Centre dedocumentation
scientifique

ComNet: combinational neural network for object detection in UAV-borne thermal images / Minglei Li in IEEE Transactions on geoscience and remote sensing, vol 59 n° 8 (August 2021)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 59 n° 8 (August 2021) . - pp 6662 - 6673 Titre : ComNet: combinational neural network for object detection in UAV-borne thermal images Type de document : Article/Communication Auteurs : Minglei Li, Auteur ; Xingke Zhao, Auteur ; Jiasong Li, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 6662 - 6673 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] détection d'objet [Termes IGN] image captée par drone [Termes IGN] image thermique [Termes IGN] piéton [Termes IGN] saillance [Termes IGN] véhicule Résumé : (auteur) We propose a deep learning-based method for object detection in UAV-borne thermal images that have the capability of observing scenes in both day and night. Compared with visible images, thermal images have lower requirements for illumination conditions, but they typically have blurred edges and low contrast. Using a boundary-aware salient object detection network, we extract the saliency maps of the thermal images to improve the distinguishability. Thermal images are augmented with the corresponding saliency maps through channel replacement and pixel-level weighted fusion methods. Considering the limited computing power of UAV platforms, a lightweight combinational neural network ComNet is used as the core object detection method. The YOLOv3 model trained on the original images is used as a benchmark and compared with the proposed method. In the experiments, we analyze the detection performances of the ComNet models with different image fusion schemes. The experimental results show that the average precisions (APs) for pedestrian and vehicle detection have been improved by 2%~5% compared with the benchmark without saliency map fusion and MobileNetv2. The detection speed is increased by over 50%, while the model size is reduced by 58%. The results demonstrate that the proposed method provides a compromise model, which has application potential in UAV-borne detection tasks. Numéro de notice : A2021-632 Affiliation des auteurs : non IGN Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2020.3029945 date de publication en ligne : 21/10/2020 En ligne : https://doi.org/10.1109/TGRS.2020.3029945 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98288 [article]

Semantic-aware label placement for augmented reality in street view / Jianqing Jia in The Visual Computer, vol 37 n° 7 (July 2021)  

Public [article]  inThe Visual Computer > vol 37 n° 7 (July 2021) . - pp 1805 - 1819 Titre : Semantic-aware label placement for augmented reality in street view Type de document : Article/Communication Auteurs : Jianqing Jia, Auteur ; Semir Elezovikj, Auteur ; Heng Fan, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 1805 - 1819 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] étiquetage sémantique [Termes IGN] image Streetview [Termes IGN] information sémantique [Termes IGN] optimisation (mathématiques) [Termes IGN] point d'intérêt [Termes IGN] réalité augmentée [Termes IGN] saillance [Termes IGN] scène urbaine Résumé : (auteur) In an augmented reality (AR) application, placing labels in a manner that is clear and readable without occluding the critical information from the real world can be a challenging problem. This paper introduces a label placement technique for AR used in street view scenarios. We propose a semantic-aware task-specific label placement method by identifying potentially important image regions through a novel feature map, which we refer to as guidance map. Given an input image, its saliency information, semantic information and the task-specific importance prior are integrated in the guidance map for our labeling task. To learn the task prior, we created a label placement dataset with the users’ labeling preferences, as well as use it for evaluation. Our solution encodes the constraints for placing labels in an optimization problem to obtain the final label layout, and the labels will be placed in appropriate positions to reduce the chances of overlaying important real-world objects in street view AR scenarios. The experimental validation shows clearly the benefits of our method over previous solutions in the AR street view navigation and similar applications. Numéro de notice : A2021-542 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1007/s00371-020-01939-w date de publication en ligne : 02/08/2020 En ligne : https://doi.org/10.1007/s00371-020-01939-w Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98022 [article]

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)  

Public [article]  inInternational journal of computer vision > vol 129 n° 7 (July 2021) . - pp 2076 - 2096 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 sémantique Résumé : (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 [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)  

Public [article]  inThe Visual Computer > vol 37 n° 3 (March 2021) . - pp 529 - 540 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] saillance Résumé : (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 [article]

Visualization of 3D property data and assessment of the impact of rendering attributes / Stefan Seipel in Journal of Geovisualization and Spatial Analysis, vol 4 n° 2 (December 2020)  

Public [article]  inJournal of Geovisualization and Spatial Analysis > vol 4 n° 2 (December 2020) . - n° 23 Titre : Visualization of 3D property data and assessment of the impact of rendering attributes Type de document : Article/Communication Auteurs : Stefan Seipel, Auteur ; Martin Andrée, Auteur ; Karolina Larsson, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : n° 23 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] attribut non spatial [Termes IGN] cadastre 3D [Termes IGN] cadastre étranger [Termes IGN] classification barycentrique [Termes IGN] couleur (rédaction cartographique) [Termes IGN] mesure de similitude [Termes IGN] propriété foncière [Termes IGN] rédaction cartographique [Termes IGN] rendu (géovisualisation) [Termes IGN] saillance [Termes IGN] scène 3D [Termes IGN] Stockholm (Suède) [Termes IGN] visualisation cartographique [Vedettes matières IGN] Géovisualisation Résumé : (auteur) Visualizations of 3D cadastral information incorporating both intrinsically spatial and non-spatial information are examined here. The design of a visualization prototype is linked to real-case 3D property information. In an interview with domain experts, the functional and visual features of the prototype are assessed. The choice of rendering attributes was identified as an important aspect for further analysis. A computational approach to systematic assessment of the consequences of different graphical design choices is proposed. This approach incorporates a colour similarity metric, visual saliency maps, and k-nearest-neighbour (kNN) classification to estimate risks of confusing or overlooking relevant elements in a visualization. The results indicate that transparency is not an independent visual variable, as it affects the apparent colour of 3D objects and makes them inherently more difficult to distinguish. Transparency also influences visual saliency of objects in a scene. The proposed analytic approach was useful for visualization design and revealed that the conscious use of graphical attributes, like combinations of colour, transparency, and line styles, can improve saliency of objects in a 3D scene. Numéro de notice : A2020-796 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s41651-020-00063-6 date de publication en ligne : 26/10/2020 En ligne : https://doi.org/10.1007/s41651-020-00063-6 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96612 [article]

A novel deep network and aggregation model for saliency detection / Ye Liang in The Visual Computer, vol 36 n° 9 (September 2020)  

Permalink

Comparing the roles of landmark visual salience and semantic salience in visual guidance during indoor wayfinding / Weihua Dong in Cartography and Geographic Information Science, vol 47 n° 3 (May 2020)  

Permalink

Saliency-guided single shot multibox detector for target detection in SAR images / Lan Du in IEEE Transactions on geoscience and remote sensing, vol 58 n° 5 (May 2020)  

Permalink

Saliency and Burstiness for Feature Selection in CBIR / Kamel Guissous (2020)  

Permalink

Extracting urban landmarks from geographical datasets using a random forests classifier / Yue Lin in International journal of geographical information science IJGIS, vol 33 n° 12 (December 2019)  

Permalink

Saliency-guided deep neural networks for SAR image change detection / Jie Geng in IEEE Transactions on geoscience and remote sensing, Vol 57 n° 10 (October 2019)  

Permalink

Comparative study of visual saliency maps in the problem of classification of architectural images with Deep CNNs / Abraham Montoya Obeso (2018)  

Permalink

Image retrieval based on saliency for urban image contents / Kamel Guissous (2017)  

Permalink

Road extraction based on snakes and sophisticated line extraction / Ivan Laptev (1997)

Permalink