Centre de documentation
scientifique

Detection of growth change of young forest based on UAV RGB images at single-tree level / Xiaocheng Zhou in Forests, vol 14 n° 1 (January 2023)  

Public [article]  inForests > vol 14 n° 1 (January 2023) . - n° 141 Titre : Detection of growth change of young forest based on UAV RGB images at single-tree level Type de document : Article/Communication Auteurs : Xiaocheng Zhou, Auteur ; Hongyu Wang, Auteur ; Chongcheng Chen, Auteur ; et al., Auteur Année de publication : 2023 Article en page(s) : n° 141 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] Abies (genre) [Termes IGN] âge du peuplement forestier [Termes IGN] Chine [Termes IGN] croissance des arbres [Termes IGN] détection de changement [Termes IGN] hauteur des arbres [Termes IGN] image captée par drone [Termes IGN] image RVB [Termes IGN] jeune arbre [Termes IGN] modèle numérique de surface de la canopée [Termes IGN] surveillance forestière Résumé : (auteur) With the rapid development of Unmanned Aerial Vehicle (UAV) technology, more and more UAVs have been used in forest survey. UAV (RGB) images are the most widely used UAV data source in forest resource management. However, there is some uncertainty as to the reliability of these data when monitoring height and growth changes of low-growing saplings in an afforestation plot via UAV RGB images. This study focuses on an artificial Chinese fir (Cunninghamia lancelota, named as Chinese Fir) young forest plot in Fujian, China. Divide-and-conquer (DAC) and the local maximum (LM) method for extracting seedling height are described in the paper, and the possibility of monitoring young forest growth based on low-cost UAV remote sensing images was explored. Two key algorithms were adopted and compared to extract the tree height and how it affects the young forest at single-tree level from multi-temporal UAV RGB images from 2019 to 2021. Compared to field survey data, the R2 of single saplings’ height extracted from digital orthophoto map (DOM) images of tree pits and original DSM information using a divide-and-conquer method reached 0.8577 in 2020 and 0.9968 in 2021, respectively. The RMSE reached 0.2141 in 2020 and 0.1609 in 2021. The R2 of tree height extracted from the canopy height model (CHM) via the LM method was 0.9462. The RMSE was 0.3354 in 2021. The results demonstrated that the survival rates of the young forest in the second year and the third year were 99.9% and 85.6%, respectively. This study shows that UAV RGB images can obtain the height of low sapling trees through a computer algorithm based on using 3D point cloud data derived from high-precision UAV images and can monitor the growth of individual trees combined with multi-stage UAV RGB images after afforestation. This research provides a fully automated method for evaluating the afforestation results provided by UAV RGB images. In the future, the universality of the method should be evaluated in more afforestation plots featuring different tree species and terrain. Numéro de notice : A2023-115 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.3390/f14010141 Date de publication en ligne : 10/01/2023 En ligne : https://doi.org/10.3390/f14010141 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102482 [article]

Deep supervised and contractive neural network for SAR image classification / Jie Geng in IEEE Transactions on geoscience and remote sensing, vol 55 n° 4 (April 2017)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 55 n° 4 (April 2017) . - pp 2442 - 2459 Titre : Deep supervised and contractive neural network for SAR image classification Type de document : Article/Communication Auteurs : Jie Geng, Auteur ; Hongyu Wang, Auteur ; Jianchao Fan, Auteur ; Xiaorui Ma, Auteur Année de publication : 2017 Article en page(s) : pp 2442 - 2459 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes IGN] algorithme Graph-Cut [Termes IGN] analyse discriminante [Termes IGN] apprentissage profond [Termes IGN] classification par réseau neuronal [Termes IGN] extraction de traits caractéristiques [Termes IGN] filtre de déchatoiement [Termes IGN] filtre de Gabor [Termes IGN] image radar moirée [Termes IGN] matrice de co-occurrence [Termes IGN] niveau de gris (image) Résumé : (Auteur) The classification of a synthetic aperture radar (SAR) image is a significant yet challenging task, due to the presence of speckle noises and the absence of effective feature representation. Inspired by deep learning technology, a novel deep supervised and contractive neural network (DSCNN) for SAR image classification is proposed to overcome these problems. In order to extract spatial features, a multiscale patch-based feature extraction model that consists of gray level-gradient co-occurrence matrix, Gabor, and histogram of oriented gradient descriptors is developed to obtain primitive features from the SAR image. Then, to get discriminative representation of initial features, the DSCNN network that comprises four layers of supervised and contractive autoencoders is proposed to optimize features for classification. The supervised penalty of the DSCNN can capture the relevant information between features and labels, and the contractive restriction aims to enhance the locally invariant and robustness of the encoding representation. Consequently, the DSCNN is able to produce effective representation of sample features and provide superb predictions of the class labels. Moreover, to restrain the influence of speckle noises, a graph-cut-based spatial regularization is adopted after classification to suppress misclassified pixels and smooth the results. Experiments on three SAR data sets demonstrate that the proposed method is able to yield superior classification performance compared with some related approaches. Numéro de notice : A2017-176 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2016.2645226 En ligne : http://dx.doi.org/10.1109/TGRS.2016.2645226 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=84748 [article]

Semisupervised classification for hyperspectral image based on multi-decision labeling and deep feature learning / Xiaorui Ma in ISPRS Journal of photogrammetry and remote sensing, vol 120 (october 2016)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 120 (october 2016) . - pp 99 - 107 Titre : Semisupervised classification for hyperspectral image based on multi-decision labeling and deep feature learning Type de document : Article/Communication Auteurs : Xiaorui Ma, Auteur ; Hongyu Wang, Auteur ; Jie Wang, Auteur Année de publication : 2016 Article en page(s) : pp 99 - 107 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] apprentissage semi-dirigé [Termes IGN] classification par réseau neuronal [Termes IGN] classification semi-dirigée [Termes IGN] image hyperspectrale [Termes IGN] pondération Résumé : (Auteur) Semisupervised learning is widely used in hyperspectral image classification to deal with the limited training samples, however, some more information of hyperspectral image should be further explored. In this paper, a novel semisupervised classification based on multi-decision labeling and deep feature learning is presented to exploit and utilize as much information as possible to realize the classification task. First, the proposed method takes two decisions to pre-label each unlabeled sample: local decision based on weighted neighborhood information is made by the surrounding samples, and global decision based on deep learning is performed by the most similar training samples. Then, some unlabeled ones with high confidence are selected to extent the training set. Finally, self decision, which depends on the self features exploited by deep learning, is employed on the updated training set to extract spectral-spatial features and produce classification map. Experimental results with real data indicate that it is an effective and promising semisupervised classification method for hyperspectral image. Numéro de notice : A2016-797 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2016.09.001 En ligne : https://doi.org/10.1016/j.isprsjprs.2016.09.001 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=82532 [article]