检索结果-内蒙古大学图书馆

Building Extraction from Airborne LiDAR Data Based on Multi-Constraints graph segmentation

REMOTE SENSING 2021年第18期13卷 3766-3766页

作者： Hui, Zhenyang Li, Zhuoxuan Cheng, Penggen Ziggah, Yao Yevenyo Fan, JunLin East China Univ Technol Fac Geomat Nanchang 330013 Jiangxi Peoples R China Univ Mines & Technol Fac Geosci & Environm Studies Tarkwa 999064 Ghana Jiangxi Nucl Ind Surveying & Mapping Inst Grp Co Nanchang 330038 Jiangxi Peoples R China

Building extraction from airborne Light Detection and Ranging (LiDAR) point clouds is a significant step in the process of digital urban construction. Although the existing building extraction methods perform well in simple urban environments, when encountering complicated city environments with irregular building shapes or varying building sizes, these methods cannot achieve satisfactory building extraction results. To address these challenges, a building extraction method from airborne LiDAR data based on multi-constraints graph segmentation was proposed in this paper. The proposed method mainly converted point-based building extraction into object-based building extraction through multi-constraints graph segmentation. The initial extracted building points were derived according to the spatial geometric features of different object primitives. Finally, a multi-scale progressive growth optimization method was proposed to recover some omitted building points and improve the completeness of building extraction. The proposed method was tested and validated using three datasets provided by the International Society for Photogrammetry and Remote Sensing (ISPRS). Experimental results show that the proposed method can achieve the best building extraction results. It was also found that no matter the average quality or the average F1 score, the proposed method outperformed ten other investigated building extraction methods.

关键词： airborne LiDAR building extraction graph segmentation object primitive geometric feature

来源：评论

学校读者我要写书评

暂无评论

Generic User-guided Interaction Paradigm for Precise Post-slice-wise Processing of Tomographic Deep Learning segmentations Utilizing graph Cut and graph segmentation 16

Generic User-guided Interaction Paradigm for Precise Post-sl...

引用

16th International Joint Conference on Computer Vision, Imaging and Computer graphics Theory and Applications (VISIGRAPP) / 16th International Conference on Computer Vision Theory and Applications (VISAPP)

作者： Zwettler, Gerald A. Backfrieder, Werner Karwoski, Ronald A. Holmes, David R. I. I. I. I. I. I. Univ Appl Sci Upper Austria Res Grp Adv Informat Syst & Technol AIST Dept Software Engn Softwarepk 11 A-4232 Hagenberg Austria Mayo Clin Biomed Analyt & Computat Engn Lab Dept Physiol & Biomed Engn Coll Med 200 First St SW Rochester MN 55905 USA Univ Appl Sci Upper Austria Dept Software Engn Med Informat Softwarepk 11 A-4232 Hagen Berg Austria

ISBN: (纸本)9789897584886

State of the art deep learning (DL) manifested in image processing as an accurate segmentation method. Nevertheless, its black-box nature hardly allows user interference. In this paper, we present a generic graph cut (GC) and graph segmentation (GS) approach for user-guided interactive post-processing of segmentations resulting from DL. The GC fitness function incorporates both, the original image characteristics and DL segmentation results, combining them with weights optimized by evolution strategy optimization. To allow for accurate user-guided processing, the fore- and background seeds of the graph cut are automatically selected from the DL segmentations, but implementing effective features for expert input for adaptions of position and topology. The seamless integration of DL with GC/GS leads to marginal trade-off in quality, namely Jaccard (JI) 1.3% for automated GC and JI 0.46% for GS only. Yet, in specific areas where a well-trained DL model may potentially fail, precise adaptions at a low demand for user-interaction become feasible and thus even outperforming the original DL results. The potential of GC/GS is shown running on ground-truth seeds thereby outperforming DL by 0.44% JI for the GC and even by 1.16% JI for the GS. Iterative slice-by-slice progression of the post-processed and improved results keeps the demand for user-interaction low.

