Browsing by Author "Sreevalsan-Nair, Jaya"

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    IMGD: Image-based Multiscale Global Descriptors of Airborne LiDAR Point Clouds Used for Comparative Analysis
    (The Eurographics Association, 2021) Sreevalsan-Nair, Jaya; Mohapatra, Pragyan; Singh, Satendra; Frosini, Patrizio and Giorgi, Daniela and Melzi, Simone and RodolĂ , Emanuele
    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.
  • No Thumbnail Available
    Item
    SunburstChartAnalyzer: Hierarchical Data Retrieval from Images of Sunburst Charts for Tree Visualization
    (The Eurographics Association, 2023) Rastogi, Prakhar; Singh, Karanveer; Sreevalsan-Nair, Jaya; Vangorp, Peter; Hunter, David
    Data extraction from visualization is a challenging problem in computer vision owing to the huge ''design space of possible vis idioms.'' Different visualizations pose different challenges in automated data extraction from their images, which is needed in document analysis. In the case of sunburst charts for hierarchical data, the extracted data has to be also correctly organized as a tree data structure. Overall, data extraction has to consider different components of a chart image, such as text, annular sectors, levels, etc., and their ordering. We propose an end-to-end algorithm, SunburstChartAnalyzer, for data extraction from sunburst charts. The algorithm includes chart classification, component extraction, and hierarchical data organization. We further propose a composite metric to evaluate the correctness of SunburstChartAnalyzer. Our experimental results show that our proposed method works for trees of all sizes, and particularly well for shallow and medium-depth trees.