About
46
Publications
10,117
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
127
Citations
Introduction
Xabier’s research focuses on the monitoring of natural hazards such as rockfalls or floods events using photogrammetric systems and advanced computer vision strategies. He has an active postdoctoral position in the Geosensor Systems Group at TU Dresden and is a collaborator of the RISKNAT group at the University of Barcelona
Current institution
Additional affiliations
May 2017 - March 2022
Education
May 2017 - July 2021
September 2014 - July 2015
September 2013 - July 2017
Publications
Publications (46)
The study presents a robust, automated camera gauge for long-term river water level monitoring operating in near real-time. The system employs artificial intelligence (AI) for the image-based segmentation of water bodies and the identification of ground control points (GCPs), combined with photogrammetric techniques, to determine water levels from...
This study presents a low-cost, multi-sensor monitoring setup for wadi discharge assessment. The system comprises a time-lapse camera gauge and a Raspberry Shake seismograph, both powered by solar energy and integrated with data transmission units for remote monitoring. Optical data, combined with a high-resolution digital terrain model generated v...
In this study, we present an approach to exploit the keypoint R-CNN network structure for automated detection of ground control points (GCPs) in images acquired by optical sensors. Our deep learning methodology employs fine-tuning on three distinct datasets, thereby enabling the specific addressing of inherent variations in GCP types, including sha...
The Virtual Geoscience Conference (VGC) provides a vital interdisciplinary platform for researchers in geoscience, geomatics, and related fields to exchange insights on the latest methodological advancements and applications. The conference brings together experts focused on the development and application of geomatic techniques—such as LiDAR, phot...
Active rock glaciers and landslides are critical indicators of permafrost dynamics in high mountain environments, reflecting the thermal state of permafrost and responding sensitively to climate change. Traditional monitoring methods, such as Global Navigation Satellite System (GNSS) measurements and permanent installations, face challenges in meas...
In Oman, the frequency of flash floods has significantly increased in recent years. This phenomenon is correlated with climate change, resulting in an intensification of the atmospheric water cycle. Consequently, a further escalation of flash floods can be anticipated in the future. In Oman, the issue of flash floods is exacerbated by the frequent...
Change-detection monitoring plays a crucial role in geoscience, facilitating the examination of earth surface processes and the mitigation of potential risks due to natural hazards. A significant aspect of this monitoring involves the use of images, enabling 2D to 4D monitoring approaches. Our objective is to bridge the knowledge gap in developing...
In this publication we address the lack of technical expertise in the geoscience community in the design and construction of photogrammetric systems for monitoring natural hazards at high spatio-temporal resolution. Accordingly, we provide in-depth information on the components, assembly instructions, and programming codes required to build them, m...
The 5th Virtual Geoscience Conference (VGC 2023) is a multidisciplinary forum for researchers in geoscience, geomatics and related disciplines to share their latest developments and applications.
The VGC series focuses on novel developments and applications of close range remote sensing methods within the broad field of geoscience research.
The V...
Change-detection monitoring plays a crucial role in the field of geoscience, enabling the study of various natural phenomena and, ultimately, the mitigation of their potential impacts. Currently, a significant part of this monitoring utilizes 3D models generated from images using structure-from-motion algorithms. However, the growing importance of...
In this publication we address the lack of knowledge in the design and construction of photogrammetric systems for high spatio-temporal resolution rockfall monitoring. Accordingly, we provide in-depth information on the components, assembly instructions, and programming codes required to build them, making them accessible to researchers from differ...
Obtaining real-time water level estimations is crucial for effective monitoring and response during emergencies caused by heavy rainfall and rapid flooding. Typically, this type of monitoring can be a difficult task, requiring river reach preparations and specialized equipment. Moreover, in extreme flood events, standard observation methods may bec...
