Descripteur
Documents disponibles dans cette catégorie (73)
![](./images/expand_all.gif)
![](./images/collapse_all.gif)
![Tris disponibles](./images/orderby_az.gif)
Etendre la recherche sur niveau(x) vers le bas
CNN-based RGB-D salient object detection: Learn, select, and fuse / Hao Chen in International journal of computer vision, vol 129 n° 7 (July 2021)
![]()
[article]
Titre : CNN-based RGB-D salient object detection: Learn, select, and fuse Type de document : Article/Communication Auteurs : Hao Chen, Auteur ; Yongjian Deng, Auteur ; Guosheng Lin, Auteur Année de publication : 2021 Article en page(s) : pp 2076 - 2096 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] approche hiérarchique
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] détection d'objet
[Termes IGN] extraction de traits caractéristiques
[Termes IGN] fusion de données
[Termes IGN] image RVB
[Termes IGN] profondeur
[Termes IGN] saillance
[Termes IGN] segmentation sémantiqueRésumé : (auteur) The goal of this work is to present a systematic solution for RGB-D salient object detection, which addresses the following three aspects with a unified framework: modal-specific representation learning, complementary cue selection, and cross-modal complement fusion. To learn discriminative modal-specific features, we propose a hierarchical cross-modal distillation scheme, in which we use the progressive predictions from the well-learned source modality to supervise learning feature hierarchies and inference in the new modality. To better select complementary cues, we formulate a residual function to incorporate complements from the paired modality adaptively. Furthermore, a top-down fusion structure is constructed for sufficient cross-modal cross-level interactions. The experimental results demonstrate the effectiveness of the proposed cross-modal distillation scheme in learning from a new modality, the advantages of the proposed multi-modal fusion pattern in selecting and fusing cross-modal complements, and the generalization of the proposed designs in different tasks. Numéro de notice : A2021-697 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1007/s11263-021-01452-0 Date de publication en ligne : 05/05/2021 En ligne : https://doi.org/10.1007/s11263-021-01452-0 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98532
in International journal of computer vision > vol 129 n° 7 (July 2021) . - pp 2076 - 2096[article]A hierarchical deep learning framework for the consistent classification of land use objects in geospatial databases / Chun Yang in ISPRS Journal of photogrammetry and remote sensing, vol 177 (July 2021)
![]()
[article]
Titre : A hierarchical deep learning framework for the consistent classification of land use objects in geospatial databases Type de document : Article/Communication Auteurs : Chun Yang, Auteur ; Franz Rottensteiner, Auteur ; Christian Heipke, Auteur Année de publication : 2021 Article en page(s) : pp 38 - 56 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Bases de données localisées
[Termes IGN] Allemagne
[Termes IGN] apprentissage profond
[Termes IGN] approche hiérarchique
[Termes IGN] classification automatique d'objets
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] image aérienne
[Termes IGN] jointure
[Termes IGN] objet géographique
[Termes IGN] occupation du sol
[Termes IGN] optimisation (mathématiques)
[Termes IGN] utilisation du solRésumé : (Auteur) Land use as contained in geospatial databases constitutes an essential input for different applications such as urban management, regional planning and environmental monitoring. In this paper, a hierarchical deep learning framework is proposed to verify the land use information. For this purpose, a two-step strategy is applied. First, given high-resolution aerial images, the land cover information is determined. To achieve this, an encoder-decoder based convolutional neural network (CNN) is proposed. Second, the pixel-wise land cover information along with the aerial images serves as input for another CNN to classify land use. Because the object catalogue of geospatial databases is frequently constructed in a hierarchical manner, we propose a new CNN-based method aiming to predict land use in multiple levels hierarchically and simultaneously. A so called Joint Optimization (JO) is proposed where predictions are made by selecting the hierarchical tuple over all levels which has the maximum joint class scores, providing consistent results across the different levels. The conducted experiments show that the CNN relying on JO outperforms previous results, achieving an overall accuracy up to 92.5%. In addition to the individual experiments on two test sites, we investigate whether data showing different characteristics can improve the results of land cover and land use classification, when processed together. To do so, we combine the two datasets and undertake some additional experiments. The results show that adding more data helps both land cover and land use classification, especially the identification of underrepresented categories, despite their different characteristics. Numéro de notice : A2021-370 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2021.04.022 Date de publication en ligne : 13/05/2021 En ligne : https://doi.org/10.1016/j.isprsjprs.2021.04.022 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97774
in ISPRS Journal of photogrammetry and remote sensing > vol 177 (July 2021) . - pp 38 - 56[article]Exemplaires(3)
Code-barres Cote Support Localisation Section Disponibilité 081-2021071 SL Revue Centre de documentation Revues en salle Disponible 081-2021073 DEP-RECP Revue LASTIG Dépôt en unité Exclu du prêt 081-2021072 DEP-RECF Revue Nancy Dépôt en unité Exclu du prêt Multiple convolutional features in Siamese networks for object tracking / Zhenxi Li in Machine Vision and Applications, vol 32 n° 3 (May 2021)
