Below are various events that were worth a post in the news section in the past:
- [September 2019] Starting this month, I am now an ONERA’s Maître de Recherche (literally Research Master). Not Yoda yet, but maybe like Obi Wan Kenobi…
- [September 2019] Gaston Lenczner joins the lab as PhD student, working on Interactive learning in aerial image interpretation. He is supervised by Guy Le Besnerais, Nicola Luminari and myself, and this project is carried on in collaboration with the Delair company.
- [September 2019] We propose a special issue for “Computer Vision-based Approaches for Earth Observation” in JSTARS. Guest editors include Devis Tuia, Ronny Hänsch, Naoto Yokoya, Myron Brown, Yannis Kalantidis and myself. Full CfP here.
- [September 2019] Classification is better done with regression! That’s one of the outcomes of our paper “Distance transform regression for spatially-aware deep semantic segmentation” with Nicolas Audebert, Alexandre Boulch and Sébastien Lefèvre, out now in Computer Vision and Image Understanding (CVIU): https://doi.org/10.1016/j.cviu.2019.102809
- [September 2019] Clément Rambour joins the lab as a post-doctoral researcher between CNAM-ParisTech (Michel Crucianu), Blaise Pascal Chair of Fondation de l’ENS (Mihai Datcu) and ONERA (Élise Koeniguer and I). He will work on multi-temporal analysis of SAR and optical data.
- [July 2019] Our paper “Multitask learning for large-scale semantic change detection” with Rodrigo Caye Daudt, Alexandre Boulch and Yann Gousseau is now out in Computer Vision and Image Understanding (CVIU): https://doi.org/10.1016/j.cviu.2019.07.003
- [July 2019] Ronny Hänsch (TU Berlin, Germany), Devis Tuia (Uni Wangeningen, NL), Yuliya Tarabalka (LuxCarta, FR) and I will give a tutorial on Machine Learning for Remote Sensing - Best practices and recent solutions at IGARSS 2019, in Yokohama, Japan, on July 28th.
- [June 2019] Our review on deep learning models for classification of remote sensing hyperspectral data is finally published (after 2 years of much debated editorial process) in GRSM: https://doi.org/10.1109/MGRS.2019.2912563. It comes with our DeepHyperX toolbox with several SOA networks for HSI: https://github.com/nshaud/DeepHyperX
- [June 2019] The JSTARS paper about the outcome of the 2018 Data Fusion Contest that I co-organized with Ronny Hänsch (TU Berlin, Germany), Naoto Yokoya (RIKEN, JP) and Saurabh Prasad (U. of Houston, US), is out! You can get it in open-access from https://doi.org/10.1109/JSTARS.2019.2911113. Please note that testing algorithms with this dataset is still possible on the IEEE GRSS DASE website
- [June 2019] Rodrigo Caye Daudt got the Best Student Paper Award at CVPR/Earth Vision 2019. Congrats!
- [June 2019] Not exactly an early-adopter, I now have a twitter account to post news on a more regular basis.
- [May/June 2019] Javiera Castillo-Navarro will be at JURSE 2019 to present our paper “What data are needed for supervised semantic segmentation? (preprint) and Rodrigo Caye Daudt will be at CVPR/Earth Vision 2019 to present our paper on Weakly-supervised change detection (preprint on arxiv).
- [May 2019] I will give a tutorial on Deep Learning for Remote Sensing at JURSE 2019 with Loïc Landrieu. It will cover 2D and 3D, and include practical information to deploy deep learning approaches to remote sensing data.
- [April 2019] Antoine Manier joined the lab as PhD student, to work on 3D semantic understanding for railway environment. He is co-supervised with Alexandre Boulch. This PhD is funded by SNCF Réseau as part of our common research project Drosofile.
- [March 2019] Rémy Leroy joined the lab as MSc. student intern, to work on 3D point-cloud prediction. He is co-supervised with Marcela Carvalho and Pauline Trouvé-Peloux.
