Centre dedocumentation
scientifique

Dépouillements

Robust multisource remote sensing image registration method based on scene shape similarity / Ming Hao in Photogrammetric Engineering & Remote Sensing, PERS, vol 85 n° 10 (October 2019)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 85 n° 10 (October 2019) . - pp 725 - 736 Titre : Robust multisource remote sensing image registration method based on scene shape similarity Type de document : Article/Communication Auteurs : Ming Hao, Auteur ; Jian Jin, Auteur ; Mengchao Zhou, Auteur ; et al., Auteur Année de publication : 2019 Article en page(s) : pp 725 - 736 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image mixte [Termes IGN] appariement de modèles conceptuels de données [Termes IGN] coefficient de corrélation [Termes IGN] figuré du terrain [Termes IGN] image multibande [Termes IGN] image radar moirée [Termes IGN] niveau de gris (image) [Termes IGN] points homologues [Termes IGN] superposition d'images [Termes IGN] temps de pose [Termes IGN] transformation linéaire Résumé : (Auteur) Image registration is an indispensable component of remote sensing applications, such as disaster monitoring, change detection, and classification. Grayscale differences and geometric distortions often occur among multisource images due to their different imaging mechanisms, thus making it difficult to acquire feature points and match corresponding points. This article proposes a scene shape similarity feature (SSSF) descriptor based on scene shape features and shape context algorithms. A new similarity measure called SSSFncc is then defined by computing the normalized correlation coefficient of the SSSF descriptors between multisource remote sensing images. Furthermore, the tie points between the reference and the sensed image are extracted via a template matching strategy. A global consistency check method is then used to remove the mismatched tie points. Finally, a piecewise linear transform model is selected to rectify the remote sensing image. The proposed SSSFncc aims to extract the scene shape similarity between multisource images. The accuracy of the proposed SSSFncc is evaluated using five pairs of experimental images from optical, synthetic aperture radar, and map data. Registration results demonstrate that the SSSFncc similarity measure is robust enough for complex nonlinear grayscale differences among multisource remote sensing images. The proposed method achieves more reliable registration outcomes compared with other popular methods. Numéro de notice : A2019-521 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.14358/PERS.85.10.725 Date de publication en ligne : 01/10/2019 En ligne : https://doi.org/10.14358/PERS.85.10.725 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93989 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
105-2019101	SL	Revue	Centre de documentation	Revues en salle	Disponible

Accurate detection of built-up areas from high-resolution remote sensing imagery using a fully convolutional network / Yihua Tan in Photogrammetric Engineering & Remote Sensing, PERS, vol 85 n° 10 (October 2019)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 85 n° 10 (October 2019) . - pp 737 - 752 Titre : Accurate detection of built-up areas from high-resolution remote sensing imagery using a fully convolutional network Type de document : Article/Communication Auteurs : Yihua Tan, Auteur ; Shengzhou Xiong, Auteur ; Zhi Li, Auteur ; et al., Auteur Année de publication : 2019 Article en page(s) : pp 737 - 752 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] détection du bâti [Termes IGN] extraction automatique [Termes IGN] extraction de traits caractéristiques [Termes IGN] image à haute résolution [Termes IGN] image Worldview [Termes IGN] segmentation sémantique Résumé : (Auteur) The analysis of built-up areas has always been a popular research topic for remote sensing applications. However, automatic extraction of built-up areas from a wide range of regions remains challenging. In this article, a fully convolutional network (FCN)–based strategy is proposed to address built-up area extraction. The proposed algorithm can be divided into two main steps. First, divide the remote sensing image into blocks and extract their deep features by a lightweight multi-branch convolutional neural network (LMB-CNN). Second, rearrange the deep features into feature maps that are fed into a well-designed FCN for image segmentation. Our FCN is integrated with multi-branch blocks and outputs multi-channel segmentation masks that are utilized to balance the false alarm and missing alarm. Experiments demonstrate that the overall classification accuracy of the proposed algorithm can achieve 98.75% in the test data set and that it has a faster processing compared with the existing state-of-the-art algorithms. Numéro de notice : A2019-522 Affiliation des auteurs : non IGN Thématique : IMAGERIE/URBANISME Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.14358/PERS.85.10.737 Date de publication en ligne : 01/10/2019 En ligne : https://doi.org/10.14358/PERS.85.10.737 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93992 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
105-2019101	SL	Revue	Centre de documentation	Revues en salle	Disponible