![]()
[article]
Titre : Multiple convolutional features in Siamese networks for object tracking Type de document : Article/Communication Auteurs : Zhenxi Li, Auteur ; Guillaume-Alexandre Bilodeau, Auteur ; Wassim Bouachir, Auteur Année de publication : 2021 Article en page(s) : n° 59 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image
[Termes IGN] approche hiérarchique
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] extraction de traits caractéristiques
[Termes IGN] poursuite de cible
[Termes IGN] reconnaissance d'objets
[Termes IGN] réseau neuronal siamoisRésumé : (auteur) Siamese trackers demonstrated high performance in object tracking due to their balance between accuracy and speed. Unlike classification-based CNNs, deep similarity networks are specifically designed to address the image similarity problem and thus are inherently more appropriate for the tracking task. However, Siamese trackers mainly use the last convolutional layers for similarity analysis and target search, which restricts their performance. In this paper, we argue that using a single convolutional layer as feature representation is not an optimal choice in a deep similarity framework. We present a Multiple Features-Siamese Tracker (MFST), a novel tracking algorithm exploiting several hierarchical feature maps for robust tracking. Since convolutional layers provide several abstraction levels in characterizing an object, fusing hierarchical features allows to obtain a richer and more efficient representation of the target. Moreover, we handle the target appearance variations by calibrating the deep features extracted from two different CNN models. Based on this advanced feature representation, our method achieves high tracking accuracy, while outperforming the standard siamese tracker on object tracking benchmarks. The source code and trained models are available at https://github.com/zhenxili96/MFST. Numéro de notice : A2021-470 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1007/s00138-021-01185-7 Date de publication en ligne : 11/03/2021 En ligne : https://doi.org/10.1007/s00138-021-01185-7 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97903
in Machine Vision and Applications > vol 32 n° 3 (May 2021) . - n° 59[article]Multi-level progressive parallel attention guided salient object detection for RGB-D images / Zhengyi Liu in The Visual Computer, vol 37 n° 3 (March 2021)
![]()
[article]
Titre : Multi-level progressive parallel attention guided salient object detection for RGB-D images Type de document : Article/Communication Auteurs : Zhengyi Liu, Auteur ; Quntao Duan, Auteur ; Song Shi, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 529 - 540 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] approche hiérarchique
[Termes IGN] détection automatique
[Termes IGN] détection d'objet
[Termes IGN] extraction de traits caractéristiques
[Termes IGN] image RVB
[Termes IGN] optimisation spatiale
[Termes IGN] profondeur
[Termes IGN] réseau neuronal récurrent
[Termes IGN] saillanceRésumé : (auteur) Detecting salient objects in RGB-D images attracts more and more attention in recent years. It benefits from the widespread use of depth sensors and can be applied in the comprehensive understanding of RGB-D images. Existing models focus on double-stream networks which transfer from color stream to depth stream, but depth stream with one channel information cannot learn the same feature as color stream with three channels information even if HHA representation is adopted. In our works, RGB-D four-channels input is chosen, and meanwhile, progressive parallel spatial and channel attention mechanisms are performed to improve feature representation. Spatial and channel attention can pay more attention on partial positions and channels in the image which show higher response to salient objects. Both attentive features are optimized by attentive feature from higher layer, respectively, and parallel fed into recurrent convolutional layer to generate side-output saliency maps guided by saliency map from higher layer. Last multi-level saliency maps are fused together from multi-scale perspective. Experiments on benchmark datasets demonstrate that parallel attention mechanism and progressive optimization operation play an important role in improving the accuracy of salient object detection, and our model outperforms state-of-the-art models in evaluation matrices. Numéro de notice : A2021-340 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1007/s00371-020-01821-9 Date de publication en ligne : 18/02/2020 En ligne : https://doi.org/10.1007/s00371-020-01821-9 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97578
in The Visual Computer > vol 37 n° 3 (March 2021) . - pp 529 - 540[article]Study of an integrated pre-processing architecture for smart-imaging-systems, in the context of lowpower computer vision and embedded object detection / Luis Cubero Montealegre (2021)
![]()
Titre : Study of an integrated pre-processing architecture for smart-imaging-systems, in the context of lowpower computer vision and embedded object detection Type de document : Thèse/HDR Auteurs : Luis Cubero Montealegre, Auteur Editeur : Grenoble [France] : Université Grenoble Alpes Année de publication : 2021 Importance : 161 p. Format : 21 x 30 cm Note générale : bibliographie
Thèse pour obtenir le grade de Docteur de l'Université Grenoble Alpes, spécialité : Nano-Electronique et Nano-TechnologiesLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] approche hiérarchique
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] détecteur CMOS
[Termes IGN] détection d'objet
[Termes IGN] détection de contours
[Termes IGN] extraction de traits caractéristiques
[Termes IGN] instrument embarqué
[Termes IGN] intelligence artificielle
