Flying By ML -- CNN Inversion of Affine Transforms

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Van Warren, L.
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929194914545664
author Van Warren, L.
author_facet Van Warren, L.
contents This paper describes a machine learning method to automate reading of cockpit gauges, using a CNN to invert affine transformations and deduce aircraft states from instrument images. Validated with synthetic images of a turn-and-bank indicator, this research introduces methods such as generating datasets from a single image, the 'Clean Training Principle' for optimal noise-free training, and CNN interpolation for continuous value predictions from categorical data. It also offers insights into hyperparameter optimization and ML system software engineering.
format Preprint
id arxiv_https___arxiv_org_abs_2312_17258
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Flying By ML -- CNN Inversion of Affine Transforms
Van Warren, L.
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
This paper describes a machine learning method to automate reading of cockpit gauges, using a CNN to invert affine transformations and deduce aircraft states from instrument images. Validated with synthetic images of a turn-and-bank indicator, this research introduces methods such as generating datasets from a single image, the 'Clean Training Principle' for optimal noise-free training, and CNN interpolation for continuous value predictions from categorical data. It also offers insights into hyperparameter optimization and ML system software engineering.
title Flying By ML -- CNN Inversion of Affine Transforms
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2312.17258