CUDA based Level Set Method for 3D Reconstruction of Fishes from Large Acoustic Data

Ojaswa Sharma, François Anton

    Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

    346 Downloads (Pure)

    Abstract

    Acoustic images present views of underwater dynamics, even in high depths. With multi-beam echo sounders (SONARs), it is possible to capture series of 2D high resolution acoustic images. 3D reconstruction of the water column and subsequent estimation of fish abundance and fish species identification is highly desirable for planning sustainable fisheries. Main hurdles in analysing acoustic images are the presence of speckle noise and the vast amount of acoustic data. This paper presents a level set formulation for simultaneous fish reconstruction and noise suppression from raw acoustic images. Despite the presence of speckle noise blobs, actual fish intensity values can be distinguished by extremely high values, varying exponentially from the background. Edge detection generally gives excessive false edges that are not reliable. Our approach to reconstruction is based on level set evolution using Mumford-Shah segmentation functional that does not depend on edges in an image. We use the implicit function in conjunction with the image to robustly estimate a threshold for suppressing noise in the image by solving a second differential equation. We provide details of our estimation of suppressing threshold and show its convergence as the evolution proceeds. We also present a GPU based streaming computation of the method using NVIDIA's CUDA framework to handle large volume data-sets. Our implementation is optimised for memory usage to handle large volumes.
    Original languageEnglish
    Title of host publicationInternational Conference in Central Europe on Computer Graphics, Visualization and Computer Vision
    Volume17
    Publication date2009
    ISBN (Print)978-80-86943-93-0
    Publication statusPublished - 2009
    Event17th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision - Plzen, Czech Republic
    Duration: 2 Feb 20095 Feb 2009
    Conference number: 17
    http://wscg.zcu.cz/wscg2009/wscg2009.htm

    Conference

    Conference17th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision
    Number17
    CountryCzech Republic
    CityPlzen
    Period02/02/200905/02/2009
    Internet address

    Keywords

    • Acoustic images
    • Noise suppression
    • Level Set method
    • CUDA
    • GPU
    • 3D reconstruction

    Fingerprint Dive into the research topics of 'CUDA based Level Set Method for 3D Reconstruction of Fishes from Large Acoustic Data'. Together they form a unique fingerprint.

    Cite this