Metasurfaces exhibit exceptional electromagnetic wave manipulation capabilities.However,static control struggles to adapt to dynamic environmental demands.Reconfigurable metasurfaces integrated with PIN diodes enable ...Metasurfaces exhibit exceptional electromagnetic wave manipulation capabilities.However,static control struggles to adapt to dynamic environmental demands.Reconfigurable metasurfaces integrated with PIN diodes enable dynamic tuning but face challenges in power supply and device reliability.This work proposes a solar-powered metasurface that utilizes sunlight as both an energy source and a control signal,achieving radar cross-section(RCS)reduction during daylight and maintaining reflective communication at night.Placing diodes at the unit bottom minimizes damage risk,while partitioned biasing simplifies control and reduces power consumption.The phase response under varying current and voltage conditions demonstrates its excellent voltage stability and phase robustness.Solar cells provide sufficient voltage/current,and simulations/experiments validate beam deflection performance.The metasurface operates at a low voltage of 0.8 V and 0.1 A due to simplified biasing.This work presents a reconfigurable metasurface with a simple,low-power design and novel control logic,promising broad applications in outdoor adaptive stealth and environmental sensing.展开更多
The popularity of online home design and floor plan customization has been steadily increasing. However, the manual conversion of floor plan images from books or paper materials into electronic resources can be a chal...The popularity of online home design and floor plan customization has been steadily increasing. However, the manual conversion of floor plan images from books or paper materials into electronic resources can be a challenging task due to the vast amount of historical data available. By leveraging neural networks to identify and parse floor plans, the process of converting these images into electronic materials can be significantly streamlined. In this paper, we present a novel learning framework for automatically parsing floor plan images. Our key insight is that the room type text is very common and crucial in floor plan images as it identifies the important semantic information of the corresponding room. However, this clue is rarely considered in previous learning-based methods. In contrast, we propose the Row and Column network (RC-Net) for recognizing floor plan elements by integrating the text feature. Specifically, we add the text feature branch in the network to extract text features corresponding to the room type for the guidance of room type predictions. More importantly, we formulate the Row and Column constraint module (RC constraint module) to share and constrain features across the entire row and column of the feature maps to ensure that only one type is predicted in each room as much as possible, making the segmentation boundaries between different rooms more regular and cleaner. Extensive experiments on three benchmark datasets validate that our framework substantially outperforms other state-of-the-art approaches in terms of the metrics of FWIoU, mACC and mIoU.展开更多
基金National Natural Science Foundation of China(62401614,62401617,62401615)Shaanxi Science and Technology Innovation Team(2023-CX-TD-48)+2 种基金Joint Funds of the National Natural Science Foundation of China(U24A20224)National Funded Postdoctoral Researcher Program(GZC20233577)Postdoctoral Science Foundation of China(2023M744291)。
文摘Metasurfaces exhibit exceptional electromagnetic wave manipulation capabilities.However,static control struggles to adapt to dynamic environmental demands.Reconfigurable metasurfaces integrated with PIN diodes enable dynamic tuning but face challenges in power supply and device reliability.This work proposes a solar-powered metasurface that utilizes sunlight as both an energy source and a control signal,achieving radar cross-section(RCS)reduction during daylight and maintaining reflective communication at night.Placing diodes at the unit bottom minimizes damage risk,while partitioned biasing simplifies control and reduces power consumption.The phase response under varying current and voltage conditions demonstrates its excellent voltage stability and phase robustness.Solar cells provide sufficient voltage/current,and simulations/experiments validate beam deflection performance.The metasurface operates at a low voltage of 0.8 V and 0.1 A due to simplified biasing.This work presents a reconfigurable metasurface with a simple,low-power design and novel control logic,promising broad applications in outdoor adaptive stealth and environmental sensing.
基金supported by the National Natural Science Foundation of China under Grant Nos.U21A20515,62172416,52175493,U2003109,61972459,and 62102414the Youth Innovation Promotion Association of the Chinese Academy of Sciences(2022131).
文摘The popularity of online home design and floor plan customization has been steadily increasing. However, the manual conversion of floor plan images from books or paper materials into electronic resources can be a challenging task due to the vast amount of historical data available. By leveraging neural networks to identify and parse floor plans, the process of converting these images into electronic materials can be significantly streamlined. In this paper, we present a novel learning framework for automatically parsing floor plan images. Our key insight is that the room type text is very common and crucial in floor plan images as it identifies the important semantic information of the corresponding room. However, this clue is rarely considered in previous learning-based methods. In contrast, we propose the Row and Column network (RC-Net) for recognizing floor plan elements by integrating the text feature. Specifically, we add the text feature branch in the network to extract text features corresponding to the room type for the guidance of room type predictions. More importantly, we formulate the Row and Column constraint module (RC constraint module) to share and constrain features across the entire row and column of the feature maps to ensure that only one type is predicted in each room as much as possible, making the segmentation boundaries between different rooms more regular and cleaner. Extensive experiments on three benchmark datasets validate that our framework substantially outperforms other state-of-the-art approaches in terms of the metrics of FWIoU, mACC and mIoU.
