Related Experiment Video
Updated: Jan 8, 2026
08:47
Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
Published on: February 9, 2024
2.0K
Spatial photometric information prediction based on back propagation artificial neural network.
Optics Express
|December 19, 2025
Summary
A new robotic system improves near-field goniophotometric measurements, reducing errors and time. Artificial neural networks further enhance efficiency for predicting light source photometric data.
Area of Science:
- Photometry
- Optical Engineering
- Robotics
Background:
- Near-field goniophotometric measurement is crucial for photometric data but is time-consuming and prone to errors.
- Existing methods struggle with efficiency and accuracy in capturing complex light distributions.
Purpose of the Study:
- To develop an intelligent robotic system for efficient and accurate near-field goniophotometric measurement.
- To investigate algorithms for photometric reconstruction, far-field inversion, and prediction using artificial neural networks.
Main Methods:
- Development of an intelligent robotic near-field goniophotometric measurement system.
- Experimental measurement of planar light source luminance distribution at various spatial angles.
- Application of near-field photometric reconstruction, far-field inversion algorithms, and a back propagation artificial neural network (BP-ANN).
Main Results:
- The robotic system achieved precise acquisition of spatial photometric information.
- Far-field luminous intensity inversion error averaged 2.6% using the developed system.
- The BP-ANN model predicted spatial photometric distribution with an average error of less than 2.3%.
Conclusions:
- The intelligent robotic near-field goniophotometric measurement system significantly enhances data acquisition precision.
- The BP-ANN based prediction method substantially improves experimental efficiency and reduces errors in photometric analysis.
