Translator Disclaimer
6 September 2017 Object detection from images obtained through underwater turbulence medium
Author Affiliations +
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
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
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); doi: 10.1117/12.2277180;


Back to Top