Skip to main content

Research Repository

Advanced Search

All Outputs (182)

Texture-sensitive superpixeling and adaptive thresholding for effective segmentation of sea ice floes in high-resolution optical images. (2020)
Journal Article
CHAI, Y., REN, J., HWANG, B., WANG, J., FAN, D., YAN, Y. and ZHU, S. 2021. Texture-sensitive superpixeling and adaptive thresholding for effective segmentation of sea ice floes in high-resolution optical images. IEEE journal of selected topics in applied earth observations and remote sensing [online], 14, pages 577-586. Available from: https://doi.org/10.1109/jstars.2020.3040614

Efficient and accurate segmentation of sea ice floes from high-resolution optical (HRO) remote sensing images is crucial for understanding of sea ice evolutions and climate changes, especially in coping with the large data volume. Existing methods su... Read More about Texture-sensitive superpixeling and adaptive thresholding for effective segmentation of sea ice floes in high-resolution optical images..

Multiscale 2-D singular spectrum analysis and principal component analysis for spatial–spectral noise-robust feature extraction and classification of hyperspectral images. (2020)
Journal Article
MA, P., REN, J., ZHAO, H., SUN, G., MURRAY, P. and ZHENG, J. 2021. Multiscale 2-D singular spectrum analysis and principal component analysis for spatial–spectral noise-robust feature extraction and classification of hyperspectral images. IEEE journal of selected topics in applied earth observations and remote sensing [online], 14, pages 1233-1245. Available from: https://doi.org/10.1109/JSTARS.2020.3040699

In hyperspectral images (HSI), most feature extraction and data classification methods rely on corrected dataset, in which the noisy and water absorption bands are removed. This can result in not only extra working burden but also information loss fr... Read More about Multiscale 2-D singular spectrum analysis and principal component analysis for spatial–spectral noise-robust feature extraction and classification of hyperspectral images..

Fusion of PCA and segmented-PCA domain multiscale 2-D-SSA for effective spectral-spatial feature extraction and data classification in hyperspectral imagery. (2020)
Journal Article
FU, H., SUN, G., REN, J., ZHANG, A. and JIA, X. 2020. Fusion of PCA and segmented-PCA domain multiscale 2-D-SSA for effective spectral-spatial feature extraction and data classification in hyperspectral imagery. IEEE transactions on geoscience and remote sensing [online], 60, article 5500214. Available from: https://doi.org/10.1109/TGRS.2020.3034656

As hyperspectral imagery (HSI) contains rich spectral and spatial information, a novel principal component analysis (PCA) and segmented-PCA (SPCA)-based multiscale 2-D-singular spectrum analysis (2-D-SSA) fusion method is proposed for joint spectral–... Read More about Fusion of PCA and segmented-PCA domain multiscale 2-D-SSA for effective spectral-spatial feature extraction and data classification in hyperspectral imagery..

Iterative enhanced multivariance products representation for effective compression of hyperspectral images. (2020)
Journal Article
TUNA, S., TÖREYIN, B.U., REN, J., ZHAO, H. and MARSHALL, S. 2021. Iterative enhanced multivariance products representation for effective compression of hyperspectral images. IEEE transactions on geoscience and remote sensing [online], 59(11), pages 9569-9584. Available from: https://doi.org/10.1109/TGRS.2020.3031016

Effective compression of hyperspectral (HS) images is essential due to their large data volume. Since these images are high dimensional, processing them is also another challenging issue. In this work, an efficient lossy HS image compression method b... Read More about Iterative enhanced multivariance products representation for effective compression of hyperspectral images..