- [March 2019]
I have 3 open PhD positions to work with me on deep machine learning for scene perception and understanding.
- [March. 19] On March 4th and 5th, I will be in Barcelona to participate to the EuroSDR seminar for the course on Deep Learning for Remote Sensing I will give with Sébastien Lefèvre and Loïc Landrieu.
- [Feb. 19] On Feb. 8th, I’ll give a talk about “deep learning for scene perception and understanding” for ONERA’s scientific high council.
- [Jan. 19] We at IADF launched the 2019 Data Fusion Contest, co-organized with Johns Hopkins University! It deals with Large-Scale Semantic 3D Reconstruction and aims to reconstruct both a 3D geometric model and a segmentation of semantic classes for urban scenes. It is cast as a 4-track competition: single-view semantic 3D, pairwise semantic stereo, mutli-view semantic stereo and 3D point-cloud classification.
- [Jan. 19] I co-organize the 3rd Earth Vision workshop which is dedicated to large-scale computer vision for remote sensing imagery. It will be held in conjunction with CVPR’19 in June, at Long Beach, Cal., USA. Full paper submission deadline is on March, 7.
- [Jan. 19] Javiera Castillo Navarro joined the lab as PhD student. She will work on Large-scale semi-supervised semantic segmentation and is co-advised with Alexandre Boulch and Sebastien Lefèvre. Her PhD is co-funded by ONERA and CNES.
- [Nov. 18] Former PhD student Joris Guerry got the PhD Award in “Complex Systems Engineering” from the doctoral school Interfaces. Congrats!* [Nov. 18] On Nov. 20th, I will be at Onera Scientific Days in Toulouse to talk about “Scene understanding with 2D and 3D data from UAVs”.
- [Nov. 18] In November, we present our works on Deep Depth from Defocus a few times. On Nov. 9, Marcela Carvalho and Pauline Trouvé will be at Co-design days in Paris, and I will be at the Computational photography days in Poitiers on Nov. 13.
- [Oct. 18] On Oct. 26th, 10am, I will be at Toulouse INP ENSEEIHT as part of PhD thesis jury of Vinicius Ferraris (thesis / scholar)
- [Oct. 18] Nicolas Audebert, Sébastien Lefèvre and myself will be at GDR ISIS day to present our work on Convolutional Neural Nets for Hyperspectral data and the associated DeepHyperX toolbox
- [Oct. 18] Nicolas Audebert successfully defended his PhD on Oct. 17th at the ONERA center of Palaiseau, on the topic of Classification of Big Earth-Observation Data. Congratulations!
- [Oct. 18] Marcela Carvalho and Rodrigo Daudt will be at ICIP’2018 to present our works on (resp.) loss functions for 3D depth estimations and fully-convolutioonal nets for change detection
- [September 18] Our joint work on multitask learning wins overall the 3DRMS challenge! A team work with Alexandre Boulch, Marcela Carvalho, Maxime Ferrera, Julien Moras and Pauline Trouvé which also shows that learning on synthetic data allows to make 3D semantic mapping in real robotics environments! Talk at ECCV Workshop on 3D Reconstruction meets Semantics on Sept. 9th in Munich.
- [September 18] Marcela Carvalho will present our paper on Deep Depth from Defocus at ECCV Workshop on 3D Reconstruction in the Wild on Sept 14th in Munich.
- [July 18] Nicolas Audebert, Rodrigo Daudt and Alexandre Boulch will present our common papers at IGARSS’18 in Valencia, Spain.
- [June 18] Our work on deep nets for depth-from-defocus prediction [fr/en] with Marcela Carvalho, Pauline Trouvé, Frédéric Champagnat and Andrès Almansa got the Best Paper Award at French RFIAP conference!
- [June 18] With Alexandre Boulch and Sébastien Lefèvre, I organize the TerraData 2018 Workshop dedicated to data science and machine learning for Earth observation, in conjunction with RFIAP/CFPT 2018 on June 25th, in Marne-la-Vallée, near Paris, France.
