Xavier Neyt
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Xavier Neyt has a total of 132 co-authors. Here are the top co-authors by number of shared publications:
Marc Acheroy
Signal and Image Centre, RMA
8 shared publications- Anis Elyouncha
Department of Space, Earth and Environment, Chalmers University of Technology, Gothenburg, Sweden
7 shared publications N. Pattyn
Vital Signs and Performance (VIPER) research unit of the Royal Military Academy, Brussels, Belgium
7 shared publicationsNathalie Pattyn
Vrije Universiteit Brussels, Human Physiology & Sports Medicine Department, Brussels, Belgium
7 shared publicationsFabien Gabriel
Department of Communication, Information, Systems and Sensors (CISS), Royal Military Academy (RMA), Brussels, Belgium
6 shared publications- Olivier Mairesse
Psychological Research (PSYR), Department of Psychology, Faculty of Psychology and Educational Sciences Vrije Universiteit Brussel Brussels Belgium
6 shared publications
Latest Publications
- Open Access
- 19 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 17 (19391404) , 18038-18057
D4SC: Deep Supervised Semantic Segmentation for Seabed Characterization and Uncertainty Estimation for Large Scale Mapping
Seabed characterization consists in the study of the physical and biological properties of the of ocean floors. Sonar is commonly employed to capture the acoustic backscatter reflected from the seabed. It has been extensively used for Automatic Target Recognition (ATR) within Mine Countermeasures (MCM) operations in shallow waters. However, conventional Machine Learning (ML) and Deep Learning (DL) approaches face challenges in automatically mapping the seabed due to noise and limited labels. Thus, this paper introduces the Deep Supervised Semantic Segmentation model for Seabed Characterization (D4SC), tailored for addressing challenges associated with sonar data. D4SC employs Convolutional Neural Networks (CNNs), specific High-Resolution (HR) Synthetic Aperture Sonar (SAS) data preprocessing and Data Augmentation (DA) methods, including the novel boundary pixel label rejection, and moves from the low-label regime. Performance comparisons against standard methods in the literature are conducted, demonstrating D4SC's superiority on challenging HR SAS survey datasets from real-world Mine Countermeasures (MCM) exercises at sea. Additionally, this work thoroughly explores the effect of the quality of the datasets, the robustness of training models on Out-of-Distribution (OoD) data and the estimation of epistemic uncertainty to refine predictions at large scale.
- 19 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 17 (19391404) , 18038-18057
Open AccessD4SC: Deep Supervised Semantic Segmentation for Seabed Characterization and Uncertainty Estimation for Large Scale Mapping
Seabed characterization consists in the study of the physical and biological properties of the of ocean floors. Sonar is commonly employed to capture the acoustic backscatter reflected from the seabed. It has been extensively used for Automatic Target Recognition (ATR) within Mine Countermeasures (MCM) operations in shallow waters. However, conventional Machine Learning (ML) and Deep Learning (DL) approaches face challenges in automatically mapping the seabed due to noise and limited labels. Thus, this paper introduces the Deep Supervised Semantic Segmentation model for Seabed Characterization (D4SC), tailored for addressing challenges associated with sonar data. D4SC employs Convolutional Neural Networks (CNNs), specific High-Resolution (HR) Synthetic Aperture Sonar (SAS) data preprocessing and Data Augmentation (DA) methods, including the novel boundary pixel label rejection, and moves from the low-label regime. Performance comparisons against standard methods in the literature are conducted, demonstrating D4SC's superiority on challenging HR SAS survey datasets from real-world Mine Countermeasures (MCM) exercises at sea. Additionally, this work thoroughly explores the effect of the quality of the datasets, the robustness of training models on Out-of-Distribution (OoD) data and the estimation of epistemic uncertainty to refine predictions at large scale.