Sleep state classification using power spectral density and residual neural network with multichannel EEG signals. (2020)
Journal Article
HASAN, M.J., SHON, D., IM, K., CHOI, H.-K., YOO, D.-S. and KIM, J.-M. 2020. Sleep state classification using power spectral density and residual neural network with multichannel EEG signals. Applied sciences [online], 10(21): medical signal and image processing, article 7639. Available from: https://doi.org/10.3390/app10217639

This paper proposes a classification framework for automatic sleep stage detection in both male and female human subjects by analyzing the electroencephalogram (EEG) data of polysomnography (PSG) recorded for three regions of the human brain, i.e., t... Read More about Sleep state classification using power spectral density and residual neural network with multichannel EEG signals..

Web‐based efficient dual attention networks to detect COVID‐19 from X‐ray images. (2020)
Journal Article
SARKER, M.M.K., MAKHLOUF, Y., BANU, S.F., CHAMBON, S., RADEVA, P. and PUIG, D. 2020. Web-based efficient dual attention networks to detect COVID-19 from X-ray images. Electronics letters [online], 56(24), pages 1298-1301. Available from: https://doi.org/10.1049/el.2020.1962

Rapid and accurate detection of COVID-19 is a crucial step to control the virus. For this purpose, the authors designed a web-based COVID-19 detector using efficient dual attention networks, called ‘EDANet’. The EDANet architecture is based on invert... Read More about Web‐based efficient dual attention networks to detect COVID‐19 from X‐ray images..

Generic wavelet‐based image decomposition and reconstruction framework for multi‐modal data analysis in smart camera applications. (2020)
Journal Article
YAN, Y., LIU, Y., YANG, M., ZHAO, H., CHAI, Y. and REN, J. 2020. Generic wavelet-based image decomposition and reconstruction framework for multi-modal data analysis in smart camera applications. IET computer vision [online], 14(7): computer vision for smart cameras and camera networks, pages 471-479. Available from: https://doi.org/10.1049/iet-cvi.2019.0780

Effective acquisition, analysis and reconstruction of multi-modal data such as colour and multi-/hyper-spectral imagery is crucial in smart camera applications, where wavelet-based coding and compression of images are highly demanded. Many existing d... Read More about Generic wavelet‐based image decomposition and reconstruction framework for multi‐modal data analysis in smart camera applications..

Effective melanoma recognition using deep convolutional neural network with covariance discriminant loss. (2020)
Journal Article
GUO, L., XIE, G., XU, X. and REN, J. 2020. Effective melanoma recognition using deep convolutional neural network with covariance discriminant loss. Sensors [online], 20(20), article 5786. Available from: https://doi.org/10.3390/s20205786

Melanoma recognition is challenging due to data imbalance and high intra-class variations and large inter-class similarity. Aiming at the issues, we propose a melanoma recognition method using deep convolutional neural network with covariance discrim... Read More about Effective melanoma recognition using deep convolutional neural network with covariance discriminant loss..

Human pose estimation-based real-time gait analysis using convolutional neural network. (2020)
Journal Article
ROHAN, A., RABAH, M., HOSNY, T. and KIM, S.-H. 2020. Human pose estimation-based real-time gait analysis using convolutional neural network. IEEE access [online] 8, pages 191542-191550. Available from: https://doi.org/10.1109/ACCESS.2020.3030086

Gait analysis is widely used in clinical practice to help in understanding the gait abnormalities and its association with a certain underlying medical condition for better diagnosis and prognosis. Several technologies embedded in the specialized dev... Read More about Human pose estimation-based real-time gait analysis using convolutional neural network..

SAFDet: a semi-anchor-free detector for effective detection of oriented objects in aerial images. (2020)
Journal Article
FANG, Z., REN, J., SUN, H., MARSHALL, S., HAN, J. and ZHAO, H. 2020. SAFDet: a semi-anchor-free detector for effective detection of oriented objects in aerial images. Remote sensing [online], 12(19), article 3225. Available from: https://doi.org/10.3390/rs12193225

An oriented bounding box (OBB) is preferable over a horizontal bounding box (HBB) in accurate object detection. Most of existing works utilize a two-stage detector for locating the HBB and OBB, respectively, which have suffered from the misaligned ho... Read More about SAFDet: a semi-anchor-free detector for effective detection of oriented objects in aerial images..

