Visual servoing can greatly improve underwater robot manipulation accuracy and
automation. Its main purpose is to control the end-effector pose of underwater vehicle …

Hyperspectral image (HSI) provides rich spectral–spatial information and the light detection
and ranging (LiDAR) data reflect the elevation information, which can be jointly exploited for …

With recent advances in sensing, multimodal data is becoming easily available for various
applications, especially in remote sensing (RS), where many data types like multispectral …

Hyperspectral images (HSIs) contain rich spatial and spectral detail information, while light
detection and ranging (LiDAR) data can provide the elevation information. Thus, the fusion …

Although modern machine learning has the potential to greatly speed up the interpretation of
imagery, the varied nature of the seabed and limited availability of expert annotations form …

Coral reefs are of undeniable importance to the environment, yet little is known of them on a
global scale. Assessments rely on laborious, local in-water surveys. In recent years remote …

We describe a novel semi-supervised learning method that reduces the labelling effort
needed to train convolutional neural networks (CNNs) when processing georeferenced …

Human-robot interaction benefits greatly from multimodal sensor inputs as they enable
increased robustness and generalization accuracy. Despite this observation, few HRI …

Autonomous Underwater Vehicles (AUVs) are increasingly being used to support scientific
research and monitoring studies. One such application is in benthic habitat mapping where …

Reliable obstacle detection and classification in rough and unstructured terrain such as
agricultural fields or orchards remains a challenging problem. These environments involve …