Optimization and regularization of complex task decomposition for blind removal of multi-factor degradation

Most existing image restoration methods based on deep neural networks are developed for images which only degraded by a single degradation mode and imaging under an ideal condition. They cannot be directly used to restore the images degraded by multi-factor coupling. A complex task decomposition regularization optimization strategy (TDROS) is proposed to solve the problem. The restoration of images degraded by multi-factor coupling is a complex task that can be solved by separating these multiple factors, that is, breaking the complex task into numbers of simpler tasks to make the entire complex problem be overcome more easily. Motivated by this idea, the TDROS decomposes the complex task of image restoration into two sub-task: the potential task constrained by regularization and the main task for reconstructing high-definition images. In TDROS, the front of the neural network is focused on the restoration of images degraded by additive noise, while the other part of the network is focused mainly on the restoration of images degraded by blur. We applied the TDROS to an 11-layer convolutional neural network (CNN) and compared it with initial CNNs from the aspects of restoration accuracy and generalization ability. Based on these results, we used TDROS to design a novel network model for the restoration of atmospheric turbulence-degraded images. The experimental results demonstrate that the proposed TDROS can improve the generalization ability of the existing network more effectively than current popular methods, offering a better solution for the problem of severely degraded image restoration. Moreover, the TDROS concept provides a flexible framework for low-level visual complex tasks and can be easily incorporated into existing CNNs.     

自适应融合层级特征的混合退化图像复原算法

多种退化类型混合的图像比单一类型的退化图像降质更严重,很难建立精确模型对其复原,研究端到端的神经网络算法是复原的关键.现有的基于操作选择注意力网络的算法(operation-wiseattentionnetwork,OWAN)虽然有一定的性能提升,但是其网络过于复杂,运行较慢,复原图像缺乏高频细节,整体效果也有提升的空间.针对这些问题,提出一种基于层级特征融合的自适应复原算法.该算法直接融合不同感受野分支的特征,增强复原图像的结构;用注意力机制对不同层级的特征进行动态融合,增加模型的自适应性,降低了模型冗余;另外,结合L1损失和感知损失,增强了复原图像的视觉感知效果.在DIV2K,BSD500等数据集上的实验结果表明,该算法无论是在峰值信噪比和结构相似性上的定量分析,还是在主观视觉质量方面,均优于OWAN算法,充分证明了该算法的有效性.     

Incorporating microgrids coupling with utilization of flexible switching to enhance self-healing ability of electric distribution systems

Electric distribution networks have to deal with issues caused by natural disasters. These problems possess unique characteristics, and their severity can make load restoration methods impotent. One solution that can help in alleviating the aftermath is the use of microgrids (MGs). Employing the cumulative capacity of the generation resources through MG coupling facilitates the self-healing capability and leads to better-coordinated energy management during the restoration period, while the switching capability of the system should also be considered. In this paper, to form and schedule dynamic MGs in distribution systems, a novel model based on mixed-integer linear programming (MILP) is proposed. This approach employs graph-related theories to formulate the optimal formation of the networked MGs and management of their proper participation in the load recovery process. In addition, the Benders decomposition technique is applied to alleviate computability issues of the optimization problem. The validity and applicability of the proposed model are evaluated by several simulation studies.     

自适应背景光估计与非局部先验的水下图像复原

有效地实现单幅水下降质图像复原对水下资源探索及环境监控领域的清晰图像获取具有极其重要的意义。为解决常用暗通道先验方法来复原图像时,背景光的估计易受白色物体干扰,且无法有效估计前景中白色物体透射率,复原质量不高的问题。本文提出了自适应背景光估计与非局部先验的水下图像复原算法。首先根据背景光具有高亮度及平坦性的特点,利用阈值分割算法获得背景光的候选区域,再通过图像的色调信息从候选信息中选取最佳的背景光点。随后,利用各颜色通道光的波长与散射系数的相关性,提出了适用于水下图像的非局部先验,并利用该先验估计各通道的透射率。最后针对复原结果中,因水下介质,微生物,水流影响而产生的加性噪声,设计去噪的最小优化问题,并利用引导滤波求解该问题,以去除复原结果中的加性噪声。实验表明:该算法在确保运行效率的基础上,准确地估计透射率,较常用算法的复原精度提高了约18%。证明了该算法能有效用于单幅水下图像复原的工程实践中。     

Microstructure and flexural strength of the Y:TZP/BG composite

The addition of bioactive glasses to a Y:TZP matrix represents a feasible alternative to provide bioactivity to this material and optimize osseointegration. This work evaluated the effect of the BG concentration (0 and 10 wt%) and the sintering temperature (1200°C and 1300°C) on the microstructure, relative density, and flexural strength of the composite Y:TZP/BG. The Y:TZP and Y:TZP/BG powders were uniaxially pressed and sintered at 1200°C or 1300°C for 1 h. The microstructure was characterized by X-ray diffraction analysis, scanning electron microscopy, and energy-dispersive X-ray Spectroscopy. Relative density was calculated from density values obtained using the Archimedes’ principle. For the flexural strength, specimens (n = 6) were fractured in a biaxial flexural setup using a piston-on-three-balls fixture in a universal testing machine. Bioactivity test was performed in simulated body fluid solution. The results suggested that BG addition decreased the grain size of the composite, increased porosity and caused a significant decrease in the relative density and flexural strength. Crystalline phases of calcium stabilized cubic zirconia and sodium zirconium silicate were formed after the addition of BG. Finally, it was concluded that composite specimens sintered at 1300°C showed the highest density values and larger grains compared to those sintered at 1200°C.     

古地貌恢复方法综述

古地貌形态控制着沉积相类型和展布,从而控制油气藏的生储盖组合,因此,古地貌的准确恢复对油气勘探具有非常重要的意义。在前人研究的基础之上,利用高分辨率层序地层学法、双界面法、回剥和填平补齐法、构造沉积模拟法和沉积期微幅度古地貌推算法对古地貌恢复方法进行总结,结果表明,小区域内可利用双界面法进行古地貌恢复,对于构造运动强烈地区,应采用构造沉积模拟法,而针对一些微幅构造地区,沉积期微幅度古地貌推算法能较为准确地恢复古地貌。     

新时代长江鱼类多样性保护的思考

长江是我国第一大河流,是世界生物多样性的热点区域,也是我国鱼类多样性最高的河流之一。在介绍长江鱼类主要生态习性生境条件的基础上,分析了导致鱼类多样性下降的主要因素——生境丧失和过度捕捞,并简要总结了目前已采取的保护措施及存在的问题,提出了关于新时期长江鱼类多样性保护的思考与建议:①建立以流域管理机构牵头,相关部门和地方共同组建流域生态保护机制;②有计划开展支流及通江湖泊的生态恢复,使支流的小水电逐步退出,使原本的通江湖泊恢复自然江湖关系;③提高民众环保意识,积极建立全流域禁捕机制和休闲垂钓机制,并让垂钓者成为渔政的管理者和监督者。