Centre dedocumentation
scientifique

Automated terrain feature identification from remote sensing imagery: a deep learning approach / Wenwen Li in International journal of geographical information science IJGIS, vol 34 n° 4 (April 2020)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 34 n° 4 (April 2020) . - pp 637 - 660 Titre : Automated terrain feature identification from remote sensing imagery: a deep learning approach Type de document : Article/Communication Auteurs : Wenwen Li, Auteur ; Chia-Yu Hsu, Auteur Année de publication : 2020 Article en page(s) : pp 637 - 660 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes descripteurs IGN] analyse d'image orientée objet [Termes descripteurs IGN] analyse du paysage [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] base de données d'images [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] compréhension de l'image [Termes descripteurs IGN] détection automatique [Termes descripteurs IGN] détection d'objet [Termes descripteurs IGN] extraction de traits caractéristiques [Termes descripteurs IGN] intelligence artificielle Résumé : (auteur) Terrain feature detection is a fundamental task in terrain analysis and landscape scene interpretation. Discovering where a specific feature (i.e. sand dune, crater, etc.) is located and how it evolves over time is essential for understanding landform processes and their impacts on the environment, ecosystem, and human population. Traditional induction-based approaches are challenged by their inefficiency for generalizing diverse and complex terrain features as well as their performance for scalable processing of the massive geospatial data available. This paper presents a new deep learning (DL) approach to support automatic detection of terrain features from remotely sensed images. The novelty of this work lies in: (1) a terrain feature database containing 12,000 remotely sensed images (1,000 original images and 11,000 derived images from data augmentation) that supports data-driven model training and new discovery; (2) a DL-based object detection network empowered by ensemble learning and deep and deeper convolutional neural networks to achieve high-accuracy object detection; and (3) fine-tuning the model’s characteristics and behaviors to identify the best combination of hyperparameters and other network factors. The introduction of DL into geospatial applications is expected to contribute significantly to intelligent terrain analysis, landscape scene interpretation, and the maturation of spatial data science. Numéro de notice : A2020-108 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2018.1542697 date de publication en ligne : 07/11/2018 En ligne : https://doi.org/10.1080/13658816.2018.1542697 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94708 [article]

Geocoding of trees from street addresses and street-level images / Daniel Laumer in ISPRS Journal of photogrammetry and remote sensing, vol 162 (April 2020)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 162 (April 2020) . - pp 125 - 136 Titre : Geocoding of trees from street addresses and street-level images Type de document : Article/Communication Auteurs : Daniel Laumer, Auteur ; Nico Lang, Auteur ; Natalie Van Doorn, Auteur Année de publication : 2020 Article en page(s) : pp 125 - 136 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes descripteurs IGN] analyse des correspondances [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] arbre urbain [Termes descripteurs IGN] Californie (Etats-Unis) [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] détection d'arbres [Termes descripteurs IGN] détection d'objet [Termes descripteurs IGN] géocodage par adresse postale [Termes descripteurs IGN] image panoramique [Termes descripteurs IGN] image Streetview [Termes descripteurs IGN] inventaire [Termes descripteurs IGN] service écosystémique [Termes descripteurs IGN] zone urbaine Résumé : (auteur) We introduce an approach for updating older tree inventories with geographic coordinates using street-level panorama images and a global optimization framework for tree instance matching. Geolocations of trees in inventories until the early 2000s where recorded using street addresses whereas newer inventories use GPS. Our method retrofits older inventories with geographic coordinates to allow connecting them with newer inventories to facilitate long-term studies on tree mortality etc. What makes this problem challenging is the different number of trees per street address, the heterogeneous appearance of different tree instances in the images, ambiguous tree positions if viewed from multiple images and occlusions. To solve this assignment problem, we (i) detect trees in Google street-view panoramas using deep learning, (ii) combine multi-view detections per tree into a single representation, (iii) and match detected trees with given trees per street address with a global optimization approach. Experiments for trees in 5 cities in California, USA, show that we are able to assign geographic coordinates to 38% of the street trees, which is a good starting point for long-term studies on the ecosystem services value of street trees at large scale. Numéro de notice : A2020-124 Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2020.02.001 date de publication en ligne : 21/02/2020 En ligne : https://doi.org/10.1016/j.isprsjprs.2020.02.001 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94749 [article]

