Automated Stone Detection on Side-Scan Sonar Mosaics Using Haar-Like Features

Abstract

Stony grounds form important habitats in the marine environment, especially for sessile benthic organisms. For the purpose of habitat demarcation and monitoring, knowledge of the position and abundance of individual stones is necessary. This is especially the case in areas with a scattered occurrence of stones in an environment which is otherwise characterized by relatively mobile sandy sediments. Exposed stones can be detected using side-scan sonar (SSS) data. However, apart from laborious manual identification, there is as yet no automated or semi-automated method available for a fast and spatially resolved detection of stones. In this study, a Haar-like feature detector was trained to identify individual stones on an SSS mosaic (~12 km2) showing heterogeneous sediment distribution. The results of this method were compared with those of manually derived stones. Our study shows that the Haar-like feature detector was able to detect up to 62% of the overall occurrence of stones within the study area. Even though the sheer number of correctly identified stones was influenced by, e.g., the type of sediments and the number of grey values of the mosaic, Haar-like feature detectors provide a relatively easy and fast method to identify stones on SSS mosaics when compared to the manual investigation.