Centre dedocumentation
scientifique

Development and evaluation of a deep learning model for real-time ground vehicle semantic segmentation from UAV-based thermal infrared imagery / Mehdi Khoshboresh Masouleh in ISPRS Journal of photogrammetry and remote sensing, vol 155 (September 2019)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 155 (September 2019) . - pp 172 - 186 Titre : Development and evaluation of a deep learning model for real-time ground vehicle semantic segmentation from UAV-based thermal infrared imagery Type de document : Article/Communication Auteurs : Mehdi Khoshboresh Masouleh, Auteur ; Reza Shah-Hosseini, Auteur Année de publication : 2019 Article en page(s) : pp 172 - 186 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] détection d'objet [Termes descripteurs IGN] image de drone [Termes descripteurs IGN] image RVB [Termes descripteurs IGN] image thermique [Termes descripteurs IGN] segmentation d'image [Termes descripteurs IGN] segmentation sémantique [Termes descripteurs IGN] véhicule automobile Résumé : (Auteur) Real-time unmanned aerial vehicles (UAVs)-based thermal infrared images processing, due to high spatial resolution and knowledge of the various infrared radiant energy level distribution of solid bodies, has important applications such as monitoring and control of the various phenomena in different natural situations. One of these applications is monitoring the ground vehicles in cities by using detection or semantic segmentation of them in the thermal images. In this research, our purpose is to improve the performance of deep learning combined model by using Gaussian-Bernoulli Restricted Boltzmann Machine (GB-RBM) specifications for the segmentation of the ground vehicles from UAV-based thermal infrared imagery. The proposed model is studied in three steps. First, designing the proposed model by using an encoder-decoder structure and addition of extracted features from convolutional layers and restricted Boltzmann machine in the network. Second, the implementation of the research goals on four sets of UAV-based thermal infrared imagery named NPU_CS_UAV_IR_DATA that was collected from some streets of China by using FLIR TAU2 thermal infrared sensor in 2017. Finally, analyzing the performance of the proposed model by using five state-of-the-art models in semantic segmentation. The results evaluated the performance of the proposed model as a robust model with the average precision and average processing time of approximately 0.97, and 19.73 s for all datasets, respectively. Numéro de notice : A2019-315 Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.isprsjprs.2019.07.009 date de publication en ligne : 25/07/2019 En ligne : https://doi.org/10.1016/j.isprsjprs.2019.07.009 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93341 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2019091	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2019093	DEP-RECP	Revue	MATIS	Dépôt en unité	Exclu du prêt
081-2019092	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Patch-based detection of dynamic objects in CrowdCam images / Gagan Kanojia in The Visual Computer, vol 35 n° 4 (April 2019)  

Public [article]  inThe Visual Computer > vol 35 n° 4 (April 2019) . - pp 521 - 534 Titre : Patch-based detection of dynamic objects in CrowdCam images Type de document : Article/Communication Auteurs : Gagan Kanojia, Auteur ; Shanmuganathan Raman, Auteur Année de publication : 2019 Article en page(s) : pp 521 - 534 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Photogrammétrie numérique [Termes descripteurs IGN] compréhension de l'image [Termes descripteurs IGN] détection d'objet [Termes descripteurs IGN] géométrie épipolaire [Termes descripteurs IGN] objet mobile [Termes descripteurs IGN] objet statique Résumé : (auteur) A scene can be divided into two parts: static and dynamic. The parts of the scene which do not admit any motion are static regions, while moving objects correspond to dynamic regions. In this work, we tackle the challenging task of identifying dynamic objects present in the CrowdCam images. Our approach exploits the coherency present in the natural images and utilizes the epipolar geometry present between a pair of images to achieve this objective. It does not require a dynamic object to be present in all the given images. We show that the proposed approach obtains state-of-the-art accuracy on standard datasets. Numéro de notice : A2019-120 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s00371-018-1480-3 date de publication en ligne : 06/02/2018 En ligne : https://link.springer.com/article/10.1007/s00371-018-1480-3 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92442 [article]