关键词： graph Cut graph segmentation U-Net Deep Learning Image segmentation Evolution-strategy User-guided Medical Image Analysis

来源：评论

学校读者我要写书评

暂无评论

Empowering graph segmentation methods with SOMs and CONN similarity for clustering large and complex data

引用

NEURAL COMPUTING & APPLICATIONS 2020年第24期32卷 18161-18178页

作者： Merenyi, Erzsebet Taylor, Joshua Rice Univ Dept Stat Houston TX 77005 USA Rice Univ Dept Elect & Comp Engn Houston TX 77005 USA

High-dimensional, large, and noisy data with complex structure challenge the limits of many clustering algorithms including modern graph segmentation methods. SOM-based clustering has been shown capable of capturing many clusters of widely varying statistical properties in such data. However, to date the best discovery results are produced by interactive extraction of clusters from informative SOM visualizations. This does not scale for Big Data, large archives, or near-real-time analyses. We approach this challenge by infusing SOM knowledge into leading automatic graph segmentation algorithms, which produce extremely poor results when segmenting the SOM prototypes without this information, and which would take a prohibitively long time to segment the input data sets. The knowledge translation occurs by casting the SOM prototypes as vertices and the CONN similarity measure as edge weightings of a graph which is then presented to graph segmentation algorithms. The resulting performance closely approximates the precision of the interactive SOM segmentation for complicated data and, at the same time, is extremely fast and memory-efficient. We demonstrate the effectiveness on a simple synthetic data set and on a very realistic fully labeled synthetic hyperspectral image. We also examine performance dependence on available parametrizations of the graph segmentation algorithms, in combination with parametrizations of the CONN similarity measure.

关键词： SOM clustering graph segmentation CONN similarity Big Data Automation

来源：评论

学校读者我要写书评

暂无评论

The graph segmentation Problem

引用

Electronic Notes in Discrete Mathematics 2018年 64卷 35-44页

作者： Schwartz, Stephan Borndörfer, Ralf Bartz, Gerald Department of Mathematical Optimization Zuse Institute Berlin Berlin Germany Institut für Mathematik Technische Universität Berlin Berlin Germany

We investigate a graph theoretical problem arising in the automatic billing of a network toll. Given a network and a family of user paths, we study the graph segmentation problem (GSP) to cover parts of the user paths by a set of disjoint segments. The GSP is shown to be NP-hard but for special cases it can be solved in polynomial time. We also show that the marginal utility of a segment is bounded. Computational results for real-world instances show that in practice the problem is more amenable than the theoretic bounds suggest. © 2018

关键词： combinatorial optimization graph segmentation toll billing

来源：评论

学校读者我要写书评

暂无评论

Multiorientation/multiscript scene text detection based on projection profile analysis and graph segmentation

引用

JOURNAL OF ELECTRONIC IMAGING 2016年第6期25卷 1-9页

作者： Koo, Hyung I. I. Ajou Univ Dept Elect & Comp Engn Worldcupro 206 Suwon 16499 South Korea

Textline detection in natural images has been an important problem and researchers have attempted to address this problem by grouping connected components (CCs) into clusters corresponding to textlines. However, developing bottom-up rules that work for multiorientation and/or multiscript textlines is not a simple task. In order to address this problem, we propose a framework that incorporates projection profile analysis (PPA) into the CC-based approach. Specifically, we build a graph of CCs and recursively partition the graph into subgraphs, until textline structures are detected by PPA. Although PPA has been a common technique in document image processing, it was developed for scanned documents, and we also propose a method to compute projection profiles for CCs. Experimental results show that our method is efficient and achieves better or comparable performance on conventional datasets (ICDAR 2011/2013 and MSRA-TD500), and shows promising results on a challenging dataset (ICDAR 2015 incidental text localization dataset). (C) 2016 SPIE and IS& T

关键词： projection profile analysis scene text detection graph segmentation

来源：评论

学校读者我要写书评

暂无评论

AUTOMATIC INITIALIZATION FOR NAVAL APPLICATION OF graph segmentation TECHNIQUES: A COMPARATIVE STUDY

AUTOMATIC INITIALIZATION FOR NAVAL APPLICATION OF GRAPH SEGM...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Camino, Irene Zoelzer, Udo Helmut Schmidt Univ Hamburg Germany

ISBN: (纸本)9781479928934

Nowadays, many different image processing applications are of high interest to maritime authorities because of security reasons. Depending on the application, different kinds of images are employed. The extraction of ship silhouettes requires high resolution images in order to obtain accurate results. However, when the characteristics of the naval environment are visible the background complexity increases greatly and automatic approaches fail. In order to overcome these difficulties we propose an automatic initialization for graph segmentation techniques. A comparative study of earlier suggested initializations for different graph segmentation techniques is also presented. It shows that, under such unfavorable image conditions, finding the proper initialization in an automatic way is not trivial. Yet, the precision and recall achieved by our initialization are considerable higher regardless the graph segmentation. Furthermore, the performance is highly increased since the best results are obtained after only the first iteration.