Postprocessing synchronization of a laser scanning system aboard a UAV / Marcela do Valle Machado in Photogrammetric Engineering & Remote Sensing, PERS, vol 85 n° 10 (October 2019)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 85 n° 10 (October 2019) . - pp 753 - 763 Titre : Postprocessing synchronization of a laser scanning system aboard a UAV Type de document : Article/Communication Auteurs : Marcela do Valle Machado, Auteur ; Antonio Maria Garcia Tommaselli, Auteur ; Fernanda Magri Torres, Auteur ; Mariana Batista Campos, Auteur Année de publication : 2019 Article en page(s) : pp 753 - 763 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] décalage d'horloge [Termes IGN] données altimétriques [Termes IGN] données lidar [Termes IGN] image captée par drone [Termes IGN] méthode des moindres carrés [Termes IGN] positionnement inertiel [Termes IGN] post-traitement [Termes IGN] précision altimétrique [Termes IGN] semis de points [Termes IGN] signal GNSS [Termes IGN] synchronisation [Termes IGN] télémétrie laser aéroporté [Termes IGN] trajectoire (véhicule non spatial) Résumé : (Auteur) Synchronization of airborne laser scanning devices is a critical process that directly affects data accuracy. This process can be more challenging with low-cost airborne laser scanning (ALS) systems because some device connections from off-the-shelf sensors are less stable. An alternative to synchronization is performing a postprocessing clock correction. This article presents a technique for postprocessing synchronization (off-line) that estimates clock differences based on the correlation between the signals from the global navigation satellite system (GNSS) trajectory and the light detection and ranging (lidar) range, followed by refinement with a least-squares method. The correlation between signals was automatically estimated considering the planned flight maneuvers, in a flat terrain, to produce altimetric trajectory variations. Experiments were performed with an Ibeo LUX laser unit integrated with a NovAtel SPAN-IGM-S1 inertial navigation system that was transported by an unmanned aerial vehicle (UAV). The planimetric and altimetric accuracies of the point cloud obtained with the proposed postprocessing synchronization technique were 28 cm and 10 cm, respectively, at a flight height of 35 m. Numéro de notice : A2019-523 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.14358/PERS.85.10.753 Date de publication en ligne : 01/10/2019 En ligne : https://doi.org/10.14358/PERS.85.10.753 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93994 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
105-2019101	SL	Revue	Centre de documentation	Revues en salle	Disponible

A CNN-based subpixel level DSM generation approach via single image super-resolution / Yongjun Zhang in Photogrammetric Engineering & Remote Sensing, PERS, vol 85 n° 10 (October 2019)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 85 n° 10 (October 2019) . - pp 765 - 775 Titre : A CNN-based subpixel level DSM generation approach via single image super-resolution Type de document : Article/Communication Auteurs : Yongjun Zhang, Auteur ; Zhi Zheng, Auteur ; Yimin Luo, Auteur ; et al., Auteur Année de publication : 2019 Article en page(s) : pp 765 - 775 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse de données [Termes IGN] appariement d'images [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] fusion de données multisource [Termes IGN] limite de résolution radiométrique [Termes IGN] modèle numérique de surface [Termes IGN] précision infrapixellaire [Termes IGN] reconstruction d'image Résumé : (Auteur) Previous work for subpixel level Digital Surface Model (DSM) generation mainly focused on data fusion techniques, which are extremely limited by the difficulty of multisource data acquisition. Although several DSM super resolution (SR) methods have been developed to ease the problem, a new issue that plenty of DSM samples are needed to train the model is raised. Therefore, considering the original images have vital influence on its DSM's accuracy, we address the problem by directly improving images resolution. Several SR models are refined and brought into the traditional DSM generation process as an image quality improvement stage to construct an easy but effective workflow for subpixel level DSM generation. Experiments verified the validity and significance of bringing SR technology into this kind of application. Statistical analysis also confirmed that a subpixel level DSM with higher fidelity can be obtained more easily compared to directly DSM interpolation. Numéro de notice : A2019-524 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.14358/PERS.85.10.765 Date de publication en ligne : 01/10/2019 En ligne : https://doi.org/10.14358/PERS.85.10.765 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93997 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
105-2019101	SL	Revue	Centre de documentation	Revues en salle	Disponible