Robust Polarization Orientation Method Based on Task Mutual Enhancement Under Global Noise Environment
- 10 March 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 62 (00189251) , 7699-7713
Abstract
The camera-based polarization sensor provide an effective solution for orientation in satellite-denied environments. A key issue in polarization image processing is the solar meridian extraction (SME). However, in the presence of global noise in the polarization image, such as low exposure conditions at night, the performance of existing SME methods are significantly degraded due to the lack of effective polarization information. To alleviate this problem, some methods reduce the noise by increasing the exposure time, but at the expense of dynamics. To improve the environmental adaptability and dynamic performance of the system in the global noise environment, we conduct an unsupervised image restoration (IR) framework and a task mutual enhancement module (TMEM). The IR framework is based on disentangled representation, with each unidirectional subnetwork embedding a loop for noise removal and generation, which can remove the global noise in the angle of polarization (AoP) image. Moreover, TMEM is proposed to promote task-level information interaction between IR and SME, thereby achieving simultaneous improvement in the performance of IR and SME. Specifically, SME constrains the SM in the restored polarization images to be straight, obvious and azimuth-invariant. Conversely, the noise-free polarization images in IR improves the accuracy of SME. Extensive experimental results demonstrate that the proposed method can significantly improve the quality of AoP images and implement accurate and robust orientation under global noise environment. Under 0.2 second (reduced by 25 times) exposure at low-light condition, the dynamic orientation accuracy of the proposed method can achieve $0.74^\circ$. Ablation study demonstrate the necessity of jointly learning SME and IR and the effectiveness of TMEM. The code is available at: https://github.com/Wiggins-Carter/ROTME.Keywords
Funding Information
- National Natural Science Foundation of China (92471201)
- National Natural Science Foundation of China (62403024)
- National Natural Science Foundation of China (62227813)
- National Natural Science Foundation of China (62388101)
- National Natural Science Foundation of China (62373033)
- National Natural Science Foundation of China (62425302)
- National Natural Science Foundation of China (62122007)
- Scientific Research Innovation Capability Support Project for Young Faculty (ZYGXQNJSKYCXNLZCXM-I2)
This publication has 31 references indexed in Scilit:
- Tightly-coupled INS/CNS/PNS integrated navigation based on adaptive multi-model fusion2025
- Semantic Line Combination Detector2024
- Unsupervised Image Denoising in Real-World Scenarios via Self-Collaboration Parallel Generative Adversarial Branches2023
- Conditional LS-GAN Based Skylight Polarization Image Restoration and Application in Meridian Localization2023
- Moonlit polarized skylight-aided INS/CNS: An enhanced attitude determination methodControl Engineering Practice, 2022
- Robust Orientation Method Based on Atmospheric Polarization Model for Complex WeatherIEEE Internet of Things Journal, 2022
- Simple Baselines for Image Restoration2022
- “Double-DIP”: Unsupervised Image Decomposition via Coupled Deep-Image-Priors2019
- A Trilateral Weighted Sparse Coding Scheme for Real-World Image Denoising2018
- When sparsity meets low-rankness: Transform learning with non-local low-rank constraint for image restoration2017