Using Thonny Application within Raspberry pi $464-$bit Bullseye system. Picamera$2$ seems to be the lastest module in order to use a raspberry pi camera. I am working on a YOLOv$5$ object detection test witht the use of a raspberry pi camera. This code works well with a webcam before I change the code a bit. Can you please help me make this code to detect with the use of a raspberry pi camera. My only problem is that I am having a hard time make the raspberry pi camara to work with object detection. Thank you so much.

import tkinter as tk

import torch

from picamera$2$ import Picamera$2$

import cv$2$

import numpy as np

from PIL import Image, ImageTk

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$()$

picam$2=$ Picamera$2()$

camera $=$ picam$2$

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$()$