Research on neural radiance fields for novel view synthesis has experienced explosive growth with the development of new models and extensions.The NeRF(Neural Radiance Fields)algorithm,suitable for underwater scenes o...Research on neural radiance fields for novel view synthesis has experienced explosive growth with the development of new models and extensions.The NeRF(Neural Radiance Fields)algorithm,suitable for underwater scenes or scattering media,is also evolving.Existing underwater 3D reconstruction systems still face challenges such as long training times and low rendering efficiency.This paper proposes an improved underwater 3D reconstruction system to achieve rapid and high-quality 3D reconstruction.First,we enhance underwater videos captured by a monocular camera to correct the image quality degradation caused by the physical properties of the water medium and ensure consistency in enhancement across frames.Then,we perform keyframe selection to optimize resource usage and reduce the impact of dynamic objects on the reconstruction results.After pose estimation using COLMAP,the selected keyframes undergo 3D reconstruction using neural radiance fields(NeRF)based on multi-resolution hash encoding for model construction and rendering.In terms of image enhancement,our method has been optimized in certain scenarios,demonstrating effectiveness in image enhancement and better continuity between consecutive frames of the same data.In terms of 3D reconstruction,our method achieved a peak signal-to-noise ratio(PSNR)of 18.40 dB and a structural similarity(SSIM)of 0.6677,indicating a good balance between operational efficiency and reconstruction quality.展开更多
Enhanced recovery after surgery(ERAS)protocols are applied in orthopedic surgery and are intended to reduce perioperative stress by implementing combined evidence-based practices with the cooperation of various health...Enhanced recovery after surgery(ERAS)protocols are applied in orthopedic surgery and are intended to reduce perioperative stress by implementing combined evidence-based practices with the cooperation of various health professionals as an interdisciplinary team.ERAS pathways include pre-operative patient counselling,regional anesthesia and analgesia techniques,post-operative pain management,early mobilization and early feeding.Studies have shown improvement in the recovery of patients who followed an ERAS program after hip or knee arthroplasty,compared with those who followed a traditional care approach.ERAS protocols reduce post-operative stress,contribute to rapid recovery,shorten length of stay(LOS)without increasing the complications or readmissions,improve patient satisfaction and decrease the hospital costs.We suggest that the ERAS pathway could reduce the LOS in hospital for patients undergoing total hip replacement or total knee replacement.These programs require good organization and handling by the multidisciplinary team.ERAS programs increase patient's satisfaction due to their active participation which they experience as personalized treatment.The aim of the study was to develop an ERAS protocol for oncology patients who undergo bone reconstruction surgeries using massive endoprosthesis,with a view to improving the surgical outcomes.展开更多
The simulated annealing (SA) algorithm , originally developed by White R G for speckle reduction of synthetic aperture radar (SAR) images, shows significant improvement on the reconstruction of both homogeneous and ...The simulated annealing (SA) algorithm , originally developed by White R G for speckle reduction of synthetic aperture radar (SAR) images, shows significant improvement on the reconstruction of both homogeneous and strong structured areas. But his algorithm also has drawbacks itself, especially over smooth thin and weak textures and structures. In this study, a modified version of the algorithm is presented. The SA approach is extended to incorporate an edge detection and enhancement step that makes thin and weak structures strong enough to be preserved during annealing. To cooperate with this method, a temperature steadily decreased exponential schedule is adopted instead of the logarithm plan. By delicately adjusting the SA process, the proposed approach can well preserve many fine features in an SAR image while not degrading performance of other scenes such as homogeneous and strong structured areas and without other additional image defects. This feature makes the algorithm more suitable for filtering low and medium resolution SAR images.展开更多
[目的]通过总结上海城市轨道交通既有线运能提升改造项目的实施经验,为其提出有效的运能提升方法及具体案例。[方法]深入分析上海轨道交通既有线运能不足的主要原因及其影响因素;基于这些分析,提出运能提升的技术路线及5大核心策略;详...[目的]通过总结上海城市轨道交通既有线运能提升改造项目的实施经验,为其提出有效的运能提升方法及具体案例。[方法]深入分析上海轨道交通既有线运能不足的主要原因及其影响因素;基于这些分析,提出运能提升的技术路线及5大核心策略;详细介绍了上海轨道交通9号线实现1 min 50 s最小行车间隔、3号线与4号线增能改造、5号线从4节编组扩编至6节编组、6号线增能改造及增设复线等成功案例。[结果及结论]影响线路运能的主要因素包括车辆基地规模、区间通过能力、出入场能力,以及供电能力等。针对这些因素,确定了运能提升的技术路线,即从客流预测及客流特征分析入手,进行设施设备能力评估,设计行车交路方案,最终形成科学的改造方案。同时,提出了5大策略:运营管理优化、既有系统能力挖潜及改造、信号系统升级或土建局部改造、系统规模性改造及线网整体优化。展开更多
为完善基于先验知识的标记增强方法对于情绪信息的捕捉,提出一种基于语义规则增强的蒙古语情感分布学习方法(semantic rule enhancement based Mongolian emotion distribution learning, SRE-MEDL)。在情感轮和情感词典的基础上,引入...为完善基于先验知识的标记增强方法对于情绪信息的捕捉,提出一种基于语义规则增强的蒙古语情感分布学习方法(semantic rule enhancement based Mongolian emotion distribution learning, SRE-MEDL)。在情感轮和情感词典的基础上,引入程度词典和否定词典,得到各种情感词组合,以此制定相应的语义规则计算情感词权重,将其融入到标记增强中。在情感分布学习中融入从情感分布空间到实例特征空间的反向重构映射来弥补正向映射引起的原始信息丢失问题。对比实验结果显示,在蒙古语和中英文常用数据集上,SRE-MEDL方法在标记增强任务和情感分布学习中的表现均优于现有方法。展开更多
基金This work was supported by the Key Research and Development Program of Hainan Province(Grant Nos.ZDYF2023GXJS163,ZDYF2024GXJS014)National Natural Science Foundation of China(NSFC)(Grant Nos.62162022,62162024)+2 种基金the Major Science and Technology Project of Hainan Province(Grant No.ZDKJ2020012)Hainan Provincial Natural Science Foundation of China(Grant No.620MS021)Youth Foundation Project of Hainan Natural Science Foundation(621QN211).