Vehicle detection in aerial images / Michael Ying Yang in Photogrammetric Engineering & Remote Sensing, PERS, vol 85 n° 4 (avril 2019)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 85 n° 4 (avril 2019) . - pp 297 - 304 Titre : Vehicle detection in aerial images Type de document : Article/Communication Auteurs : Michael Ying Yang, Auteur ; Wentong Liao, Auteur ; Xinbo Li, Auteur ; et al., Auteur Année de publication : 2019 Article en page(s) : pp 297 - 304 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] compréhension de l'image [Termes descripteurs IGN] détection d'objet [Termes descripteurs IGN] entropie [Termes descripteurs IGN] image aérienne [Termes descripteurs IGN] orthoimage [Termes descripteurs IGN] précision de la classification [Termes descripteurs IGN] qualité d'image [Termes descripteurs IGN] réseau neuronal convolutif [Termes descripteurs IGN] véhicule automobile Résumé : (Auteur) The detection of vehicles in aerial images is widely applied in many applications. Comparing with object detection in the ground view images, vehicle detection in aerial images remains a challenging problem because of small vehicle size and the complex background. In this paper, we propose a novel double focal loss convolutional neural network (DFL-CNN) framework. In the proposed framework, the skip connection is used in the CNN structure to enhance the feature learning. Also, the focal loss function is used to substitute for conventional cross entropy loss function in both of the region proposal network (RPN) and the final classifier. We further introduce the first large-scale vehicle detection dataset ITCVD with ground truth annotations for all the vehicles in the scene. We demonstrate the performance of our model on the existing benchmark German Aerospace Center (DLR) 3K dataset as well as the ITCVD dataset. The experimental results show that our DFL-CNN outperforms the baselines on vehicle detection. Numéro de notice : A2019-163 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.14358/PERS.85.4.297 date de publication en ligne : 01/04/2019 En ligne : https://doi.org/10.14358/PERS.85.4.297 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92568 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
105-2019041	SL	Revue	Centre de documentation	Revues en salle	Disponible

An image-pyramid-based raster-to-vector conversion (IPBRTVC) framework for consecutive-scale cartography and synchronized generalization of classic objects / Chang Li in Photogrammetric Engineering & Remote Sensing, PERS, vol 85 n° 3 (March 2019)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 85 n° 3 (March 2019) . - pp 169 - 178 Titre : An image-pyramid-based raster-to-vector conversion (IPBRTVC) framework for consecutive-scale cartography and synchronized generalization of classic objects Type de document : Article/Communication Auteurs : Chang Li, Auteur ; Xiaojuan Liu, Auteur ; Lu Wei, Auteur Année de publication : 2019 Article en page(s) : pp 169 - 178 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] chaîne de traitement [Termes descripteurs IGN] contrôle qualité [Termes descripteurs IGN] détection d'objet [Termes descripteurs IGN] image DMSP-OLS [Termes descripteurs IGN] image Landsat-8 [Termes descripteurs IGN] vectorisation Résumé : (Auteur) There are some key problems in raster-to-vector conversion and cartographic generalization, which include (1) deficient automation and low accuracy in the traditional raster-to-vector conversion processing; (2) data-source inconsistency in cartographic generation, i.e., different raster data sources converted to vector; and (3) how to acquire arbitrary-scale vector data. To solve these problems, we initially propose an innovative image-pyramid-based raster-to-vector conversion (IPBRTVC) framework with quality control for consecutive-scale cartography and synchronized generalization, of which details can be modified accordingly under the IPBRTVC framework. Landsat-8 imagery and Defense Meteorological Satellite Program (DMSP)/Operational Linescan System (OLS) night-time light imagery are used as a test dataset to extract classic objects in the geometry level. Experimental results show that the IPBRTVC framework not only solves the aforementioned problems well but also (1) improves efficiency of data processing by avoiding problems of corresponding features matching and topology errors, (2) contributes to develop relevant parallel computing system, and (3) helps to integrate the raster-to-vector conversion and consecutive-scale cartography. Numéro de notice : A2019-146 Thématique : GEOMATIQUE/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.14358/PERS.85.3.169 date de publication en ligne : 01/03/2019 En ligne : https://doi.org/10.14358/PERS.85.3.169 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92474 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
105-2019031	SL	Revue	Centre de documentation	Revues en salle	Disponible

