Results 91 to 100 of about 18,850,036 (270)

RGBT Salient Object Detection: A Large-scale Dataset and Benchmark [PDF]

, 2022
Salient object detection in complex scenes and environments is a challenging research topic. Most works focus on RGB-based salient object detection, which limits its performance of real-life applications when confronted with adverse conditions such as ...
Tu, Zhengzheng, Liu, Yongtao, Li, Zhun, Xu, Jieming, Ma, Yan, Li, Chenglong   +5 more
core  

U‐Net‐Based Prediction of Concealed Volume Loss in AZ31 From Optical Corrosion Imprints and As‐Exposed Surface Topography

Advanced Intelligent Discovery, EarlyView.
How much material loss is concealed beneath a layer of corrosion products? This proof‐of‐concept study demonstrates how concealed volume loss is inferred from the optical appearance and as‐exposed surface topography of AZ31 corrosion imprints. By predicting postcleaning depth maps, a multimodal U‐Net model estimates hidden volume loss without chromic ...
Lars Dammann, Ci Song, Bahram Vaghefinazari, Tim Würger, Anna Lisitsyna, Shadi Albarqouni, Mikhail L. Zheludkevich, Sviatlana V. Lamaka, Christian Feiler   +8 more
wiley   +1 more source

RGB depth salient object detection via cross‐modal attention and boundary feature guidance

IET Computer Vision
RGB depth (RGB‐D) salient object detection (SOD) is a meaningful and challenging task, which has achieved good detection performance in dealing with simple scenes using convolutional neural networks, however, it cannot effectively handle scenes with ...
Lingbing Meng, Mengya Yuan, Xuehan Shi, Le Zhang, Qingqing Liu, Dai Ping, Jinhua Wu, Fei Cheng   +7 more
doaj   +1 more source

MonoSOD: Monocular Salient Object Detection based on Predicted Depth

, 2021
Salient object detection (SOD) can directly improve the performance of tasks like obstacle detection, semantic segmentation and object recognition. Such tasks are important for robotic and other autonomous navigation systems.
Dimas G., Gatoula P., Iakovidis D.K.
core   +1 more source

Designing Wire Mazes for Replicating Natural Echoes to Study Bat Biosonar Function

Advanced Intelligent Systems, EarlyView.
A validated framework combining efficient physical modeling (multiple scattering model) and deep learning is presented to guide wire‐maze design for bat biosonar studies. This approach rapidly generates large datasets to test acoustic distinguishability among wire arrangements.
Chunlin Jia, Gengkai Hu, Boo Cheong Khoo, Rolf Müller   +3 more
wiley   +1 more source

HeaTrace: A Parametric Design‐to‐Fabrication Workflow for Thermally Programmable Soft Robots

Advanced Intelligent Systems, EarlyView.
A programmable thermal actuation workflow enables soft robots to be designed and fabricated with embedded heaters that drive multiple responses. By combining performance‐driven heater design with multimaterial fabrication, the system supports thermally triggered shape change, stiffness tuning, and thermochromic visual response, as demonstrated through ...
Naresh Kumar Thanigaivel, Thileepan Stalin, Elgar Kanhere, Aby Raj Plamootil Mathai, Konstantin Sakharov, Yong Lin, Hirusha Madhuwantha Loku Hettige, Gumawang Hiramandala, Shlomo Magdassi, Pablo Valdivia Y Alvarado   +9 more
wiley   +1 more source

Discriminative unimodal feature selection and fusion for RGB-D salient object detection

, 2022
Most existing RGB-D salient object detectors make use of the complementary information of RGB-D images to overcome the challenging scenarios, e.g., low contrast, clutter backgrounds.
Luo, Yongjiang, Han, Jungong, Zhang, Qiang, Huang, Nianchang   +3 more
core   +1 more source

AI‐Enabled RGB Light‐to‐Frequency Sensor for Nondestructive Salinity Stress Monitoring in Medicinal Plants

Advanced Intelligent Systems, EarlyView.
A distributed wireless sensing framework enables noninvasive monitoring of plant salinity stress through leaf reflectance measurements acquired with portable optical sensors. The collected data are processed using TinyML‐based neural network models deployed at the edge, enabling accurate, real‐time, and low‐cost classification of salinity levels, while
Ali Ahmad, Vinie Lee Silva‐Alvarado, Arman Heydari, Sandra Sendra, Jaime Lloret   +4 more
wiley   +1 more source

AI‐Powered Smart Displays and AR Glasses: Perspectives and Challenges

Advanced Intelligent Systems, EarlyView.
This perspective examines how AI is reshaping smart displays and AR glasses. The latest in image‐quality enhancement, sensor‐integrated display optimization, and physiological sensing in display systems, followed by AI‐assisted AR technologies including waveguide optimization, image compensation, foveated rendering, and multimodal sensing, is discussed.
Luke Benoit, Yizhou Qian, Yi‐Chien Chen, Ziyang Shen, Po‐Sheng Chiu, Youngeon Lee, Cheng‐Han Ke, Chih‐Lung Lin, Shin‐Tson Wu   +8 more
wiley   +1 more source

Quantitative muscle architecture in large carnivorous marsupials (Marsupialia: Dasyuridae) and links to substrate use and prey processing

The Anatomical Record, EarlyView.
Abstract The Dasyurid species Sarcophilus harrisii, Dasyurus maculatus, and Dasyurus viverrinus, occupying diverse ecological niches and forming a guild structure in Tasmania, provide a basis for examining the roles of various forelimb muscle groups in prey capture and locomotion.
Riya G. Bidaye, Samuel H. Frenkel, David P. Hocking, Alistair R. Evans, Justin W. Adams   +4 more
wiley   +1 more source