Improved-YOLOv3 network for object detection in simulated Space Solar Power Systems images
Guangjun Wang, Nongwei Lei, Huimin Liu · 2020
In this paper, the object detection technology based on deep learning is applied to the assembly process of space power station simulation, which can provide assistance for the attitude adjustment and navigation of the aircraft through the detection of some components. Firstly, the 3D modeling and rendering of the space power station are carried out, on which the image dataset is collected and established. Then, based on the YOLOv3 network, we improve the structure of feature extraction. By fusing the information of shallow and deep features, we can improve the detection ability of the network for different scale objects. Qualitative and quantitative experimental results show that the improved YOLOv3 network can accurately and effectively detect the key components of the Space solar power station.