Improving the Accuracy of Intelligent Pose Estimation Systems Through Low Level Image Processing Operations

Research output: Contribution to journalConference article in JournalResearchpeer-review

  • Jannik Christian Lærkegård Pedersen
  • Mattias Foltmar Sander
  • Niklas Fruerlund Jensen
  • Jonas Lasham Lakhrissi
  • Mikkel Gede Hansen
  • Patrick Staalbo
  • Andreas Wulff-Abramsson

Abstract

The development of powerful and popular machine learning driven pose estimation systems have been on the rise during the past years. In this research we have investigated how the accuracy level can be increased by applying low level image processing techniques unto the footage before they are submitted to the pose estimation system. The techniques used were high and low contrast, histogram equalization, sharpness and canny edge detection. By applying them on datasets, containing different environments and lighting conditions the system’s accuracy was increased, ranging from 0.29% increase to 38.37% increase dependent on the context. These increases have potential to upgrade the pose estimation system to be less lighting sensitive.
Close

Details

The development of powerful and popular machine learning driven pose estimation systems have been on the rise during the past years. In this research we have investigated how the accuracy level can be increased by applying low level image processing techniques unto the footage before they are submitted to the pose estimation system. The techniques used were high and low contrast, histogram equalization, sharpness and canny edge detection. By applying them on datasets, containing different environments and lighting conditions the system’s accuracy was increased, ranging from 0.29% increase to 38.37% increase dependent on the context. These increases have potential to upgrade the pose estimation system to be less lighting sensitive.
Original languageDanish
Journalforeløbig ukendt
Pages (from-to)1
Number of pages4
Publication statusAccepted/In press - 17 Jan 2019
Publication categoryResearch
Peer-reviewedYes
EventDigital Image and Signal Processing - St. Hugh's College, Oxford University, Oxford, United Kingdom
Duration: 29 Apr 201930 Apr 2019
https://www.disp-conference.org/

Conference

ConferenceDigital Image and Signal Processing
LocationSt. Hugh's College, Oxford University
CountryUnited Kingdom
CityOxford
Period29/04/201930/04/2019
Internet address
ID: 294188919