About this document
Neural Network for Lens Distortion Correction by Seetha Chinna is a document available to read on EtoBox.
This document discusses using a neural network approach to correct camera distortion. It proposes a three-step method: 1) perform direct linear calibration to obtain initial camera parameters, 2) use the linear model outputs as inputs to a neural network and train it to minimize the error between actual and linear model 3D coordinates, 3) the trained neural network serves as a camera distortion correction model to map from the linear model outputs to the actual 3D coordinates. A backpropagation neural netwo
- Author
- Seetha Chinna
- Language
- EN