Y. Tan, J. K. Tan, H. Kim and S. Ishikawa,” Classifying Seabed Sediments Using the Local Auto-correlation Features”, Biomedical Soft Computing and Human Sciences, Vol.19, No.1, pp.43-50, 2014.
Understanding the distribution of seafloor sediment using a side-scan sonar is very important to grasp the distribution of seabed resources. This task is traditionally carried out by a skilled human operator. However, with the appearance of Autonomous Underwater Vehicles, automated pro-cessing is now needed to tackle the large amount of data produced and to enable on the fly adap-tation of the missions and near real time update of the operator. We propose in this paper a meth-od that applies a higher-order local auto-correlation feature and a subspace method to the acous-tic image provided by the side-scan sonar to classify seabed sediment automatically. In texture classification, the proposed method outperformed other methods such as a gray level co-occurrence matrix and a Local Binary Pattern operator. Experimental results show that the proposed method produces consistent maps of a seafloor.