Use VPI for distortion correction with pre-calculated correction matrix

AI & Data Science Deep Learning (Training & Inference) TensorRT
1

Description

I want to replace my OpenCV code and use VPI for distortion correction.
I have pre-calculated matrix for the correction, using OpenCV remap:

cv::Mat src = /* read image /;
cv::Mat dst(src.size(), src.type());
cv::Mat correction_x = / image x correction /;
cv::Mat correction_y = / image y correction */;

remap(src, dst, correction_x, correction_y, INTER_LINEAR, BORDER_CONSTANT, Scalar(0, 0, 0));

I want to use VPI Lens Distortion Correction or vpi remap examples but I don’t find a way to use my pre-calculated matrix without initializing the VPIWarpMap with a for loop.

Environment

vpi1

1 Like
2

Hi,

This forum talks more about TensorRT related updates and issues. We recommend you please reach out to the VPI related platform for better help.

https://docs.nvidia.com/vpi/getting_started.html

Thank you.

1 Like
5

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.