Transmission line detection in aerial images: An instance segmentation approach based on multitask neural networks

Camera-based transmission line detection (TLD) is a fundamental and crucial task for automatically patrolling powerlines by aircraft. Motivated by instance segmentation, a TLD algorithm is proposed in this paper with a novel deep neural network, i.e., CableNet. The network structure is designed based on fully convolutional networks (FCNs) with two major improvements, considering the specific appearance characteristics of transmission lines. First, overlaying dilated convolutional layers and spatial convolutional layers are configured to better represent continuous long and thin cable shapes. Second, two branches of outputs are arranged to generate multidimensional feature maps for instance segmentation. Thus, cable pixels can be detected and assigned cable IDs simultaneously. Multiple experiments are conducted on aerial images, and the results show that the proposed algorithm obtains reliable detection performance and is superior to traditional TLD methods. Meanwhile, segmented pixels can be accurately identified as cable instances, contributing to line fitting for further applications.     

IL-10 in Mast Cell-Mediated Immune Responses: Anti-Inflammatory and Proinflammatory Roles

Mast cells (MCs) play critical roles in Th2 immune responses, including the defense against parasitic infections and the initiation of type I allergic reactions. In addition, MCs are involved in several immune-related responses, including those in bacterial infections, autoimmune diseases, inflammatory bowel diseases, cancers, allograft rejections, and lifestyle diseases. Whereas antigen-specific IgE is a well-known activator of MCs, which express FcεRI on the cell surface, other receptors for cytokines, growth factors, pathogen-associated molecular patterns, and damage-associated molecular patterns also function as triggers of MC stimulation, resulting in the release of chemical mediators, eicosanoids, and various cytokines. In this review, we focus on the role of interleukin (IL)-10, an anti-inflammatory cytokine, in MC-mediated immune responses, in which MCs play roles not only as initiators of the immune response but also as suppressors of excessive inflammation. IL-10 exhibits diverse effects on the proliferation, differentiation, survival, and activation of MCs in vivo and in vitro. Furthermore, IL-10 derived from MCs exerts beneficial and detrimental effects on the maintenance of tissue homeostasis and in several immune-related diseases including contact hypersensitivity, auto-immune diseases, and infections. This review introduces the effects of IL-10 on various events in MCs, and the roles of MCs in IL-10-related immune responses and as a source of IL-10.     

超宽带大功率合成器设计北大核心CSCD

在80 MHz~1 GHz频段,单个功率管输出功率能达到100 W以上,为研制输出功率400 W的功率放大器,文中设计了四路功率合成器。该合成器需要实现功率容量大、工作频带宽、体积小的设计目标。在功率容量方面,文中采用悬置带状线结构,其功率容量远远大于微带线结构;在工作频带方面,采用切比雪夫九节阻抗变换器,将工作带宽拓宽为80 MHz~1 GHz;在体积方面,文中合成器的功率合成部分采用Y型节级联实现四路功率合成,阻抗变换部分采用切比雪夫阻抗变换器进行阻抗变换,该结构相较于磁环巴伦功率合成器,不但具有损耗小、平坦度高的优点,而且通过将阻抗变换器设计成曲折的形状,进一步缩小了合成器体积。仿真与实测结果显示该合成器在80 MHz~1 GHz范围内还具有较高的平坦度,合成效率可达90%以上。     

基于人工神经网络的智能化架空线路应变快速解调方法北大核心

为了提高智能化光纤复合架空线路态势感知的实时性,将人工神经网络方法应用于光纤沿线应变解调,确定了神经网络的结构。编程实现了基于洛伦兹模型的最小二乘谱拟合方法和神经网络方法,采用不同信噪比和布里渊频移的布里渊谱训练神经网络,将它们应用于某光纤复合架空线路沿线光纤应变的测量,从不同角度比较了两种方法的计算结果。计算结果表明,神经网络方法能有效获得光纤沿线的布里渊频移进而获得应变,具有与谱拟合方法相似的准确性,但应变解调时间仅约为谱拟合方法的1/20000。研究结果为提高智能光纤复合架空线路态势感知的实时性提供了参考。     

