908 resultados para satellite imagery
Resumo:
Résumé Suite aux recentes avancées technologiques, les archives d'images digitales ont connu une croissance qualitative et quantitative sans précédent. Malgré les énormes possibilités qu'elles offrent, ces avancées posent de nouvelles questions quant au traitement des masses de données saisies. Cette question est à la base de cette Thèse: les problèmes de traitement d'information digitale à très haute résolution spatiale et/ou spectrale y sont considérés en recourant à des approches d'apprentissage statistique, les méthodes à noyau. Cette Thèse étudie des problèmes de classification d'images, c'est à dire de catégorisation de pixels en un nombre réduit de classes refletant les propriétés spectrales et contextuelles des objets qu'elles représentent. L'accent est mis sur l'efficience des algorithmes, ainsi que sur leur simplicité, de manière à augmenter leur potentiel d'implementation pour les utilisateurs. De plus, le défi de cette Thèse est de rester proche des problèmes concrets des utilisateurs d'images satellite sans pour autant perdre de vue l'intéret des méthodes proposées pour le milieu du machine learning dont elles sont issues. En ce sens, ce travail joue la carte de la transdisciplinarité en maintenant un lien fort entre les deux sciences dans tous les développements proposés. Quatre modèles sont proposés: le premier répond au problème de la haute dimensionalité et de la redondance des données par un modèle optimisant les performances en classification en s'adaptant aux particularités de l'image. Ceci est rendu possible par un système de ranking des variables (les bandes) qui est optimisé en même temps que le modèle de base: ce faisant, seules les variables importantes pour résoudre le problème sont utilisées par le classifieur. Le manque d'information étiquétée et l'incertitude quant à sa pertinence pour le problème sont à la source des deux modèles suivants, basés respectivement sur l'apprentissage actif et les méthodes semi-supervisées: le premier permet d'améliorer la qualité d'un ensemble d'entraînement par interaction directe entre l'utilisateur et la machine, alors que le deuxième utilise les pixels non étiquetés pour améliorer la description des données disponibles et la robustesse du modèle. Enfin, le dernier modèle proposé considère la question plus théorique de la structure entre les outputs: l'intègration de cette source d'information, jusqu'à présent jamais considérée en télédétection, ouvre des nouveaux défis de recherche. Advanced kernel methods for remote sensing image classification Devis Tuia Institut de Géomatique et d'Analyse du Risque September 2009 Abstract The technical developments in recent years have brought the quantity and quality of digital information to an unprecedented level, as enormous archives of satellite images are available to the users. However, even if these advances open more and more possibilities in the use of digital imagery, they also rise several problems of storage and treatment. The latter is considered in this Thesis: the processing of very high spatial and spectral resolution images is treated with approaches based on data-driven algorithms relying on kernel methods. In particular, the problem of image classification, i.e. the categorization of the image's pixels into a reduced number of classes reflecting spectral and contextual properties, is studied through the different models presented. The accent is put on algorithmic efficiency and the simplicity of the approaches proposed, to avoid too complex models that would not be used by users. The major challenge of the Thesis is to remain close to concrete remote sensing problems, without losing the methodological interest from the machine learning viewpoint: in this sense, this work aims at building a bridge between the machine learning and remote sensing communities and all the models proposed have been developed keeping in mind the need for such a synergy. Four models are proposed: first, an adaptive model learning the relevant image features has been proposed to solve the problem of high dimensionality and collinearity of the image features. This model provides automatically an accurate classifier and a ranking of the relevance of the single features. The scarcity and unreliability of labeled. information were the common root of the second and third models proposed: when confronted to such problems, the user can either construct the labeled set iteratively by direct interaction with the machine or use the unlabeled data to increase robustness and quality of the description of data. Both solutions have been explored resulting into two methodological contributions, based respectively on active learning and semisupervised learning. Finally, the more theoretical issue of structured outputs has been considered in the last model, which, by integrating outputs similarity into a model, opens new challenges and opportunities for remote sensing image processing.
