Centre dedocumentation
scientifique

Active and incremental learning for semantic ALS point cloud segmentation / Yaping Lin in ISPRS Journal of photogrammetry and remote sensing, vol 169 (November 2020)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 169 (November 2020) . - pp 73 - 92 Titre : Active and incremental learning for semantic ALS point cloud segmentation Type de document : Article/Communication Auteurs : Yaping Lin, Auteur ; M. George Vosselman, Auteur ; Yanpeng Cao, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 73 - 92 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] classification dirigée [Termes descripteurs IGN] données lidar [Termes descripteurs IGN] entropie [Termes descripteurs IGN] incertitude des données [Termes descripteurs IGN] itération [Termes descripteurs IGN] segmentation sémantique [Termes descripteurs IGN] semis de points Résumé : (auteur) Supervised training of a deep neural network for semantic segmentation of point clouds requires a large amount of labelled data. Nowadays, it is easy to acquire a huge number of points with high density in large-scale areas using current LiDAR and photogrammetric techniques. However it is extremely time-consuming to manually label point clouds for model training. In this paper, we propose an active and incremental learning strategy to iteratively query informative point cloud data for manual annotation and the model is continuously trained to adapt to the newly labelled samples in each iteration. We evaluate the data informativeness step by step and effectively and incrementally enrich the model knowledge. The data informativeness is estimated by two data dependent uncertainty metrics (point entropy and segment entropy) and one model dependent metric (mutual information). The proposed methods are tested on two datasets. The results indicate the proposed uncertainty metrics can enrich current model knowledge by selecting informative samples, such as considering points with difficult class labels and choosing target objects with various geometries in the labelled training pool. Compared to random selection, our metrics provide valuable information to significantly reduce the labelled training samples. In contrast with training from scratch, the incremental fine-tuning strategy significantly save the training time. Numéro de notice : A2020-638 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2020.09.003 date de publication en ligne : 14/09/2020 En ligne : https://doi.org/10.1016/j.isprsjprs.2020.09.003 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96061 [article]

A novel deep learning instance segmentation model for automated marine oil spill detection / Shamsudeen Temitope Yekeen in ISPRS Journal of photogrammetry and remote sensing, vol 167 (September 2020)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 167 (September 2020) . - pp 190 - 200 Titre : A novel deep learning instance segmentation model for automated marine oil spill detection Type de document : Article/Communication Auteurs : Shamsudeen Temitope Yekeen, Auteur ; Abdul‐Lateef Balogun, Auteur ; Khamaruzaman B. Wan Yusof, Auteur Année de publication : 2020 Article en page(s) : pp 190 - 200 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] détection automatique [Termes descripteurs IGN] extraction de traits caractéristiques [Termes descripteurs IGN] hydrocarbure [Termes descripteurs IGN] image radar moirée [Termes descripteurs IGN] marée noire [Termes descripteurs IGN] segmentation sémantique [Termes descripteurs IGN] vision par ordinateur [Termes descripteurs IGN] zone d'intérêt Résumé : (auteur) The visual similarity of oil slick and other elements, known as look-alike, affects the reliability of synthetic aperture radar (SAR) images for marine oil spill detection. So far, detection and discrimination of oil spill and look-alike are still limited to the use of traditional machine learning algorithms and semantic segmentation deep learning models with limited accuracy. Thus, this study developed a novel deep learning oil spill detection model using computer vision instance segmentation Mask-Region-based Convolutional Neural Network (Mask R-CNN) model. The model training was conducted using transfer learning on the ResNet 101 on COCO as backbone in combination with Feature Pyramid Network (FPN) architecture for feature extraction at 30 epochs with 0.001 learning rate. Testing of the model was conducted using the least training and validation loss value on the withheld testing images. The model’s performance was evaluated using precision, recall, specificity, IoU, F1-measure and overall accuracy values. Ship detection and segmentation had the highest performance with overall accuracy of 98.3%. The model equally showed a higher accuracy for oil spill and look-alike detection and segmentation although oil spill detection outperformed look-alike with overall accuracy values of 96.6% and 91.0% respectively. The study concluded that the deep learning instance segmentation model performs better than conventional machine learning models and deep learning semantic segmentation models in detection and segmentation. Numéro de notice : A2020-548 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2020.07.011 date de publication en ligne : 28/07/2020 En ligne : https://doi.org/10.1016/j.isprsjprs.2020.07.011 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95774 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2020091	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2020093	DEP-RECP	Revue	MATIS	Dépôt en unité	Exclu du prêt
081-2020092	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Vehicle detection of multi-source remote sensing data using active fine-tuning network / Xin Wu in ISPRS Journal of photogrammetry and remote sensing, vol 167 (September 2020)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 167 (September 2020) . - pp 39 - 53 Titre : Vehicle detection of multi-source remote sensing data using active fine-tuning network Type de document : Article/Communication Auteurs : Xin Wu, Auteur ; Wei Li, Auteur ; Danfeng Hong, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 39 - 53 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes descripteurs IGN] Allemagne [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] détection d'objet [Termes descripteurs IGN] données multisources [Termes descripteurs IGN] étiquette [Termes descripteurs IGN] image aérienne [Termes descripteurs IGN] modèle numérique de surface [Termes descripteurs IGN] modèle stéréoscopique [Termes descripteurs IGN] segmentation [Termes descripteurs IGN] segmentation sémantique [Termes descripteurs IGN] véhicule Résumé : (auteur) Vehicle detection in remote sensing images has attracted increasing interest in recent years. However, its detection ability is limited due to lack of well-annotated samples, especially in densely crowded scenes. Furthermore, since a list of remotely sensed data sources is available, efficient exploitation of useful information from multi-source data for better vehicle detection is challenging. To solve the above issues, a multi-source active fine-tuning vehicle detection (Ms-AFt) framework is proposed, which integrates transfer learning, segmentation, and active classification into a unified framework for auto-labeling and detection. The proposed Ms-AFt employs a fine-tuning network to firstly generate a vehicle training set from an unlabeled dataset. To cope with the diversity of vehicle categories, a multi-source based segmentation branch is then designed to construct additional candidate object sets. The separation of high quality vehicles is realized by a designed attentive classifications network. Finally, all three branches are combined to achieve vehicle detection. Extensive experimental results conducted on two open ISPRS benchmark datasets, namely the Vaihingen village and Potsdam city datasets, demonstrate the superiority and effectiveness of the proposed Ms-AFt for vehicle detection. In addition, the generalization ability of Ms-AFt in dense remote sensing scenes is further verified on stereo aerial imagery of a large camping site. Numéro de notice : A2020-546 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2020.06.016 date de publication en ligne : 13/07/2020 En ligne : https://doi.org/10.1016/j.isprsjprs.2020.06.016 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95772 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2020091	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2020093	DEP-RECP	Revue	MATIS	Dépôt en unité	Exclu du prêt
081-2020092	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Can SPOT-6/7 CNN semantic segmentation improve Sentinel-2 based land cover products? sensor assessment and fusion / Olivier Stocker in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, V-2 (August 2020)  

