Polarized skylight orientation determination artificial neural network

TL;DR

This paper introduces a neural network with dilated convolution and exponential encoding to accurately determine orientation from polarized skylight, inspired by insect polarization encoding, demonstrating stability and effectiveness on a public dataset.

Contribution

The paper presents a novel neural network architecture with specialized encoding for improved polarized skylight orientation determination.

Findings

The neural network accurately extracts DOP and AOP from polarized skylight.

Experimental results show the network's stability and effectiveness.

The method outperforms previous approaches in orientation accuracy.

Abstract

This paper proposes an artificial neural network to determine orientation using polarized skylight. This neural network has specific dilated convolution, which can extract light intensity information of different polarization directions. Then, the degree of polarization (DOP) and angle of polarization (AOP) are directly extracted in the network. In addition, the exponential function encoding of orientation is designed as the network output, which can better reflect the insect's encoding of polarization information, and improve the accuracy of orientation determination. Finally, training and testing were conducted on a public polarized skylight navigation dataset, and the experimental results proved the stability and effectiveness of the network.