METHOD OF SOLVING THE PROBLEM OF PEOPLE RECOGNITION AT REAL TIME IN CONDITIONS OF OCCLUDED VISIBILITY

Authors

  • Oliynyk Volodymyr National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute", Ukraine
  • Pylypenko Pavlo National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute", Ukraine
  • Pantelieiev Oleksandr National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute", Ukraine

Abstract

This paper proposes a method of solving the problem of recognizing people in real time in conditions of occluded visibility. A combination of human and facial detectors used for detecting. For facial modeling, the LBP method and the SVM classifier recognition are used. MCNF tracker is used to confirm the recognition.

Key words: face recognition, human detector, confirmation through tracking.

Fig.: 2. Bibl.: 3.

Published

2023-11-08

Issue

2018

Section

Machine learning, Big Data