This work demonstrates that automated mine countermeasure (MCM) tasks are greatly facilitated by characterizing the seafloor environment in which the sensors operate as a first step within a comprehensive strategy for how to exploit information from available sensors, multiple detector types, measured features, and target classifiers, depending on the specific seabed characteristics present within the high-frequency synthetic aperture sonar (SAS) imagery used to perform MCM tasks. This approach is able to adapt as environmental characteristics change and includes the ability to recognize novel seabed types. Classifiers are then adaptively retrained through active learning in these unfamiliar seabed types, resulting in improved mitigation of challenging environmental clutter as it is encountered. Further, a segmentation constrained network algorithm is introduced to enable enhanced generalization abilities for recognizing mine-like objects from underrepresented environments within the training data. Additionally, a fusion approach is presented that allows the combination of multiple detectors, feature types spanning both measured expert features and deep learning, and an ensemble of classifiers for the particular seabed mixture proportions measured around each detected target. The environmentally adaptive approach is demonstrated to provide the best overall performance for automated mine-like object recognition.
The complexity of the natural underwater environment creates a challenging arena in which to find underwater mines. In this work, we demonstrate that automated mine-like object detection tasks are greatly facilitated by a comprehensive fusion process. Our approach begins with characterization of the seafloor based on textures within synthetic aperture sonar (SAS) imagery and uses this to exploit information from the available sensors, multiple detector types, measured features, and target classifiers, to facilitate mine-like object recognition. Our approach is able to adapt as environmental characteristics change, including the ability to recognize novel seabed types. We then adaptively retrain classifiers through active learning in these novel seabed types resulting in improved mitigation of challenging environmental clutter as it is encountered, and develop a segmentation constrained network (SCN) algorithm which enables increased generalization abilities for recognizing mine-like objects in both under-represented and novel, unseen environments in available training data. Additionally, we present a fusion approach that allows us to combine multiple detectors, feature types spanning both measured expert features and deep learning, and an ensemble of classifiers, for the particular seabed mixture proportions measured around each detected target. [Work supported by the Office of Naval Research.]
Seabed characterization has utility for numerous applications that seek to explore and interact with the seafloor, ranging from costal habitat monitoring and sub-bottom profiling to man-made object detection. In the work presented here, we characterize the seabed based on the texture patterns within SAS images constructed from high-frequency side-scan sonar. Features are measured from the SAS images (e.g., lacunarity, an established texture feature coding method, and a rotationally invariant histogram of oriented gradients). Based on these SAS image features, we perform unsupervised clustering with a hierarchical Bayesian model, which creates categories of seabed textures. Our clustering model is a new variant of the hierarchical Dirichlet process that is both adaptive to changes in the seabed and processes batches of SAS imagery in an online fashion. This allows the model to learn new seabed types as they are encountered and provides usable clustering results after each batch is processed, rather than having to wait for all the data to be collected before being processed. The model’s performance of seabed characterization by SAS image texture is demonstrated in the overall range and internal consistency of textures specific to each learned cluster. [Work supported by the Office of Naval Research.]
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.