A novel intelligent computational approach to model epidemiological trends and assess the impact of non-pharmacological interventions for COVID-19. (2020)
Journal Article
REN, J., YAN, Y., ZHAO, H., MA, P., ZABALZA, J., HUSSAIN, Z., LUO, S., DAI, Q., ZHAO, S., SHEIKH, A., HUSSAIN, A. and LI, H. 2020. A novel intelligent computational approach to model epidemiological trends and assess the impact of non-pharmacological interventions for COVID-19. IEEE Journal of biomedical and health informatics [online], 24(12), pages 3551-3563. Available from: https://doi.org/10.1109/jbhi.2020.3027987

The novel coronavirus disease 2019 (COVID-19) pandemic has led to a worldwide crisis in public health. It is crucial we understand the epidemiological trends and impact of non-pharmacological interventions (NPIs), such as lockdowns for effective mana... Read More about A novel intelligent computational approach to model epidemiological trends and assess the impact of non-pharmacological interventions for COVID-19..

Multi-sensor fusion-based time-frequency imaging and transfer learning for spherical tank crack diagnosis under variable pressure conditions. (2020)
Journal Article
HASAN, M.J., ISLAM, M.M.M. and KIM, J.-M. 2021. Multi-sensor fusion-based time-frequency imaging and transfer learning for spherical tank crack diagnosis under variable pressure conditions. Measurement [online], 168, article 108478. Available from: https://doi.org/10.1016/j.measurement.2020.108478

In this paper, a crack diagnosis framework is proposed that combines a new signal-to-imaging technique and transfer learning-aided deep learning framework to automate the diagnostic process. The objective of the signal-to-imaging technique is to conv... Read More about Multi-sensor fusion-based time-frequency imaging and transfer learning for spherical tank crack diagnosis under variable pressure conditions..

Rewritable and sustainable 2D barcode for traceability application in smart IoT based fault-tolerant mechanism. (2020)
Journal Article
CHEN, R., YU, Y., XIE, S., ZHAO, H., LIU, S., REN, J. and TAN, H.-Z. 2020. Rewritable and sustainable 2D barcode for traceability application in smart IoT based fault-tolerant mechanism. Sustainability [online], 12(17), article 7192. Available from: https://doi.org/10.3390/su12177192

With the development of the Internet of Things (IoT) technology, two-dimensional (2D) barcodes are widely used in smart IoT applications as a perception portal. In industries with many circulations and testing links like traceability, since the exist... Read More about Rewritable and sustainable 2D barcode for traceability application in smart IoT based fault-tolerant mechanism..

Helmet use detection of tracked motorcycles using CNN-based multi-task learning. (2020)
Journal Article
LIN, H., DENG, J.D., ALBERS, D. and SIEBERT, F.W. 2020. Helmet use detection of tracked motorcycles using CNN-based multi-task learning. IEEE access [online], 8, pages 162073-162084. Available from: https://doi.org/10.1109/access.2020.3021357

Automated detection of motorcycle helmet use through video surveillance can facilitate efficient education and enforcement campaigns that increase road safety. However, existing detection approaches have a number of shortcomings, such as the inabilit... Read More about Helmet use detection of tracked motorcycles using CNN-based multi-task learning..

Topological optimization of the DenseNet with pretrained-weights inheritance and genetic channel selection. (2020)
Journal Article
FANG, Z, REN, J., MARSHALL, S., ZHAO, H., WANG, S. and LI, X. 2021. Topological optimization of the DenseNet with pretrained-weights inheritance and genetic channel selection. Pattern recognition [online], 109, article ID 107608. Available from: https://doi.org/10.1016/j.patcog.2020.107608

Convolutional neural networks (CNNs) have been successfully applied in many computer vision applications, especially in image classification tasks, where most of the structures have been designed manually. With the aid of skip connection and dense co... Read More about Topological optimization of the DenseNet with pretrained-weights inheritance and genetic channel selection..

