Large depth range binary-focusing projection 3D shape reconstruction via unpaired data learning

J Tan, J Liu, X Wang, Z He, W Su, T Huang… - Optics and Lasers in …, 2024 - Elsevier
The binary-defocusing technique (BDT) shows prospects in high-speed 3D reconstruction.
However, the defocusing projection mechanism results in low accuracy at inappropriate …

Bayesian-neural-network-based strain estimation approach for optical coherence elastography

Y Bai, K Zhang, R Mo, Z Ni, Z He, S Xie, B Dong - Optica, 2024 - opg.optica.org
Strain estimation is critical for quantitative elastography in quasi-static phase-sensitive
optical coherence elastography (PhS-OCE). Deep-learning methods have achieved …

HSNet: An Intelligent Hierarchical Semantic-Aware Network System for Real-Time Semantic Segmentation

X Peng, J Cheng, X Tang, Z Deng… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Semantic segmentation, which aims to accurately identify each pixel, is a meaningful and
challenging task. Recently, we witness a strong tendency to improve model efficiency in low …

MD-YOLO: Surface Defect Detector for Industrial Complex Environments

H Zheng, X Chen, H Cheng, Y Du, Z Jiang - Optics and Lasers in …, 2024 - Elsevier
Computer vision inspection techniques are currently being effectively used in industry with
positive outcomes. Due to flaws in the manufacturing process and the interference of outside …

[HTML][HTML] Enhancing scanning electron microscopy imaging quality of weakly conductive samples through unsupervised learning

X Gao, T Huang, P Tang, J Di, L Zhong, W Zhang - Scientific Reports, 2024 - nature.com
Scanning electron microscopy (SEM) is a crucial tool for analyzing submicron-scale
structures. However, the attainment of high-quality SEM images is contingent upon the high …

A progressive segmentation network for navigable areas with semantic-spatial information flow

W Li, M Liao, W Zou - Expert Systems with Applications, 2024 - Elsevier
Segmentation of safe navigable areas is a crucial technology for scene parsing in autopilot
systems. However, existing segmentation methods often fail to adequately exploit the …

LAACNet: Lightweight adaptive activation convolution network-based defect detection on polished metal surfaces

Z Lv, Z Lu, K Xia, H Zuo, X Jia, H Li, Y Xu - Engineering Applications of …, 2024 - Elsevier
After the metal workpiece has been polished, there may still be small defects on the surface,
which will adversely affect the quality of the product and the service life and availability of the …

Single shot interferenceless coded aperture correlation holography via a learnable Wiener deconvolution network

L Yang, J Yang, H Wang, Y Wang, T Huang… - Optics and Lasers in …, 2024 - Elsevier
One of the challenges in interferenceless coded aperture correlation holography (I-COACH)
is high-quality single-shot reconstruction, as conventional cross-correlation reconstruction …

[HTML][HTML] Real-Time Semantic Segmentation Algorithm for Street Scenes Based on Attention Mechanism and Feature Fusion

B Wu, X Xiong, Y Wang - Electronics, 2024 - mdpi.com
In computer vision, the task of semantic segmentation is crucial for applications such as
autonomous driving and intelligent surveillance. However, achieving a balance between …

Temporal Fusion Dynamically Separable Graph Convolutional Network for EEG Motion Intention Decoding Based on Source Information Extraction

X Tang, T Wang, X Li, W Zhu, X Hong… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
The electroencephalogram (EEG) signals acquired through scalp electrodes are susceptible
to the volume conduction effect, which introduces a considerable degree of redundant …