Research on target recognition based on edge features

Author

Yue Wang ; Qian Wang ; Derong Chen

Author_Institution

Sch. of Mechatronical Eng., Beijing Inst. of Technol., Beijing, China

fYear

2012

fDate

16-18 Oct. 2012

Firstpage

1312

Lastpage

1315

Abstract

A method of target recognition based on edge features of the images acquired before and after the damage is proposed to improve the accuracy of registration and recognition in Battlefield Damage Assessment. The image registration combined circle area method and angular point extraction is conducted after the preprocessing. The vector groups of edge features can be obtained from the extraction of color and textural features of the targets. By comparing the vector groups of the images, the object in the post-damage image can be recognized whether it is the target or not. The verification results indicate that the targets in minor damage can be recognized accurately and quickly.

Keywords

edge detection; feature extraction; image colour analysis; image registration; image texture; military computing; object recognition; angular point extraction; battlefield damage assessment; circle area method; color feature extraction; image edge features; image registration; object recognition; post-damage image; recognition accuracy improvement; registration accuracy improvement; target recognition method; textural feature extraction; vector groups; Feature extraction; Image edge detection; Image registration; Shape; Target recognition; Vehicles; edge feature; feature extraction; target recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Image and Signal Processing (CISP), 2012 5th International Congress on

Conference_Location

Chongqing

Print_ISBN

978-1-4673-0965-3

Type

conf

DOI

10.1109/CISP.2012.6469938

Filename

6469938