Centre dedocumentation
scientifique

3D target detection using dual domain attention and SIFT operator in indoor scenes / Hanshuo Zhao in The Visual Computer, vol 38 n° 11 (November 2022)  

Public [article]  inThe Visual Computer > vol 38 n° 11 (November 2022) . - pp3765 - 3774 Titre : 3D target detection using dual domain attention and SIFT operator in indoor scenes Type de document : Article/Communication Auteurs : Hanshuo Zhao, Auteur ; Dedong Yang, Auteur ; Jiankang Yu, Auteur Année de publication : 2022 Article en page(s) : pp3765 - 3774 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] attention (apprentissage automatique) [Termes IGN] détection d'objet [Termes IGN] détection de cible [Termes IGN] jeu de données [Termes IGN] objet 3D [Termes IGN] scène intérieure [Termes IGN] SIFT (algorithme) Résumé : (auteur) In a large number of real-life scenes and practical applications, 3D object detection is playing an increasingly important role. We need to estimate the position and direction of the 3D object in the real scene to complete the 3D object detection task. In this paper, we propose a new network architecture based on VoteNet to detect 3D point cloud targets. On the one hand, we use channel and spatial dual-domain attention module to enhance the features of the object to be detected while suppressing other useless features. On the other hand, the SIFT operator has scale invariance and the ability to resist occlusion and background interference. The PointSIFT module we use can capture information in different directions of point cloud in space, and is robust to shapes of different proportions, so as to better detect objects that are partially occluded. Our method is evaluated on the SUN-RGBD and ScanNet datasets of indoor scenes. The experimental results show that our method has better performance than VoteNet. Numéro de notice : A2022-840 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1007/s00371-021-02217-z Date de publication en ligne : 28/06/2021 En ligne : https://doi.org/10.1007/s00371-021-02217-z Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102042 [article]

Improving deep learning on point cloud by maximizing mutual information across layers / Di Wang in Pattern recognition, vol 131 (November 2022)  

Public [article]  inPattern recognition > vol 131 (November 2022) . - n° 108892 Titre : Improving deep learning on point cloud by maximizing mutual information across layers Type de document : Article/Communication Auteurs : Di Wang, Auteur ; Lulu Tang, Auteur ; Xu Wang, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 108892 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] détection d'objet [Termes IGN] entropie de Shannon [Termes IGN] information sémantique [Termes IGN] segmentation sémantique [Termes IGN] semis de points [Termes IGN] transformation géométrique [Termes IGN] vision par ordinateur [Termes IGN] visualisation 3D Résumé : (auteur) It is a fundamental and vital task to enhance the perception capability of the point cloud learning network in 3D machine vision applications. Most existing methods utilize feature fusion and geometric transformation to improve point cloud learning without paying enough attention to mining further intrinsic information across multiple network layers. Motivated to improve consistency between hierarchical features and strengthen the perception capability of the point cloud network, we propose exploring whether maximizing the mutual information (MI) across shallow and deep layers is beneficial to improve representation learning on point clouds. A novel design of Maximizing Mutual Information (MMI) Module is proposed, which assists the training process of the main network to capture discriminative features of the input point clouds. Specifically, the MMI-based loss function is employed to constrain the differences of semantic information in two hierarchical features extracted from the shallow and deep layers of the network. Extensive experiments show that our method is generally applicable to point cloud tasks, including classification, shape retrieval, indoor scene segmentation, 3D object detection, and completion, and illustrate the efficacy of our proposed method and its advantages over existing ones. Our source code is available at https://github.com/wendydidi/MMI.git. Numéro de notice : A2022-780 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : https://doi.org/10.1016/j.patcog.2022.108892 Date de publication en ligne : 08/07/2022 En ligne : https://doi.org/10.1016/j.patcog.2022.108892 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101859 [article]