Public [article]  inISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences > V-2 (August 2020) . - pp 557 - 564 Titre : Can SPOT-6/7 CNN semantic segmentation improve Sentinel-2 based land cover products? sensor assessment and fusion Type de document : Article/Communication Auteurs : Olivier Stocker, Auteur ; Arnaud Le Bris , Auteur Congrès : Congrès: ISPRS 2020, virtual Congress Imaging today foreseeing tomorrow (31 aout - 2 septembre 2020; Nice, France) , Auteur Année de publication : 2020 Projets : MAESTRIA / Mallet, Clément Article en page(s) : pp 557 - 564 Note générale : bibliographie This work was done within the PARCELLE project funded by the French CNES TOSCA program and within the MAESTRIA project supported by the French National Research Agency under the grant ANR-18-CE23-0023. Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] fusion d'images [Termes descripteurs IGN] image Sentinel-MSI [Termes descripteurs IGN] image SPOT 7 [Termes descripteurs IGN] occupation du sol [Termes descripteurs IGN] segmentation sémantique Résumé : (auteur) Needs for fine-grained, accurate and up-to-date land cover (LC) data are important to answer both societal and scientific purposes. Several automatic products have already been proposed, but are mostly generated out of satellite sensors like Sentinel-2 (S2) or Landsat. Metric sensors, e.g. SPOT-6/7, have been less considered, while they enable (at least annual) acquisitions at country scale and can now be efficiently processed thanks to deep learning (DL) approaches. This study thus aimed at assessing whether such sensor can improve such land cover products. A custom simple yet effective U-net - Deconv-Net inspired DL architecture is developed and applied to SPOT-6/7 and S2 for different LC nomenclatures, aiming at comparing the relevance of their spatial/spectral configurations and investigating their complementarity. The proposed DL architecture is then extended to data fusion and applied to previous sensors. At the end, the proposed fusion framework is used to enrich an existing S2 based LC product, as it is generic enough to cope with fusion at distinct levels. Numéro de notice : A2020-504 Affiliation des auteurs : LaSTIG (2020- ) Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.5194/isprs-annals-V-2-2020-557-2020 date de publication en ligne : 03/08/2020 En ligne : https://doi.org/10.5194/isprs-annals-V-2-2020-557-2020 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95644 [article]

