Restoration of Noisy Underwater Acoustic Images Using Markov Random Fields

Vittorio Murino, Enrico Frumento, Flavio Gabino

Abstract

This paper describes a method for the restoration of noisy underwater 3D acoustic images. A beamforming technique is used to build a 3D map associated with corresponding map representing the confidence (i.e., reliability) of measures. Backscattered echoes coming from a scene previously insonified are received by a two-dimensional array antenna and an image is formed, where each pixel represents the distance from the sensor in a specified direction. In the proposed algorithm, depth and confidence images are modelled as Markov Random Fields whose associated probability distributions are specified by a single energy functional, that embeds a-priori knowledge on the images and on the noise affecting measurements. Confidence measures are also considered to improve the restoration. Simulated Annealing is used to find the optimal MAP estimate of both images. Experimental results show the improvements in the resulting images as compared with initial data.
BibTeX
@inproceedings{murino1995restoration,
  author = {Vittorio Murino and Enrico Frumento and Flavio Gabino},
  title = {{Restoration of Noisy Underwater Acoustic Images Using Markov Random Fields}},
  booktitle = {ICIAP},
  year = {1995},
  doi = {10.1007/3-540-60298-4\_281},
}

Loading related content...

Figure