- [May 18] Check out our next 2 papers at ICIP’2018 and 5 papers at IGARSS’2018 on the publication page
- [May 18] Javiera Castillo Navarro (MSc from École Polytechnique’s Master Data Science) joins the lab as intern, working on “Large-scale semi-supervised semantic segmentation”
- [April 18] On April, 3rd, I will give a seminar at Telecom Paristech/LTCI lab about “Deep Learning for Scene Understanding, from 2D to 3D.”
- [April 18] On April, 5th, we organize a Joint ONERA - CNAM workshop about Deep Learning for Earth Observation (with Élise Koeniguer and Martine Chanteclerc from ONERA, Michel Crucianu from CNAM and Blaise Pascal Chair awardee Mihai Datcu). Mihai Datcu will present an overview of the particularities of Artificial Intelligence (AI) in the fields of Earth Observation (EO). The focus will be on the methods of Deep Learning and their specificities for multispectral and Synthetic Aperture Radar.
- [April 18] The results of the 2018 Data Fusion Contest are published! Congratulations to the winners and the participants who made more than 1300 submissions in our multimodal classification benchmark!
- [March 18] Open-access to our SnapNet article on 3D point cloud semantic labeling in Computer and Graphics.
- [Fev. 18] Alexandre Boulch and I have two open PhD positions in our lab: one on “Semi-supervised semantic segmentation for large-scale automated cartography” with Sébastien Lefèvre from IRISA (co-funded by CNES, please apply here), and the other one on “Neural networks for semantic segmentation of 3D data” (call in French) with Renaud Marlet from ENPC.
- [Jan. 18] On Jan. 15th, we (at IADF TC, with University of Houston) launched the 2018 Data Fusion Contest, which consists in a classification benchmark with multimodal optical imagery: multispectral LiDAR, hyperspectral data and VHR RGB imagery. Do not miss this opportunity to test your algorithms!
- [Nov. 17] Jorris Guerry successfully defended his PhD thesis about “visual recognition by neural networks for robotics” at École Polytechnique on Nov. 20th. Congratulations !
- [Nov 17] Nicolas Audebert got nice results) with a new approach on the Inria Aerial dataset: more than 71% IoU for detecting buildings in aerial images.
- [Oct. 17] Rodrigo Daudt joined the lab as a PhD student, co-supervised by Alexandre Boulch, Yann Gousseau from Telecom Paristech/LTCI lab and myself. He will work on analysis of multi-temporal activity in Earth-observation data.
- [Oct. 17] I will be at ICCV workshop on 3D Reconstruction meets Semantics to speak about a SnapNet variation for robotics. SnapNet is our multi-view CNN for point cloud labeling, and we used it to perform 3D-consistent data augmentation, which results in state-of-the-art performances in semantic segmentation on SunRGBD and NYUv2 datasets.
- [Oct. 17] I will deliver a keynote talk about “Semantic Labeling of Remote Sensing Data from 2D to 3D” at TUM-DLR Remote Sensing Summer School on Oct. 4-6th.
[Sept. 17] Marcela Cavalho, Jorris Guerry and Nicolas Audebert will be at French Gretsi’17 to speak about the lab’s last advances in neural networks for depth prediction, people detection and aerial image segmentation.
[Sept. 17] Joris Guerry will be at ECMR in Paris to talk about RGBD RCNN for people detection in the context of mobile robotics.
- [July. 17] I’ve been elected chair of the Image analysis and Data Fusion Technical Committee. Together with Ronny Hänsch and Naoto Yokoya, I will run the IADF activities including the Data Fusion Contest organization.
[July 17] Nicolas Audebert will be at CVPR / Earth Vision in Honolulu to talk about how to jointly use widely available OpenStreetMap data with Earth-observation images to drive the network training towards better classification.
[June 17] Multitemporal very-high resolution from space: Outcome of the 2016 Data Fusion Contest now published in JSTARS.