[Termes IGN] restauration d'imageIndex. décimale : THESE Thèses et HDR Résumé : (auteur) Embedded Computer vision, as many real application scenarios other areas of artificial intelligence, is facing hardware and power constraints with the rising of edge computing applications. For instance, the object detection problem, consisting in finding different objects of specific classes (types) in an image, turns out to be quite complicated to embed near the image sensor as two complex tasks are required: multi-scale localization and multi-class classification (i.e. identifying bounding boxes that perfectly enclose each object, whatever its size, and labeling the type of the detected object). Today these tasks are mainly often performed on general-purpose desktop machines. Nevertheless, attractive applications like autonomous-driving, augmented reality or video surveillance are urging the need for low-power, low-latency and compact low power devices.The state of the art has approached this challenge by optimizing specific sections of the complete processing-pipeline for a comparable object detection performance. A typical example in the last decade corresponds to minimizing the computing precision, hence the power, to a minimal value. Diminishing the bit-depth or image size has then been studied while implementing pre-processing steps that increase robustness against the loss in bit and image resolution. An algorithm that doesn’t require that kind of pre-processing stage to be programmable is obviously desirable in order to simplify its implementation (e.g. no memory access to learned weights). Another strategy has been to reduce power due to I/O communications amongst different chips or devices thanks to a more exhaustive integration of specialized circuitry and thanks to more efficient memory accesses and mathematical operations.In that context of near-sensor computing, this work points towards a more energy efficient detection pipeline. We target several specific key aspects:1. We try to assess if a dedicated-class-agnostic region proposal algorithm, based on pre-processed low-level features, could replace the typical sliding window approach for object localization in integrated smart imaging systems, allowing to target more efficiently objects in the image. Then, we propose a pipeline that takes into account near image sensor features extraction for Region Proposals with an embedded version of an algorithm called EdgeBoxes.2. We try to assess an optimal type of pre-processing (based on an efficient architecture) that would allow extracting low level features (oriented gradients), and give the best trade-off between power consumption, hardware complexity and object detection performance. Specifically, while being this architecture is fully compatible with region proposal algorithms beyond the sliding window.3. Finally, we try to assess if non-standard, or neuromorphic, image acquisition techniques can be exploited in order to further increase the detection efficiency in real case scenarios.Our methodology relies on behavioral simulations carried out thanks to a custom framework written in Python and C++ code. We propose a hierarchical model (and code architecture) of different image acquisition and processing techniques, and we study their performance through specific metrics related to runtime, memory usage, hardware complexity, I/O data-rate, localization performance and classification performance. We provide comparison with the state of the art and several benchmarks giving guidance to choose one or another architecture depending on the specific needs, and we conclude by stating which one would give, from our perspective, the best trade-offs. Note de contenu : 1. Introduction
2. State of the art
3. Our simulation Framework
4. Region proposals pipeline design
5. Embedded Edge Extraction Circuitry
6. Object Localization benchmarks
7. Dynamic Vision Pre-processing
8. ConclusionNuméro de notice : 28692 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Thèse française Note de thèse : Thèse de Doctorat : Nano-Electronique et Nano-Technologies : Grenoble : 2021 Organisme de stage : LETI DOI : sans En ligne : https://tel.archives-ouvertes.fr/tel-03612476/document Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100289 Climate sensitive single tree growth modeling using a hierarchical Bayes approach and integrated nested Laplace approximations (INLA) for a distributed lag model / Arne Nothdurft in Forest ecology and management, vol 478 ([15/12/2020])
PermalinkObject-based classification of mixed forest types in Mongolia / E. Nyamjargal in Geocarto international, vol 35 n° 14 ([15/10/2020])
PermalinkNear-real time forecasting and change detection for an open ecosystem with complex natural dynamics / Jasper A. Slingsby in ISPRS Journal of photogrammetry and remote sensing, vol 166 (August 2020)
PermalinkMining spatiotemporal association patterns from complex geographic phenomena / Zhanjun He in International journal of geographical information science IJGIS, vol 34 n° 6 (June 2020)
PermalinkUsing multi-scale and hierarchical deep convolutional features for 3D semantic classification of TLS point clouds / Zhou Guo in International journal of geographical information science IJGIS, vol 34 n° 4 (April 2020)
PermalinkAssessment of salt marsh change on Assateague Island National Seashore between 1962 and 2016 / Anthony Campbell in Photogrammetric Engineering & Remote Sensing, PERS, vol 86 n° 3 (March 2020)
PermalinkPermalinkA thematic mapping method to assess and analyze potential urban hazards and risks caused by flooding / Mohammad Khalid Hossain in Computers, Environment and Urban Systems, vol 79 (January 2020)
PermalinkPermalinkA new generation of the United States National Land Cover Database : Requirements, research priorities, design, and implementation strategies / Limin Yang in ISPRS Journal of photogrammetry and remote sensing, vol 146 (December 2018)
Permalink