Develop Reference

I was creating a virtual mouse and I keep getting this error. I have tried with autopy and with pyautogui but in both cases it gives me same error

This is the error I'm getting right now and I just can't figure out what the problem is.
INFO: Created TensorFlow Lite XNNPACK delegate for CPU.
Traceback (most recent call last):
File "C:\AIproject\virMouse.py", line 18, in <module>
lmList, bbox = detector.findPosition(img)
ValueError: not enough values to unpack (expected 2, got 0)
Process finished with exit code 1
Here is my code for the virtual mouse program that I have written so far.
import cv2
import numpy as np
import time
import HTmodule as htm
import autopy
wCam, hCam = 640, 480
cap = cv2.VideoCapture(0)
cap.set(3, wCam)
cap.set(4, hCam)
pTime = 0
detector = htm.handDetector(maxHands=1)
while True:
success, img = cap.read()
img = detector.findHands(img)
lmList, bbox = detector.findPosition(img)
cTime = time.time()
fps = 1 / (cTime - pTime)
pTime = cTime
cv2.putText(img, f'FPS:{(int(fps))}', (5, 30), cv2.FONT_HERSHEY_DUPLEX, 1, (204, 0, 0), 2)
cv2.imshow("Image", img)
cv2.waitKey(1)
And here is the code for the hand tracking module that I wrote.
import cv2
import mediapipe as mp
import time
class handDetector():
def __init__(self, mode=False, maxHands=2,modelC=1, detectionCon=0.5, trackCon=0.5):
self.mode = mode
self.maxHands = maxHands
self.modelC = modelC
self.detectionCon = detectionCon
self.trackCon = trackCon
self.mpHands = mp.solutions.hands
self.hands = self.mpHands.Hands(self.mode, self.maxHands, self.modelC, self.detectionCon, self.trackCon)
self.mpDraw = mp.solutions.drawing_utils
def findHands(self, img, draw=True):
imgRGB = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
self.results = self.hands.process(imgRGB)
# print(result.multi_hand_landmarks)
if self.results.multi_hand_landmarks:
for handLms in self.results.multi_hand_landmarks:
if draw:
self.mpDraw.draw_landmarks(img, handLms, self.mpHands.HAND_CONNECTIONS)
return img
def findPosition(self, img, handNo=0, draw=True):
lmList=[]
if self.results.multi_hand_landmarks:
myHand = self.results.multi_hand_landmarks[handNo]
for id, lm in enumerate(myHand.landmark):
# print(id,lm)
h, w, c = img.shape
cx, cy = int(lm.x * w), int(lm.y * h)
# print(id, cx, cy)
lmList.append([id, cx, cy])
# if id == 0:
if draw:
cv2.circle(img, (cx, cy), 3, (229, 25, 66), cv2.FILLED)
return lmList
def main():
pTime = 0
cTime = 0
cap = cv2.VideoCapture(0)
detector = handDetector()
while True:
success, img = cap.read()
img = detector.findHands(img)
lmList = detector.findPosition(img, draw=False)
# print(lmList) # PRINTS THE LIST OF LANDMARKS
if len(lmList) != 0:
print(lmList[4])
cTime = time.time()
fps = 1 / (cTime - pTime)
pTime = cTime
cv2.putText(img, f'FPS:{(int(fps))}', (5, 30), cv2.FONT_HERSHEY_DUPLEX, 1, (9, 9, 255), 1)
cv2.imshow("Image", img)
cv2.waitKey(1)
if __name__ == "__main__":
main()
I don't think it has anything to do with autopy I think it has something to do with findPosition() function but I can't figure out what it is. I just started studying computer vision with python and decided to make this project for my practice but this error I can't seem to debug. Any kind of help would be greatly appreciated. Thankyou very much.

