Results 181 to 190 of about 118,357 (248)

Survey on AI‐Enabled Computer Vision Technologies and Applications for Space Robotic Missions

Journal of Field Robotics, EarlyView.
ABSTRACT This survey provides a comprehensive overview of recent advancements and challenges in Artificial Intelligence (AI)‐enabled computer vision (CV) techniques for space robotic missions, spanning critical phases such as Entry, Descent, and Landing (EDL), orbital operations, and planetary surface exploration.
Maciej Quoos, Steven Kay, Julia Wajoras, Robert Field, Evridiki V. Ntagiou, Fakher Mohammad, Yang Gao   +6 more
wiley   +1 more source

DuckNet: an open‐source deep learning tool for waterfowl species identification in UAV imagery

Remote Sensing in Ecology and Conservation, EarlyView.
Using drones with thermal‐RGB sensors and a deep learning model (RetinaNet with ResNet‐50), we surveyed non‐breeding waterfowl across restored wetlands in the Mississippi Alluvial Valley. Our model, DuckNet, achieved high accuracy and offers an open‐source, customizable tool for automated waterfowl detection to support conservation monitoring ...
Zack Loken, Kevin M. Ringelman, Anne Mini, J. Dale James, Mike Mitchell   +4 more
wiley   +1 more source

Deep learning‐based ecological analysis of camera trap images is impacted by training data quality and quantity

Remote Sensing in Ecology and Conservation, EarlyView.
Machine learning image classifiers are increasingly being used to automate camera trap image labelling, but we don't know how much ML model accuracy matters for downstream ecological analyses. Using two large data sets from an African savannah and an Asian dry forest ecosystem, we compared human labelled data with predictions from deep‐learning models ...
Peggy A. Bevan, Omiros Pantazis, Holly A.I. Pringle, Guilherme Braga Ferreira, Daniel J. Ingram, Emily K. Madsen, Liam Thomas, Dol Raj Thanet, Thakur Silwal, Santosh Rayamajhi, Gabriel J. Brostow, Oisin Mac Aodha, Kate E. Jones   +12 more
wiley   +1 more source

Big Bird: A global dataset of birds in drone imagery annotated to species level

Remote Sensing in Ecology and Conservation, EarlyView.
Drones are a valuable tool for surveying birds, but manually detecting and identifying birds in drone images is costly. We assembled a diverse dataset of 23 865 images of birds captured with 21 different drones across 11 countries. We labelled 4824 of these images, detailing the location, species, posture category, age category, and sex of 49 990 birds
Joshua P. Wilson, Tatsuya Amano, Thomas Bregnballe, Alejandro Corregidor‐Castro, Roxane Francis, Diego Gallego‐García, Jarrod C. Hodgson, Landon R. Jones, César R. Luque‐Fernández, Dominik Marchowski, John McEvoy, Ann E. McKellar, W. Chris Oosthuizen, Christian Pfeifer, Martin Renner, José Hernán Sarasola, Mateo Sokač, Roberto Valle, Adam Zbyryt, Richard A. Fuller   +19 more
wiley   +1 more source

Distributed AutoML framework for multi‐objective optimization of concrete crack segmentation models

Structural Concrete, EarlyView.
Abstract Monitoring cracks in concrete surfaces is essential for structural safety. While machine vision techniques have received significant interest in this domain, selecting optimal models and tuning hyperparameters remain challenging. This paper proposes a Distributed Automated Machine Learning (AutoML) framework for efficiently designing and ...
Armin Dadras Eslamlou, Shiping Huang, Belén Riveiro, M. Z. Naser   +3 more
wiley   +1 more source

Pixel Lens: A Granular Assessment of Saliency Explanations

Artificial Intelligence for Engineering, EarlyView.
We propose a pipeline that detects shortcut‐dominated classifiers by comparing predictions on clean and shortcut‐perturbed images and checking dominance via a Shapley‐based ground‐truth explainer. The workflow quantifies the explanation quality of different explainable artificial intelligence (XAI) methods.
Kanglong Fan, Chen Ma, Yifan Peng, Jinglong Yang, Qilin Sun, Yuming Fang   +5 more
wiley   +1 more source

AML‐Net: Attention‐based multi‐scale lightweight model for brain tumour segmentation in internet of medical things

CAAI Transactions on Intelligence Technology, EarlyView.
Abstract Brain tumour segmentation employing MRI images is important for disease diagnosis, monitoring, and treatment planning. Till now, many encoder‐decoder architectures have been developed for this purpose, with U‐Net being the most extensively utilised. However, these architectures require a lot of parameters to train and have a semantic gap. Some
Muhammad Zeeshan Aslam, Basit Raza, Muhammad Faheem, Aadil Raza   +3 more
wiley   +1 more source

ECG‐TransCovNet: A hybrid transformer model for accurate arrhythmia detection using Electrocardiogram signals

CAAI Transactions on Intelligence Technology, EarlyView.
Abstract Abnormalities in the heart's rhythm, known as arrhythmias, pose a significant threat to global health, often leading to severe cardiac conditions and sudden cardiac deaths. Therefore, early and accurate detection of arrhythmias is crucial for timely intervention and potentially life‐saving treatment.
Hasnain Ali Shah, Faisal Saeed, Muhammad Diyan, Nouf Abdullah Almujally, Jae‐Mo Kang   +4 more
wiley   +1 more source

Brain‐RetinaNet: Detection of Brain Tumour Using an Improved RetinaNet in Magnetic Resonance Imaging

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Brain tumours disrupt the normal functioning of the brain and, if left untreated, can invade surrounding tissues, blood vessels, and nerves, posing a severe threat. Consequently, early detection is crucial to prevent tragic outcomes. Distinguishing brain tumours through manual detection poses a significant challenge given their diverse ...
Rashid Iqbal, Rabbia Mahum, Mohamed Sharaf, Javed Ali Khan   +3 more
wiley   +1 more source

Physics‐Driven Deep Neural Networks for Solving the Optimal Transport Problem Associated With the Monge–Ampère Equation

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Monge–Ampère equations (MAEs) are fully nonlinear second‐order partial differential equations (PDEs), which are closely related to various fields including optimal transport (OT) theory, geometrical optics and affine geometry. Despite their significance, MAEs are extremely challenging to solve.
Xinghua Pan, Zexin Feng, Kang Yang
wiley   +1 more source