Search results for "Geomatics"
showing 10 items of 495 documents
Image boundaries detection: from thresholding to implicit curve evolution
2014
The development of high dimensional large-scale imaging devices increases the need of fast, robust and accurate image segmentation methods. Due to its intrinsic advantages such as the ability to extract complex boundaries, while handling topological changes automatically, the level set method (LSM) has been widely used in boundaries detection. Nevertheless, their computational complexity limits their use for real time systems. Furthermore, most of the LSMs share the limit of leading very often to a local minimum, while the effectiveness of many computer vision applications depends on the whole image boundaries. In this paper, using the image thresholding and the implicit curve evolution fra…
Architecture-Driven Level Set Optimization: From Clustering to Sub-pixel Image Segmentation
2016
Thanks to their effectiveness, active contour models (ACMs) are of great interest for computer vision scientists. The level set methods (LSMs) refer to the class of geometric active contours. Comparing with the other ACMs, in addition to subpixel accuracy, it has the intrinsic ability to automatically handle topological changes. Nevertheless, the LSMs are computationally expensive. A solution for their time consumption problem can be hardware acceleration using some massively parallel devices such as graphics processing units (GPUs). But the question is: which accuracy can we reach while still maintaining an adequate algorithm to massively parallel architecture? In this paper, we attempt to…
Quantifying water stress effect on daily light use efficiency in Mediterranean ecosystems using satellite data
2016
16 pages, 2 figures, 6 tables, supplemental material https://dx.doi.org/10.1080/17538947.2016.1247301
Early assessment of crop yield from remotely sensed water stress and solar radiation data
2018
Soil moisture (SM) available for evapotranspiration is crucial for food security, given the significant interannual yield variability of rainfed crops in large agricultural regions. Also, incoming solar radiation (Rs) influences the photosynthetic rate of vegetated surfaces and can affect productivity. The aim of this work is to evaluate the ability of crop water stress and Rs remotely sensed data to forecast yield at regional scale. Temperature Vegetation Dryness Index (TVDI) was computed as an indicator of crop water stress and soil moisture availability. TVDI during critical growth stage of crops was calculated from MODIS products: MODIS/AQUA 8-day composite LST at 1 km and 16-day compos…
Towards the Operational Spatialization of the Single Band Thermal Atmospheric Correction. Application to Landsat 7 ETM+
2018
This work aims to improve the accuracy in Land Surface Temperature (LST) from single-channel thermal sensors by providing spatialized maps of transmittance, upwelling and downwelling atmospheric radiances required in the radiative transfer equation. Two different techniques are introduced for the estimation of pixel-by-pixel atmospheric parameters, focusing on the correction of Landsat Thermal Infrared (TIR) data. First technique is based on the linearization of the atmospheric parameters with the total column water vapor (W), extracted from the MOD05 product, whereas a second technique uses the Single Band Atmospheric Correction (SBAC) tool. Ground-measured values of LST in an agricultural…
Evolucion paleoambiental desde el Holoceno temprano hasta la actualidad del marjal de Almenara (Mediterráneo occidental)
2018
The main aim of this study is to characterize the different stages in the palaeoenvironmental evolution of the Almenara marsh, Spain, from the early Holocene to the present day. This marsh is one of the most important in Castellón province. Five cores extracted from the marsh underwent sedimentological analysis, micropalaeontological study (foraminifera, ostracods and gastropods) and 14C dating. The results show that before the maximum transgression of the Mediterranean during the Marine Isotope Stage 1 (5500 cal yr. BP dating in the Almenara marsh), the area was occupied by a brackish marsh (prior to the 8.2 ka event). During the middle Holocene, the regional sea level rise and later stabi…
Multitemporal Cloud Masking in the Google Earth Engine
2018
The exploitation of Earth observation satellite images acquired by optical instruments requires an automatic and accurate cloud detection. Multitemporal approaches to cloud detection are usually more powerful than their single scene counterparts since the presence of clouds varies greatly from one acquisition to another whereas surface can be assumed stationary in a broad sense. However, two practical limitations usually hamper their operational use: the access to the complete satellite image archive and the required computational power. This work presents a cloud detection and removal methodology implemented in the Google Earth Engine (GEE) cloud computing platform in order to meet these r…
MODIS probabilistic cloud masking over the Amazonian evergreen tropical forests: a comparison of machine learning-based methods
2019
Amazonian tropical forests play a significant role in global water, carbon and energy cycles. Satellite remote sensing is presented as a feasible means in order to monitor these forests. In particu...
Convolutional Neural Networks for Multispectral Image Cloud Masking
2020
Convolutional neural networks (CNN) have proven to be state of the art methods for many image classification tasks and their use is rapidly increasing in remote sensing problems. One of their major strengths is that, when enough data is available, CNN perform an end-to-end learning without the need of custom feature extraction methods. In this work, we study the use of different CNN architectures for cloud masking of Proba-V multispectral images. We compare such methods with the more classical machine learning approach based on feature extraction plus supervised classification. Experimental results suggest that CNN are a promising alternative for solving cloud masking problems.
Physics-Aware Gaussian Processes for Earth Observation
2017
Earth observation from satellite sensory data pose challenging problems, where machine learning is currently a key player. In recent years, Gaussian Process (GP) regression and other kernel methods have excelled in biophysical parameter estimation tasks from space. GP regression is based on solid Bayesian statistics, and generally yield efficient and accurate parameter estimates. However, GPs are typically used for inverse modeling based on concurrent observations and in situ measurements only. Very often a forward model encoding the well-understood physical relations is available though. In this work, we review three GP models that respect and learn the physics of the underlying processes …