检索结果-内蒙古大学图书馆

Exploring Novel Ai-Based Approaches for Plant Features Extraction in Image Datasets with Small Size: The Case Study of Nitrogen Estimation in Sorghum Using Uav-Based Rgb Sensing

SSRN

引用

SSRN 2023年

作者： Hammouch, Hajar Patil, Suchitra El-Yacoubi, Mounim A.A. Masner, Jan Kholová, Jana Choudhary, Sunita Anbazhagan, Krithika Vaněk, Jiří Qin, Huafeng Stočes, Michal Berbia, Hassan Jagarlapudi, Adinarayana Chandramouli, Magesh Mamidi, Srinivas Prasad, K.V.S.V. Baddam, Rekha SAMOVAR Telecom SudParis Institut Polytechnique de Paris Palaiseau91120 France Mohamed V University Rabat Morocco Centre of Studies in Resources Engineering Indian Institute of Technology Bombay Powai Maharashtra Mumbai400076 India Telangana Patancheru502 324 India Department of Information Technology K. J. Somaiya College of Engineering Vidyavihar Maharashtra Mumbai400 077 India Department of Information Technologies Czech University of Life Sciences Prague Prague165 00 Czech Republic Chongqing University China Computer Graphics Technology Purdue University NW HammondIN46323 United States Marut Dronetech Private Limited Gachibowli Telangana Hyderabad500032 India Patancheru Hyderabad502 324 India

This study was primarily triggered by the requirements of crop breeding programs to rapidly, accurately and cost-effectively select crop genotypes with enhanced biomass Nitrogen (N) content (an essential indicator of stover quality as feed) and, at the same time, possibly speed up the agriculture transition to the more sustainable and precise application of fertilizers (crop health status). This proof of concept study explores whether and how precisely it is possible to predict the N content in sorghum crop biomass using a minimum unmanned aerial vehicle (UAV)-carried imaging technology (Red Green Blue (RGB) camera) and a small dataset. To this end, we raised a post-rainy (rabi) 2021 and 2022 season sorghum crop in the field with standard and sub-optimal management practices (N and water stress) at the International Crop Research Institute for Semi-arid Tropics (ICRISAT), India. RGB images were collected during different crop growth stages (rabi 2021, 2022) using a low-cost RGB camera DJI Zenmuse X5S mounted UAV DJI Matrice 210 *** collected three ground-truth points with corresponding RGB images to build the N-prediction model (rabi 2021) and then six ground-truth points with corresponding RGB to evaluate the model with a second independent test set (rabi 2022). We have assessed statistical and AI-based models for N prediction, namely multiple linear regression (MLR), multi-layer perceptron (MLP) and various convolutional neural network (CNN) architectures, as well as their combinations. The first two take as input five handcrafted features computed using RGB spectrum vegetation indices (VIs) while the CNN automatically extracts discriminant features from the raw images. These schemes have already been proposed in state-of-the-art and the novelty of our study lies in the assessment of several fusion strategies in order to leverage both the deep features learned automatically by the CNN and the human-expertise-based handcrafted features, harnessing, thereb

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

3D Fluid Flow Estimation with Integrated Particle Reconstruction 40th

3D Fluid Flow Estimation with Integrated Particle Reconstruc...

引用

40th German Conference on Pattern Recognition, GCPR 2018

作者： Lasinger, Katrin Vogel, Christoph Pock, Thomas Schindler, Konrad Photogrammetry and Remote Sensing ETH Zurich Zürich Switzerland Institute of Computer Graphics and Vision Graz University of Technology Graz Austria AIT Austrian Institute of Technology Vienna Austria

ISBN: (纸本)9783030129385

The standard approach to densely reconstruct the motion in a volume of fluid is to inject high-contrast tracer particles and record their motion with multiple high-speed cameras. Almost all existing work processes the acquired multi-view video in two separate steps: first, a per-frame reconstruction of the particles, usually in the form of soft occupancy likelihoods in a voxel representation;followed by 3D motion estimation, with some form of dense matching between the precomputed voxel grids from different time steps. In this sequential procedure, the first step cannot use temporal consistency considerations to support the reconstruction, while the second step has no access to the original, high-resolution image data. We show, for the first time, how to jointly reconstruct both the individual tracer particles and a dense 3D fluid motion field from the image data, using an integrated energy minimization. Our hybrid Lagrangian/Eulerian model explicitly reconstructs individual particles, and at the same time recovers a dense 3D motion field in the entire domain. Making particles explicit greatly reduces the memory consumption and allows one to use the high-resolution input images for matching. Whereas the dense motion field makes it possible to include physical a-priori constraints and account for the incompressibility and viscosity of the fluid. The method exhibits greatly (≈70) improved results over a recent baseline with two separate steps for 3D reconstruction and motion estimation. Our results with only two time steps are comparable to those of state-of-the-art tracking-based methods that require much longer sequences. © 2019, Springer Nature Switzerland AG.

