I am currently running Raspberry pi $64-$bit OS $($bookworm$).$ I am currently doing an object detection project using YOLOv$5$ in Pycharms using python. This code works well when I connect webcam to raspberry pi but it seems it does not work with raspberry pi camera. Please make this code below that can connect to my raspberry pi camera for object detection. Please take note that the old picamera module does not work anymore with the latest OS of raspberry pi$.$ As far as I am aware, it seems picamera$2$ or libcamera works fine.

The code so far:

import tkinter as tk

import torch

import picamera$2$

import cv$2$

import numpy as np

from PIL import Image, ImageTk

model $=$ torch.hub.load$(\text{'}$ultralytics$/$yolov$5\text{'},$ 'custom', path$=$'yolov$5/$best$.$pt$\text{'},$ force$\_$reload$=$True$)$

model.conf $=0\mathrm{.}2$

app $=$ tk$.$Tk$()$

app.geometry$("700$x$600")$

app.title$("$ObjectTest$")$

label$1=$ tk$.$Label$($app$,$ text$=$'detectionTest', font$=("$Arial$",24))$

label$1.$pack$($side$=$'top', pady$=20)$

vidFrame $=$ tk$.$Frame$($height$=600,$ width$=600)$

vidFrame.pack$()$

vid $=$ tk$.$Label$($vidFrame$,$ text$="")$

vid.pack$()$

camera $=$ picamera$2.$PiCamera$()$

def detect$()$:

frame $=$ np$.$empty$((240,320,3),$ dtype$=$np$.$uint$8)$

camera.capture$($frame$,\text{'}$bgr$\text{'},$ use$\_$video$\_$port$=$True$)$

results $=$ model$($frame$)$

output$\_$image $=$ results.render$()$

display$\_$image $=$ Image.fromarray$($output$\_$image$)$

imgtk $=$ ImageTk.PhotoImage$($image$=$display$\_$image$)$

vid.imgtk $=$ imgtk

vid.configure$($image$=$imgtk$)$

vid.after$(10,$ detect$)$

detect$()$

app.mainloop$()$

I will appreciate explanations for the code that you will add and please also let me know if you installed any other packages. Thank you so much