Multispectral imaging light estimation based on convolutional neural networks

Long Ma; Fengqi Zhao

doi:10.1117/12.3035177

3 September 2024 Multispectral imaging light estimation based on convolutional neural networks

Long Ma, Fengqi Zhao

Proceedings Volume 13227, 2024 AI Photonics Technology Symposium; 1322708 (2024) https://doi.org/10.1117/12.3035177
Event: 2024 AI Photonics Technology Symposium, 2024, Wuhan, China

Abstract

In this work, we describe a convolutional neural network (CNN) to accurately predict field lighting. In the network structure, feature learning and regression are integrated into an optimization process to form a more effective model for scene illumination estimation, and we have added an attention mechanism to reinforce learning. This approach is trained with ICVL data sets and tested with Foster HSI data for better performance. The stability of the proposed neural network for local illumination estimation and the improvement of the global illumination estimation performance are verified by experiments on the spatial illumination variation images.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Long Ma and Fengqi Zhao "Multispectral imaging light estimation based on convolutional neural networks", Proc. SPIE 13227, 2024 AI Photonics Technology Symposium, 1322708 (3 September 2024); https://doi.org/10.1117/12.3035177

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
8 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Tunable filters

Light sources

Light sources and illumination

Convolutional neural networks

Optical filters

Education and training

Image filtering

Show All Keywords

Keywords/Phrases

Search In:

Publication Years