- Open Access
- 23 May 2022
- Published by MDPI AG in Remote Sensing
- Vol. 14 (10) , 2496
Green Area Index and Soil Moisture Retrieval in Maize Fields Using Multi-Polarized C- and L-Band SAR Data and the Water Cloud Model
The green area index (GAI) and the soil moisture under the canopy are two key variables for agricultural monitoring. The current most accurate GAI estimation methods exploit optical data and are rendered ineffective in the case of frequent cloud cover. Synthetic aperture radar (SAR) measurements could allow the remote estimation of both variables at the parcel level, on a large scale and regardless of clouds. In this study, several methods were implemented and tested for the simultaneous estimation of both variables using the water cloud model (WCM) and dual-polarized radar backscatter measurements. The methods were tested on the BELSAR-Campaign data set consisting of in-situ measurements of bio-geophysical variables of vegetation and soil in maize fields combined with multi-polarized C- and L-band SAR data from Sentinel-1 and BELSAR. Accurate GAI estimates were obtained using a random forest regressor for the inversion of a pair of WCMs calibrated using cross and vertical co-polarized SAR data in L- and C-band, with correlation coefficients of 0.79 and 0.65 and RMSEs of 0.77 m2 m−2 and 0.98 m2 m−2, respectively, between estimates and in-situ measurements. The WCM, however, proved inadequate for soil moisture monitoring in the conditions of the campaign. These promising results indicate that GAI retrieval in maize crops using only dual-polarized radar data could successfully substitute for estimates derived from optical data.
- 23 May 2022
- Published by MDPI AG in Remote Sensing
- Vol. 14 (10) , 2496
Open AccessGreen Area Index and Soil Moisture Retrieval in Maize Fields Using Multi-Polarized C- and L-Band SAR Data and the Water Cloud Model
The green area index (GAI) and the soil moisture under the canopy are two key variables for agricultural monitoring. The current most accurate GAI estimation methods exploit optical data and are rendered ineffective in the case of frequent cloud cover. Synthetic aperture radar (SAR) measurements could allow the remote estimation of both variables at the parcel level, on a large scale and regardless of clouds. In this study, several methods were implemented and tested for the simultaneous estimation of both variables using the water cloud model (WCM) and dual-polarized radar backscatter measurements. The methods were tested on the BELSAR-Campaign data set consisting of in-situ measurements of bio-geophysical variables of vegetation and soil in maize fields combined with multi-polarized C- and L-band SAR data from Sentinel-1 and BELSAR. Accurate GAI estimates were obtained using a random forest regressor for the inversion of a pair of WCMs calibrated using cross and vertical co-polarized SAR data in L- and C-band, with correlation coefficients of 0.79 and 0.65 and RMSEs of 0.77 m2 m−2 and 0.98 m2 m−2, respectively, between estimates and in-situ measurements. The WCM, however, proved inadequate for soil moisture monitoring in the conditions of the campaign. These promising results indicate that GAI retrieval in maize crops using only dual-polarized radar data could successfully substitute for estimates derived from optical data.
- Open Access
A New Earth Observation Service Based on Sentinel-1 and Sentinel-2 Time Series for the Monitoring of Redevelopment Sites in Wallonia, Belgium
Urban planning is a challenge, especially when it comes to limiting land take. In former industrial regions such as Wallonia, the presence of a large number of brownfields, here called “redevelopment sites”, opens up new opportunities for sustainable urban planning through their revalorization. The Walloon authorities are currently managing an inventory of more than 2200 sites, which requires a significant amount of time and resources to update. In this context, the Sentinel satellites and the Terrascope platform, the Sentinel Collaborative Ground Segment for Belgium, enabled us to deploy SARSAR, an Earth observation service used for the automated monitoring of redevelopment sites that generates regular and automatic change reports that are directly usable by the Walloon authorities. In this paper, we present the methodological aspects and implementation details of the service, which combines two well-known and robust methods: the Pruned Exact Linear Time method for change point detection and threshold-based classification, which assigns the detected changes to three different classes (vegetation, building and soil). The overall accuracy of the system is in the range of 70–90%, depending on the different methods and classes considered. Some remarks on the advantages and possible drawbacks of this approach are also provided.
Open AccessA New Earth Observation Service Based on Sentinel-1 and Sentinel-2 Time Series for the Monitoring of Redevelopment Sites in Wallonia, Belgium
Urban planning is a challenge, especially when it comes to limiting land take. In former industrial regions such as Wallonia, the presence of a large number of brownfields, here called “redevelopment sites”, opens up new opportunities for sustainable urban planning through their revalorization. The Walloon authorities are currently managing an inventory of more than 2200 sites, which requires a significant amount of time and resources to update. In this context, the Sentinel satellites and the Terrascope platform, the Sentinel Collaborative Ground Segment for Belgium, enabled us to deploy SARSAR, an Earth observation service used for the automated monitoring of redevelopment sites that generates regular and automatic change reports that are directly usable by the Walloon authorities. In this paper, we present the methodological aspects and implementation details of the service, which combines two well-known and robust methods: the Pruned Exact Linear Time method for change point detection and threshold-based classification, which assigns the detected changes to three different classes (vegetation, building and soil). The overall accuracy of the system is in the range of 70–90%, depending on the different methods and classes considered. Some remarks on the advantages and possible drawbacks of this approach are also provided.