find the biggest ball - detect object

i am a newby in python and i am researching about detect object. I'm looking for the biggest ball. I have no idea how to make it work. Can anybody give me some pointers? Here is what I have so far.
my code: (from: "https://youtu.be/Vg9rrOFmwHo")
import cv2
import serial
from time import sleep
classNames = []
classFile = "/home/pi/Desktop/Object_Detection_Files/coco.names"
with open(classFile,"rt") as f:
classNames = f.read().rstrip("\n").split("\n")
configPath = "/home/pi/Desktop/Object_Detection_Files/ssd_mobilenet.pbtxt"
weightsPath = "/home/pi/Desktop/Object_Detection_Files/frozen_inference_graph.pb"
net = cv2.dnn_DetectionModel(weightsPath,configPath)
net.setInputSize(320,320)
net.setInputScale(1/ 127.5)
net.setInputMean((127.5, 127.5, 127.5))
net.setInputSwapRB(True)
def getObjects(img, thres, nms, draw=True, objects=[]):
classIds, confs, bbox = net.detect(img,confThreshold=thres,nmsThreshold=nms)
if len(objects) == 0: objects = classNames
objectInfo =[]
if len(classIds) != 0:
for classId, confidence,box in zip(classIds.flatten(),confs.flatten(),bbox):
className = classNames[classId - 1]
if className in objects:
objectInfo.append([box,className])
if (draw):
cv2.rectangle(img,box,color=(0,255,0),thickness=2)
cv2.putText(img,'sports ball',(box[0]+10,box[1]+30),
cv2.FONT_HERSHEY_COMPLEX,1,(0,255,0),2)
x= int(box[0]+box[2]/2)
y= int(box[1]+box[3]/2)
cv2.circle(img, (x, y), 5, (0,255,0), 1)
return img,objectInfo
if __name__ == "__main__":
cap = cv2.VideoCapture(0)
cap.set(3,640)
cap.set(4,480)
while True:
success, img = cap.read()
height, width, _ = img.shape
result, objectInfo = getObjects(img,0.29,0.2, objects=['sports ball'] )
#print(objectInfo)
cv2.imshow("Output",img)
cv2.waitKey(1)

Pywin32, win32gui window capture black screen

I need to make a screen capture of a specific application. If I grab the Windows desktop (hwnd = None), everything works, but I get a black screen when I try to grab the screen of a specific application, e.g. hwnd = win32gui.FindWindow(None, 'Albion Online Client').
import cv2 as cv
import numpy as np
import os
from time import time
import win32gui
import win32ui
import win32con
os.chdir(os.path.dirname(os.path.abspath(__file__)))
def window_capture():
w = 1920 # set this
h = 1080 # set this
#hwnd = None ### Everything works
hwnd = win32gui.FindWindow(None, 'Albion Online Client') ### Black Screen
wDC = win32gui.GetWindowDC(hwnd)
dcObj = win32ui.CreateDCFromHandle(wDC)
cDC = dcObj.CreateCompatibleDC()
dataBitMap = win32ui.CreateBitmap()
dataBitMap.CreateCompatibleBitmap(dcObj, w, h)
cDC.SelectObject(dataBitMap)
cDC.BitBlt((0, 0), (w, h), dcObj, (0, 0), win32con.SRCCOPY)
#Save screenshoot
#dataBitMap.SaveBitmapFile(cDC, 'debug.bmp' )
signedIntsArray = dataBitMap.GetBitmapBits(True)
img = np.fromstring(signedIntsArray, dtype='uint8')
img.shape = (h, w, 4)
# Free Resources
dcObj.DeleteDC()
cDC.DeleteDC()
win32gui.ReleaseDC(hwnd, wDC)
win32gui.DeleteObject(dataBitMap.GetHandle())
img = img[..., :3]
img = np.ascontiguousarray(img)
return img
# initialize the WindowCapture clas
loop_time = time()
while(True):
screenshot = window_capture()
cv.imshow('Computer Vision', screenshot)
# debug the loop rate
print('FPS {}'.format(1 / (time() - loop_time)))
loop_time = time()
# press 'q' with the output window focused to exit.
# waits 1 ms every loop to process key presses
if cv.waitKey(1) == ord('q'):
cv.destroyAllWindows()
break
print('Done.')

