3-D convolutional encoder-decoder network for low-dose CT via transfer learning from a 2-D trained network

H Shan, Y Zhang, Q Yang, U Kruger… - IEEE transactions on …, 2018 - ieeexplore.ieee.org
Low-dose computed tomography (LDCT) has attracted major attention in the medical
imaging field, since CT-associated X-ray radiation carries health risks for patients. The …

Revisiting single image depth estimation: Toward higher resolution maps with accurate object boundaries

J Hu, M Ozay, Y Zhang, T Okatani - 2019 IEEE winter …, 2019 - ieeexplore.ieee.org
This paper considers the problem of single image depth estimation. The employment of
convolutional neural networks (CNNs) has recently brought about significant advancements …

Maximum entropy scaled super pixels segmentation for multi-object detection and scene recognition via deep belief network

AA Rafique, M Gochoo, A Jalal, K Kim - Multimedia Tools and Applications, 2023 - Springer
Recent advances in visionary technologies impacted multi-object recognition and scene
understanding. Such scene-understanding tasks are a demanding part of several …

UAV environmental perception and autonomous obstacle avoidance: A deep learning and depth camera combined solution

D Wang, W Li, X Liu, N Li, C Zhang - Computers and Electronics in …, 2020 - Elsevier
Abstract In agriculture, Unmanned Aerial Vehicles (UAVs) have shown great potential for
plant protection. Uncertain obstacles randomly distributed in the unstructured farmland …

Automated sustainable multi-object segmentation and recognition via modified sampling consensus and Kernel sliding perceptron

AA Rafique, A Jalal, K Kim - Symmetry, 2020 - mdpi.com
Object recognition in depth images is challenging and persistent task in machine vision,
robotics, and automation of sustainability. Object recognition tasks are a challenging part of …

Computer vision-based grasp pattern recognition with application to myoelectric control of dexterous hand prosthesis

C Shi, D Yang, J Zhao, H Liu - IEEE Transactions on Neural …, 2020 - ieeexplore.ieee.org
Artificial intelligence provides new feasibilities to the control of dexterous prostheses. To
achieve suitable grasps over various objects, a novel computer vision-based classification …

GeoAI in terrain analysis: Enabling multi-source deep learning and data fusion for natural feature detection

S Wang, W Li - Computers, Environment and Urban Systems, 2021 - Elsevier
In this paper we report on a new GeoAI research method which enables deep machine
learning from multi-source geospatial data for natural feature detection. In particular, a multi …

Permeability prediction of low-resolution porous media images using autoencoder-based convolutional neural network

HL Zhang, H Yu, XH Yuan, HY Xu, M Micheal… - Journal of Petroleum …, 2022 - Elsevier
Permeability prediction of porous media from numerical approaches is an important
supplement for experimental measurements with the benefits of being more economical and …

RGB-D-based object recognition using multimodal convolutional neural networks: a survey

M Gao, J Jiang, G Zou, V John, Z Liu - IEEE access, 2019 - ieeexplore.ieee.org
Object recognition in real-world environments is one of the fundamental and key tasks in
computer vision and robotics communities. With the advanced sensing technologies and low …

[HTML][HTML] Marker-free surgical navigation of rod bending using a stereo neural network and augmented reality in spinal fusion

M von Atzigen, F Liebmann, A Hoch, JM Spirig… - Medical Image …, 2022 - Elsevier
The instrumentation of spinal fusion surgeries includes pedicle screw placement and rod
implantation. While several surgical navigation approaches have been proposed for pedicle …