Paper
3 September 2024 Multispectral imaging light estimation based on convolutional neural networks
Long Ma, Fengqi Zhao
Author Affiliations +
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.
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
Advertisement
Advertisement
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

RELATED CONTENT


Back to Top