Abstract
In this article, an array thermal camera equipment is developed to capture multiple infrared images with spatial and parallax information. Based on the captured images, an end-to-end method called spatial-parallax prior network (SPPN) is proposed. Specifically, we design a spatial-parallax prior block with two symmetric branches to extract spatial and parallax features in an interactive guidance manner. Then, to effectively integrate spatial and parallax features, we introduce a channel attention mechanism to enable the network to focus on and fuse the most useful information adaptively. In this way, spatial and parallax information can be fully utilized without any explicit alignment operation. Finally, considering the scarcity and poor quality of infrared training data, we leverage transfer learning to better train the network. Extensive experimental results demonstrate that the proposed SPPN consistently outperforms the current state-of-the-art methods, providing a highly effective and scalable solution for the improvement of infrared image quality.
| Original language | English |
|---|---|
| Pages (from-to) | 6642-6651 |
| Number of pages | 10 |
| Journal | IEEE Transactions on Industrial Informatics |
| Volume | 18 |
| Issue number | 10 |
| DOIs | |
| State | Published - Oct 2022 |
Funding
This work was supported by the National Natural Science Foundation of China under Grant 62061160370, Grant 62075169, Grant 62003247, and Grant 61773295. Paper no. TII-212490.
Keywords
- Feature extraction
- Cameras
- Image enhancement
- Image reconstruction
- Convolution
- Thermal sensors
- Informatics
- Array thermal camera
- convolutional neural network (CNN)
- infrared image enhancement
- spatial-parallax prior
Indexed by
- Scopus
- EI
- SCIE
Fingerprint
Dive into the research topics of 'Learning Spatial-Parallax Prior Based on Array Thermal Camera for Infrared Image Enhancement'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver