stepacool / eye-tracker Goto Github PK

I had to change line 33 from:
self.capture = cv2.VideoCapture(cv2.CAP_DSHOW)
to
self.capture = cv2.VideoCapture(0)
in order to work with the built-in webcam on a macbook pro running Mojave.

AttributeError: module 'cv2.cv2' has no attribute 'drawKeypoints'

(commenting out stops crash, but loses a key feature)

Exception after executing the file some time:

Traceback (most recent call last):
File "main.py", line 62, in update_frame
right_keypoints, self.previous_right_keypoints, self.previous_right_blob_area = self.get_keypoints(
File "main.py", line 92, in get_keypoints
previous_area = keypoints[0].size
IndexError: too many indices for array

.I installed the python-opencv version in tutorial with pip but I get "AttributeError: module 'cv2' has no attribute 'CascadeClassifier'" I'm on archlinux... any idea ?

I am getting this error code in running this. I have all the pre-reqs installed.

This application failed to start because it could not find or load the Qt platform plugin "windows".

Available platform plugins are: minimal (from C:\Python27\lib\site-packages\PyQt5\plugins\platforms), offscreen (from C:\Python27\lib\site-packages\PyQt5\plugins\platforms), windows (from C:\Python27\lib\site-packages\PyQt5\plugins\platforms), minimal, offscreen.

Reinstalling the application may fix this problem.

Traceback (most recent call last):
File "main.py", line 45, in update_frame
self.display_image(base_image)
File "main.py", line 100, in display_image
if len(img.shape) == 3:
AttributeError: 'NoneType' object has no attribute 'shape'
Abort trap: 6

Changed the lines as suggested by 3 other people on the forum to

 def start_webcam(self):
        if not self.camera_is_running:
            self.capture = cv2.VideoCapture(0)  # VideoCapture(0) sometimes drops error #-1072875772
            if self.capture is None:
            	self.capture = cv2.VideoCapture(0)

But still this error :--

VIDEOIO ERROR: V4L2: Pixel format of incoming image is unsupported by OpenCV
Unable to stop the stream: Device or resource busy
VIDEOIO ERROR: V4L: can't open camera by index 0
Traceback (most recent call last):
  File "main.py", line 45, in update_frame
    self.display_image(base_image)
  File "main.py", line 100, in display_image
    if len(img.shape) == 3:
AttributeError: 'NoneType' object has no attribute 'shape'
Aborted (core dumped)

Hi there,

Get the following errors while attempting following command on Raspberry Pi 3 B+

`sudo python3 main.py

ImportError: libQtGui.so.4: cannot open shared object file: No such file or directory

LibEGL warning: DRI2: failed to authenticate
QStandardPaths: XGD_RUNTIME_DIR not set, defaulting to '/tmp/runtime-root'
`

thanks for the great work.

by the way, I have tested the same with an eyeglass and without but it only works with without eyeglasses.

with eye glasses, it not at all detecting the eyes

Note:
i have included the eyeglass HAAR xml file but NO LUCK

Exception after clicking the start button :

Traceback (most recent call last):
File "main.py", line 45, in update_frame
self.display_image(base_image)
File "main.py", line 100, in display_image
if len(img.shape) == 3:
AttributeError: 'NoneType' object has no attribute 'shape'
Abandon (core dumped)

Hello,
Thanks for the great project.
I ran the noGUI ver on my Windows machine & I noticed the detection doesn't pickup unless I raise the threshold to 70 or so.. does that affect the accuracy of the detection alot? Is there a recommended threshold or an ideal setting to give better accuracy?
Also, can I use the code to detect more than 1 face?

thanks,

Hi,

I came across your project and it is well put together!

I'm getting back into python so my skills are rusty.

When I run poetry install, I get this message:

Current Python version (3.12.0) is not allowed by the project (>=3.7,<3.11).
Please change python executable via the "env use" command.

What do you suggest on how to get past this message? I was thinking the easy thing is to install a lower version of py.

Thank you for your help.

Сама программа один раз найдет глаза и все.... помогите

Ran into a few snags trying to get the requirements installed on Ubuntu 20.04. After creating the venv, poetry failed to find Qt6. Updating pip with python -m pip install --upgrade pip then running poetry did the trick, however when running the tracker I get:

(venv) playaspec@Cortex1:~/Documents/Programming/Eye-Tracker/project$ python main.py 
Traceback (most recent call last):
  File "main.py", line 7, in <module>
    from gui.application_window import Window
  File "/Users/playaspec/Documents/Programming/Eye-Tracker/project/gui/application_window.py", line 8, in <module>
    from video_source import FrameSource
ModuleNotFoundError: No module named 'video_source'

I've also tried cloning the repo into a Conda environment. Both venvs have difficulty finding Qt6 or the right opencv. Is there a missing requirement or environment variable that's preventing the module from being found?

Working perfectly. But there is a problem.
When i select the "Blob" slider, the blob does not appear or just appear on the right eye.
And when i select the circle option slider, circle appears on both eyes but are not so correct.
Please help me out as soon as possible that How can i get correct blob and circle as your appeared in the Youtube video.

Thanks.