- Open Access
An Operational Tool for the Automatic Detection and Removal of Border Noise in Sentinel-1 GRD Products
The presence of border noise in Sentinel-1 Ground Range Detected (GRD) products is an undesired processing artifact that limits their full exploitation in a number of applications. All of the Sentinel-1 GRD products generated before March 2018—more than 800,000—are affected by this particular type of noise. In March 2018, an official fix was deployed that solved the problem for a large portion of the newly generated products, but it did not cover the entire range of products, hence the need for an operational tool that is able to effectively and consistently remove border noise in an automated way. Currently, a few solutions have been proposed that try to address the problem, but all of them have limitations. The scope of this paper is therefore to present a new method based on mathematical morphology for the automatic detection and masking of border noise in Sentinel-1 GRD products that is able to overcome the existing limitations. To evaluate the performance of the method, a detailed numerical assessment was carried out, using, as a benchmark, the ‘Remove GRD Border Noise’ module integrated in ESA’s Sentinel Application Platform. The results showed that the proposed method is capable of very accurately removing the undesired noisy pixels from GRD images, regardless of their acquisition mode, polarization, or resolution and can cope with challenging features within the image scenes that typically affect other approaches.
Open AccessAn Operational Tool for the Automatic Detection and Removal of Border Noise in Sentinel-1 GRD Products
The presence of border noise in Sentinel-1 Ground Range Detected (GRD) products is an undesired processing artifact that limits their full exploitation in a number of applications. All of the Sentinel-1 GRD products generated before March 2018—more than 800,000—are affected by this particular type of noise. In March 2018, an official fix was deployed that solved the problem for a large portion of the newly generated products, but it did not cover the entire range of products, hence the need for an operational tool that is able to effectively and consistently remove border noise in an automated way. Currently, a few solutions have been proposed that try to address the problem, but all of them have limitations. The scope of this paper is therefore to present a new method based on mathematical morphology for the automatic detection and masking of border noise in Sentinel-1 GRD products that is able to overcome the existing limitations. To evaluate the performance of the method, a detailed numerical assessment was carried out, using, as a benchmark, the ‘Remove GRD Border Noise’ module integrated in ESA’s Sentinel Application Platform. The results showed that the proposed method is capable of very accurately removing the undesired noisy pixels from GRD images, regardless of their acquisition mode, polarization, or resolution and can cope with challenging features within the image scenes that typically affect other approaches.
- 1 November 2017
- Published by Elsevier in Journal of Science and Medicine in Sport
- Vol. 20, S44
When the hypoxia “silent killer” starts to talk: The early detection of pre-symptomatic hypoxia through voice stress analysis
- 1 November 2017
- Published by Elsevier in Journal of Science and Medicine in Sport
- Vol. 20, S44
When the hypoxia “silent killer” starts to talk: The early detection of pre-symptomatic hypoxia through voice stress analysis
- 1 April 2016
- Published by Oxford University Press (OUP) in SLEEP
- Vol. 39 (4) , 773-783
Exercise during Short-Term and Long-Term Continuous Exposure to Hypoxia Exacerbates Sleep-Related Periodic Breathing
S and full research articles published in SLEEP, the official journal of the APSS. Sleep and sleep disorder scientific findings.
- 1 April 2016
- Published by Oxford University Press (OUP) in SLEEP
- Vol. 39 (4) , 773-783
Exercise during Short-Term and Long-Term Continuous Exposure to Hypoxia Exacerbates Sleep-Related Periodic Breathing
S and full research articles published in SLEEP, the official journal of the APSS. Sleep and sleep disorder scientific findings.
- 14 October 2015
- Published by SPIE-Intl Soc Optical Eng
- Vol. 9638, 963803-963803-11
Assessment of the corrected CMOD6 GMF using scatterometer data
- 14 October 2015
- Published by SPIE-Intl Soc Optical Eng
- Vol. 9638, 963803-963803-11
Assessment of the corrected CMOD6 GMF using scatterometer data
- 1 May 2015
- Published by Elsevier in Biological Psychology
- Vol. 108, 132-141
Whose clock makes yours tick? How maternal cardiorespiratory physiology influences newborns’ heart rate variability
- 1 May 2015
- Published by Elsevier in Biological Psychology
- Vol. 108, 132-141
Whose clock makes yours tick? How maternal cardiorespiratory physiology influences newborns’ heart rate variability
- 1 May 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10975659,p. 0117-0122
Improved cross-range resolution in TOPSAR imaging using Sentinel-1A in bistatic operation
Wide-swath SAR imaging modes such as ScanSAR or TOPSAR offer synoptic observations of large-scale phenomena with a high revisit frequency at the expense of a degraded cross-range resolution. In the bistatic configuration using a SAR satellite as illuminator of opportunity and a ground-based stationary receiver close to the imaged area, this poor cross-range resolution can be improved in some favourable geometries by exploiting the sidelobe emissions of the beams illuminating the adjacent sub-swaths. This has been already demonstrated for ScanSAR mode while this paper analyzes in detail the TOPSAR mode based on measurements of ESA's recently launched satellite Sentinel-1A.
