Back to the Feature: Learning Robust Camera Localization from Pixels to Pose

Autor: Hugo Germain, Torsten Sattler, Fredrik Kahl, Paul-Edouard Sarlin, Vincent Lepetit, Marc Pollefeys, Viktor Larsson, Ajaykumar Unagar, Lars Hammarstrand, Måns Larsson, Carl Toft

Publikováno v: CVPR
Conference on Computer Vision and Pattern Recognition
Conference on Computer Vision and Pattern Recognition, 2021, Online, United States
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Camera pose estimation in known scenes is a 3D geometry task recently tackled by multiple learning algorithms. Many regress precise geometric quantities, like poses or 3D points, from an input image. This either fails to generalize to new viewpoints

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::22b78e02039e0f35d7f53b3be98d1f3a

Long-Term Visual Localization Revisited

Autor: Akihiko Torii, Fredrik Kahl, Josef Sivic, Carl Toft, Daniel Safari, Lars Hammarstrand, Masatoshi Okutomi, Marc Pollefeys, Will Maddern, Tomas Pajdla, Torsten Sattler, Erik Stenborg

Publikováno v: IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2020, pp.14. ⟨10.1109/TPAMI.2020.3032010⟩
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, pp.14. ⟨10.1109/TPAMI.2020.3032010⟩

International audience; Visual localization enables autonomous vehicles to navigate in their surroundings and augmented reality applications to linkvirtual to real worlds. Practical visual localization approaches need to be robust to a wide variety o

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8c2fe59b2413c08c49dbc7e4bd2f4919
https://pubmed.ncbi.nlm.nih.gov/33074802

A Cross-Season Correspondence Dataset for Robust Semantic Segmentation

Autor: Fredrik Kahl, Lars Hammarstrand, Måns Larsson, Marc Pollefeys, Torsten Sattler, Erik Stenborg

Publikováno v: CVPR

In this paper, we present a method to utilize 2D-2D point matches between images taken during different image conditions to train a convolutional neural network for semantic segmentation. Enforcing label consistency across the matches makes the final

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ddbb875c5e5ef568fbf4b514a5664817
https://doi.org/10.1109/cvpr.2019.00976

Coordination of Cooperative Autonomous Vehicles: Toward safer and more efficient road transportation

Autor: Henk Wymeersch, Paolo Falcone, Erik Steinmetz, Lars Hammarstrand, Gabriel Rodrigues de Campos, Robert Hult

Publikováno v: IEEE Signal Processing Magazine
IEEE Signal Processing Magazine (1053-5888) vol.33(2016)

While intelligent transportation systems come in many shapes and sizes, arguably the most transformational realization will be the autonomous vehicle. As such vehicles become commercially available in the coming years, first on dedicated roads and un

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fa23dc7040cc900ab6065634bfa0146a
https://doi.org/10.1109/msp.2016.2602005

Variational Bayesian Expectation Maximization for Radar Map Estimation

Autor: Lars Hammarstrand, Malin Lundgren, Lennart Svensson

Publikováno v: IEEE Transactions on Signal Processing. 64:1391-1404

For self-localization, a detailed and reliable map of the environment can be used to relate sensor data to static features with known locations. This paper presents a method for construction of detailed radar maps that describe the expected intensity

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::eac21ddcd449b8f30e09fd349f034e9d
https://doi.org/10.1109/tsp.2015.2496287