River detection using LBP and morphology in infrared image

Yuhan Liu; Zhenming Peng; Suqi Huang; Zhuoran Wang; Tian Pu

doi:10.1117/12.2505921

8 February 2019 River detection using LBP and morphology in infrared image

Yuhan Liu, Zhenming Peng, Suqi Huang, Zhuoran Wang, Tian Pu

Proceedings Volume 10843, 9th International Symposium on Advanced Optical Manufacturing and Testing Technologies: Optoelectronic Materials and Devices for Sensing and Imaging; 108430L (2019) https://doi.org/10.1117/12.2505921
Event: Ninth International Symposium on Advanced Optical Manufacturing and Testing Technologies (AOMATT2018), 2018, Chengdu, China

Abstract

Detecting landscapes such as rivers, mountains or forests in the complex scenes is a challenging problem in the field of infrared image, which has been applied widely in military and civilian. This paper aims to detect the river from infrared images, presenting an approach that combines the local binary pattern (LBP) and morphology to extract the river. The LBP descriptor is highly discriminative, computationally efficient and stable for monotonous gray level images. In this paper, we propose an improved LBP descriptor, which adopts a radius of 1.5 pixels and uses every neighbor pixel of center to acquire more information. Firstly, we preprocess the data and extract the feature by the improved LBP descriptor. Then a combination of the threshold processing, filtering and morphological operator is used to emphasize the feature result. Finally, through connected component analysis, the maximum connected component is focused to detect the river in the infrared image. The performance of algorithm is tested on a set of images. Areas of the extracted river and time cost are measured as well.

Citation Download Citation

Yuhan Liu, Zhenming Peng, Suqi Huang, Zhuoran Wang, and Tian Pu "River detection using LBP and morphology in infrared image", Proc. SPIE 10843, 9th International Symposium on Advanced Optical Manufacturing and Testing Technologies: Optoelectronic Materials and Devices for Sensing and Imaging, 108430L (8 February 2019); https://doi.org/10.1117/12.2505921

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