Centre de documentation
scientifique

Evaluating interactive comparison techniques in a multiclass density map for visual crime analytics / Lukas Svicarovic (2021)  

Public Titre : Evaluating interactive comparison techniques in a multiclass density map for visual crime analytics Type de document : Article/Communication Auteurs : Lukas Svicarovic, Auteur ; Denis Parra, Auteur ; María-Jesús Lobo , Auteur Editeur : Genève : Eurographics Association Année de publication : 2021 Projets : 3-projet - voir note / Conférence : EuroVis 2021, 23rd edition of EG conference on visualisation 14/06/2021 18/06/2021 Zurich online Suisse OA short papers Proceedings Importance : pp 79 - 83 Note générale : bibliographie This work was funded by ANID - Millennium Science Initiative Program - Code ICN17_002 and by ANID, FONDECYT grant 1191791. Langues : Français (fre) Descripteur : [Termes IGN] analyse comparative [Termes IGN] analyse géovisuelle [Termes IGN] données localisées [Termes IGN] figuration de la densité [Termes IGN] infraction [Termes IGN] lentille magique [Termes IGN] superposition de données [Vedettes matières IGN] Géovisualisation Mots-clés libres : multiclass density map Résumé : (auteur) Techniques for presenting objects spatially via density maps have been thoroughly studied, but there is lack of research on how to display this information in the presence of several classes, i.e., multiclass density maps. Moreover, there is even less research on how to design an interactive visualization for comparison tasks on multiclass density maps. One application domain which requires this type of visualization for comparison tasks is crime analytics, and the lack of research in this area results in ineffective visual designs. To fill this gap, we study four types of techniques to compare multiclass density maps, using car theft data. The interactive techniques studied are swipe, translucent overlay, magic lens, and juxtaposition. The results of a user study (N=32) indicate that juxtaposition yields the worst performance to compare distributions, whereas swipe and magic lens perform the best in terms of time needed to complete the experiment. Our research provides empirical evidence on how to design interactive idioms for multiclass density spatial data, and it opens a line of research for other domains and visual tasks. Numéro de notice : C2021-072 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Thématique : GEOMATIQUE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.2312/evs.20211059 En ligne : https://doi.org/10.2312/evs.20211059 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99427

Initialization methods of convolutional neural networks for detection of image manipulations / Ivan Castillo Camacho (2021)  

Public Titre : Initialization methods of convolutional neural networks for detection of image manipulations Titre original : Méthodes d'initialisation des réseaux de neurones convolutifs pour la détection des manipulations d'images Type de document : Thèse/HDR Auteurs : Ivan Castillo Camacho, Auteur ; Kai Wang, Directeur de thèse Editeur : Grenoble [France] : Université Grenoble Alpes Année de publication : 2021 Importance : 145 p. Format : 21 x 30 cm Note générale : bibliographie Thèse pour obtenir le grade de Docteur de l'Université Grenoble, spécialité : signal, image, paroles, télécoms Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] altération [Termes IGN] apprentissage profond [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] covariance [Termes IGN] détection d'anomalie [Termes IGN] estompage [Termes IGN] filtre passe-haut [Termes IGN] flux de données [Termes IGN] infraction [Termes IGN] manipulation de données [Termes IGN] qualité des données [Termes IGN] retouche [Termes IGN] variance Index. décimale : THESE Thèses et HDR Résumé : (auteur) Fake images and videos have engulfed mass communication media. This is not something recent, manipulations and forgeries have occurred since the advent of photography itself. These alterations can go from innocent retouches in an attempt to make an image visually attractive to the spread of misleading information or even the use of false media in legal instances. Accordingly, the creation of methods that can help us assure the authenticity of an image presented as non-modified is of paramount importance. In this thesis, we aim at detecting image manipulation operations using deep learning techniques. We present three methods showing the progression of our work under one common objective, i.e, the design and test of Convolutional Neural Network (CNN) initialization methods for image forensic problems with a variance stability focus for the output of a CNN layer.First, we carry out an extensive review of the state of the art in deep-learning-based methods for image forensics. From this review we can confirm that the first layer of a CNN has big impact on the final performance. Specifically, the initialization used on the first-layer filters plays an important role that should be in line with the image forensic task in hand.As our first attempt to address this research problem, we propose a low-complexity initialization method for CNNs. Taking advantage of previous methods designed for the computer vision field, we extend the popular Xavier method to design a filter that would provide variance stability after a convolution operation. This method generates a set of random high-pass filters for the initialization of a CNN's first layer. These filters allow us to better identify forensic traces which usually lie towards the high-frequency part of the image.This first approach constitutes a good staring point of our work. However, a wrong assumption, largely utilized in the research community, was made. This is corrected in our second method where we follow a different data-dependent approach and take into consideration the real statistical properties of natural images. Accordingly, we propose a scaling method for first-layer filters which can cope well with different CNN initialization algorithms. The objective remains in keeping the stability of the variance of data flow in a CNN. We also present theoretical and experimental studies on the output variance for convolutional filter, which are the basis of our proposed data-dependent scaling.Next we describe a revisited version of our first proposal now with a corrected assumption on the statistics of natural images. More precisely, we propose an improved random high-pass initialization method which does not explicitly compute the statistics of input data. We believe that such a ``data-independent'' approach has higher flexibility and broader application range than our second method in situations where the computation of input statistics is not possible.Our proposed methods are tested over several image forensic problems and different CNN architectures.Finally, during all this thesis work we took part in a challenge competition of image forgery detection organized by the French National Research Agency and the French Directorate General of Armaments. We explain in the Appendix the objectives of the challenge along with a brief description of our work conducted for the competition. Note de contenu : 1- Introduction 2- Background knowledge and state of the art 3- Random high-pass initialization 4- Data-dependent initialization 5- Revisiting the random high-pass initialization 6- Conclusions and perspectives Numéro de notice : 28437 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse française Note de thèse : Thèse de Doctorat : signal, image, paroles, télécoms : Grenoble : 2021 DOI : sans En ligne : https://hal.science/tel-03346063/ Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98833

