Mu LI, Yilang ZHANG, Xizheng KE. Infrared image enhancement algorithm based on multi-scale feature extraction and fusion[J]. Infrared and Laser Engineering, 2025, 54(2): 20240400
- Infrared and Laser Engineering
- Vol. 54, Issue 2, 20240400 (2025)
Fig. 1. Complete network framework
Fig. 2. Multi-scale adaptive feature extraction module
Fig. 3. The process of using multi-scale convolution to extract the detail information of infrared images
Fig. 4. Multi-scale adaptive feature extraction module
Fig. 5. Global attention mechanism
Fig. 6. Channel attention submodule
Fig. 7. Spatial attention submodule
Fig. 8. Feature fusion and image reconstruction module
Fig. 9. Example of building the dataset (red dashed line is the original image)
Fig. 10. Comparison of six image enhancement methods under Self-dataset
Fig. 11. Comparison of six image enhancement methods under MSRS
Fig. 12. Comparison of six image enhancement algorithms for object detection
Fig. 13. Analysis of the results of the fire hazard algorithm
| |||||||||||||||||||||||||||||||||||||||||||||||||||||||
Table 1. Comparison of enhancement effects of different methods(Self-dataset)
| |||||||||||||||||||||||||||||||||||||||||||||||||||||||
Table 2. Comparison of enhancement effects of different methods(MSRS dataset)
|
Table 3. Comparison of enhancement effects at different network stage
|
Table 4. Structure and validation of improved effectiveness
|
Table 5. Validity verification of different expansion rates
|
Table 6. Validity verification of different pixel parameters
|
Table 7. Comparison of early fire detection results of different algorithms
Set citation alerts for the article
Please enter your email address
© Copyright 2018-2021 | Chinese Laser Press. All Rights Reserved 沪ICP备15018463号-20