The application of bidirectional reflectance distribution function data to recognize the spatial heterogeneity of mixed pixels in vegetation remote sensing: a simulation study / Yanan Yan in Photogrammetric Engineering & Remote Sensing, PERS, vol 86 n° 3 (March 2020)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 86 n° 3 (March 2020) . - pp 161 - 167 Titre : The application of bidirectional reflectance distribution function data to recognize the spatial heterogeneity of mixed pixels in vegetation remote sensing: a simulation study Type de document : Article/Communication Auteurs : Yanan Yan, Auteur ; Lei Deng, Auteur ; L. Xian-Lin, Auteur Année de publication : 2020 Article en page(s) : pp 161 - 167 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes descripteurs IGN] agrégation spatiale [Termes descripteurs IGN] anisotropie [Termes descripteurs IGN] approche pixel [Termes descripteurs IGN] bande spectrale [Termes descripteurs IGN] détection d'objet [Termes descripteurs IGN] dispersion [Termes descripteurs IGN] distribution du coefficient de réflexion bidirectionnelle BRDF [Termes descripteurs IGN] distribution spatiale [Termes descripteurs IGN] extraction de la végétation [Termes descripteurs IGN] hétérogénéité spatiale [Termes descripteurs IGN] modèle de simulation [Termes descripteurs IGN] modèle de transfert radiatif [Termes descripteurs IGN] réflectance [Termes descripteurs IGN] régression linéaire [Termes descripteurs IGN] télédétection Résumé : (auteur) Spectral decomposition of mixed pixels can provide information about the abundance of end members but fails to indicate the spatial distribution of end members in vegetation remote sensing. This work is a significant attempt to use the bidirectional reflectance distribution function (BRDF) characteristics of mixed pixels in the prediction of spatial-heterogeneity metrics. Data sets from this function with different spatial distributions were constructed by the discrete anisotropic radiative transfer model, and three spatial aggregation and dispersion metrics were calculated: percentage of like adjacencies, spatial division index, and aggregation index. A simple linear regression method was used to construct the prediction model of spatial aggregation and dispersion metrics. The potential of multiangle remote sensing model for identifying spatial patterns well was demonstrated, and its importance was found to differ for different spatial aggregation and dispersion metrics. Specifically, the precision of the model based on multiangle reflectance used for predicting the spatial division index could meet a minimum root mean square of 5.95%. The reflectance features from backward observation on the principal plane play the leading role in recognizing the spatial heterogeneity of mixed pixels. The prediction model is sufficiently robust to distinguish the same vegetation with different growth trends, but also performs well when the ground objects have a smaller reflectance difference in the mixed pixels in a certain band. This study is expected to offer a new thought for spatial-heterogeneity identification of ground objects and thus promote the development of remote sensing technology in assessing spatial distribution. Numéro de notice : A2020-146 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.14358/PERS.86.3.161 date de publication en ligne : 01/03/2020 En ligne : https://doi.org/10.14358/PERS.86.3.161 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94775 [article]

Context-aware convolutional neural network for object detection in VHR remote sensing imagery / Yiping Gong in IEEE Transactions on geoscience and remote sensing, vol 58 n° 1 (January 2020)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 58 n° 1 (January 2020) . - pp 34 - 44 Titre : Context-aware convolutional neural network for object detection in VHR remote sensing imagery Type de document : Article/Communication Auteurs : Yiping Gong, Auteur ; Zhifeng Xiao, Auteur ; Xiaowei Tan, Auteur Année de publication : 2020 Article en page(s) : pp 34 - 44 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] analyse contextuelle [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] description multiniveau [Termes descripteurs IGN] détection d'objet [Termes descripteurs IGN] extraction de traits caractéristiques [Termes descripteurs IGN] image à très haute résolution [Termes descripteurs IGN] vision par ordinateur [Termes descripteurs IGN] zone d'intérêt Résumé : (auteur) Object detection in very-high-resolution (VHR) remote sensing imagery remains a challenge. Environmental factors, such as illumination intensity and weather, reduce image quality, resulting in poor feature representation and limited detection accuracy. To enrich the feature representation and mine the underlying context information among objects, this article proposes a context-aware convolutional neural network (CA-CNN) model for object detection that includes proposal generation, context feature extraction, feature fusion, and classification. During feature extraction, we propose integrating a context-regions-of-interests (Context-RoIs) mining layer into the CNN model and extracting context features by mapping Context-RoIs mined from the foreground proposals to multilevel feature maps. Finally, the context features extracted from multilevel layers are fused into a single layer, and the proposals represented by the fused features are classified by a softmax classifier. In this article, through numerous experiments, we thoroughly explore the influence of key factors, such as Context-RoIs, different feature scales, and different spatial context window sizes. Because of the end-to-end network design approach, our proposed model simultaneously maintains high efficiency and effectiveness. We conducted all model testing on the public NWPU VHR-10 data set. The experimental results demonstrate that our proposed CA-CNN model achieves significantly improved model performance and better detection results compared with the state-of-the-art methods. Numéro de notice : A2020-038 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2019.2930246 date de publication en ligne : 23/09/2019 En ligne : http://doi.org/10.1109/TGRS.2019.2930246 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94492 [article]