A relation-augmented embedded graph attention network for remote sensing object detection / Shu Tian in IEEE Transactions on geoscience and remote sensing, vol 60 n° 10 (October 2022)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 60 n° 10 (October 2022) . - n° 1000718 Titre : A relation-augmented embedded graph attention network for remote sensing object detection Type de document : Article/Communication Auteurs : Shu Tian, Auteur ; Lihong Kang, Auteur ; Xiangwei Xing, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 1000718 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] attention (apprentissage automatique) [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] détection d'objet [Termes IGN] graphe [Termes IGN] image à haute résolution [Termes IGN] information sémantique [Termes IGN] relation sémantique [Termes IGN] relation spatiale [Termes IGN] réseau neuronal de graphes [Termes IGN] SIFT (algorithme) Résumé : (auteur) Multiclass geospatial object detection in high spatial resolution remote sensing imagery (HSRI) is still a challenging task. The main reason is that the objects in HRSI are location-variable and semantic-confusable, which results in the difficulties in differentiating the complicated spatial patterns and deriving the implicitly semantic labels among different categories of objects. In this article, we propose a relation-augmented embedded graph attention network (EGAT), which enables the full exploitation of the underlying spatial and semantic relations among objects for improving the detection performance. Specifically, we first construct two sets of spatial and semantic graphs of objects–objects for object relations modeling. Second, a Siamese architecture-based embedding spatial and semantic graph attention network is designed for relations reasoning, which is implemented by introducing the long short-term memory (LSTM) mechanism into the EGAT, for learning the relations among different categories of intraobjects and interobjects. Driven by the spatial and semantic LSTM, the EGAT-LSTM can adaptively focus on the critical information of reason graphs for spatial–semantic correlation discrimination in the embedding non-Euclidean feature space. By this way, the EGAT-LSTM can effectively capture the global and local spatial–semantic relationships of objects–objects, and then produce relations-augmented features for improving the performance of object detection. We conduct comprehensive experiments on three public datasets for multiclass geospatial object detection. Our method achieves state-of-the-art performance, which demonstrates the superiority and effectiveness of the proposed method. Numéro de notice : A2022-766 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2021.3073269 Date de publication en ligne : 18/05/2021 En ligne : https://doi.org/10.1109/TGRS.2021.3073269 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101788 [article]

Mapping individual abandoned houses across cities by integrating VHR remote sensing and street view imagery / Shengyuan Zou in International journal of applied Earth observation and geoinformation, vol 113 (September 2022)  

Public [article]  inInternational journal of applied Earth observation and geoinformation > vol 113 (September 2022) . - n° 103018 Titre : Mapping individual abandoned houses across cities by integrating VHR remote sensing and street view imagery Type de document : Article/Communication Auteurs : Shengyuan Zou, Auteur ; Le Wang, Auteur Année de publication : 2022 Article en page(s) : n° 103018 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] carte thématique [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] détection d'objet [Termes IGN] image à très haute résolution [Termes IGN] image Streetview [Termes IGN] logement [Termes IGN] New York (Etats-Unis ; état) [Termes IGN] théorie de Dempster-Shafer [Termes IGN] zone urbaine Résumé : (auteur) Abandoned houses (AH) present an utmost challenge confronting the urban environment in contemporary U.S. shrinking cities. Data accessibility is a major hurdle that prevents the acquisition of large-scale AH information at the individual property level. To this end, the latest revolution of open-access remote sensing platforms has witnessed a plethora of multi-source, multi-perspective fine-spatial-resolution data for urban environments, among which very-high-resolution (VHR) top-down view remote sensing images and horizontal-perspective Google Street View (GSV) images are prominent exemplifiers. In this study, we aim to map individual-level abandoned houses across cities by developing a method that can effectively leverage VHR remote sensing and GSV images. The proposed method is composed of four steps. First, we explored the feasibility of the three most relevant and complementary remote sensing data for individual-level AH detection, i.e., daytime VHR images, nighttime light VHR images, and GSV images. Second, we extracted discriminative features that are indicative of housing abandonment conditions from the three disparate data sources. Third, we applied decision-level fusion with Dempster-Shafer Theory (DST) to better leverage the prior knowledge about data effectiveness. In the last step, a geographical random forests (GRF) model was first implemented to improve the predictions of where houses were occluded on GSV images. We mapped individual AH in two typical U.S. shrinking cities, Buffalo, NY, and Cleveland, OH, which allowed us to further explore the individual-property-level spatial characteristics of AH. Results revealed that the proposed DST fusion and GRF prediction consistently achieved promising performance across the two cities. Given the merits of incorporating open-access and multi-perspective data, our proposed method has the potential to be generalized to understanding regional and national-scale urban environments tackling housing abandonment challenges. Numéro de notice : A2022-788 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.jag.2022.103018 Date de publication en ligne : 18/09/2022 En ligne : https://doi.org/10.1016/j.jag.2022.103018 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101894 [article]