- 1 May 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10975659,p. 0117-0122
Improved cross-range resolution in TOPSAR imaging using Sentinel-1A in bistatic operation
Wide-swath SAR imaging modes such as ScanSAR or TOPSAR offer synoptic observations of large-scale phenomena with a high revisit frequency at the expense of a degraded cross-range resolution. In the bistatic configuration using a SAR satellite as illuminator of opportunity and a ground-based stationary receiver close to the imaged area, this poor cross-range resolution can be improved in some favourable geometries by exploiting the sidelobe emissions of the beams illuminating the adjacent sub-swaths. This has been already demonstrated for ScanSAR mode while this paper analyzes in detail the TOPSAR mode based on measurements of ESA's recently launched satellite Sentinel-1A.
- 1 April 2015
- Published by Aerospace Medical Association in Aerospace Medicine and Human Performance
- Vol. 86 (4) , 392-396
Altitude and Seasonality Impact on Sleep in Antarctica
BACKGROUND: This study investigates the effects of seasonality and altitude on sleep in extreme Antarctic conditions.METHODS: During summer and winter periods, 24 h of actimetric recordings were obtained at two different research stations, Dumont d’Urville (sea level altitude) and Concordia (corrected altitude 12,467 ft or 3800 m).RESULTS: During daytime, there were no altitude- or season-related differences in time spent at work, energy expenditure, or number of walking steps. During the nighttime however, total sleep time was longer (m = 427.4; SD = 42.4), sleep efficiency higher (m = 90; SD = 4.8), and wake after sleep onset shorter (m = 42.2; SD = 28.7) at sea level. Additionally, sleep fragmentation episodes and energy expenditure were higher during summer than winter periods.DISCUSSION: Our results show that dramatic variations in light exposure are not the only main factor affecting sleep quality in Antarctica, as altitude also markedly impacted sleep in these conditions. The effect of altitude-induced hypoxia should be taken into account in future investigations of sleep in extreme environments.Collet G, Mairesse O, Cortoos A, Tellez HF, Neyt X, Peigneux P, Macdonald-Nethercott E, Ducrot Y-M, Pattyn N. Altitude and seasonality impact on sleep in Antarctica. Aerosp Med Hum Perform. 2015; 86(4):392–396.
- 1 April 2015
- Published by Aerospace Medical Association in Aerospace Medicine and Human Performance
- Vol. 86 (4) , 392-396
Altitude and Seasonality Impact on Sleep in Antarctica
BACKGROUND: This study investigates the effects of seasonality and altitude on sleep in extreme Antarctic conditions.METHODS: During summer and winter periods, 24 h of actimetric recordings were obtained at two different research stations, Dumont d’Urville (sea level altitude) and Concordia (corrected altitude 12,467 ft or 3800 m).RESULTS: During daytime, there were no altitude- or season-related differences in time spent at work, energy expenditure, or number of walking steps. During the nighttime however, total sleep time was longer (m = 427.4; SD = 42.4), sleep efficiency higher (m = 90; SD = 4.8), and wake after sleep onset shorter (m = 42.2; SD = 28.7) at sea level. Additionally, sleep fragmentation episodes and energy expenditure were higher during summer than winter periods.DISCUSSION: Our results show that dramatic variations in light exposure are not the only main factor affecting sleep quality in Antarctica, as altitude also markedly impacted sleep in these conditions. The effect of altitude-induced hypoxia should be taken into account in future investigations of sleep in extreme environments.Collet G, Mairesse O, Cortoos A, Tellez HF, Neyt X, Peigneux P, Macdonald-Nethercott E, Ducrot Y-M, Pattyn N. Altitude and seasonality impact on sleep in Antarctica. Aerosp Med Hum Perform. 2015; 86(4):392–396.