Resumo:
The processing of human bodies is important in social life and for the recognition of another person's actions, moods, and intentions. Recent neuroimaging studies on mental imagery of human body parts suggest that the left hemisphere is dominant in body processing. However, studies on mental imagery of full human bodies reported stronger right hemisphere or bilateral activations. Here, we measured functional magnetic resonance imaging during mental imagery of bilateral partial (upper) and full bodies. Results show that, independently of whether a full or upper body is processed, the right hemisphere (temporo-parietal cortex, anterior parietal cortex, premotor cortex, bilateral superior parietal cortex) is mainly involved in mental imagery of full or partial human bodies. However, distinct activations were found in extrastriate cortex for partial bodies (right fusiform face area) and full bodies (left extrastriate body area). We propose that a common brain network, mainly on the right side, is involved in the mental imagery of human bodies, while two distinct brain areas in extrastriate cortex code for mental imagery of full and upper bodies.
Resumo:
PURPOSE: This descriptive article illustrates the application of Global Positioning System (GPS) professional receivers in the field of locomotion studies. The technological challenge was to assess the external mechanical work in outdoor walking. METHODS: Five subjects walked five times during 5 min on an athletic track at different imposed stride frequency (from 70-130 steps x min(-1)). A differential GPS system (carrier phase analysis) measured the variation of the position of the trunk at 5 Hz. A portable indirect calorimeter recorded breath-by-breath energy expenditure. RESULTS: For a walking speed of 1.05 +/- 0.11 m x s(-1), the vertical lift of the trunk (43 +/- 14 mm) induced a power of 46.0 +/- 20.4 W. The average speed variation per step (0.15 +/- 0.03 m x s(-1)) produced a kinetic power of 16.9 +/- 7.2 W. As compared with commonly admitted values, the energy exchange (recovery) between the two energy components was low (39.1 +/- 10.0%), which induced an overestimated mechanical power (38.9 +/- 18.3 W or 0.60 W x kg(-1) body mass) and a high net mechanical efficiency (26.9 +/- 5.8%). CONCLUSION: We assumed that the cause of the overestimation was an unwanted oscillation of the GPS antenna. It is concluded that GPS (in phase mode) is now able to record small body movements during human locomotion, and constitutes a promising tool for gait analysis of outdoor unrestrained walking. However, the design of the receiver and the antenna must be adapted to human experiments and a thorough validation study remains to be conducted.
Resumo:
The report describes the state of the art video equipment used and experiences gained from the 6,800 mile field test. The first objective of this project was to determine if laser disc equipment could capture and store usable roadway images while operating in a mobile environment. The second objective was to evaluate methods of using optical disc storage and retrieval features to enhance highway planning and design function. Several highway departments have attempted to use video technology to replace the traditional 16 and 35 mm film format used in photologging. These attempts have met with limited success because of the distortion caused by video technology not being capable of dealing with highway speeds. The distortion has caused many highway signs to be unreadable and, therefore, clients have labeled the technology unusable. Two methods of using optical laser disc storage and retrieval have been successfully demonstrated by Wisconsin and Connecticut Departments of Transportation. Each method provides instantaneous retrieval and linking of images with other information. However, both methods gather the images using 35 mm film techniques. The 35 mm film image is then transferred to laser disc. Eliminating the film conversion to laser disc has potential for saving $4 to $5 per logging mile. In addition to a cost savings, the image would be available immediately as opposed to delays caused by film developing and transferring to laser disc. In June and November of 1986 Iowa DOT staff and cooperating equipment suppliers demonstrated the concept of direct image capture. The results from these tests were promising and an FHWA Demonstration program established. Since 1986 technology advancements have been incorporated into the design that further improve the image quality originally demonstrated.
