Infrared Image Segmentation Algorithm Using Histogram-Based Self-adaptive K-means Clustering

DOI

10.2991/iccsae-15.2016.127How to use a DOI?

Keywords

K-means; Histogram; Infrared Image Segmentation; Human Detection

Abstract

For the problem that the different parameters of infrared imaging equipment and the environment around the target cause the poor robustness of threshold value automatic acquisition method in infrared human target segmentation algorithm, starting from the principle of infrared imagery and connecting with the characteristics of the histogram and K-means clustering algorithm, we propose an infrared image segmentation algorithm using histogram-based self-adaptive K-means clustering. We use histogram peaks to determine the K’ value of K-means clustering and select the grey values corresponding to this K peaks as the K initial cluster center values of clustering algorithm. After clustering, we select appropriate trough as a segmentation point through the cluster center’s moving direction. This algorithm does not require to balance the image beforehand and to suppose background distribution. The experimental results show that the algorithm is simple and flexible, easy to implement, and has good robustness.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Zhiqiang Zhao
AU  - Xin Ling
AU  - Jian Wu
AU  - Xiaoyong Rui
PY  - 2016/02
DA  - 2016/02
TI  - Infrared Image Segmentation Algorithm Using Histogram-Based Self-adaptive K-means Clustering
BT  - Proceedings of the 2015 5th International Conference on Computer Sciences and Automation Engineering
PB  - Atlantis Press
SP  - 682
EP  - 688
SN  - 2352-538X
UR  - https://doi.org/10.2991/iccsae-15.2016.127
DO  - 10.2991/iccsae-15.2016.127
ID  - Zhao2016/02
ER  -