关键词： naval images automatic initialization silhouette extraction graph segmentation

来源：评论

学校读者我要写书评

暂无评论

A Radar Signal Deinterleaving Method Based on Enhanced Sparse Subspace Clustering

引用

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS 2025年第2期61卷 2956-2972页

作者： Guo, Qiang Huang, Shuai Liu, Li-Chao Kaliuzhnyi, Mykola Douplii, Stepan Harbin Engn Univ Coll Informat & Commun Engn Harbin 150001 Peoples R China Kharkiv Natl Univ Radio Elect Adv Res Lab UA-61166 Kharkov Ukraine Univ Munster Ctr Informat Technol D-48149 Munster Germany

In the modern information battlefield, radar signal deinterleaving plays a pivotal role in perceiving the electromagnetic spatial situation and grasping the initiative of the battle. The increasingly complex electromagnetic environment of modern battlefields leads to serious feature distribution space overlap of radar signal parameters, resulting in limited intraclass aggregation and interclass separability. Therefore, this article introduces the concept of a sparse subspace and proposes a radar signal deinterleaving method based on enhanced sparse subspace clustering. The generalized orthogonal matching pursuit algorithm is used in this study to construct a complex network on the basis of the self-expressiveness property among radar pulses in the same subspace, reducing the connection of pulses from different radars and thus decreasing computational complexity. The graph segmentation concept is incorporated into this algorithm, and Laplacian spectrum decomposition is employed to mine the geometric correlation from radar pulse signals. This approach enables efficient radar signal deinterleaving under nonideal conditions. Simultaneously, an algorithm based on an energy-corrected splitting threshold is proposed to calculate the number of cluster centers accurately. The proposed method effectively addresses the deinterleaving error issue caused by overlapping or missing working state parameters in intercepted complex radar pulse signals, achieving a deinterleaving accuracy of 94.74% for ten interleaved radar pulse signals with severe parameter feature overlap.

关键词： Radar Clustering algorithms Matching pursuit algorithms Complex networks Approximation algorithms Electromagnetics Radar countermeasures Computational complexity Accuracy Spaceborne radar Complex network graph segmentation parameter feature overlap radar signal deinterleaving sparse subspace clustering

来源：评论

学校读者我要写书评

暂无评论

Partially Occluded Face Reconstruction Using graph-based Algorithm

引用

JOURNAL OF ELECTRICAL ENGINEERING & TECHNOLOGY 2024年第6期19卷 3655-3664页

作者： Meena, Manisha Kumari Meena, Hemant Kumar Sharma, Ramnivas Malaviya Natl Inst Technol Jaipur Dept Elect Engn Jaipur Rajasthan India

This study introduces a novel algorithm rooted in spectral graph theory for the reconstruction of occluded facial images, with the aim of enhancing face recognition accuracy. The proposed method, Face Reconstruction using graph Fourier Transform (FRGFT) comprises three key stages: firstly, construct a graph representation of the image where each pixel is a node, and edges between nodes represent pixel adjacency with weights that capture both intensity and spatial relationships;secondly, identify occluded parts of the image using a graph-based segmentation technique to update the occlusion mask;and thirdly, reconstruct the original image from the occluded version using the Laplacian matrix of the graph and the updated occlusion mask. The whole process lies on the graph Laplacian (GL) technique, which draws the concepts from graphical models and the Laplace equation, proving to be effective in the high-quality restoration of faces that are damaged or occluded. This paper establishes the connection between GL and the traditional Fourier transform methods. To assess the utility of the GL-based restoration, completed facial images processed through the algorithm are subjected to face recognition testing. The effectiveness of the proposed approach is validated on two datasets: extended AR and CelebA face dataset, which have been significantly noticeable as our proposed approach achieves 98.5% accuracy as compared with the existing method.