Resumo:
Activity monitors based on accelerometry are used to predict the speed and energy cost of walking at 0% slope, but not at other inclinations. Parallel measurements of body accelerations and altitude variation were studied to determine whether walking speed prediction could be improved. Fourteen subjects walked twice along a 1.3 km circuit with substantial slope variations (-17% to +17%). The parameters recorded were body acceleration using a uni-axial accelerometer, altitude variation using differential barometry, and walking speed using satellite positioning (DGPS). Linear regressions were calculated between acceleration and walking speed, and between acceleration/altitude and walking speed. These predictive models, calculated using the data from the first circuit run, were used to predict speed during the second circuit. Finally the predicted velocity was compared with the measured one. The result was that acceleration alone failed to predict speed (mean r = 0.4). Adding altitude variation improved the prediction (mean r = 0.7). With regard to the altitude/acceleration-speed relationship, substantial inter-individual variation was found. It is concluded that accelerometry, combined with altitude measurement, can assess position variations of humans provided inter-individual variation is taken into account. It is also confirmed that DGPS can be used for outdoor walking speed measurements, opening up new perspectives in the field of biomechanics.
Resumo:
We investigate the relevance of morphological operators for the classification of land use in urban scenes using submetric panchromatic imagery. A support vector machine is used for the classification. Six types of filters have been employed: opening and closing, opening and closing by reconstruction, and opening and closing top hat. The type and scale of the filters are discussed, and a feature selection algorithm called recursive feature elimination is applied to decrease the dimensionality of the input data. The analysis performed on two QuickBird panchromatic images showed that simple opening and closing operators are the most relevant for classification at such a high spatial resolution. Moreover, mixed sets combining simple and reconstruction filters provided the best performance. Tests performed on both images, having areas characterized by different architectural styles, yielded similar results for both feature selection and classification accuracy, suggesting the generalization of the feature sets highlighted.
Resumo:
Abstract
Resumo:
Land use/cover classification is one of the most important applications in remote sensing. However, mapping accurate land use/cover spatial distribution is a challenge, particularly in moist tropical regions, due to the complex biophysical environment and limitations of remote sensing data per se. This paper reviews experiments related to land use/cover classification in the Brazilian Amazon for a decade. Through comprehensive analysis of the classification results, it is concluded that spatial information inherent in remote sensing data plays an essential role in improving land use/cover classification. Incorporation of suitable textural images into multispectral bands and use of segmentation‑based method are valuable ways to improve land use/cover classification, especially for high spatial resolution images. Data fusion of multi‑resolution images within optical sensor data is vital for visual interpretation, but may not improve classification performance. In contrast, integration of optical and radar data did improve classification performance when the proper data fusion method was used. Among the classification algorithms available, the maximum likelihood classifier is still an important method for providing reasonably good accuracy, but nonparametric algorithms, such as classification tree analysis, have the potential to provide better results. However, they often require more time to achieve parametric optimization. Proper use of hierarchical‑based methods is fundamental for developing accurate land use/cover classification, mainly from historical remotely sensed data.
Resumo:
Abstract
Resumo:
The main objective of this study was todo a statistical analysis of ecological type from optical satellite data, using Tipping's sparse Bayesian algorithm. This thesis uses "the Relevence Vector Machine" algorithm in ecological classification betweenforestland and wetland. Further this bi-classification technique was used to do classification of many other different species of trees and produces hierarchical classification of entire subclasses given as a target class. Also, we carried out an attempt to use airborne image of same forest area. Combining it with image analysis, using different image processing operation, we tried to extract good features and later used them to perform classification of forestland and wetland.