In recent years, photogrammetric models have gained widespread use in geosciences due to their ability to reproduce natural surfaces. These models offer a cost-effective and user-friendly alternative to other systems, such as LiDAR, for creating 3D point clouds. On the other hand, rockfalls pose a significant risk to society, as they are the most c...
River Water Segmentation Dataset (RIWA)
New Version 2: It is the largest high quality (min size of 400x400) dataset as far as we know (01/2023).
The dataset called RIWA represents a pixel-wise binary river water segmentation. It consist of manually labelled smartphone, drone and DSLR images of rivers as well as suiting images of the Water Segment...
The purpose of this communication is to show the results obtained in a doctoral thesis based on the development of new algorithms and time-lapse photogrammetric systems for automatic rockfall monitoring that were tested on two active slopes in different geographical environments.
On the one hand, a very cost-efficient photogrammetric system using R...
Image-based methods for water level estimation facilitate the development of a low-cost river surveillance network in a quick and remote approach compared to most conventional water stage monitoring techniques. The densification of the observation network aims for an improved flood warning and management. Images can be obtained by means of cameras...
The handling of natural disasters, especially heavy rainfall and corresponding floods, requires special demands on emergency services. The need to obtain a quick, efficient and real-time estimation of the water level is critical for monitoring a flood event. This is a challenging task and usually requires specially prepared river sections. In addit...
The handling of natural disasters, especially heavy rainfall and corresponding floods, requires special demands on emergency services. The need to obtain a quick, efficient and real-time estimation of the water level is critical for monitoring a flood event. This is a challenging task and usually requires specially prepared river sections. In addit...
The importance of optical measurement methods in hydrology is increasing in the last years. In contrast to conventional gauging techniques, they can be applied remotely, making the measurement safe for humans and equipment, even under difficult measurement conditions. One important hydrological parameter to measure is discharge. Deriving discharge...
In recent years, photogrammetric models have become a widely used tool in the field of geosciences thanks to their ability to reproduce natural surfaces. As an alternative to other systems such as LiDAR (Light Detection and Ranging), photogrammetry makes it possible to obtain 3D points clouds at a lower cost and with a lower learning curve.
This c...
Monitoring the evolution of natural slopes with 3D data is a key strategy for detecting and investigating rockfalls (Abellan et al, 2016). In order to improve our understanding of rock slope failures and to reduce the associated risk, different monitoring strategies have been developed during the last decade using LiDAR, allowing the study of the s...
Using photogrammetric techniques for 3D modelling of natural surfaces has increased significantly in recent years (Eltner, et al. 2016). The easiness of obtaining photographs in an automated way, as well as the low cost of the whole photogrammetric system ensures a great usability when compared to LiDAR point clouds. Currently, there are different...
Photogrammetric models have become a standard tool for the study of surfaces, structures and natural elements. As an alternative to Light Detection and Ranging (LiDAR), photogrammetry allows 3D point clouds to be obtained at a much lower cost. This paper presents an enhanced workflow for image-based 3D reconstruction of high-resolution models desig...
The emerging use of photogrammetric point clouds in three-dimensional (3D) monitoring processes has revealed some constraints with respect to the use of LiDAR point clouds. Oftentimes, point clouds (PC) obtained by time-lapse photogrammetry have lower density and precision, especially when Ground Control Points (GCPs) are not available or the camer...
Monitoring rock slope failures in natural environments using LiDAR has considerably increased our understanding of rockfall phenomena during the last decade, but the economic and logistic costs associated with the instrument and data acquisition has considerably limited our ability to increase the frequency of monitoring campaigns, especially in re...
Monitoring rock slope failures in natural environments using LiDAR has considerably increased our understanding of rockfall phenomena during the last decade, but the economic and logistic costs associated with the instrument and data acquisition has considerably limited our ability to increase the frequency of monitoring campaigns, especially in re...