Structured binary neural networks for image recognition / Bohan Zhuang in International journal of computer vision, vol 130 n° 9 (September 2022)  

Public [article]  inInternational journal of computer vision > vol 130 n° 9 (September 2022) . - pp 2081 - 2102 Titre : Structured binary neural networks for image recognition Type de document : Article/Communication Auteurs : Bohan Zhuang, Auteur ; Chunhua Shen, Auteur ; Mingkui Tan, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 2081 - 2102 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] décomposition [Termes IGN] détection d'objet [Termes IGN] implémentation (informatique) [Termes IGN] logique binaire [Termes IGN] segmentation sémantique Résumé : (auteur) In this paper, we propose to train binarized convolutional neural networks (CNNs) that are of significant importance for deploying deep learning to mobile devices with limited power capacity and computing resources. Previous works on quantizing CNNs often seek to approximate the floating-point information of weights and/or activations using a set of discrete values. Such methods, termed value approximation here, typically are built on the same network architecture of the full-precision counterpart. Instead, we take a new “structured approximation” view for network quantization — it is possible and valuable to exploit flexible architecture transformation when learning low-bit networks, which can achieve even better performance than the original networks in some cases. In particular, we propose a “group decomposition” strategy, termed GroupNet, which divides a network into desired groups. Interestingly, with our GroupNet strategy, each full-precision group can be effectively reconstructed by aggregating a set of homogeneous binary branches. We also propose to learn effective connections among groups to improve the representation capability. To improve the model capacity, we propose to dynamically execute sparse binary branches conditioned on input features while preserving the computational cost. More importantly, the proposed GroupNet shows strong flexibility for a few vision tasks. For instance, we extend the GroupNet for accurate semantic segmentation by embedding the rich context into the binary structure. The proposed GroupNet also shows strong performance on object detection. Experiments on image classification, semantic segmentation, and object detection tasks demonstrate the superior performance of the proposed methods over various quantized networks in the literature. Moreover, the speedup and runtime memory cost evaluation comparing with related quantization strategies is analyzed on GPU platforms, which serves as a strong benchmark for further research. Numéro de notice : A2022-637 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s11263-022-01638-0 Date de publication en ligne : 22/06/2022 En ligne : https://doi.org/10.1007/s11263-022-01638-0 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101443 [article]

Exploring the vertical dimension of street view image based on deep learning: a case study on lowest floor elevation estimation / Huan Ning in International journal of geographical information science IJGIS, vol 36 n° 7 (juillet 2022)  

Permalink

Street-view imagery guided street furniture inventory from mobile laser scanning point clouds / Yuzhou Zhou in ISPRS Journal of photogrammetry and remote sensing, vol 189 (July 2022)  

Permalink

Adversarial defenses for object detectors based on Gabor convolutional layers / Abdollah Amirkhani in The Visual Computer, vol 38 n° 6 (June 2022)  

Permalink

Detecting interchanges in road networks using a graph convolutional network approach / Min Yang in International journal of geographical information science IJGIS, vol 36 n° 6 (June 2022)  

Permalink

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)  

Permalink

Large-scale automatic identification of urban vacant land using semantic segmentation of high-resolution remote sensing images / Lingdong Mao in Landscape and Urban Planning, vol 222 (June 2022)  

Permalink

Line-based deep learning method for tree branch detection from digital images / Rodrigo L. S. Silva in International journal of applied Earth observation and geoinformation, vol 110 (June 2022)  

Permalink

Unsupervised multi-view CNN for salient view selection and 3D interest point detection / Ran Song in International journal of computer vision, vol 130 n° 5 (May 2022)  

Permalink

Deep learning for archaeological object detection on LiDAR: New evaluation measures and insights / Marco Fiorucci in Remote sensing, vol 14 n° 7 (April-1 2022)  

Permalink

Determination of building flood risk maps from LiDAR mobile mapping data / Yu Feng in Computers, Environment and Urban Systems, vol 93 (April 2022)  

Permalink