Half a percent of labels is enough: efficient animal detection in UAV imagery using deep CNNs and active learning / Benjamin Kellenberger in IEEE Transactions on geoscience and remote sensing, vol 57 n° 12 (December 2019)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 57 n° 12 (December 2019) . - pp 9524 - 9533 Titre : Half a percent of labels is enough: efficient animal detection in UAV imagery using deep CNNs and active learning Type de document : Article/Communication Auteurs : Benjamin Kellenberger, Auteur ; Diego Marcos, Auteur ; Sylvain Lobry, Auteur ; Devis Tuia, Auteur Année de publication : 2019 Article en page(s) : pp 9524 - 9533 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] analyse d'image orientée objet [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] cible mobile [Termes descripteurs IGN] classification orientée objet [Termes descripteurs IGN] classification par réseau neuronal [Termes descripteurs IGN] détection d'objet [Termes descripteurs IGN] données localisées [Termes descripteurs IGN] échantillonnage de données [Termes descripteurs IGN] faune locale [Termes descripteurs IGN] image de drone [Termes descripteurs IGN] Namibie [Termes descripteurs IGN] réalité de terrain [Termes descripteurs IGN] recensement Résumé : (auteur) We present an Active Learning (AL) strategy for reusing a deep Convolutional Neural Network (CNN)-based object detector on a new data set. This is of particular interest for wildlife conservation: given a set of images acquired with an Unmanned Aerial Vehicle (UAV) and manually labeled ground truth, our goal is to train an animal detector that can be reused for repeated acquisitions, e.g., in follow-up years. Domain shifts between data sets typically prevent such a direct model application. We thus propose to bridge this gap using AL and introduce a new criterion called Transfer Sampling (TS). TS uses Optimal Transport (OT) to find corresponding regions between the source and the target data sets in the space of CNN activations. The CNN scores in the source data set are used to rank the samples according to their likelihood of being animals, and this ranking is transferred to the target data set. Unlike conventional AL criteria that exploit model uncertainty, TS focuses on very confident samples, thus allowing quick retrieval of true positives in the target data set, where positives are typically extremely rare and difficult to find by visual inspection. We extend TS with a new window cropping strategy that further accelerates sample retrieval. Our experiments show that with both strategies combined, less than half a percent of oracle-provided labels are enough to find almost 80% of the animals in challenging sets of UAV images, beating all baselines by a margin. Numéro de notice : A2019-598 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2019.2927393 date de publication en ligne : 20/08/2019 En ligne : http://doi.org/10.1109/TGRS.2019.2927393 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94592 [article]

Sig-NMS-based faster R-CNN combining transfer learning for small target detection in VHR optical remote sensing imagery / Ruchan Dong in IEEE Transactions on geoscience and remote sensing, vol 57 n° 11 (November 2019)  

Permalink

Scene context-driven vehicle detection in high-resolution aerial images / Chao Tao in IEEE Transactions on geoscience and remote sensing, Vol 57 n° 10 (October 2019)  

Permalink

Traffic signal detection from in-vehicle GPS speed profiles using functional data analysis and machine learning / Yann Méneroux in International Journal of Data Science and Analytics JDSA, vol inconnu ([01/10/2019])  

Permalink

Partial linear NMF-based unmixing methods for detection and area estimation of photovoltaic panels in urban hyperspectral remote sensing data / Moussa Sofiane Karoui in Remote sensing, vol 11 n° 18 (September 2019)    

Permalink

Detecting and mapping traffic signs from Google Street View images using deep learning and GIS / Andrew Campbell in Computers, Environment and Urban Systems, vol 77 (september 2019)  

Permalink

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)  

Permalink

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

Permalink

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

Permalink

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)  

Permalink

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

Permalink