image.open(image_path)
        self.image_ratio = self.original_image.width / self.original_image.height

        # Get screen dimensions
        screen_width = self.master.winfo_screenwidth() * 0.8  # Use 80% of screen width
        screen_height = self.master.winfo_screenheight() * 0.8  # Use 80% of screen height

        # Calculate scaling factor
        width_ratio = screen_width / self.original_image.width
        height_ratio = screen_height / self.original_image.height
        self.scale_factor = min(width_ratio, height_ratio)

        # Resize image
        new_width = int(self.original_image.width * self.scale_factor)
        new_height = int(self.original_image.height * self.scale_factor)
        self.bg_image = self.original_image.resize((new_width, new_height), Image.LANCZOS)
        self.bg_photo = ImageTk.PhotoImage(self.bg_image)

        # Create a canvas and display the image
        self.canvas = tk.Canvas(master, width=new_width, height=new_height)
        self.canvas.pack(side=tk.LEFT)
        self.canvas.create_image(0, 0, anchor=tk.NW, image=self.bg_photo)

        # Initialize coordinates
        self.start_x = self.start_y = self.end_x = self.end_y = 0
        self.rect_id = None

        # Bind mouse events
        self.canvas.bind("<ButtonPress-1>", self.on_press)
        self.canvas.bind("<B1-Motion>", self.on_drag)
        self.canvas.bind("<ButtonRelease-1>", self.on_release)

        # Create coordinate display labels
        self.coord_frame = tk.Frame(master)
        self.coord_frame.pack(side=tk.RIGHT, padx=10)

        self.start_label = tk.Label(self.coord_frame, text="Start (x, y): (0, 0)")
        self.start_label.pack()

        self.end_label = tk.Label(self.coord_frame, text="End (x, y): (0, 0)")
        self.end_label.pack()

        self.size_label = tk.Label(self.coord_frame, text="Size (w, h): (0, 0)")
        self.size_label.pack()

        # Create a button to save coordinates
        self.save_button = tk.Button(self.coord_frame, text="Save Coordinates", command=self.save_coordinates)
        self.save_button.pack(pady=10)

    def scaled_to_original(self, x, y):
        return int(x / self.scale_factor), int(y / self.scale_factor)

    def on_press(self, event):
        self.start_x = self.canvas.canvasx(event.x)
        self.start_y = self.canvas.canvasy(event.y)

        if self.rect_id:
            self.canvas.delete(self.rect_id)

        self.rect_id = self.canvas.create_rectangle(self.start_x, self.start_y, self.start_x, self.start_y, outline='red')

    def on_drag(self, event):
        cur_x = self.canvas.canvasx(event.x)
        cur_y = self.canvas.canvasy(event.y)

        self.canvas.coords(self.rect_id, self.start_x, self.start_y, cur_x, cur_y)
        self.update_labels(cur_x, cur_y)

    def on_release(self, event):
        self.end_x = self.canvas.canvasx(event.x)
        self.end_y = self.canvas.canvasy(event.y)
        self.update_labels(self.end_x, self.end_y)

    def update_labels(self, cur_x, cur_y):
        orig_start_x, orig_start_y = self.scaled_to_original(self.start_x, self.start_y)
        orig_cur_x, orig_cur_y = self.scaled_to_original(cur_x, cur_y)

        self.start_label.config(text=f"Start (x, y): ({orig_start_x}, {orig_start_y})")
        self.end_label.config(text=f"End (x, y): ({orig_cur_x}, {orig_cur_y})")
        
        width = abs(orig_cur_x - orig_start_x)
        height = abs(orig_cur_y - orig_start_y)
        self.size_label.config(text=f"Size (w, h): ({width}, {height})")

    def save_coordinates(self):
        start_x, start_y = self.scaled_to_original(min(self.start_x, self.end_x), min(self.start_y, self.end_y))
        end_x, end_y = self.scaled_to_original(max(self.start_x, self.end_x), max(self.start_y, self.end_y))

        coordinates = {
            "start_x": start_x,
            "start_y": start_y,
            "end_x": end_x,
            "end_y": end_y
        }
        with open("video_area_coordinates.json", "w") as f:
            json.dump(coordinates, f)
        print("Coordinates saved to video_area_coordinates.json")

if __name__ == "__main__":
    root = tk.Tk()
    app = CoordinateVisualizer(root, "background.png")
    root.mainloop()