关键词： Motion estimation

来源：评论

学校读者我要写书评

暂无评论

Integrating anatomy and electrophysiology in the healthy human heart: Insights from biventricular statistical shape analysis using universal coordinates

引用

computers in Biology and Medicine 2025年第Pt A期192卷 110230-110230页

作者： Van Santvliet, Lore Zappon, Elena Gsell, Matthias A.F. Thaler, Franz Blondeel, Maarten Dymarkowski, Steven Claessen, Guido Willems, Rik Urschler, Martin Vandenberk, Bert Plank, Gernot De Vos, Maarten KU Leuven Kasteelpark Arenberg 10 Leuven3001 Belgium Division of Medical Physics and Biophysics Gottfried Schatz Research Center Medical University of Graz Graz Austria Department of Cardiology University Hospitals Leuven Herestraat 49 Leuven3000 Belgium Division of Radiology University Hospitals Leuven Herestraat 49 Leuven3000 Belgium Division of Cardiology Hartcentrum Jessa Ziekenhuis Stadsomvaart 11 Hasselt3500 Belgium Department of Medicine and Life Sciences University of Hasselt Stadsomvaart 11 Hasselt3500 Belgium Department of Cardiovascular Sciences KU Leuven Herestraat 49 Leuven3000 Belgium Institute of Computer Graphics and Vision Graz University of Technology Graz Austria Institute for Medical Informatics Statistics and Documentation Medical University of Graz Graz Austria BioTechMed-Graz Graz Austria

A cardiac digital twin is a virtual replica of a patient-specific heart, mimicking its anatomy and physiology. A crucial step of building a cardiac digital twin is anatomical twinning, where the computational mesh of the digital twin is tailored to the patient-specific cardiac anatomy. In a number of studies, the effect of anatomical variation on clinically relevant functional measurements like electrocardiograms (ECGs) is investigated, using computational simulations. While such a simulation environment provides researchers with a carefully controlled ground truth, the impact of anatomical differences on functional measurements in real-world patients remains understudied. In this study, we develop a biventricular statistical shape model and use it to quantify the effect of biventricular anatomy on ECG-derived and demographic features, providing novel insights for the development of digital twins of cardiac electrophysiology. To this end, a dataset comprising high-resolution cardiac CT scans from 271 healthy individuals, including athletes, is utilized. Furthermore, a novel, universal, ventricular coordinate-based method is developed to establish lightweight shape correspondence. The performance of the shape model is rigorously established, focusing on its dimensionality reduction capabilities and the training data requirements. The most important variability in healthy ventricles captured by the model is their size, followed by their elongation. These anatomical factors are found to significantly correlate with ECG-derived and demographic features. Additionally, a comprehensive synthetic cohort is made available, featuring ready-to-use biventricular meshes with fiber structures and anatomical region annotations. These meshes are well-suited for electrophysiological simulations. © 2025 Elsevier Ltd

关键词： Population statistics

来源：评论

学校读者我要写书评

暂无评论

An experimental investigation of the integration of smart building components with building information model (BIM) 36

An experimental investigation of the integration of smart bu...

引用

36th International Symposium on Automation and Robotics in Construction, ISARC 2019

作者： Afsari, K. Florez, L. Maneke, E. Afkhamiaghda, M. School of Construction Management Technology Purdue University United States Department of Architecture and Built Environment Northumbria University United Kingdom Department of Computer Graphics Technology Purdue University United States

Building Information Modeling (BIM) is a methodology to digitally represent all the physical and functional characteristics of a building. Importantly, in smart buildings smart components that are enabled with sensing and actuation need to be modeled accurately within the BIM model. This data representation needs to include multiple status of the smart component based on their performance to guide the design and construction process. However, currently there is not a clear methodology or guideline on how to embed smart components in the BIM model. Visualization techniques have been developed based on CAD technology to integrate smart components in the building model but these techniques have not been applied to BIM environment. To accurately model smart components, the component must be more than a single status representation and must contain complete and accurate dynamic data of the smart component. In this research, data properties, visualization techniques, and categorization of smart components is investigated. Then, through an experimental investigation, nine smart components across five building disciplines are modeled and embedded in a BIM model of a smart space. The model includes parameters that facilitate the data representation of the smart components. Data properties, data organization, and simulation of the smart component within the building model is explained. Challenges and future research is discussed. © 2019 International Association for Automation and Robotics in Construction I.A.A.R.C. All rights reserved.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Sketch-aided retrieval of incomplete 3D cultural heritage objects 12

Sketch-aided retrieval of incomplete 3D cultural heritage ob...

