Related Experiment Video
Updated: May 21, 2025
03:31
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
Published on: December 15, 2023
448
Dual-Encoder UNet-Based Narrowband Uncooled Infrared Imaging Denoising Network.
Minghe Wang1, Pan Yuan1, Su Qiu1
1MOE Key Laboratory of Optoelectronic Imaging Technology and System, Beijing Institute of Technology, Beijing 100081, China.
Sensors (Basel, Switzerland)
|March 17, 2025
Summary
This study introduces a novel dual-encoder network to denoise infrared images from hazardous gas leak detection. The method effectively removes mixed noise, significantly improving image quality for industrial safety applications.
Area of Science:
- Infrared Imaging Technology
- Signal Processing
- Artificial Intelligence
Background:
- Uncooled infrared imaging is crucial for detecting hazardous gas leaks.
- Narrowband filters in these systems capture low incident energy, causing mixed noise (fixed pattern and Gaussian).
- Existing denoising methods are ineffective against this composite noise, hindering gas plume identification.
Purpose of the Study:
- To develop an advanced denoising network for narrowband uncooled infrared images.
- To effectively address the challenge of mixed noise in infrared gas leak detection.
- To enhance the signal-to-noise ratio for clearer identification of gas plumes.
Main Methods:
- A UNet-structured dual-encoder network was designed.
- Two encoders, Basic Scale Residual Attention (BSRA) and Enlarged Scale Residual Attention (ESRA), were developed to capture noise at different scales.
- Noise features from both scales were fused and processed by a decoder for image reconstruction.
Main Results:
- The proposed network effectively denoises composite noise in narrowband uncooled infrared images.
- Objective and subjective evaluations confirmed superior performance compared to existing methods.
- Significant enhancement of the signal-to-noise ratio was achieved.
Conclusions:
- The developed dual-encoder network offers a robust solution for denoising infrared images affected by mixed noise.
- This technology holds significant potential for improving hazardous gas leak detection, remote sensing, and medical imaging.
- The method enhances the practical applicability of uncooled infrared imaging systems in critical industrial and scientific fields.
Related Concept Videos
01:03IR Frequency Region: Fingerprint Region
682
IR spectra are divided into two main regions: the diagnostic region and the fingerprint region. The diagnostic region of the spectrum lies above 1500 cm−1. The absorptions resulting from single-bond vibrations of the N–H, C–H, and O–H stretch at higher wavenumbers and appear on the left side of the spectrum. The stretching absorptions of the C≡C and C≡N occur between 2100–2300 cm−1. In contrast, those arising from stretching absorptions of the...
682
01:09Infrared (IR) Spectroscopy: Overview
1.4K
When electromagnetic radiation passes through a material, atoms or molecules transition from a lower to a higher energy state by absorbing radiation corresponding to the energy difference between the two states. The absorption of infrared (IR) radiation causes transitions between vibrational energy levels in a molecule. Therefore, IR spectroscopy is a useful analytical tool for determining the molecular structure of molecules.
Different compounds display unique properties due to their...
Different compounds display unique properties due to their...
1.4K
01:24IR Frequency Region: X–H Stretching
891
In IR spectroscopy, signals produced by the X−H bonds (such as C−H, O−H, or N−H) can be observed in the frequency range of 2700–4000 cm–1. The C−H stretching vibration forms sharp bands in the region 2850–3000 cm–1. The presence of the O−H stretching vibration leads to the forming of an absorption band in the frequency range 3650–3200 cm−1. At the same time, N−H stretching can be confirmed by absorption bands in...
891