检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Arora, Vidhu Gupta, Shreyan Kudupu, Ananthakrishna Priyadarshi, Aditya Mundayatt, Aswathi Sreevalsan-Nair, Jaya Graphics-Visualization-Computing Lab International Institute of Information Technology Karnataka Bangalore560100 India

In this article, we improve the deep learning solution for coastline extraction from Synthetic Aperture Radar (SAR) images by proposing a two-stage model involving image classification followed by segmentation. We hypothesize that a single segmentation model usually used for coastline detection is insufficient to characterize different coastline types. We demonstrate that the need for a two-stage workflow prevails through different compression levels of these images. Our results from experiments using a combination of CNN and U-Net models on Sentinel-1 images show that the two-stage workflow, coastline classification-extraction from SAR images (CCESAR) outperforms a single U-Net segmentation model. © 2025, CC BY-SA.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

EVOLUTION OF DATA-DRIVEN SINGLE- AND MULTI-HAZARD SUSCEPTIBILITY MAPPING AND EMERGENCE OF DEEP LEARNING METHODS

arXiv

引用

arXiv 2025年

作者： Sreevalsan-Nair, Jaya Mundayatt, Aswathi Graphics-Visualization-Computing Lab International Institute of Information Technology Karnataka Bangalore560100 India

Data-driven susceptibility mapping of natural hazards has harnessed the advances in classification methods used on heterogeneous sources represented as raster images. Susceptibility mapping is an important step towards risk assessment for any natural hazard. Increasingly, multiple hazards co-occur spatially, temporally, or both, which calls for an in-depth study on multi-hazard susceptibility mapping. In recent years, single-hazard susceptibility mapping algorithms have become well-established and have been extended to multi-hazard susceptibility mapping. Deep learning is also emerging as a promising method for single-hazard susceptibility mapping. Here, we discuss the evolution of methods for a single hazard, their extensions to multi-hazard maps as a late fusion of decisions, and the use of deep learning methods in susceptibility mapping. We finally propose a vision for adapting data fusion strategies in multimodal deep learning to multi-hazard susceptibility mapping. From the background study of susceptibility methods, we demonstrate that deep learning models are promising, untapped methods for multi-hazard susceptibility mapping. Data fusion strategies provide a larger space of deep learning models applicable to multi-hazard susceptibility mapping. © 2025, CC BY.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

To the Point: From Dynamic Heatmap Video to Gaze Points 25

To the Point: From Dynamic Heatmap Video to Gaze Points

引用

Proceedings of the 2025 Symposium on Eye Tracking Research and Applications

作者： Beryl Gnanaraj Swetha Manivasagam Jaya Sreevalsan-Nair Graphics-Visualization-Computing Lab International Institute of Information Technology Bangalore Bangalore Karnataka India Department of Computer Science and Engineering PSG College of Technology Coimbatore Tamil Nadu India

来源：评论

学校读者我要写书评

暂无评论

IMGD: Image-based Multiscale Global Descriptors of Airborne LiDAR Point Clouds Used for Comparative Analysis 8

IMGD: Image-based Multiscale Global Descriptors of Airborne ...

引用

8th Smart Tools and Applications in graphics Conference, STAG 2021

作者： Sreevalsan-Nair, J. Mohapatra, P. Singh, S. Graphics-Visualization-Computing Lab International Institute of Information Technology Bangalore India

ISBN: (纸本)9783038681656

Both geometric and semantic information are required for a complete understanding of regions acquired as three-dimensional (3D) point clouds using the Light Detection and Ranging (LiDAR) technology. However, the global descriptors of such datasets that integrate both the information types are rare. With a focus on airborne LiDAR point clouds, we propose a novel global descriptor that transforms the point cloud from Cartesian to barycentric coordinate spaces. We use both the probabilistic geometric classification, aggregated from multiple scales, and the semantic classification to construct our descriptor using point rendering. Thus, we get an image-based multiscale global descriptor, IMGD. To demonstrate its usability, we propose the use of distribution distance measures between the descriptors for comparing the point clouds. Our experimental results demonstrate the effectiveness of our descriptor, when constructed of publicly available datasets, and on applying our selected distance measures. © 2021 The Author(s)

关键词： Uncertainty analysis

来源：评论

学校读者我要写书评

暂无评论

Tensor Fields for Data Extraction from Chart Images: Bar Charts and Scatter Plots 8th

Tensor Fields for Data Extraction from Chart Images: Bar Cha...