引用

12th Eurographics Workshop on 3D Object Retrieval, 3DOR 2019, in conjunction with the 40th Annual Conference of the European Association for computer graphics, EG 2019

作者： Lengauer, S. Komar, A. Labrada, A. Karl, S. Trinkl, E. Preiner, R. Bustos, B. Schreck, T. Institute of Computer Graphics and Knowledge Visualisation Graz University of Technology Austria Institute of Archaeology University of Graz Austria Millenium Institute for Foundational Research on Data Department of Computer Science University of Chile Chile

ISBN: (纸本)9783038680772

Due to advances in digitization technology, documentation efforts and digital library systems, increasingly large collections of visual Cultural Heritage (CH) object data becomes available, offering rich opportunities for domain analysis, e.g., for comparing, tracing and studying objects created over time. In principle, existing shape- and image-based similarity search methods can aid such domain analysis tasks. However, in practice, visual object data are given in different modalities, including 2D, 3D, sketches or conventional drawings like profile sections or unwrappings. In addition, collections may be distributed across different publications and repositories, posing a challenge for implementing encompassing search and analysis systems. We introduce a methodology and system for cross-modal visual search in CH object data. Specifically, we propose a new query modality based on 3D views enhanced by user sketches (3D+sketch). This allows for adding new context to the search, which is useful e.g., for searching based on incomplete query objects, or for testing hypotheses on existence of certain shapes in a collection. We present an appropriately designed workflow for constructing query views from incomplete 3D objects enhanced by a user sketch based on shape completion and texture inpainting. Visual cues additionally help users compare retrieved objects with the query. We apply our method on a set of relevant 3D and view-based CH object data, demonstrating the feasibility of our approach and its potential to support analysis of domain experts in Archaeology and the field of CH in general. © 2019 The Author(s)

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Generalisation of Segmentation Using Generative Adversarial Networks

Generalisation of Segmentation Using Generative Adversarial ...

引用

IEEE International Symposium on Biomedical Imaging

作者： André Ferreira Gijs Luijten Behrus Puladi Jens Kleesiek Victor Alves Jan Egger Institute for AI in Medicine (IKIM) University Hospital Essen (AöR) Essen Germany Center Algoritmi / LASI University of Minho Braga Portugal Computer Algorithms for Medicine Laboratory Graz Austria Institute of Medical Informatics University Hospital RWTH Aachen Aachen Germany Department of Oral and Maxillofacial Surgery University Hospital RWTH Aachen Aachen Germany Institute of Computer Graphics and Vision (ICG) Graz University of Technology Graz Austria Cancer Research Center Cologne Essen (CCCE) West German Cancer Center Essen (WTZ) University Hospital Essen (AöR) Essen Germany Partner Site Essen German Cancer Consortium (DKTK) Essen Germany Department of Physics TU Dortmund University Dortmund Germany Center for Virtual and Extended Reality in Medicine (ZvRM) University Hospital Essen Essen Germany

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

State-of-the-art deep learning algorithms are easily biased and evaluated in misleading scenarios, especially in the medical context, where scenarios change rapidly and diseases develop quickly. The BraTS 2024 GoAT challenge aims to evaluate how brain tumour segmentation algorithms can adapt to different circumstances when these are not available for training. Our solution utilises state-of-the-art conditional generative adversarial networks to generate realistic new cases and train a segmentation algorithm that takes advantage of the convolutions and attention mechanisms. Our solution achieved a DSC value of 0.855, 0.863, 0.883 and an HD95 value of 24.83, 24.10 and 21.72 for the enhancing tumour, the tumour core and the whole tumour in the validation set, respectively.

关键词： Training Knowledge engineering Deep learning Generative adversarial networks Robustness Inference algorithms Tumors

来源：评论

学校读者我要写书评

暂无评论

REGULARIZATION OF BUILDING BOUNDARIES IN SATELLITE IMAGES USING ADVERSARIAL AND REGULARIZED LOSSES

REGULARIZATION OF BUILDING BOUNDARIES IN SATELLITE IMAGES US...

