Centre de documentation
scientifique

Efficient convolutional neural architecture search for LiDAR DSM classification / Aili Wang in IEEE Transactions on geoscience and remote sensing, vol 60 n° 5 (May 2022)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 60 n° 5 (May 2022) . - n° 5703317 Titre : Efficient convolutional neural architecture search for LiDAR DSM classification Type de document : Article/Communication Auteurs : Aili Wang, Auteur ; Dong Xue, Auteur ; Haibin Wu, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 5703317 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] attention (apprentissage automatique) [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] extraction de traits caractéristiques [Termes IGN] modèle de transfert radiatif [Termes IGN] modèle numérique de surface [Termes IGN] précision de la classification [Termes IGN] semis de points Résumé : (auteur) Light detection and ranging (LiDAR) data provide rich elevation information, so it plays an irreplaceable role in ground object classification. Recently, convolutional neural networks (CNNs) have shown excellent performance in LiDAR digital surface models (DSMs) classification. However, the architecture of CNN model relies heavily on manual design, so it has great limitations. In addition, different sensors capture LiDAR datasets with different properties, so the model should be designed to suit for different datasets, which further increases the workload of architecture design. Therefore, this article proposes a method of automatic design of LiDAR DSM classification model. First, attention mechanism is introduced into search space to improve the feature extraction capability of the model. Then, a gradient-based search strategy is used to obtain the optimal architecture from this search space. Second, a learning rate adjustment strategy is proposed to reduce the time spent in the search stage and evaluation stage to improve the classification accuracy of the model. Finally, a regularization scheme is introduced to enhance the robustness of the model and avoid overfitting. Experimental results on three public LiDAR datasets (Bayview Park, Recology, and Houston) obtained from different sensors show that the proposed neural architecture search method achieves the impressive classification performance compared to several state-of-the-art classification methods and improves the classification accuracy under the condition of limited training samples. Numéro de notice : A2022-408 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2022.3171520 Date de publication en ligne : 02/05/2022 En ligne : https://doi.org/10.1109/TGRS.2022.3171520 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100742 [article]