Object detection from images obtained through underwater turbulence medium

Md. Hasan Furhad; Murat Tahtali; Andrew Lambert

doi:10.1117/12.2277180

6 September 2017 Object detection from images obtained through underwater turbulence medium

Md. Hasan Furhad, Murat Tahtali, Andrew Lambert

Proceedings Volume 10410, Unconventional and Indirect Imaging, Image Reconstruction, and Wavefront Sensing 2017; 104100S (2017) https://doi.org/10.1117/12.2277180
Event: SPIE Optical Engineering + Applications, 2017, San Diego, California, United States

Abstract

Imaging through underwater experiences severe distortions due to random fluctuations of temperature and salinity in water, which produces underwater turbulence through diffraction limited blur. Lights reflecting from objects perturb and attenuate contrast, making the recognition of objects of interest difficult. Thus, the information available for detecting underwater objects of interest becomes a challenging task as they have inherent confusion among the background, foreground and other image properties. In this paper, a saliency-based approach is proposed to detect the objects acquired through an underwater turbulent medium. This approach has drawn attention among a wide range of computer vision applications, such as image retrieval, artificial intelligence, neuro-imaging and object detection. The image is first processed through a deblurring filter. Next, a saliency technique is used on the image for object detection. In this step, a saliency map that highlights the target regions is generated and then a graph-based model is proposed to extract these target regions for object detection.

Conference Presentation

Citation Download Citation

Md. Hasan Furhad, Murat Tahtali, and Andrew Lambert "Object detection from images obtained through underwater turbulence medium", Proc. SPIE 10410, Unconventional and Indirect Imaging, Image Reconstruction, and Wavefront Sensing 2017, 104100S (6 September 2017); https://doi.org/10.1117/12.2277180

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