Breast tumor segmentation in ultrasound images using contextual-information-aware deep adversarial learning framework. (2020)
Journal Article
SINGH, V.K., ABDEL-NASSER, M., AKRAM, F., RASHWAN, H.A., SARKER, M.M.K., PANDEY, N., ROMANI, S. and PUIG, D. 2020. Breast tumor segmentation in ultrasound images using contextual-information-aware deep adversarial learning framework. Expert systems with applications [online], 162, article 113870. Available from: https://doi.org/10.1016/j.eswa.2020.113870

Automatic tumor segmentation in breast ultrasound (BUS) images is still a challenging task because of many sources of uncertainty, such as speckle noise, very low signal-to-noise ratio, shadows that make the anatomical boundaries of tumors ambiguous,... Read More about Breast tumor segmentation in ultrasound images using contextual-information-aware deep adversarial learning framework..

Semisupervised hypergraph discriminant learning for dimensionality reduction of hyperspectral image. (2020)
Journal Article
LUO, F., GUO, T., LIN, Z., REN, J. and ZHOU, X. 2020. Semisupervised hypergraph discriminant learning for dimensionality reduction of hyperspectral image. IEEE journal of selected topics in applied earth observations and remote sensing [online], 13, pages 4242-4256. Available from: https://doi.org/10.1109/jstars.2020.3011431

Semisupervised learning is an effective technique to represent the intrinsic features of a hyperspectral image (HSI), which can reduce the cost to obtain the labeled information of samples. However, traditional semisupervised learning methods fail to... Read More about Semisupervised hypergraph discriminant learning for dimensionality reduction of hyperspectral image..

STEM teaching for the Internet of Things maker course: a teaching model based on the iterative loop. (2020)
Journal Article
CHEN, R., ZHENG, Y., XU, X., ZHAO, H., REN, J. and TAN, H.-Z. 2020. STEM teaching for the Internet of Things maker course: a teaching model based on the interative loop. Sustainability [online], 12(14), article 5758. Available from: https://doi.org/10.3390/su12145758

As the key technology for 5G applications in the future, the Internet of Things (IoT) is developing rapidly, and the demand for the cultivation of engineering talents in the IoT is also expanding. The rise of maker education has brought new teaching... Read More about STEM teaching for the Internet of Things maker course: a teaching model based on the iterative loop..

A novel spectral-spatial singular spectrum analysis technique for near real-time in-situ feature extraction in hyperspectral imaging. (2020)
Journal Article
FU, H., SUN, G., ZABALZA, J., ZHANG, A., REN, J. and JIA, X. 2020. A novel spectral-spatial singular spectrum analysis technique for near real-time in-situ feature extraction in hyperspectral imaging. IEEE journal of selected topics in applied earth observations and remote sensing [online], 13, pages 2214-2225. Available from: https://doi.org/10.1109/JSTARS.2020.2992230

As a cutting-edge technique for denoising and feature extraction, singular spectrum analysis (SSA) has been applied successfully for feature mining in hyperspectral images (HSI). However, when applying SSA for in situ feature extraction in HSI, conve... Read More about A novel spectral-spatial singular spectrum analysis technique for near real-time in-situ feature extraction in hyperspectral imaging..

Content-sensitive superpixel generation with boundary adjustment. (2020)
Journal Article
ZHANG, D., XIE, G., REN, J., ZHANG, Z., BAO, W. and XU, X. 2020. Content-sensitive superpixel generation with boundary adjustment. Applied sciences [online], 10(9), article 3150. Available from: https://doi.org/10.3390/app10093150

Superpixel segmentation has become a crucial tool in many image processing and computer vision applications. In this paper, a novel content-sensitive superpixel generation algorithm with boundary adjustment is proposed. First, the image local entropy... Read More about Content-sensitive superpixel generation with boundary adjustment..