Real-Time Corner Detection on Mobile Platforms Using Cuda

Hector Chahuara, Paul Rodriguez

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

Corner detection is a widespread task in many high-end applications such as autonomous driving systems and augmented reality. However, corner detection algorithms are computationally expensive and thus are not suitable for real-time applications on mobile devices. The Tegra device series, which incorporates Graphics Processing Units (GPUs), is aimed at mobile computing and accelerates computations for mobile applications. In this paper, a GPU realization of a color-adapted Harris corner detector with high-level extensions is proposed and tested in Tegra-based platforms Jetson TK1, TX1 and TX2. The proposed realization achieves good detection quality, real-time processing for grayscale and color images up to full HD resolution (1080p) in all platforms and frame rates of 14.02 ∼ 18.71, 27.76 ∼ 39.44 and 34.82 ∼ 51.32 for images of resolution 4K UHD (2160p) in Jetson TK1, TX1 and TX2 respectively.

Original languageEnglish
Title of host publicationProceedings of the 2018 IEEE 25th International Conference on Electronics, Electrical Engineering and Computing, INTERCON 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538654903
DOIs
StatePublished - 6 Nov 2018
Event25th IEEE International Conference on Electronics, Electrical Engineering and Computing, INTERCON 2018 - Lima, Peru
Duration: 8 Aug 201810 Aug 2018

Publication series

NameProceedings of the 2018 IEEE 25th International Conference on Electronics, Electrical Engineering and Computing, INTERCON 2018

Conference

Conference25th IEEE International Conference on Electronics, Electrical Engineering and Computing, INTERCON 2018
Country/TerritoryPeru
CityLima
Period8/08/1810/08/18

Keywords

  • CUDA
  • Corner detection
  • mobile platforms

Fingerprint

Dive into the research topics of 'Real-Time Corner Detection on Mobile Platforms Using Cuda'. Together they form a unique fingerprint.

Cite this