Modeling the risk of robbery in the city of Tshwane, South Africa / Nicolas Kemp in Cartography and Geographic Information Science, vol 48 n° 1 (January 2021)  

Public [article]  inCartography and Geographic Information Science > vol 48 n° 1 (January 2021) . - pp 29 - 42 Titre : Modeling the risk of robbery in the city of Tshwane, South Africa Type de document : Article/Communication Auteurs : Nicolas Kemp, Auteur ; Gregory D. Breetzke, Auteur ; Anthony K. Cooper, Auteur Année de publication : 2021 Article en page(s) : pp 29 - 42 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] Afrique du sud (état) [Termes IGN] criminalité [Termes IGN] modèle de simulation [Termes IGN] modélisation spatiale [Termes IGN] prévention des risques [Termes IGN] protection civile [Termes IGN] zone à risque Résumé : (auteur) In this study, we model the risk of robbery in the City of Tshwane in South Africa. We use the collective knowledge of two prominent spatial theories of crime (social disorganization theory, and crime pattern theory) to guide the selection of data and employ rudimentary geospatial techniques to create a crude model that identifies the risk of future robbery incidents in the city. The model is validated using actual robbery incidences recorded for the city. Overall the model performs reasonably well with approximately 70% of future robbery incidences accurately identified within a small subset of the overall model. Developing countries such as South Africa are in dire need of crime risk intensity models that are simple, and not data intensive to allocate scarce crime prevention resources in a more optimal fashion. It is anticipated that this model is a first step in this regard. Numéro de notice : A2021-017 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/15230406.2020.1814872 Date de publication en ligne : 10/09/2020 En ligne : https://doi.org/10.1080/15230406.2020.1814872 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96455 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
032-2021011	RAB	Revue	Centre de documentation	En réserve L003	Disponible

