A comparison of MAE Based Image Search for Hexagonally and Regularly Structured Pixel Data

DOI

10.2991/icecee-15.2015.238How to use a DOI?

Keywords

A comparison of MAE Based Image Search for Hexagonally and Regularly Structured Pixel Data

Abstract

Motion tracking is an important application in video processing. By tracking motion, we can detect the presence of moving object, track and analyze the motion of object and even make prediction of the next step of a selected object. Motion tracking can be applied to facial recognition, intelligent transportation system, medical imaging and so on. Mean average error is a main step in motion tracking which set a reference block in the former frame and compare it with every block having the same size within a selected searching area in the next frame. In addition, hexagonal pixel based images have been recently investigated for image capture and processing due to their ability to represent curved structures that are common in real images better than traditional rectangular pixel based images. Therefore, we present an approach to mean average error on hexagonal images and demonstrate that accuracy is comparable rectangular pixel based images.

Copyright

© 2015, 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  - Sijing Liu
PY  - 2015/06
DA  - 2015/06
TI  - A comparison of MAE Based Image Search for Hexagonally and Regularly Structured Pixel Data
BT  - Proceedings of the 2015 International Conference on Electrical, Computer Engineering and Electronics
PB  - Atlantis Press
SP  - 1283
EP  - 1286
SN  - 2352-538X
UR  - https://doi.org/10.2991/icecee-15.2015.238
DO  - 10.2991/icecee-15.2015.238
ID  - Liu2015/06
ER  -