[June 17] Sébastien Lefèvre (Univ. Bretagne Sud/IRISA) and Ronan Fablet (IMT Atlantique/LabSTICC) will give talks in our Machine Learning and Remote Sensing seminar at ONERA in Palaiseau, on June 7th.
[June 17] Nicolas Audebert will give a talk on Deep Learning for hyperspectral data at GDR ISIS event on multi-spectral and color imaging, in Paris, on June 2nd.
[May 17] Marcela Carvalho will give a talk on Generative Adversarial Networks (GANs) at Univ. de Brasilia on May, 26th.
[April 17] Our new article on aerial vehicle detection and classification is published in Remote Sensing special issue on object-based image analysis: Segment-before-detect.
[April 17] I will give a talk about 3D semantic mapping of point-clouds with deep networks at EuroGraphics/3DOR workshop in Lyon, on april 23rd. Our SnapNet approach tops the semantic3D leaderboard for 3D urban mapping !
- [Mar 17] Nicolas Audebert got the 2nd Best Student Paper award @ JURSE’2017 in Dubaï !
- [Mar 17] I give two seminars this month: at IGN/MATIS lab (the French mapping agency) on march, 21st and at Uni. Zurich, in Devis Tuia’s MultiModal Remote Sensing group on march, 29th.
[Mar 17] On March, 15th, Marcela Pinheiro de Carvalho will present our works on 3D estimation from monocular imaging at JIONC’2017 (at ESPCI in Paris).
[Mar 17] Nicolas Audebert and myself will be at JURSE’2017 in Dubaï for two talks about deep learning and urban remote sensing.
[Feb 17] We released the first pre-trained deep network models for EO data semantic labeling in the Caffe Model Zoo: check out the project repository for more details.
[Jan. 17] New Data Fusion Contest 2017 launched ! Get multi-mode, multi-temporal satellite imagery and OpenStreetMap data over several cities all around the world to perform Local Climate Zone classification !
[Nov. 16] Nicolas Audebert will present our paper on residual correction for data fusion at ACCV 2016 in Taipei.
[Nov. 16] Alexandre Boulch and I will present our work on point-cloud classification during the Plenary Meeting of the FP7 Inachus Project in Freiburg, Germany.
- [Oct. 16] Marcela Pinheiro de Carvalho started her PhD thesis on “Deep Learning of Depth from Defocus”. She will work with Pauline Trouvé-Peloux, Frédéric Champagnat, Andrés Almansa and myself.
[Sep. 16] Nicolas Audebert’s algorithm for semantic labeling of aerial images tops the learderboard of the ISPRS Vaihingen benchmark (ONE_6 and ONE_7 entries). He received the Award for the Best Contribution to the Benchmark at GEOBIA’16 conference. Stay tuned for the forthcoming paper accepted at ACCV 2016 !
[Sep. 16] Gabriele Moser and I will chair an invited session about Data Fusion for Urban Remote Sensing at next JURSE 2017 conference in Abu Dhabi.
[Sep. 16] Nicolas Audebert and Sébastien Lefèvre will be at GEOBIA’16 in Enschede, Netherlands, for presenting our common paper about the use of deep networks for object-based aerial imagery analysis.
[Aug. 16] The JSTARS article on the outcome of the 2015 IEEE GRSS Contest (where our team was awarded) is out now: http://dx.doi.org/10.1109/JSTARS.2016.2569162
[July 16] Nicolas Audebert will give a talk about spatial constraints for deep networks @ IGARSS 2016, in Beijing.
[July 16] Do not miss the IADF-organized sessions @ IGARSS 2016: TU4.L6 Data Fusion Contest session and WE1.L6: Data Fusion I and WE2.L6: Data Fusion II.
[July 16] Joris Guerry will give a talk at the Deep Learning for Robotics workshop held @ RFIA’2016, the French conference on artificial intelligence and pattern recognition, in Clermont-Ferrand.
[June 16] Nicolas Audebert will present our lab activities around Deep Learning for Remote Sensing at the ONERA-DLR ODAS workshop, near Munich.