文摘Research on neural radiance fields for novel view synthesis has experienced explosive growth with the development of new models and extensions.The NeRF(Neural Radiance Fields)algorithm,suitable for underwater scenes or scattering media,is also evolving.Existing underwater 3D reconstruction systems still face challenges such as long training times and low rendering efficiency.This paper proposes an improved underwater 3D reconstruction system to achieve rapid and high-quality 3D reconstruction.First,we enhance underwater videos captured by a monocular camera to correct the image quality degradation caused by the physical properties of the water medium and ensure consistency in enhancement across frames.Then,we perform keyframe selection to optimize resource usage and reduce the impact of dynamic objects on the reconstruction results.After pose estimation using COLMAP,the selected keyframes undergo 3D reconstruction using neural radiance fields(NeRF)based on multi-resolution hash encoding for model construction and rendering.In terms of image enhancement,our method has been optimized in certain scenarios,demonstrating effectiveness in image enhancement and better continuity between consecutive frames of the same data.In terms of 3D reconstruction,our method achieved a peak signal-to-noise ratio(PSNR)of 18.40 dB and a structural similarity(SSIM)of 0.6677,indicating a good balance between operational efficiency and reconstruction quality.
文摘Enhanced recovery after surgery(ERAS)protocols are applied in orthopedic surgery and are intended to reduce perioperative stress by implementing combined evidence-based practices with the cooperation of various health professionals as an interdisciplinary team.ERAS pathways include pre-operative patient counselling,regional anesthesia and analgesia techniques,post-operative pain management,early mobilization and early feeding.Studies have shown improvement in the recovery of patients who followed an ERAS program after hip or knee arthroplasty,compared with those who followed a traditional care approach.ERAS protocols reduce post-operative stress,contribute to rapid recovery,shorten length of stay(LOS)without increasing the complications or readmissions,improve patient satisfaction and decrease the hospital costs.We suggest that the ERAS pathway could reduce the LOS in hospital for patients undergoing total hip replacement or total knee replacement.These programs require good organization and handling by the multidisciplinary team.ERAS programs increase patient's satisfaction due to their active participation which they experience as personalized treatment.The aim of the study was to develop an ERAS protocol for oncology patients who undergo bone reconstruction surgeries using massive endoprosthesis,with a view to improving the surgical outcomes.
文摘The simulated annealing (SA) algorithm , originally developed by White R G for speckle reduction of synthetic aperture radar (SAR) images, shows significant improvement on the reconstruction of both homogeneous and strong structured areas. But his algorithm also has drawbacks itself, especially over smooth thin and weak textures and structures. In this study, a modified version of the algorithm is presented. The SA approach is extended to incorporate an edge detection and enhancement step that makes thin and weak structures strong enough to be preserved during annealing. To cooperate with this method, a temperature steadily decreased exponential schedule is adopted instead of the logarithm plan. By delicately adjusting the SA process, the proposed approach can well preserve many fine features in an SAR image while not degrading performance of other scenes such as homogeneous and strong structured areas and without other additional image defects. This feature makes the algorithm more suitable for filtering low and medium resolution SAR images.
文摘[目的]通过总结上海城市轨道交通既有线运能提升改造项目的实施经验,为其提出有效的运能提升方法及具体案例。[方法]深入分析上海轨道交通既有线运能不足的主要原因及其影响因素;基于这些分析,提出运能提升的技术路线及5大核心策略;详细介绍了上海轨道交通9号线实现1 min 50 s最小行车间隔、3号线与4号线增能改造、5号线从4节编组扩编至6节编组、6号线增能改造及增设复线等成功案例。[结果及结论]影响线路运能的主要因素包括车辆基地规模、区间通过能力、出入场能力,以及供电能力等。针对这些因素,确定了运能提升的技术路线,即从客流预测及客流特征分析入手,进行设施设备能力评估,设计行车交路方案,最终形成科学的改造方案。同时,提出了5大策略:运营管理优化、既有系统能力挖潜及改造、信号系统升级或土建局部改造、系统规模性改造及线网整体优化。
文摘为完善基于先验知识的标记增强方法对于情绪信息的捕捉,提出一种基于语义规则增强的蒙古语情感分布学习方法(semantic rule enhancement based Mongolian emotion distribution learning, SRE-MEDL)。在情感轮和情感词典的基础上,引入程度词典和否定词典,得到各种情感词组合,以此制定相应的语义规则计算情感词权重,将其融入到标记增强中。在情感分布学习中融入从情感分布空间到实例特征空间的反向重构映射来弥补正向映射引起的原始信息丢失问题。对比实验结果显示,在蒙古语和中英文常用数据集上,SRE-MEDL方法在标记增强任务和情感分布学习中的表现均优于现有方法。
