I found a code written by others, which can open the kinect videostream and show in the windows by OpenCV, however there are sth. wrong

[yxp1003]

the code:
from pykinect2 import PyKinectV2
from pykinect2.PyKinectV2 import *
from pykinect2 import PyKinectRuntime
import numpy as np
import cv2

kinect = PyKinectRuntime.PyKinectRuntime(PyKinectV2.FrameSourceTypes_Color)

while True:
# --- Getting frames and drawing
if kinect.has_new_color_frame():
frame = kinect.get_last_color_frame()
frame = frame.astype(np.uint8)
frame = np.reshape(frame, (2880, 2880))
img = cv2.cvtColor(frame, cv2.COLOR_GRAY2BGR)
output = cv2.bilateralFilter(img, 9, 150, 75)
cv2.imshow('KINECT Video Stream', output)
frame = None

key = cv2.waitKey(1)
if key == 27: break

the result:

I dont know how to fix it, anybody can help me, plz...

[Franzisdrak]

Hey there,

Did you read all of that code? Try to understand what each line does. You learn way more then if sb just tells you.

Hint:
Check what resolution the kinect uses for the rgb image.

[yxp1003]

Hey there,

Did you read all of that code? Try to understand what each line does. You learn way more then if sb just tells you.

Hint:
Check what resolution the kinect uses for the rgb image.

I checked the resolution of kinect , and change the 'frame = np.reshape(frame, (2880, 2880))' to '(1920, 1080)', but there has a Exception: 'ValueError: cannot reshape array of size 8294400 into shape (1920,1080)'
yeah, I read the sourcecode just now, and successed show it by pygame.
Nevertheless when I wanna to preccess it with OpenCV, there are sth trouble:

frame = self._kinect.get_last_color_frame()
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)

Error:
Traceback (most recent call last):
File "E:/PycharmProjects/PyKinect2/venv/real.py", line 97, in
game.run();
File "E:/PycharmProjects/PyKinect2/venv/real.py", line 72, in run
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
cv2.error: OpenCV(3.4.4) c:\projects\opencv-python\opencv\modules\imgproc\src\color.hpp:255: error: (-2:Unspecified error) in function '__cdecl cv::CvtHelper<struct cv::Set<3,4,-1>,struct cv::Set<1,-1,-1>,struct cv::Set<0,2,5>,2>::CvtHelper(const class cv::_InputArray &,const class cv::_OutputArray &,int)'

Invalid number of channels in input image:
'VScn::contains(scn)'
where
'scn' is 1

I have fixed it for a long time.....
anyway, thanks a lot for your help

[yxp1003]

嘿，

你读过所有代码了吗？试着了解每一行的作用。如果某人告诉你，你会学到更多的东西。

提示：
检查kinect用于rgb图像的分辨率。

Hi,

嘿，

你读过所有代码了吗？试着了解每一行的作用。如果某人告诉你，你会学到更多的东西。

提示：
检查kinect用于rgb图像的分辨率。

Hi,
Can you leave me a E-mail address? I really have some questions that have been bothering me for several days. plz
thank you so much