That's an OpenGL or Direct3D application. It doesn't draw to its own window. It creates textures and surfaces, and has the graphics card render its display list directly into the frame buffer.

OpenCv window cascading the screen when it's clicked on

I wrote this code to capture screen footage by taking screenshots everything second, however the OpenCv window cascades the screen when it's clicked on.
When you hover over the Opencv window, it shows me the screen without a hundred duplicates. What is exactly the bug? Picture:
The code for using the class I made:
from window_capture import Window_Capture
from time import time
import cv2 as cv
import numpy
loop_time = time()
wincap = Window_Capture()
while True:
screenshot = wincap.screenshare()
cv.imshow('Screen', screenshot)
print("FPS {}".format(round(1 / (time() - loop_time))))
loop_time = time()
if cv.waitKey(1) == ord('q'):
print("Capture Ended")
cv.destroyWindow(screenshot)
The class for screen capturing:
import pyautogui
import numpy
import cv2 as cv
from time import time
from PIL import ImageGrab
import win32gui, win32ui, win32con
from win32api import GetSystemMetrics
import time
class Window_Capture:
w = 0
h = 0
hwnd = None
def __init__(self, window_name=None):
# checking is windowname exists
if window_name is None:
print("No window set to capture: Setting to active Window")
time.sleep(3)
self.hwnd = win32gui.GetDesktopWindow()
print(win32gui.GetWindowText(win32gui.GetDesktopWindow()))
else:
# self.hwnd = win32gui.FindWindow(None, window_name)
self.hwnd = win32gui.FindWindow(None, window_name)
print("Window Found: Setting to preferred Window")
# define monitor height and width and hwnd
self.w = GetSystemMetrics(0)
self.h = GetSystemMetrics(1)
def screenshare(self):
wDC = win32gui.GetWindowDC(self.hwnd)
dcObj = win32ui.CreateDCFromHandle(wDC)
cDC = dcObj.CreateCompatibleDC()
dataBitMap = win32ui.CreateBitmap()
dataBitMap.CreateCompatibleBitmap(dcObj, self.w, self.h)
cDC.SelectObject(dataBitMap)
cDC.BitBlt((0, 0), (self.w, self.h), dcObj, (0, 0), win32con.SRCCOPY)
signedIntsArray = dataBitMap.GetBitmapBits(True)
img = numpy.frombuffer(signedIntsArray, dtype='uint8')
img.shape = (self.h, self.w, 4)
dcObj.DeleteDC()
cDC.DeleteDC()
win32gui.ReleaseDC(self.hwnd, wDC)
win32gui.DeleteObject(dataBitMap.GetHandle())
img = img[..., :3]
img = numpy.ascontiguousarray(img)
return img
This bug is preventing me from moving onto the next part my image detection project.

Better solution is :
import time
import cv2
import numpy as np
from mss import mss
#import pyautogui
#width, height= pyautogui.size()
width=900
height=900
mon = {'top': 0, 'left': 0, 'width': width, 'height': height}
with mss() as sct:
# mon = sct.monitors[0]
while True:
last_time = time.time()
img = sct.grab(mon)
print('fps: {0}'.format(1 / (time.time()-last_time)))
cv2.imshow('test', np.array(img))
if cv2.waitKey(25) & 0xFF == ord('q'):
cv2.destroyAllWindows()
break
Note:
When you hover then you won't be seeing many windows beacuse you see the complete window without the opencv window opended and else you see many of them

you see a cascade because you take a screenshot of the window itself, repeatedly.
it's like standing between two mirrors.