引用

8th Workshop on Topological Methods in Data Analysis and visualization, TopoInVis 2019

作者： Sreevalsan-Nair, Jaya Dadhich, Komal Daggubati, Siri Chandana Graphics-Visualization-Computing Lab International Institute of Information Technology Bangalore Karnataka India

ISBN: (纸本)9783030834999

Charts are an essential part of both graphicacy (graphical literacy), and statistical literacy. As chart understanding has become increasingly relevant in data science, automating chart analysis by processing raster images of the charts has become a significant problem. Automated chart reading involves data extraction and contextual understanding of the data from chart images. In this paper, we perform the first step of determining the computational model of chart images for data extraction for selected chart types, namely, bar charts, and scatter plots. We demonstrate the use of positive semidefinite second-order tensor fields as an effective model. We identify an appropriate tensor field as the model and propose a methodology for the use of its degenerate point extraction for data extraction from chart images. Our results show that tensor voting is effective for data extraction from bar charts and scatter plots, and histograms, as a special case of bar charts. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Design as traversal and consequences: An exploration tool for experimental designs 07

Design as traversal and consequences: An exploration tool fo...

引用

graphics Interface 2007

作者： Jennings, Christopher G. Kirkpatrick, Arthur E. Graphics Visualization and Usability Lab. Department of Computing Science Simon Fraser University Canada

ISBN: (纸本)1568813376

We present a design space explorer for the space of experimental designs. For many design problems, design decisions are determined by the consequences of the design rather than its elemental parts. To support this need, the explorer is constructed to make the designer aware of design-level options, provide a structured context for design, and provide feedback on the consequences of design decisions. We argue that this approach encourages the designer to consider a wider variety of designs, which will lead to more effective designs overall. In a qualitative study, experiment designers using the explorer were found to consider a wider variety of designs and more designs overall than they reported considering in their normal practice.

关键词： Computer graphics

来源：评论

学校读者我要写书评

暂无评论

Evaluating and Improving RoSELS for Road Surface Extraction from 3D Automotive LiDAR Point Cloud Sequences 1

引用

3rd International Conference on Deep Learning Theory and Applications, DeLTA 2022

作者： Katkoria, Dhvani Sreevalsan-Nair, Jaya Graphics-Visualization-Computing Lab IIIT Bangalore 26/C Electronics City Karnataka 560100 India

ISBN: (数字)9783031373176

ISBN: (纸本)9783031373169

Navigable space determination is a difficult problem encountered in robotics and intelligent vehicle technology and it requires integrated solutions using advances in computer vision and computational geometry. The conventional data processing workflow uses semantic segmentation to identify road points from three-dimensional (3D) automotive LiDAR point clouds, which have to be extended to determine its boundary points. The boundary points are critical in getting an initial coarse extraction of its surface. Hence, to filter the curb or edge points from the road points, the semantic segmentation results are post-processed. The road surface is determined by the entire trajectory information, which is captured as a sequence of LiDAR point clouds. For the entire road surface extraction, we use an automated system, RoSELS (Road Surface Extraction for LiDAR point cloud Sequence) that works at different scales, i.e., at the scale of a point, a point cloud, and the sequence of point clouds. In this paper, we evaluate the algorithms used in RoSELS, namely, the Gaussian Mixture Model for curb detection and ResNet-50 for transfer learning in frame classification. We evaluate the quality of the mesh extracted using RoSELS, which is intended for straight-road geometry. Here, we also show how the initial extracted surface can be further post-processed to extend RoSELS for curved roads. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