Semantic understanding of scenes through the ADE20K dataset / Bolei Zhou in International journal of computer vision, vol 127 n° 3 (March 2019)  

Public [article]  inInternational journal of computer vision > vol 127 n° 3 (March 2019) . - pp 302 - 321 Titre : Semantic understanding of scenes through the ADE20K dataset Type de document : Article/Communication Auteurs : Bolei Zhou, Auteur ; Hang Zhao, Auteur ; Xavier Puig, Auteur ; Tete Xiao, Auteur ; Sanja Fidler, Auteur ; et al., Auteur Année de publication : 2019 Article en page(s) : pp 302 - 321 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] compréhension de l'image [Termes descripteurs IGN] détection d'objet [Termes descripteurs IGN] jeu de données localisées [Termes descripteurs IGN] réseau neuronal artificiel [Termes descripteurs IGN] scène [Termes descripteurs IGN] segmentation sémantique Résumé : (Auteur) Semantic understanding of visual scenes is one of the holy grails of computer vision. Despite efforts of the community in data collection, there are still few image datasets covering a wide range of scenes and object categories with pixel-wise annotations for scene understanding. In this work, we present a densely annotated dataset ADE20K, which spans diverse annotations of scenes, objects, parts of objects, and in some cases even parts of parts. Totally there are 25k images of the complex everyday scenes containing a variety of objects in their natural spatial context. On average there are 19.5 instances and 10.5 object classes per image. Based on ADE20K, we construct benchmarks for scene parsing and instance segmentation. We provide baseline performances on both of the benchmarks and re-implement state-of-the-art models for open source. We further evaluate the effect of synchronized batch normalization and find that a reasonably large batch size is crucial for the semantic segmentation performance. We show that the networks trained on ADE20K are able to segment a wide variety of scenes and objects. Numéro de notice : A2018-602 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s11263-018-1140-0 date de publication en ligne : 07/12/2018 En ligne : https://doi.org/10.1007/s11263-018-1140-0 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92529 [article]

Détection et localisation d'objets 3D par apprentissage profond en topologie capteur / Pierre Biasutti (2019)    

Permalink

Robust vehicle detection in aerial images using bag-of-words and orientation aware scanning / Hailing Zhou in IEEE Transactions on geoscience and remote sensing, vol 56 n° 12 (December 2018)  

Permalink

Multi-scale object detection in remote sensing imagery with convolutional neural networks / Zhipeng Deng in ISPRS Journal of photogrammetry and remote sensing, vol 145 - part A (November 2018)  

Permalink

Automated extraction of 3D vector topographic feature line from terrain point cloud / Wei Zhou in Geocarto international, vol 33 n° 10 (October 2018)  

Permalink

Novel fusion approach on automatic object extraction from spatial data: case study Worldview-2 and TOPO5000 / Umut G. Sefercik in Geocarto international, vol 33 n° 10 (October 2018)  

Permalink

Augmented reality meets computer vision : efficient data generation for urban driving scenes / Hassan Abu Alhaija in International journal of computer vision, vol 126 n° 9 (September 2018)  

Permalink

Adaptive correlation filters with long-term and short-term memory for object tracking / Chao Ma in International journal of computer vision, vol 126 n° 8 (August 2018)  

Permalink

A light and faster regional convolutional neural network for object detection in optical remote sensing images / Peng Ding in ISPRS Journal of photogrammetry and remote sensing, vol 141 (July 2018)  

Permalink

Predicting foreground object ambiguity and efficiently crowdsourcing the segmentation(s) / Danna Gurari in International journal of computer vision, vol 126 n° 7 (July 2018)  

Permalink

Application of deep learning for object detection / Ajeet Ram Pathak in Procedia Computer Science, vol 132 (2018)  

Permalink