Taking fast screenshot Winapi and Opencv

I need to take very fast screenshots of a game for an OpenCV project I am working on. I can use PIL easily for example:
def take_screenshot1(hwnd):
rect = win32gui.GetWindowRect(hwnd)
img = ImageGrab.grab(bbox=rect)
img_np = np.array(img)
return cv2.cvtColor(img_np, cv2.COLOR_RGB2BGR)
But it takes on average of 0.05 seconds which isn't fast enough for real time capture.
I can use the answer posted here, but that only saves the bitmap to a file. That is over 10 times faster than by using PIL, but I am unsure of any methods within OpenCV to convert it to a bgr/hsv image.
def take_screenshot(hwnd):
wDC = win32gui.GetWindowDC(hwnd)
dcObj=win32ui.CreateDCFromHandle(wDC)
cDC=dcObj.CreateCompatibleDC()
dataBitMap = win32ui.CreateBitmap()
dataBitMap.CreateCompatibleBitmap(dcObj, 500, 500)
cDC.SelectObject(dataBitMap)
cDC.BitBlt((0, 0), (500, 500), dcObj, (0, 0), win32con.SRCCOPY)
dataBitMap.SaveBitmapFile(cDC, "foo.png")
dcObj.DeleteDC()
cDC.DeleteDC()
win32gui.ReleaseDC(hwnd, wDC)
win32gui.DeleteObject(dataBitMap.GetHandle())
im = cv2.imread("foo.png")
return cv2.cvtColor(im, cv2.COLOR_RGB2BGR)
EDIT:The size of the window is 500x500, so it is saving the same area in both examples.
Even if I save the image, and then reopen it with OpenCV it is still faster than PIL, but surely there is an easier way?
EDIT: Ok so using the comments and doing some research on winapi I now can access the bitmap data directly as follows:
def take_screenshot1(hwnd):
wDC = win32gui.GetWindowDC(hwnd)
dcObj=win32ui.CreateDCFromHandle(wDC)
cDC=dcObj.CreateCompatibleDC()
dataBitMap = win32ui.CreateBitmap()
dataBitMap.CreateCompatibleBitmap(dcObj, 500, 500)
cDC.SelectObject(dataBitMap)
cDC.BitBlt((0, 0), (500, 500), dcObj, (0, 0), win32con.SRCCOPY)
im = dataBitMap.GetBitmapBits(True) # Tried False also
img = np.array(im)
cv2.cvtColor(img, cv2.COLOR_RGB2BGR)
print(img)
dcObj.DeleteDC()
cDC.DeleteDC()
win32gui.ReleaseDC(hwnd, wDC)
win32gui.DeleteObject(dataBitMap.GetHandle())
But i'm not sure how to convert the returned bitmap to a form that OpenCV understands, as there are no methods to convert bitmap to rgb/bgr in OpenCV

I'll just show the code that works for me.
import time
import win32gui
import win32ui
import win32con
import win32api
import numpy as np
import cv2
def window_capture():
hwnd = 0
hwndDC = win32gui.GetWindowDC(hwnd)
mfcDC = win32ui.CreateDCFromHandle(hwndDC)
saveDC = mfcDC.CreateCompatibleDC()
saveBitMap = win32ui.CreateBitmap()
MoniterDev = win32api.EnumDisplayMonitors(None, None)
w = MoniterDev[0][2][2]
h = MoniterDev[0][2][3]
saveBitMap.CreateCompatibleBitmap(mfcDC, w, h)
saveDC.SelectObject(saveBitMap)
saveDC.BitBlt((0, 0), (w, h), mfcDC, (0, 0), win32con.SRCCOPY)
im = saveBitMap.GetBitmapBits(True) # Tried False also
img = np.frombuffer(im, dtype=np.uint8).reshape((h, w, 4))
cv2.imshow("demo", img)
cv2.waitKey(100)
beg = time.time()
for i in range(100):
window_capture()
end = time.time()
print(end - beg)
cv2.destroyAllWindows()