Recognition of thermal infrared oil tank targets based on blotch detection and clustering and SVM classification

Lan Ma; Xiaoyong Chen; Juncai Peng

doi:10.1117/12.2520936

12 March 2019 Recognition of thermal infrared oil tank targets based on blotch detection and clustering and SVM classification

Lan Ma, Xiaoyong Chen, Juncai Peng

Author Affiliations +

Proceedings Volume 11023, Fifth Symposium on Novel Optoelectronic Detection Technology and Application; 110230Y (2019) https://doi.org/10.1117/12.2520936
Event: Fifth Symposium on Novel Optoelectronic Detection Technology and Application, 2018, Xi'an, China

Abstract

This paper proposes a method for detecting oil tank targets that combines improved blotch feature detection and SVM sample learning in order to address deficiencies in the recognition of oil tank targets in thermal infrared remote sensing images due to indistinct edge information, high noise level, and small dimensions. First of all, initial detection was conducted on the basis of blotch features and mass features. Then the features of oil tank targets and an optimal combination of classification features were generated from sample learning. Finally oil tank targets were detected through classification based on SVM sample learning. The results of the experiment show that: 1) by setting appropriate parameters, this method combines blotch features and textural features for the extraction of a more comprehensive range of TIR oil tank features that can achieve the effective detection of oil tank targets; 2) based on the detection of blotch targets, this method can filter out false targets with relatively high accuracy and is capable of more stable and efficient recognition of Type #1 and Type #2 targets.

Citation Download Citation

Lan Ma, Xiaoyong Chen, and Juncai Peng "Recognition of thermal infrared oil tank targets based on blotch detection and clustering and SVM classification", Proc. SPIE 11023, Fifth Symposium on Novel Optoelectronic Detection Technology and Application, 110230Y (12 March 2019); https://doi.org/10.1117/12.2520936

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available