Underwater dam crack detection and classification based on sonar images is a challenging task because underwater environments are complex and because cracks are quite random and diverse in nature. Furthermore, obtainable sonar images are of low resolution. To address these problems, a novel underwater dam crack detection and classification approach based on sonar imagery is proposed. First, the...

In a number of sonar studies, bathymetric information is used to correct and visualise amplitude data. This work proposes a method which combines amplitude features (describing backscattering strength and sonar texture) with bathymetric features (indicating seafloor variability) for sonar classification. Features are selected per window (of user defined size) and areas around grab samples in a ...

More difficult tasks are generally regarded as such because they demand greater attention. Echolocators provide rare insight into this relationship because biosonar signals can be monitored. Here we show that bats produce longer terminal buzzes and more sonar sound groups during their approach to prey under presumably more difficult conditions. Specifically, we found Daubenton's bats, Myotis da...

This paper describes an approach to combining range data from both a set of sonar sensors as well as from a directional laser range nder to e ciently take advantage of the characteristics of both types of devices when exploring and mapping unknown worlds. We call our approach \just in time sensing" because it uses the more accurate but constrained laser range sensor only as needed, based upon a...

Odontocetes (toothed whales) routinely produce pulsed sounds, which many studies have shown to be used for echolocation [1]. The deliberate production by dolphins of bubble nets suggested that their echolocation may function well in bubbly water that would confound man-made sonar [2,3], an observation supported by the outstanding sonar performance of such animals in shallow waters. A sonar sche...

This paper describes an approach to combining range data from both a set of sonar sensors as well as from a directional laser range finder to efficiently take advantage of the characteristics of both types of devices when exploring and mapping unknown worlds. We call our approach “just in time sensing” because it uses the more accurate but constrained laser range sensor only as needed, based up...

This paper addresses the problem of mapping the features of a gas distribution by creating concentration gridmaps from the data collected by a mobile robot equipped with an electronic nose. By contrast to metric gridmaps extracted from sonar or laser range scans, a single measurement of the electronic nose provides information about a comparatively small area. To overcome this problem, a mappin...

This paper describes a new technique for tracking locally curved unknown objects using sonar. The approach explicitly accounts for relevant robot dynamics. Objects are tracked by looking for temporal sequences of observations that fit a kinematic model. The method is illustrated using data from a synthetic aperture sonar gathered by a BPAUV at NATO SACLANT’s GOATS 2002 experiment in the Liguria...

Stationary clutter arises in a wide area of different radar or sonar applications. Without adaption to a non-uniform clutter distribution, tracking algorithms try to initialize tracks in these areas repeatedly while in most cases there is no target to be found. The intention of this paper is to discuss different ways to enable clutter mapping in order to use this as an efficient tool for target...