关键词： Face reconstruction graph Fourier transform (GFT) Occlusion detection graph segmentation Peak signal-to-noise ratio Structural similarity index

来源：评论

学校读者我要写书评

暂无评论

Multi-Table Programmable Parser with online flow-level update consistency for satellite networks

引用

COMPUTER NETWORKS 2024年 247卷

作者： Zhang, Jin Wang, Daoye Liu, Kai Lu, Jianhua Tsinghua Univ Dept Elect Engn Beijing 100084 Peoples R China Tsinghua Univ Beijing Natl Res Ctr Informat Sci & Technol BNRist Beijing 100084 Peoples R China

Programmable packet parsers in the space data plane, responsible for identifying protocols and extracting keywords on demand, are significant to realize protocol upgrading for satellite networks. Because flow -level update consistency is significant, onboard resources are limited, and space radiation may cause errors in packet parsers, programmable packet parsers with online flow -level update consistency, low complexity, and high reliability are urgently needed. In our previous work, a Multi -Table Programmable Parser (MTPP) [1] is designed for fast configuration and low storage cost by networking configuration and multiple tables. In this paper, we propose a Multi -Table Programmable Parser with Online Flow -Level Update Consistency (MTPPOFLUC), consisting of five tables and eight models. To guarantee the flow -level update consistency, each table consists of a main table and a backup table. Moreover, to improve the reliability of MTPP-OFLUC, a fault tolerance mechanism is designed. Furthermore, an Online Configuration based on Super Parse graph segmentation (OC-SPGS) is proposed to achieve fast configuration with flow -level update consistency. The numerical analysis under typical parse graphs demonstrates that MTPP-OFLUC uses less storage than that of PISA -based parser. Due to backup tables adapted to guarantee the flow -level update consistency, the storage cost of MTPP-OFLUC is only 11.53% more than that of MTPP. Through OC-SPGS, the parsing success ratio of MTPP-OFLUC is up to 66.7% larger than that of MTPP. Finally, a prototype of MTPP-OFLUC is implemented on Xilinx Virtex-7 FPGA. The response time of MTPP-OFLUC and the network is 1.460 us and 4.196 ms, respectively. The size of configuration information is less than that of PISA -based parser. In summary, rapid response and flow -level update consistency are realized by MTPP-OFLUC. Moreover, security risks, user-friendly interfaces, potential capacity of upgrades, and supports for higher data rates still n

关键词： Satellite networks Programmable packet parser Online configuration Flow-level update consistency graph segmentation

来源：评论

学校读者我要写书评

暂无评论

Automatic multi-storey building partitioning from point cloud via bidirectional cloth simulation

引用

JOURNAL OF BUILDING ENGINEERING 2024年 97卷

作者： Li, Feng Shi, Wenzhong Zhang, Hua Tu, Yunlin Hao, Ming Sun, Yangjie China Univ Min & Technol Sch Environm & Spatial Informat Xuzhou Peoples R China Hong Kong Polytech Univ Smart Cities Res Inst Dept Land Surveying & Geoinformat Hong Kong Peoples R China

With the advancements in scanning technology, the rapid acquisition of point cloud spanning multiple storeys of buildings has become feasible. Accurately dividing the building into individual storeys deepens the understanding of the building environment, accelerates the processing of the vast point cloud, and is crucial for numerous fields such as model reconstruction, indoor navigation, and building management. However, it remains a challenge to handle the building with rooms across multiple storeys. This study presents a novel method to partition complex multistorey building from cluttered point cloud. First, the non-vertical structural elements are detected by taking the difference of height and normal vector as growth conditions. Next, we iteratively employ bidirectional cloth with height variation constraints to simulate the floor and ceiling trend surface. In this step, candidate ceiling patches are obtained through the optimization of a cost function. Finally, the irregular boundary between adjacent storeys that used for partitioning the point cloud is rasterized in terms of the ceilings at lower storey and the floors at upper storey. Each point is orderly classified into the correspond storey with reference to the elevation of the estimated boundary. Through comprehensive evaluation and analysis, our method has demonstrated its effectiveness and adaptability across various datasets. Our method yields superior results compared to the advanced methods, achieving an approximate value of 99 % on the weighted recall, weighted precision and weighted F1-score. Besides, the proposed method is not limited to Manhattan world buildings and requires only the spatial coordinate of points.

关键词： Storey partitioning Point cloud Structural elements detection graph segmentation Bidirectional cloth simulation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：