当我运行此代码以制作带有 gui 的树莓派人脸跟踪机器人时出现错误，没有任何伺服电机只是为了跟随人

Question

Please tell me what wrong here. It gives error like this

if face == True:#i have used this to make if there is no face found then stop if face found go forward
ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()

The code is here:

import RPi.GPIO as GPIO

import cv2

import carapp

import sys

vid = cv2.VideoCapture(0)

face_cascade = cv2.CascadeClassifier('/home/pi/harr cascade/haarcascade_frontalface_default.xml')


Motor1A = 21

Motor1B = 20

Motor2A = 16

Motor2B = 26

GPIO.setwarnings(False)

GPIO.setmode(GPIO.BCM)

GPIO.setup(Motor1A,GPIO.OUT)

GPIO.setup(Motor1B,GPIO.OUT)

GPIO.setup(Motor2A,GPIO.OUT)

GPIO.setup(Motor2B,GPIO.OUT)

def forward():

    print("GOING FORWARD")

    GPIO.output(Motor1A,GPIO.LOW)

    GPIO.output(Motor1B,GPIO.HIGH)

    GPIO.output(Motor2A,GPIO.LOW)

    GPIO.output(Motor2B,GPIO.HIGH)

def backward():

    print("GOING BACKWARD")

    GPIO.output(Motor1A,GPIO.HIGH)

    GPIO.output(Motor1B,GPIO.LOW)

    GPIO.output(Motor2A,GPIO.HIGH)

    GPIO.output(Motor2B,GPIO.LOW)

def Left():

    print("Going Left")

    GPIO.output(Motor1A,GPIO.HIGH)

    GPIO.output(Motor1B,GPIO.LOW)

    GPIO.output(Motor2A,GPIO.LOW)

    GPIO.output(Motor2B,GPIO.HIGH)

def Right():

    print("Going Right")

    GPIO.output(Motor1A,GPIO.LOW)

    GPIO.output(Motor1B,GPIO.HIGH)

    GPIO.output(Motor2A,GPIO.HIGH)

    GPIO.output(Motor2B,GPIO.LOW)

def stop():

    print("Stopping")

    GPIO.output(Motor1A,GPIO.LOW)

    GPIO.output(Motor1B,GPIO.LOW)

    GPIO.output(Motor2A,GPIO.LOW)

    GPIO.output(Motor2B,GPIO.LOW)
    

def cameo():
    while(True):
        _,img = vid.read()
        gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
        face = face_cascade.detectMultiScale(gray,1.1,4)
        for (x,y,w,h) in face:
            cv2.rectangle(img,(x,y),(x+w,y+h),(50,20,70),3)
            
        if face == True:#i have used this to make if there is no face found then stop if face found go forward
            carapp.forward()
        else:
            carapp.stop()

        cv2.imshow('img',img)
        if cv2.waitKey(1) & 0xff == ord('q'):
            break
            sys.exit()
    vid.release()
    cv2.destroyAllWindows()

import tkinter as tk

gui = tk.Tk()

gui.title("Car control")

gui.geometry("500x500")

lol = tk.Button(gui,text="Forward",bg="red",command=forward)

lol.grid(row=2,column=5)

bot = tk.Button(gui,text="Backward",bg="green",command=backward)

bot.grid(row=10,column=5)

ron = tk.Button(gui,text="Left",bg="orange",command=Left)

ron.grid(row=5,column=0)

bob = tk.Button(gui,text="Right",bg="yellow",command=Right)

bob.grid(row=5,column=10)

dol = tk.Button(gui,text="camera",bg="blue",command = cameo)

dol.grid(row=5,column=100)

sod = tk.Button(gui,text="stop",bg="cyan",command = stop)

sod.grid(row=5,column=5)

button = tk.Button(text = "Click and Quit", command = sys.exit)

button.grid(row=15,column=10)

gui.mainloop()

#this product is copytright of shouryawadhwa aka @programmerShourya

Answer 1

The return value from

face_cascade = cv2.CascadeClassifier('/home/pi/harr cascade/haarcascade_frontalface_default.xml')

Is not a single True/False value - it's something that (from the error message) contains multiple values - perhaps that's something over which you can iterate, or alternately use the all, any functions to perform boolean tests over the collection.

Are the results even boolean?

Why don't you look inside of face_cascade and see what kind of data it holds? Once you know that, you'll be better equipped to deal with the result.

Also here:

for (x,y,w,h) in face:
        cv2.rectangle(img,(x,y),(x+w,y+h),(50,20,70),3)
        
    if face == True:#i have used this to make if there is no face found then stop if face found go forward
        carapp.forward()
    else:
        carapp.stop() 

You start iterating over face in your for-loop, but then later you try to ask whether it's True or False.

Which is inconsistent.

What are the contents of x,y,w,h? They look like they might describe bounding boxes, not what I'd imagine you'd sensibly be able to test with a True or False.

Are any of those boolean?

Also, some of this "copyrighted code" looks like you copy/pasted it from these docs:

https://opencv-python-tutroals.readthedocs.io/en/latest/py_tutorials/py_objdetect/py_face_detection/py_face_detection.html