Centre de documentation
scientifique

Beyond single receptive field: A receptive field fusion-and-stratification network for airborne laser scanning point cloud classification / Yongqiang Mao in ISPRS Journal of photogrammetry and remote sensing, vol 188 (June 2022)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 188 (June 2022) . - pp 45 - 61 Titre : Beyond single receptive field: A receptive field fusion-and-stratification network for airborne laser scanning point cloud classification Type de document : Article/Communication Auteurs : Yongqiang Mao, Auteur ; Kaiqiang chen, Auteur ; Wenhui Diao, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 45 - 61 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] apprentissage automatique [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] données laser [Termes IGN] données localisées 3D [Termes IGN] Perceptron multicouche [Termes IGN] représentation parcimonieuse [Termes IGN] réseau neuronal de graphes [Termes IGN] semis de points [Termes IGN] stratification de données [Termes IGN] voxel Résumé : (Auteur) The classification of airborne laser scanning (ALS) point clouds is a critical task of remote sensing and photogrammetry fields. Although recent deep learning-based methods have achieved satisfactory performance, they have ignored the unicity of the receptive field, which makes the ALS point cloud classification remain challenging for the distinguishment of the areas with complex structures and extreme scale variations. In this article, for the objective of configuring multi-receptive field features, we propose a novel receptive field fusion-and-stratification network (RFFS-Net). With a novel dilated graph convolution (DGConv) and its extension annular dilated convolution (ADConv) as basic building blocks, the receptive field fusion process is implemented with the dilated and annular graph fusion (DAGFusion) module, which obtains multi-receptive field feature representation through capturing dilated and annular graphs with various receptive regions. The stratification of the receptive fields with point sets of different resolutions as the calculation bases is performed with Multi-level Decoders nested in RFFS-Net and driven by the multi-level receptive field aggregation loss (MRFALoss) to drive the network to learn in the direction of the supervision labels with different resolutions. With receptive field fusion-and-stratification, RFFS-Net is more adaptable to the classification of regions with complex structures and extreme scale variations in large-scale ALS point clouds. Evaluated on the ISPRS Vaihingen 3D dataset, our RFFS-Net significantly outperforms the baseline (i.e. PointConv) approach by 5.3% on mF1 and 5.4% on mIoU, accomplishing an overall accuracy of 82.1%, an mF1 of 71.6%, and an mIoU of 58.2%. The experiments show that our RFFS-Net achieves a new state-of-the-art classification performance on powerline, car, and fence classes. Furthermore, experiments on the LASDU dataset and the 2019 IEEE-GRSS Data Fusion Contest dataset show that RFFS-Net achieves a new state-of-the-art classification performance. The code is available at github.com/WingkeungM/RFFS-Net. Numéro de notice : A2022-273 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2022.03.019 Date de publication en ligne : 07/04/2022 En ligne : https://doi.org/10.1016/j.isprsjprs.2022.03.019 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100532 [article]

Exemplaires(3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2022061	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2022063	DEP-RECP	Revue	LASTIG	Dépôt en unité	Exclu du prêt
081-2022062	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Invariant structure representation for remote sensing object detection based on graph modeling / Zicong Zhu in IEEE Transactions on geoscience and remote sensing, vol 60 n° 6 (June 2022)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 60 n° 6 (June 2022) . - n° 5625217 Titre : Invariant structure representation for remote sensing object detection based on graph modeling Type de document : Article/Communication Auteurs : Zicong Zhu, Auteur ; Xian Sun, Auteur ; Wenhui Diao, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 5625217 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] détection d'objet [Termes IGN] données d'entrainement sans étiquette [Termes IGN] extraction de traits caractéristiques [Termes IGN] filtrage numérique d'image [Termes IGN] granularité d'image [Termes IGN] graphe [Termes IGN] invariant Résumé : (auteur) Due to the characteristics of vertical orthophoto imaging, the apparent structural features of the object in the remote sensing (RS) image are relatively stable, such as the cross-shaped structure of the aircraft and the rectangular structure of the vehicle. Compared with the traditional visual features, using these features is conducive to improving the accuracy of object detection. However, there are few studies on such characteristics. In this article, we systematically study the invariant structural features of remote sensing objects and propose a graph focusing aggregation network (GFA-Net) to represent the structural features of remote sensing objects. Among them, in view of the problem that traditional convolutional neural networks (CNNs) are sensitive to the changes in rotation, scale, and other factors, which makes it difficult to extract structural features, we propose the graph focusing process (GFP) based on the idea of graph convolution. Analysis and experiments show that graph structure has significant advantages over Euclidean feature space under CNN in expressing such structural features. In order to realize the end-to-end efficient training of the above model, we design a graph aggregation network (GAN) to update the weight of nodes. We verify the effectiveness of our method on the proposed multitask datasets aircraft component segmentation dataset (ACSD) and the large-scale Fine-grAined object recognItion in high-Resolution RS imagery (FAIR1M). Experiments conducted on the object detection datasets of large-scale Dataset for Object deTection in Aerial images (DOTA) and HRSC2016 prove that the proposed method is superior to the current state-of-the-art (SOTA) method. Numéro de notice : A2022-560 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2022.3181686 Date de publication en ligne : 09/06/2022 En ligne : https://doi.org/10.1109/TGRS.2022.3181686 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101186 [article]