Image-based 3D modeling is an effective method for reconstructing large-scale scenes,especially city-level scenarios.In the image-based modeling pipeline,obtaining a watertight mesh model from a noisy multi-view stere...Image-based 3D modeling is an effective method for reconstructing large-scale scenes,especially city-level scenarios.In the image-based modeling pipeline,obtaining a watertight mesh model from a noisy multi-view stereo point cloud is a key step toward ensuring model quality.However,some state-of-the-art methods rely on the global Delaunay-based optimization formed by all the points and cameras;thus,they encounter scaling problems when dealing with large scenes.To circumvent these limitations,this study proposes a scalable pointcloud meshing approach to aid the reconstruction of city-scale scenes with minimal time consumption and memory usage.Firstly,the entire scene is divided along the x and y axes into several overlapping chunks so that each chunk can satisfy the memory limit.Then,the Delaunay-based optimization is performed to extract meshes for each chunk in parallel.Finally,the local meshes are merged together by resolving local inconsistencies in the overlapping areas between the chunks.We test the proposed method on three city-scale scenes with hundreds of millions of points and thousands of images,and demonstrate its scalability,accuracy,and completeness,compared with the state-of-the-art methods.展开更多
Large-scale virtual scene exploration is still a challenging task. The novice users caneasily get distracted and disorientated, which results in being lost in space. Assistedcamera control technology is the most effec...Large-scale virtual scene exploration is still a challenging task. The novice users caneasily get distracted and disorientated, which results in being lost in space. Assistedcamera control technology is the most effective solution for virtual environment exploration problems which requires viewpoint computation and path planning. In this paper,a novel approach for large-scale virtual scene based on viewpoint scoring is proposed.First, the scene was adaptively divided into several meaningful and easily analyzedsubregions according to the optimal view distance criterion. Second, a novel viewpointscoring method based on visual perception and information entropy fusion was developed for optimal viewpoint determination and greedy N-Best viewpoint selection algorithm was utilized for visual perceptibility calculation. Then evolutionary programmingapproach for the Traveling Salesman problem was applied for intra-subregion and intersubregion exploring path optimization. Finally, the Cubic Hermite Curve was introduced to smoothen the inflection point on the exploration path. The experimental resultsdemonstrate that the proposed method can effectively generate an automatic smooth,informative, aesthetic and non-intersecting path, with the characteristics of good exploring comfort, strong immersion and high scene information perception.展开更多
现有变电站运维系统电力设备的三相有功功率超过35 kW,不符合运维要求,为此研究基于Web前端开发技术的变电站三维实景交互运维系统设计。硬件方面,系统选择同步动态随机存储器(Synchronous Dynamic Random Access Memory,SDRAM)作为运...现有变电站运维系统电力设备的三相有功功率超过35 kW,不符合运维要求,为此研究基于Web前端开发技术的变电站三维实景交互运维系统设计。硬件方面,系统选择同步动态随机存储器(Synchronous Dynamic Random Access Memory,SDRAM)作为运行空间,采用以太网接口芯片进行接口设计。软件方面,通过建立具有交互性的Web页面,利用超文本标记语言5(Hyper Text Markup Language 5,HTML5)对变电站使用场景进行响应设计,并采用Autodesk Revit搭建模型平台,按照设计图放置设备族,构建三维实景模型。通过最短路径法设计运维策略,优化变电站运维策略并保证系统运行的安全性能。测试结果表明,系统满足日常电力设备的运维要求,确保电力设备负荷情况的准确获取。展开更多
变电站设备种类繁多、缺陷类型复杂、特征差异大,传统的基于深度学习的缺陷图像检测模型难以同时有效处理不同设备的多种缺陷。为此,提出了一种基于语义信息距离解耦的缺陷图像检测模型(sematic-distance based decoupling detection mo...变电站设备种类繁多、缺陷类型复杂、特征差异大,传统的基于深度学习的缺陷图像检测模型难以同时有效处理不同设备的多种缺陷。为此,提出了一种基于语义信息距离解耦的缺陷图像检测模型(sematic-distance based decoupling detection model,SDB-DDM)。首先对缺陷类别进行语义信息聚簇,构建解耦式网络结构,然后对网络输出进行加权锚框融合,并在损失函数中加入局部预测损失以提升预测能力,同时提出解耦式非极大值抑制策略以加快模型推理速度。该模型可根据缺陷类别进行自适应调整,以适用变电运维多类别缺陷图像检测的应用场景。实验结果显示,该模型的平均精度均值达到了69.68%。同平台下相较于目前性能最佳的目标检测模型(YOLOX),精度提升了1.36个百分点,参数量下降了5%,推理速度提升了34%。展开更多