离线式带钢双面翻转检查站方案设计及实践

针对某酸轧机组检查站穿带困难、检查效率低、产生废品多、故障率高的问题,开发了一种离线式带钢双面检查站。该检查站新增了带钢翻转装置,将在入口分切剪处完成定尺剪切的带钢试样由两侧压板夹紧,中间可升降皮带机落下,翻转装置将带钢试样张紧,并翻转90°或者180°,实现带钢的双面检查。皮带机两侧布置有可升降、可横移的活动操作平台,检测人员站在平台上对带钢进行打磨检查,可同时对带钢上下表面进行检测。由于缩短了带钢的传输距离,有效减少了其他擦划伤的影响,提高了带钢表面质量检测准确性。     

Optical design of the Lyman alpha based beam emission spectroscopy(LAB)diagnostic on the HL-2A tokamak

In this article, we present the optical design of a novel diagnostic on the HL-2 A tokamak, i.e. the20-channel edge Lyman-alpha beam emission spectroscopy, which is a promising solution for edge density turbulence research on tokamaks, as it offers the possibility of density fluctuation measurement with a 3.3 mm spatial resolution while maintains a high temporal resolution of1 μs. The optical path, including the reflective collection optics, the high-dispersion spectrometer, and the linear detector array, is carefully optimized to obtain a good image quality and a high throughput. The maximum root mean square radius of the collection optics is 64 μm.The detected photon flux is estimated to be about 10~(11) photons/s/channel.     

基于阶段注意力机制的电力线提取算法

电力系统维护是电力系统稳定运行的重要保障，应用智能算法的无人机电力巡检则为电力系统维护提供便捷。电力线提取是自主电力巡检以及保障飞行器低空飞行安全的关键技术，结合深度学习理论进行电力线提取是电力巡检的重要突破点。本文将深度学习方法用于电力线提取任务，结合电力线图像特点嵌入改进的图像输入策略和注意力模块，提出一种基于阶段注意力机制的电力线提取模型（SA-Unet）。本文提出的SA-Unet模型编码阶段采用阶段输入融合策略（Stage input fusion strategy， SIFS），充分利用图像的多尺度信息减少空间位置信息丢失。解码阶段通过嵌入阶段注意力模块（Stage attention module，SAM）聚焦电力线特征，从大量信息中快速筛选出高价值信息。实验结果表明，该方法在复杂背景的多场景中具有良好的性能。     

"不知火"柑橘全自动包装生产线的设计与研究

目的为了解决柑橘在实际包装过程中因于人工手动装袋、装箱等导致的效率低下问题,设计一条全自动柑橘包装生产线。方法基于“不知火”柑橘的特殊体型特征,使用传送带分级装置对其进行分级;通过倾斜皮带解决柑橘排列姿态的整理问题;经给袋式包装机装袋后,采用扭结式扎口装置对其进行封口;利用并联机器人对其进行装箱。通过计算生产节拍,合理规划每个工序的循环时间,并通过Flexsim软件对该生产线进行仿真分析与平衡优化。结果该生产线整体效率由89%提升到93%,能够正常运行且满足生产力的需求。结论该柑橘包装生产线实现了柑橘的分级、整料、装袋、装箱等工序,降低了工作强度,提高了生产效率,实现了包装过程的自动化。     

Learn from the past – sequentially one-to-one video deblurring network

With the growing availability of hand-held cameras in recent years, more and more images and videos are taken at any time and any place. However, they usually suffer from undesirable blur due to camera shake or object motion in the scene. In recent years, a few modern video deblurring methods are proposed and achieve impressive performance. However, they are still not suitable for practical applications as high computational cost or using future information as input. To address the issues, we propose a sequentially one-to-one video deblurring network (SOON) which can deblur effectively without any future information. It transfers both spatial and temporal information to the next frame by utilizing the recurrent architecture. In addition, we design a novel Spatio-Temporal Attention module to nudge the network to focus on the meaningful and essential features in the past. Extensive experiments demonstrate that the proposed method outperforms the state-of-the-art deblurring methods, both quantitatively and qualitatively, on various challenging real-world deblurring datasets. Moreover, as our method deblurs in an online manner and is potentially real-time, it is more suitable for practical applications.