Improving Constrained Bundle Adjustment Through Semantic Scene Labeling
Autor: | Vincent Gay-Bellile, Achkan Salehi, Frédéric Chausse, Steve Bourgeois |
---|---|
Přispěvatelé: | Département Intelligence Ambiante et Systèmes Interactifs ( DIASI ), Laboratoire d'Intégration des Systèmes et des Technologies ( LIST ), Commissariat à l'énergie atomique et aux énergies alternatives ( CEA ) -Université Paris-Saclay-Commissariat à l'énergie atomique et aux énergies alternatives ( CEA ) -Université Paris-Saclay, Institut Pascal ( IP ), Université Blaise Pascal - Clermont-Ferrand 2 ( UBP ) -Sigma CLERMONT ( Sigma CLERMONT ) -Centre National de la Recherche Scientifique ( CNRS ), Département Intelligence Ambiante et Systèmes Interactifs (DIASI), Laboratoire d'Intégration des Systèmes et des Technologies (LIST), Direction de Recherche Technologique (CEA) (DRT (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Direction de Recherche Technologique (CEA) (DRT (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Institut Pascal (IP), Université Blaise Pascal - Clermont-Ferrand 2 (UBP)-SIGMA Clermont (SIGMA Clermont)-Centre National de la Recherche Scientifique (CNRS), Laboratoire d'Intégration des Systèmes et des Technologies (LIST (CEA)) |
Rok vydání: | 2016 |
Předmět: |
City scale
0209 industrial biotechnology [ INFO ] Computer Science [cs] Computer science Bundle adjustments Bundle adjustment 02 engineering and technology 020901 industrial engineering & automation Robustness (computer science) Learning process Constrained bundle adjustments 0202 electrical engineering electronic engineering information engineering [INFO]Computer Science [cs] Computer vision VSLAM Learning systems business.industry Deep learning Semantics SLAM 020201 artificial intelligence & image processing Artificial intelligence business Scene labeling |
Zdroj: | Lecture Notes in Computer Science ISBN: 9783319494081 ECCV Workshops (3) Computer Vision – ECCV 2016 Workshops. ECCV 2016. Computer Vision – ECCV 2016 Workshops. ECCV 2016., 9915 pp.133-142, 2016, Lecture Notes in Computer Science, 〈10.1007/978-3-319-49409-8_13〉 ECCV 2016: Computer Vision – ECCV 2016 Workshops ECCV 2016: Computer Vision – ECCV 2016 Workshops, Oct 2016, Amsterdam, Netherlands. pp.133-142, ⟨10.1007/978-3-319-49409-8_13⟩ |
DOI: | 10.1007/978-3-319-49409-8_13 |
Popis: | Conference of 14th European Conference on Computer Vision, ECCV 2016 ; Conference Date: 8 October 2016 Through 16 October 2016; Conference Code:184029; International audience; There is no doubt that SLAM and deep learning methods can benefit from each other. Most recent approaches to coupling those two subjects, however, either use SLAM to improve the learning process, or tend to ignore the geometric solutions that are currently used by SLAM systems. In this work, we focus on improving city-scale SLAM through the use of deep learning. More precisely, we propose to use CNNbased scene labeling to geometrically constrain bundle adjustment. Our experiments indicate a considerable increase in robustness and precision. |
Databáze: | OpenAIRE |
Externí odkaz: |