为了提升变电站巡检机器人对自身所处环境的理解能力,将深度学习技术应用于变电站巡检机器人对道路场景的识别中,提出了一种全卷积道路场景识别网络(road scene recognition net,RSRNet)。该网络主要由相对浅层的编码网络和镜像结构与...为了提升变电站巡检机器人对自身所处环境的理解能力,将深度学习技术应用于变电站巡检机器人对道路场景的识别中,提出了一种全卷积道路场景识别网络(road scene recognition net,RSRNet)。该网络主要由相对浅层的编码网络和镜像结构与跳层融合结构相结合的解码网络组成,通过编码网络提取图像特征后由解码网络识别出图像目标信息。通过实验表明,本文提出的网络在同类型网络中识别精度及效率更高,同时在实际变电站场景中也表现出了优良的场景识别性能。展开更多
基金This work was supported by the Natural Science Foundation of China(Nos.61632003,61873265)。
文摘Image-based 3D modeling is an effective method for reconstructing large-scale scenes,especially city-level scenarios.In the image-based modeling pipeline,obtaining a watertight mesh model from a noisy multi-view stereo point cloud is a key step toward ensuring model quality.However,some state-of-the-art methods rely on the global Delaunay-based optimization formed by all the points and cameras;thus,they encounter scaling problems when dealing with large scenes.To circumvent these limitations,this study proposes a scalable pointcloud meshing approach to aid the reconstruction of city-scale scenes with minimal time consumption and memory usage.Firstly,the entire scene is divided along the x and y axes into several overlapping chunks so that each chunk can satisfy the memory limit.Then,the Delaunay-based optimization is performed to extract meshes for each chunk in parallel.Finally,the local meshes are merged together by resolving local inconsistencies in the overlapping areas between the chunks.We test the proposed method on three city-scale scenes with hundreds of millions of points and thousands of images,and demonstrate its scalability,accuracy,and completeness,compared with the state-of-the-art methods.
文摘Large-scale virtual scene exploration is still a challenging task. The novice users caneasily get distracted and disorientated, which results in being lost in space. Assistedcamera control technology is the most effective solution for virtual environment exploration problems which requires viewpoint computation and path planning. In this paper,a novel approach for large-scale virtual scene based on viewpoint scoring is proposed.First, the scene was adaptively divided into several meaningful and easily analyzedsubregions according to the optimal view distance criterion. Second, a novel viewpointscoring method based on visual perception and information entropy fusion was developed for optimal viewpoint determination and greedy N-Best viewpoint selection algorithm was utilized for visual perceptibility calculation. Then evolutionary programmingapproach for the Traveling Salesman problem was applied for intra-subregion and intersubregion exploring path optimization. Finally, the Cubic Hermite Curve was introduced to smoothen the inflection point on the exploration path. The experimental resultsdemonstrate that the proposed method can effectively generate an automatic smooth,informative, aesthetic and non-intersecting path, with the characteristics of good exploring comfort, strong immersion and high scene information perception.
文摘现有变电站运维系统电力设备的三相有功功率超过35 kW,不符合运维要求,为此研究基于Web前端开发技术的变电站三维实景交互运维系统设计。硬件方面,系统选择同步动态随机存储器(Synchronous Dynamic Random Access Memory,SDRAM)作为运行空间,采用以太网接口芯片进行接口设计。软件方面,通过建立具有交互性的Web页面,利用超文本标记语言5(Hyper Text Markup Language 5,HTML5)对变电站使用场景进行响应设计,并采用Autodesk Revit搭建模型平台,按照设计图放置设备族,构建三维实景模型。通过最短路径法设计运维策略,优化变电站运维策略并保证系统运行的安全性能。测试结果表明,系统满足日常电力设备的运维要求,确保电力设备负荷情况的准确获取。
文摘变电站设备种类繁多、缺陷类型复杂、特征差异大,传统的基于深度学习的缺陷图像检测模型难以同时有效处理不同设备的多种缺陷。为此,提出了一种基于语义信息距离解耦的缺陷图像检测模型(sematic-distance based decoupling detection model,SDB-DDM)。首先对缺陷类别进行语义信息聚簇,构建解耦式网络结构,然后对网络输出进行加权锚框融合,并在损失函数中加入局部预测损失以提升预测能力,同时提出解耦式非极大值抑制策略以加快模型推理速度。该模型可根据缺陷类别进行自适应调整,以适用变电运维多类别缺陷图像检测的应用场景。实验结果显示,该模型的平均精度均值达到了69.68%。同平台下相较于目前性能最佳的目标检测模型(YOLOX),精度提升了1.36个百分点,参数量下降了5%,推理速度提升了34%。
文摘为了提升变电站巡检机器人对自身所处环境的理解能力,将深度学习技术应用于变电站巡检机器人对道路场景的识别中,提出了一种全卷积道路场景识别网络(road scene recognition net,RSRNet)。该网络主要由相对浅层的编码网络和镜像结构与跳层融合结构相结合的解码网络组成,通过编码网络提取图像特征后由解码网络识别出图像目标信息。通过实验表明,本文提出的网络在同类型网络中识别精度及效率更高,同时在实际变电站场景中也表现出了优良的场景识别性能。