- [June 16] Nicolas Audebert and I will be at Polytech Annecy to participate to the Total Image WG. We will talk about deep learning for remote sensing data.
- [May 16] Winners of the Data Fusion Contest 2016 announced ! Do not miss the corresponding session @ IGARSS’2016 in Beijing.
- [April 16] Open PhD position: 3D Camera by Depth from Defocus and Deep Learning, with Pauline Trouvé from ONERA and Andrès Almansa from TelecomParisTech.
- [April 16] Last month to enter the IEEE GRSS IADTF TC Data Fusion Contest 2016 (video from space and multitemporal HR satellite imagery). Submission website is now open, deadline on April, 29th
- [April 16] Nicolas Audebert will present a poster on Deep learning for aerial cartography at StatLearn, the conference of the French Society of Statistics in Vannes (on Apr., 7th)
[March 16] New plenary meeting of the FP7 Inachus Project in Toulouse and field test of the UAVs with Lidar sensor.
- [March 16] Hicham Randrianarivo presented our work on how spatial context can help deep-learning classifiers at ESA Big Data in Space (BiDS) workshop in Tenerife.
- [Jan’16] Launch of the IEEE GRSS IADTF TC Data Fusion Contest 2016. Register and work with video from space and multitemporal HR satellite imagery !
- [Oct’15] Joris Guerry got the best poster award at JJCR’15 (Young Researchers in Robotics Event), in Amiens.
- [Oct’15] Hicham Randrianarivo presented our work on vehicle detection in aerial images at IIM’15 conference in Bucharest.
- [Oct’15] Nicolas Audebert started his PhD about Classification of Big Remote Sensing Data co-advised with Sébastien Lefèvre of IRISA/Univ Bretagne Sud
- [Sep’15] Hicham Randrianarivo and Pauline Trouvé-Peloux will present our common papers at French conf. Gretsi’15
[Jul’15] I joined Devis Tuia and Gabriele Moser as co-chair of the IEEE GRSS Image Analysis and Data Fusion Technical Committee
- [Jul’15] Talk about Benchmarking classification algorithms for EO data at Igarss’15, in Milan
- [Jun’15] Plenary meeting of FP7 Inachus and end-user workshop in EPLFM, Gardanne
- [May’15] Our paper about classification of EO data got an award in the Data Fusion Contest 2015 ;o) [Apr’15] Kick-off of FP7 Inachus Work-Package #4, in Leiden
- [Apr’15] Talk about Environment mapping and interpretation by drone at Jurse 2015, in Lausanne [Mar’15] Adrien Lagrange (Ensta ParisTech) joined the group
- [Jan’15] Talk about Discriminative models for object detection in earth-observation data at Sébastien Lefèvre’s team Irisa/Obelix, in Vannes
- [Oct’14] Joris Guerry started his PhD about 3D object detection and domain adaptation for UAVs, co-advised with David Filliat and Antoine Manzanera at Ensta ParisTech
- [Aug’14] Talk about Interactive design of classifiers in remote sensing at ICPR’14, in Stockholm
- [Jul’14] Hicham Randrianarivo gave an invited talk about classification with deformable part-models for urban cartography at IGARSS’14, in Quebec City
- [May’14] 2nd field trial “Urban (Earthquake) Search-and-Rescue Demonstration” of the FP7 Darius project , near Avignon [video].
- [Nov’13] Talk about Rapid semantic mapping for UAVs at IROS’13, in Tokyo
- [Sep’13] Morgane Rivière got honours from the internship award jury of École Polytechnique for her thesis about domain adaptation of object detectors for UAVs
- [Oct’12] Hicham Randrianarivo started his PhD about Co-learning of semantic classifiers for remote-sensing, co-advised with Marin Ferecatu and Michel Crucianu at CNAM Paris
- [Jul’12] 2 talks about interactive classification and exploration of remote sensing data at IGARSS’12, in Munich
- [Sep’11] Nicolas Chauffert got honours from the internship award jury of École Polytechnique for his thesis about boosting for interactive man-made classification