Memory Efficient 3D Integral Volumes

Martin Urschler, Alexander Bornik, Michael Donoser

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Integral image data structures are very useful in computer vision applications that involve machine learning approaches based on ensembles of weak learners. The weak learners often are simply several regional sums of intensities subtracted from each other. In this work we present a memory efficient integral volume data structure, that allows reduction of required RAM storage size in such a supervised learning framework using 3D training data. We evaluate our proposed data structure in terms of the tradeoff between computational effort and storage, and show an application for 3D object detection of liver CT data.
Original languageEnglish
Title of host publicationIEEE International Conference on Computer Vision Workshops (ICCVW)
Subtitle of host publicationBig Data in 3D Computer Vision
PublisherInstitute of Electrical and Electronics Engineers
Pages722-729
DOIs
Publication statusPublished - 2013

Fields of Expertise

  • Information, Communication & Computing

Fingerprint Dive into the research topics of 'Memory Efficient 3D Integral Volumes'. Together they form a unique fingerprint.

  • Projects

    Cite this

    Urschler, M., Bornik, A., & Donoser, M. (2013). Memory Efficient 3D Integral Volumes. In IEEE International Conference on Computer Vision Workshops (ICCVW): Big Data in 3D Computer Vision (pp. 722-729). Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ICCVW.2013.99