BarChartAnalyzer: Data Extraction and Summarization of Bar Charts from Images

引用

SN Computer Science 2022年第6期3卷 500页

作者： Daggubati, Siri Chandana Sreevalsan-Nair, Jaya Dadhich, Komal Graphics-Visualization-Computing Lab IIIT Bangalore 26/C Electronics City Hosur Road Karnataka Bangalore 560100 India

Charts or scientific plots are widely used visualizations for efficient knowledge dissemination from datasets. However, these charts are predominantly available in image format. There are various scenarios where these images are interpreted in the absence of their source data table. This leads to a pertinent need for data extraction from an available chart image. We narrow down our scope to bar charts and its subtypes. We propose a semi-automated workflow, BarChartAnalyzer, for data extraction from chart images. Our workflow integrates the following tasks in sequence: chart type classification, image annotation, object detection, text detection and recognition, data table extraction, chart summarization, and, optionally, chart redesign. Our data extraction uses second-order tensor fields from tensor voting used in computer vision. Here, we propose a novel application of design study methodology for the chart summarization component. Our results show that our workflow can effectively and accurately extract data from images of different resolutions and subtypes of bar charts. © 2022, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Bar charts Chart classification Chart image analysis Chart segmentation Convolutional neural Network Data extraction Design study methodology Grouped bar charts Histograms Optical character recognition Stacked bar charts Text recognition Text summarization

来源：评论

学校读者我要写书评

暂无评论

Convex hull covering of polygonal scenes for accurate collision detection in games

Convex hull covering of polygonal scenes for accurate collis...

引用

graphics Interface 2008

作者： Liu, Rong Zhang, Hao Busby, James Graphics Usability and Visualization Lab School of Computing Science Simon Fraser University Canada Radical Entertainment Canada

ISBN: (纸本)9781568814230

Decomposing a complex object into simpler pieces, e.g., convex patches or convex polyhedra, is a well-studied geometry problem. A well constructed decomposition can greatly accelerate collision detection since intersections with and between convex objects are fast to compute. In this paper, we look at a particular instance of the convex decomposition problem which arises from real-world game development. Given a collection of polyheclral surfaces (possibly with boundaries, holes, and complex interior structures) that model the scene geometry in a game environment, we wish to find a small set of convex hulls such that colliding objects in the scene against such a set of convex hulls produces the same game behavior as colliding against the original surfaces. The vague formulation of the problem is due to the difficulty of defining the space accessible by the objects involved in the game play. Under reasonable assumptions, we arrive at a set of conditions for valid convex decomposition and develop a construction algorithm via greedy merging driven by patch compactness. We show that our validity conditions ensure valid collision-related game behavior. The effectiveness of our decomposition algorithm is demonstrated through real examples from game development. To the best of our knowledge, no previous convex hull decomposition or surface decomposition algorithms were designed to handle the type of models we consider or be able to compute a set of convex hulls that ensure accurate collision detection results.

关键词： Software design

来源：评论

学校读者我要写书评

暂无评论

Remote interactive visualization of parallel implementation of structural feature extraction of three-dimensional lidar point cloud 3

Remote interactive visualization of parallel implementation ...

引用

3rd International Conference on Big Data Analytics, BDA 2014

作者： Kumari, Beena Ashe, Avijit Sreevalsan-Nair, Jaya Graphics-Visualization-Computing-Lab International Institute of Information Technology Bangalore 26/C Electronics City Bangalore560100 India

ISBN: (纸本)9783319138190

Lidar (Light detection and ranging) is a popularly used technology to collect dense and precise data of topographic structures of the surface of the earth. In this paper, we have proposed a user assisted remote visualization system for extraction and visualization of structural features obtained from point cloud data obtained from lidar data. The sharp feature lines such as crest lines, edges of buildings, ravines, ridges are known as structural features of point cloud. Our work includes: (a) parallel implementation a topology-based algorithm for extraction of structural features from lidar point cloud using GPGPU (General Purpose graphics Processing Unit) computing, and (b) using a LAN (Local Area Network)-based server-client architecture to achieve remote visualization. © Springer International Publishing Switzerland 2014.

关键词： graphics processing unit

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：