The two-stream network proposed for thermal and visible images fusion

Illustration of the proposed network structure. Credit: XIOPM
Illustration of the proposed network structure. Credit: XIOPM

Student Liu Luolin from the Xi'an Institute of Optics and Precision Mechanics (XIOPM) of the Chinese Academy of Sciences (CAS) has proposed a two-stream end-to-end model named TSFNet for thermal and visible image fusion. The results were published in Neurocomputing.

The TSFNet, using two branches for feature learning, is quite different from previous two-stream methods, and it can fully capture the information from both sources.

Thermal images are insensitive to brightness and can distinguish objects and backgrounds by differentiating thermal radiation. Visible images can understand human vision more intuitively and have a higher resolution. Therefore, it can be inferred that the fusion of the two may yield a new image with clear objects and high resolution for all-weather and all-day/night monitoring.

In this study, in order to enable the model to retain the detailed information of the source image autonomously during the fusion, LIU and his team members adopted an adaptive weight allocation strategy to guide feature selection. The whole framework was disassembled into three modules, feature extraction, fusion, and reconstruction.

According to the results of the experiment, TSFNet outperforms state-of-the-art methods under different evaluation metrics. In the future, it will provide a guide for designing a new network of image fusion.

Journal Information: Luolin Liu et al, Two-stream network for infrared and visible images fusion, Neurocomputing (2021). DOI: 10.1016/j.neucom.2021.05.034

2 views0 comments

Recent Posts

See All

Streaming video giant Netflix has decided to cut 150 jobs after releasing disappointing first-quarter results, citing "slower revenue growth

Before Elon Musk completed his acquisition deal, three more senior employees left Twitter. Currently, the acquisition has stalled. Twitter V