PoseDetector in cvzone reads video coordinate information problem

When implementing the 3DMotionCapture project, the character pose coordinate information in the video read by the findPosition() function at the beginning only has two dimensions of x, y, but what we need is the coordinates of the three dimensions of x, y, and z.

After excluding various hypothetical reasons, I concluded that the cvzone 1.5.4 version I configured is too old and needs to be upgraded to a higher version. The latest version on April 9, 2022 is cvzone 1.5.6.

At the beginning, configure the new version directly in pycharm, you can find the latest version, and you can also install it successfully, but after running it is still version 1.5.4, remove the old version and install the latest version, run it again and find that the detection is normal .

Conclusion: When the original old version of the third-party library cannot meet the needs, it should be updated in time, and the old version should be removed when installing the new version of the third-party library to avoid errors.

Guess you like

Origin blog.csdn.net/qq_52309640/article/details/124062053