引用

IEEE International Geoscience and Remote Sensing Symposium

作者： Stefano Zorzi Friedrich Fraundorfer Institute of Computer Graphics and Vision Graz University of Technology

In this paper we present a method for building boundary refinement and regularization in satellite images using a fully convolutional neural network trained with a combination of adversarial and regularized losses. Compared to a pure Mask R-CNN model, the overall algorithm can achieve equivalent performance in terms of accuracy and completeness. However, unlike Mask R-CNN that produces irregular footprints, our framework generates regularized and visually pleasing building boundaries which are beneficial in many applications.

关键词： Buildings Image reconstruction Image segmentation Training Satellites Erbium Pipelines

来源：评论

学校读者我要写书评

暂无评论

Motif-Driven retrieval of greek painted pottery

Motif-Driven retrieval of greek painted pottery

引用

2019 Eurographics Workshop on graphics and Cultural Heritage, GCH 2019

ISBN: (纸本)9783038680826

The analysis of painted pottery is instrumental for understanding ancient Greek society and human behavior of past cultures in Archaeology. A key part of this analysis is the discovery of cross references to establish links and correspondences. However, due to the vast amount of documented images and 3D scans of pottery objects in today's domain repositories, manual search is very time consuming. computer aided retrieval methods are of increasing importance. Mostly, current retrieval systems for this kind of cultural heritage data only allow to search for pottery of similar vessel's shape. However, in many cases important similarity cues are given by motifs painted on these vessels. We present an interactive retrieval system that makes use of this information to allow for a motif-driven search in cultural heritage repositories. We address the problem of unsupervised motif extraction for preprocessing and the shape-based similarity search for Greek painted pottery. Our experimental evaluation on relevant repository data demonstrates effectiveness of our approach on examples of different motifs of interests. © 2019 Eurographics Association.

关键词： Behavioral research

来源：评论

学校读者我要写书评

暂无评论

Research on Palm Vein Recognition Algorithm Based on Improved Convolutional Neural Network

Research on Palm Vein Recognition Algorithm Based on Improve...

引用

International Automatic Control Conference

作者： Bo Sun Xunfang Tao Ji li Xiaonan Luo Guangxi Key Laboratory of Intelligent processing of Computer Images and Graphics Guilin University of Electronic Technology Guilin China Guilin Huigu Institute of Artificial Intelligence Industrial Technology Guilin University of Electronic Technology Guilin China

ISBN: (数字)9781728171982

ISBN: (纸本)9781728171999

When collecting palm vein images, it is easy to be affected by external factors such as light source and placement angle, which result in poor recognition accuracy. In this paper, a new method, which involve a new method of region of interest segmentation and an improved palm recognition method of VGG16 deep convolutional neural network, was proposed to promote the recognition accuracy and be well adapted to the actual application scenarios. Firstly, the original palm vein image is obtained through profile original image, positioning key point of original image, and extract region of interest image. Afterwards, the adaptive histogram equalization technique and Gaussian Filters are utilized to improve image quality. Secondly, for palm vein image recognition application scenarios, the output of the convolutional layer of the VGG-16 convolutional neural network is standardized in batches, and the attention mechanism is introduced to optimize the VGG-16 neural network. The optimized network is used for feature extraction and recognition of palm vein images. Thirdly, data enhancement was performed on the public Polyu multispectral palm vein data set, and then a large number of experiments were carried out, and the best recognition rate was 99.57%.

关键词： Image segmentation Image recognition Veins Neural networks Feature extraction Convolutional neural networks Light sources

来源：评论

学校读者我要写书评

暂无评论

FuseSeg: LiDAR point cloud segmentation fusing multi-modal data

arXiv

引用

arXiv 2019年

作者： Krispel, Georg Opitz, Michael Waltner, Georg Possegger, Horst Bischof, Horst Institute of Computer Graphics and Vision Graz University of Technology

We introduce a simple yet effective fusion method of LiDAR and RGB data to segment LiDAR point clouds. Utilizing the dense native range representation of a LiDAR sensor and the setup calibration, we establish point correspondences between the two input modalities. Subsequently, we are able to warp and fuse the features from one domain into the other. Therefore, we can jointly exploit information from both data sources within one single network. To show the merit of our method, we extend SqueezeSeg, a point cloud segmentation network, with an RGB feature branch and fuse it into the original structure. Our extension called FuseSeg leads to an improvement of up to 18% IoU on the KITTI benchmark. In addition to the improved accuracy, we also achieve real-time performance at 50 fps, five times as fast as the KITTI LiDAR data recording speed. Copyright © 2019, The Authors. All rights reserved.

关键词： Optical radar

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：