INTRODUCTION Nowadays, seismic measurements are used to quantitatively characterize mass movements (rockfalls, debris flows, snow avalanches, etc.). The parameters involved in this characterization are the equivalent (earthquake) magnitude, the energy transferred to the ground and the energy efficiency (potential energy to seismic energy ratio) amo...
RISKNAT is a Consolidated Research Group acknowledged by the Government of Catalonia (Generalitat de Catalunya). It was born in 2001, originally named Research Group on Surficial Geodynamic Processes. It is currently formed by 17 researchers (11 PhDs, 5 pre-docs and 1 technician), affiliated to the Departament de Dinàmica de la Terra i de l’Oceà (F...
Este trabajo presenta el análisis de los desprendimientos que se producen en el escarpe del deslizamiento de Puigcercós (Pallars Jussà-Lleida) a partir de datos LiDAR. El escarpe se ha escaneado periódicamente desde 2007 pudiendo detectar un total de 4072 desprendimientos. El análisis de los desprendimientos detectados ha permitido obtener la relac...
El macizo de Montserrat es una de las zonas turísticas más visitadas de Cataluña debido al peculiar relieve de sus cimas, a su cercanía con la ciudad de Barcelona y a la presencia de monasterios religiosos. Pero a su vez, también forman parte del macizo de Montserrat las inestabilidades de laderas y las avenidas torrenciales que han dañado en varia...
Poster for the field triep of the 6th Interdisciplinary Workshop on Rockfall Protection
After 10 years of monitoring using terrestrial LiDAR data in the Montserrat massif (NE Spain), detailed information about rockfall source zones and pre-failure movements is acquired. The study comprises a detailed joint analysis (revealing the existence of at least 5 joint sets) and an exhaustive rockfall inventory (with volumes greater than 0.0001...
This field trip has been devised as the closure of this sixth edition of the RocExs workshop, on the Wednesday May 24th. According to the purposes of this interdisciplinary meeting, most of the suggested topics for the workshop are tried to be present during the field trip: Rockfall characterization, inventory and mapping; testing and modeling; haz...
The village of Puigcercós (∼50 inhabitants) is located in the region of Pallars Jussà (Lleida) in Catalonia, several km south of the town of Tremp. In 1881 the entire village had to be moved from its historical location on top of the hill to its current location. This was caused by a series of landslides caused by continuing rainfall. The most impo...
Khazaradze, G., Vasquez, S., López, R., Guinau, G., Calvet, J., Vilaplana, J. M., … Suriñach, E. (2017). Fracture and slope stability monitoring at Puigcercós landslide (Catalonia, Spain). Geophysical Research Abstracts, 19(16599). Retrieved from http://meetingorganizer.copernicus.org/EGU2017/EGU2017-16599.pdf
The emphasis of this research is on characterizing rockfall source areas by analyzing 3D discontinuity sets identified from TLS data, in order to describe the mechanisms and possible features and volumes of potential rockfalls. This work is developed in the Montserrat Massif located about 50 Km north-west of Barcelona (Spain). The study site includ...
Presentación de la comunicación del IX Congreso geológico de España
The main escarpment of the Puigcercos landslide (Pallars Jussà, Catalonia) has recurrent rockfall activity. These events have been detected from the multitemporal comparison of point clouds obtained with a terrestrial LiDAR (TLS). To carry out the study 28 scans of the escarpment have been performed from September 2007 to March 2015 (2733 days of m...
The Mountain of Montserrat is one of the most visited tourist areas of Catalonia. Strong episodes of natural risks that have been produced over time have repeatedly damaged the infrastructures of access and some service buildings. For this reason, the mountain has always been on focus for the study of geological hazards with the intention of mitiga...
This paper presents an analysis of the rockfalls that take place in a scarp and they are detected using a LiDAR. The pilot study area, which is located at the Puigcercós cliff (Pallars Jussà), has been scanned since 2007, with these scans we managed to detect 4072 rockfalls. In addition with these detected rockfalls we obtained the relationship bet...
