Light-weight Fusion Network for UAV Visible-light and Infrared Images based on Real-time Brain-like Intelligent Computing

Light-weight Fusion Network for UAV Visible-light and Infrared Images based on Real-time Brain-like Intelligent Computing

Blog Article

Multiple sensors equipped on the Unmanned Aerial Vehicle (UAV) enables the acquisition of multi-modal and multi-source remote sensing data.UAV remote sensing usually faces with real-time or near-real-time tasks in complex and highly dynamic environments, such as disaster monitoring, traffic management, border Football - Shoes - Men patrol and so on.Under these conditions, the image fusion algorithm needs to be high efficiency, precision and reliability.

In this paper, we proposed an intelligent real-time fusion network for UAV multi-source remote sensing data based on AI brain-like chips, and deployed the algorithm on the UAV platform to achieve online high-efficiency computing.Firstly, we have developed a novel image fusion algorithm named SFNet for infrared and visible image fusion based on ShuffleNetv2.Then, we use ZCA and l1-norm to process the remodeled anal-vibrators deep feature.

The weight maps are generated by bi-cubic interpolation and soft-max operation.Finally, the fused image is reconstructed by weighted-average operation.The proposed SFNet is deployed on the Lynxi KA200 brain computing chip, and a comprehensive inference test is carried out with UAV remote sensing data.

Several State-Of-The-Art (SOTA) data fusion algorithms are deployed on the same chip for experimental comparison.The proposed SFNet is proved to have faster inference speed and better feature extraction results on brain-like chips.It is more suitable for real-time UAV remote sensing image fusion tasks.