Resumo:
Menestyäkseen nykymaailmassa ihmiset ovat turvautuneet toisiinsa muodostaen samallaerilaisia yhteisöjä ja verkostoja. Näille yhteisöille on tunnusomaista, että niissä vaikuttavien jäsenien ajatustavat yhtyvät keskenään. Yhteisöissä syntyy uusia ideoita ja keksintöjä. Niiden välittäminen maailmalle on usein kuitenkin ongelmallista. Digitaalisuus, Internet ja monet muut uudet teknologiat tuovat yhden ratkaisun ongelmaan. Eräs uuden teknologian mahdollistama kanava on yhteisötelevisio, jonka kautta yhteisön viestintää voidaan tehokkaasti välittää. Yhteisöilläei kuitenkaan ole teknistä taitoa toteuttaa tällaista palvelua. Yhteisöille, kuten pk-yrityksille, kouluille, seuroille, yhdistyksille ja jopa yksittäisille ihmisille, tuleekin pystyä tarjoamaan valmis konsepti, joka on helposti heidän käytettävissään. Tämä diplomityö toimii teknisenä pohjana Finnish Satellite Television Oy:n yhteisö-tv -palvelukonseptille, joka tullaan ottamaan laajamittaiseen käyttöön vuoden 2007 aikana. Työssä käydään läpi yhteisön ja yhteisöllisyyden tunnusmerkit ja peruspiirteet, luodaan katsaus yhteisötelevision alkutaipaleisiin, nykytilaan ja sen eri ratkaisuihin. Lisäksi tutustutaan yhteisö-tv:n kansainvälisiin ja kotimaisiin kokeiluihin ja pilottiprojekteihin. Työn teknisessä osassa tutkitaan yhteisötelevision mahdollistaviin teknologioihin, siirtoteihin sekä digitaalisiin tuotantojärjestelmiin. Lopuksi työssä kootaan yhteen käytettävyydeltään, liikutettavuudeltaan ja kustannustehokkuudeltaan sopivimmat tekniset toteutusvaihtoehdot konseptin käyttöönottoa varten.
Resumo:
This project proposes a preliminary architectural design for a control and data processing center, also known as 'ground segment', for Earth observation satellites.
Resumo:
Peroxisome proliferator-activated receptor β/δ (PPARβ/δ) is a ubiquitously expressed gene with higher levels observed in skeletal muscle. Recently, our laboratory showed (Bonala S, Lokireddy S, Arigela H, Teng S, Wahli W, Sharma M, McFarlane C, Kambadur R. J Biol Chem 287: 12935-12951, 2012) that PPARβ/δ modulates myostatin activity to induce myogenesis in skeletal muscle. In the present study, we show that PPARβ/δ-null mice display reduced body weight, skeletal muscle weight, and myofiber atrophy during postnatal development. In addition, a significant reduction in satellite cell number was observed in PPARβ/δ-null mice, suggesting a role for PPARβ/δ in muscle regeneration. To investigate this, tibialis anterior muscles were injured with notexin, and muscle regeneration was monitored on days 3, 5, 7, and 28 postinjury. Immunohistochemical analysis revealed an increased inflammatory response and reduced myoblast proliferation in regenerating muscle from PPARβ/δ-null mice. Histological analysis confirmed that the regenerated muscle fibers of PPARβ/δ-null mice maintained an atrophy phenotype with reduced numbers of centrally placed nuclei. Even though satellite cell numbers were reduced before injury, satellite cell self-renewal was found to be unaffected in PPARβ/δ-null mice after regeneration. Previously, our laboratory had showed (Bonala S, Lokireddy S, Arigela H, Teng S, Wahli W, Sharma M, McFarlane C, Kambadur R. J Biol Chem 287: 12935-12951, 2012) that inactivation of PPARβ/δ increases myostatin signaling and inhibits myogenesis. Our results here indeed confirm that inactivation of myostatin signaling rescues the atrophy phenotype and improves muscle fiber cross-sectional area in both uninjured and regenerated tibialis anterior muscle from PPARβ/δ-null mice. Taken together, these data suggest that absence of PPARβ/δ leads to loss of satellite cells, impaired skeletal muscle regeneration, and postnatal myogenesis. Furthermore, our results also demonstrate that functional antagonism of myostatin has utility in rescuing these effects.