Research on edge detection method of infrared image based-on dynamic programming theory

Xiaoke Yan*, Caicheng Shi, Baojun Zhao, H. E. Peikun

*Corresponding author for this work

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

Abstract

In this paper, a dynamic programming (DP) method, concerning the edge detection of infrared (IR) target from a given field background, is proposed. It involves locally adaptive threshold technique and fractal theory. Firstly, optimal control function based on different fractal dimensions and gray level features on infrared image is created. The second step is to seek latent object point by locally adaptive threshold technique and to calculate the minimum cumulative cost matrix. Finally optimal and connected contours are determined by DP. Experiments with real targets show that the method can detect target effectively and reduce false alarm probability.

Original languageEnglish
Title of host publication2004 7th International Conference on Signal Processing Proceedings, ICSP
Pages1016-1019
Number of pages4
Publication statusPublished - 2004
Event2004 7th International Conference on Signal Processing Proceedings, ICSP - Beijing, China
Duration: 31 Aug 20044 Sept 2004

Publication series

Name2004 7th International Conference on Signal Processing Proceedings, ICSP

Conference

Conference2004 7th International Conference on Signal Processing Proceedings, ICSP
Country/TerritoryChina
CityBeijing
Period31/08/044/09/04

Keywords

  • Cost matrix
  • Dynamic programming (DP)
  • Edged detection
  • Fractal dimensions
  • Infrared (IR) image

Fingerprint

Dive into the research topics of 'Research on edge detection method of infrared image based-on dynamic programming theory'. Together they form a unique fingerprint.

Cite this