Mel-spectrogram and deep CNN based representation learning from bio-sonar implementation on UAVs
In this paper, we present an approach for estimating the leaf density of trees while
navigating in a forest. To this end, we consider an Unmanned Aerial Vehicle (UAV) …
navigating in a forest. To this end, we consider an Unmanned Aerial Vehicle (UAV) …
Detecting submerged objects using active acoustics and deep neural networks: A test case for pelagic fish
A Testolin, D Kipnis, R Diamant - IEEE Transactions on Mobile …, 2020 - ieeexplore.ieee.org
The accurate detection and quantification of submerged targets has been recognized as a
key challenge in marine exploration, one that traditional census approaches cannot handle …
key challenge in marine exploration, one that traditional census approaches cannot handle …
Enhancing generalization of active sonar classification using semisupervised anomaly detection with multisphere for normal data
G Kim, Y Choo - IEEE Journal of Oceanic Engineering, 2024 - ieeexplore.ieee.org
Anomaly detection is suitable for active sonar classification due to its ability to handle the
challenges posed by small imbalanced data sets. Recently, a modified anomaly detection …
challenges posed by small imbalanced data sets. Recently, a modified anomaly detection …
Bi-sphere anomaly detection with learnable centroid for active sonar classification
G Kim, Y Choo - IEEE Access, 2022 - ieeexplore.ieee.org
Machine learning (ML)-based approaches are desirable for discriminating targets from
clutter signals to enhance the performance of active sonar systems. However, a small …
clutter signals to enhance the performance of active sonar systems. However, a small …
Underwater tracking based on the sum-product algorithm enhanced by a neural network detections classifier
The necessity of long-range underwater surveillance has strongly increased in the last
decades, and low-frequency active sonar (LFAS) systems seem to fulfill this need. However …
decades, and low-frequency active sonar (LFAS) systems seem to fulfill this need. However …
Automatic object classification with active sonar using unsupervised anomaly detection
P Stinco, G De Magistris, A Tesei… - 2020 28th European …, 2021 - ieeexplore.ieee.org
This work describes an unsupervised anomaly detection method for automatic contacts
classification of an active sonar system. The proposed method refers to littoral, shallow water …
classification of an active sonar system. The proposed method refers to littoral, shallow water …
Robust model-dependent Poisson multi Bernoulli mixture trackers for multistatic sonar networks
E Özer, AK Hocaoğlu - Ieee Access, 2021 - ieeexplore.ieee.org
This work proposes a robust tracker based on the Poisson Multi Bernoulli Mixture (PMBM)
filter for multistatic sonar networks (MSNs) systems. The PMBM based trackers estimate the …
filter for multistatic sonar networks (MSNs) systems. The PMBM based trackers estimate the …
Unsupervised active sonar contact classification through anomaly detection
Target detection and sonar contact classification with active sonar systems are not trivial
especially when operating in coastal and shallow water environments with multipath …
especially when operating in coastal and shallow water environments with multipath …
Passive and active graded-index acoustic metamaterials: Spatial and frequency domain multiplexing
A Yazdkhasti - 2022 - search.proquest.com
Acoustic metamaterials, similar to their electromagnetic counterparts, are artificial
subwavelength materials designed to manipulate sound waves. By tailoring the material's …
subwavelength materials designed to manipulate sound waves. By tailoring the material's …
Selective information transmission using convolutional neural networks for cooperative underwater surveillance
Cooperation among multiple autonomous surface and underwater vehicles is an important
capability for detection and tracking of underwater objects. Cooperative autonomy in the …
capability for detection and tracking of underwater objects. Cooperative autonomy in the …