A spatio-temporal method for crime prediction using historical crime data and transitional zones identified from nightlight imagery / Bo Yang in International journal of geographical information science IJGIS, vol 34 n° 9 (September 2020)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 34 n° 9 (September 2020) . - pp 1740 - 1764 Titre : A spatio-temporal method for crime prediction using historical crime data and transitional zones identified from nightlight imagery Type de document : Article/Communication Auteurs : Bo Yang, Auteur ; Lin Liu, Auteur ; Minxuan Lan, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 1740 - 1764 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] coefficient de corrélation [Termes IGN] criminalité [Termes IGN] données spatiotemporelles [Termes IGN] géostatistique [Termes IGN] historique des données [Termes IGN] image NPP-VIIRS [Termes IGN] krigeage [Termes IGN] modèle dynamique [Termes IGN] nuit [Termes IGN] Ohio (Etats-Unis) [Termes IGN] prédiction [Termes IGN] prévention des risques [Termes IGN] prise de vue nocturne [Termes IGN] test statistique [Termes IGN] zone urbaine Résumé : (auteur) Accurate crime prediction can help allocate police resources for crime reduction and prevention. There are two popular approaches to predict criminal activities: one is based on historical crime, and the other is based on environmental variables correlated with criminal patterns. Previous research on geo-statistical modeling mainly considered one type of data in space-time domain, and few sought to blend multi-source data. In this research, we proposed a spatio-temporal Cokriging algorithm to integrate historical crime data and urban transitional zones for more accurate crime prediction. Time-series historical crime data were used as the primary variable, while urban transitional zones identified from the VIIRS nightlight imagery were used as the secondary co-variable. The algorithm has been applied to predict weekly-based street crime and hotspots in Cincinnati, Ohio. Statistical tests and Predictive Accuracy Index (PAI) and Predictive Efficiency Index (PEI) tests were used to validate predictions in comparison with those of the control group without using the co-variable. The validation results demonstrate that the proposed algorithm with historical crime data and urban transitional zones increased the correlation coefficient by 5.4% for weekdays and by 12.3% for weekends in statistical tests, and gained higher hit rates measured by PAI/PEI in the hotspots test. Numéro de notice : A2020-475 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2020.1737701 Date de publication en ligne : 13/03/2020 En ligne : https://doi.org/10.1080/13658816.2020.1737701 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95622 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
079-2020091	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Reestimating a minimum acceptable geocoding hit rate for conducting a spatial analysis / Alvaro Briz-Redon in International journal of geographical information science IJGIS, vol 34 n° 7 (July 2020)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 34 n° 7 (July 2020) . - pp 1283 - 1305 Titre : Reestimating a minimum acceptable geocoding hit rate for conducting a spatial analysis Type de document : Article/Communication Auteurs : Alvaro Briz-Redon, Auteur ; Francisco Martinez-Ruiz, Auteur ; Francisco Montes, Auteur Année de publication : 2020 Article en page(s) : pp 1283 - 1305 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] analyse de groupement [Termes IGN] appariement automatique [Termes IGN] criminalité [Termes IGN] géocodage [Termes IGN] géopositionnement [Termes IGN] infraction [Termes IGN] simulation [Termes IGN] taux d'échantillonnage Résumé : (auteur) Geocoding consists in converting a textual description of a location into coordinates. Hence, geocoding a dataset of events has to be carried out before performing a spatial analysis of some data. Automated procedures are necessary to geocode large datasets of events, but they can produce errors. Therefore, it is natural to ask oneself what is the minimum percentage of events that should be geocoded. An 85% of success was established 15 years ago as the first estimate of a minimum acceptable rate, becoming a reference for many spatial analysts. In this paper, the goal is reestimating a minimum acceptable geocoding match rate through the same procedure that was employed for computing the first estimate while accounting for some spatial factors that could possibly influence this estimation: intensity, clustering and aggregation levels. Several statistical techniques and the presence of nonrandomly distributed errors are also explored in this context. The results indicate that variations in intensity, clustering and aggregation levels lead to different minimum acceptable geocoding match rates. Furthermore, specific techniques such as cluster detection seem to be especially sensitive to the existence of non-geocoded data. Therefore, the highly approved 85% geocoding rate may need to be raised. Numéro de notice : A2020-303 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2019.1703994 Date de publication en ligne : 18/12/2019 En ligne : https://doi.org/10.1080/13658816.2019.1703994 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95143 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
079-2020071	RAB	Revue	Centre de documentation	En réserve L003	Disponible

A novel method of spatiotemporal dynamic geo-visualization of criminal data, applied to command and control centers for public safety / Mayra Salcedo-Gonzalez in ISPRS International journal of geo-information, vol 9 n° 3 (March 2020)  

Permalink

Placial analysis of events: a case study on criminological places / Sunghwan Cho in Cartography and Geographic Information Science, Vol 46 n° 6 (November 2019)  

Permalink

Attention les cybercriminels veulent utiliser vos serveurs / Xavier Fodor in SIGmag, n° 17 (juin 2018)

Permalink

Coopting cops with maps : the rhetorical power of cartography in modern policing / William Heiden in Cartographica, vol 53 n° 1 (Spring 2018)  

Permalink

Spatial Analysis, Modelling and Planning / Jorge Rocha (2018)  

Permalink

Localisation des caméras ANPR sur le réseau routier pour le profilage géographique / Marie Trotta in Revue internationale de géomatique, vol 27 n° 4 (octobre - décembre 2017)  

Permalink

Exploring spatiotemporal clusters based on extended kernel estimation methods / Jay Lee in International journal of geographical information science IJGIS, vol 31 n° 5-6 (May-June 2017)  

Permalink

Adaptive areal elimination (AAE): A transparent way of disclosing protected spatial datasets / Ourania Kounadi in Computers, Environment and Urban Systems, vol 57 (May 2016)  

Permalink

Cartographie policière : une analyse ethnographique / Françoise de Blomac in DécryptaGéo le mag, n° 175 (mars 2016)

Permalink

Crime data process in Waterloo region / Victor Brinon (2016) 

Permalink