Improving Chamfer template matching using image segmentation

Duc Thanh Nguyen, Ngoc-Son Vu, Thanh-Toan Do, Thin Nguyen, John Yearwood

Research output: Contribution to journalArticleResearchpeer-review

1 Citation (Scopus)

Abstract

This letter proposes an effective method to improve object location in Chamfer template matching (CTM) based object detection using image segmentation. In our method, object bounding boxes are iteratively adjusted to fit with the object images obtained from image segmentation in a probabilistic model. The proposed method was tested with state-of-the-art CTM-based object detectors. Experimental results have shown the proposed method improved the location accuracy of the object detectors and reduce the false alarms rate.

Original languageEnglish
Pages (from-to)1635-1639
Number of pages5
JournalIEEE Signal Processing Letters
Volume25
Issue number11
DOIs
Publication statusPublished - Nov 2018
Externally publishedYes

Keywords

  • Chamfer template matching (CTM)
  • image segmentation
  • object detection

Cite this