CNN semantic segmentation to retrieve past land cover out of historical orthoimages and DSM: first experiments / Arnaud Le Bris in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, V-2 (August 2020)  

Public [article]  inISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences > V-2 (August 2020) . - pp 1013 - 1019 Titre : CNN semantic segmentation to retrieve past land cover out of historical orthoimages and DSM: first experiments Type de document : Article/Communication Auteurs : Arnaud Le Bris , Auteur ; Sébastien Giordano , Auteur ; Clément Mallet , Auteur Congrès : Congrès: ISPRS 2020, virtual Congress Imaging today foreseeing tomorrow (31 aout - 2 septembre 2020; Nice, France) , Auteur Année de publication : 2020 Projets : HIATUS / Giordano, Sébastien Article en page(s) : pp 1013 - 1019 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] base de données historiques [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] image aérienne [Termes descripteurs IGN] modèle numérique de surface [Termes descripteurs IGN] occupation du sol [Termes descripteurs IGN] orthoimage [Termes descripteurs IGN] segmentation sémantique Résumé : (auteur) Images from archival aerial photogrammetric surveys are a unique and relatively unexplored means to chronicle 3D land-cover changes occurred since the mid 20th century. They provide a relatively dense temporal sampling of the territories with a very high spatial resolution. Thus, they offer time series data which can answer a large variety of long-term environmental monitoring studies. Besides, they are generally stereoscopic surveys, making it possible to derive 3D information (Digital Surface Models). In recent years, they have often been digitized, making them more suitable to be considered in automatic analyses processes. Some photogrammetric softwares make it possible to retrieve their geometry (pose and camera calibration) and to generate corresponding DSM and orthophotomosaic. Thus, archival aerial photogrammetric surveys appear as being a powerful remote sensing data source to study land use/cover evolution over the last century. However, several difficulties have to be faced to be able to use them in automatic analysis processes. Indeed, surveys available on a study area can exhibit very different characteristics: survey pattern, focal, spatial resolution, modality (panchromatic, colour, infrared…). Planimetric and altimetric accuracies of derived products strongly depend on these characteristics. Thus, analysis processes have to cope with these uncertainties. Another important gap states in the lack of training data. Deep learning methods and especially Convolutional Neural Networks (CNN) are at present the most efficient semantic segmentation methods as long as a sufficient training dataset is available. However, temporal gaps can be very important between existing available databases and archival data. In this study, two custom variants of simple yet effective U-net - Deconv-Net inspired DL architectures are developed to process ortho-image and DSM based information. They are then trained out of a groundtruth derived out of a recent database to process archival datasets. Numéro de notice : A2020-469 Affiliation des auteurs : LaSTIG (2020- ) Thématique : IMAGERIE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.5194/isprs-annals-V-2-2020-1013-2020 date de publication en ligne : 03/08/2020 En ligne : https://doi.org/10.5194/isprs-annals-V-2-2020-1013-2020 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95637 [article]

Unsupervised semantic and instance segmentation of forest point clouds / Di Wang in ISPRS Journal of photogrammetry and remote sensing, vol 165 (July 2020)  

Permalink

Counting of grapevine berries in images via semantic segmentation using convolutional neural networks / Laura Zabawa in ISPRS Journal of photogrammetry and remote sensing, vol 164 (June 2020)  

Permalink

A hybrid deep learning–based model for automatic car extraction from high-resolution airborne imagery / Mehdi Khoshboresh Masouleh in Applied geomatics, vol 12 n° 2 (June 2020)  

Permalink

Comparing the roles of landmark visual salience and semantic salience in visual guidance during indoor wayfinding / Weihua Dong in Cartography and Geographic Information Science, vol 47 n° 3 (May 2020)  

Permalink

Sea-land segmentation using deep learning techniques for Landsat-8 OLI imagery / Ting Yang in Marine geodesy, Vol 43 n° 2 (March 2020)  

Permalink

Application of machine learning techniques for evidential 3D perception, in the context of autonomous driving / Edouard Capellier (2020)  

Permalink

Cross-year multi-modal image retrieval using siamese networks / Margarita Khokhlova (2020)  

Permalink

Recherche multimodale d'images aériennes multi-date à l'aide d'un réseau siamois / Margarita Khokhlova (2020)    

Permalink

Remote sensing based building extraction / Mohammad Awrangjeb (2020)  

Permalink

Superpixel-enhanced deep neural forest for remote sensing image semantic segmentation / Li Mi in ISPRS Journal of photogrammetry and remote sensing, vol 159 (January 2020)  

Permalink