TransFuseGrid: Transformer-based Lidar-RGB fusion for semantic grid prediction

Autor: Gustavo Salazar-Gomez, David Sierra-Gonzalez, Manuel Diaz-Zapata, Anshul Paigwar, Wenqian Liu, Ozgur Erkent, Christian Laugier

Publikováno v: ICARCV 2022-17th International Conference on Control, Automation, Robotics and Vision
ICARCV 2022-17th International Conference on Control, Automation, Robotics and Vision, Dec 2022, Singapore, Singapore. pp.1-6

International audience; Semantic grids are a succinct and convenient approach to represent the environment for mobile robotics and autonomous driving applications. While the use of Lidar sensors is now generalized in robotics, most semantic grid pred

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3e27400a74da84053f1a6e0dc2b480af
https://inria.hal.science/hal-03768008

GridTrack: Detection and Tracking of Multiple Objects in Dynamic Occupancy Grids

Autor: Anshul Paigwar, David Sierra Gonzalez, Ozgur Erkent, Christian Laugier

Publikováno v: ICCV 2021-International Conference on Computer Vision
ICCV 2021-International Conference on Computer Vision, Oct 2021, Virtual Conference, Austria. pp.1-14
Lecture Notes in Computer Science ISBN: 9783030871550
ICVS
ICVS 2021-International Conference on Vision Systems
ICVS 2021-International Conference on Vision Systems, Oct 2021, Virtual Conference, Austria. pp.1-14, ⟨10.1007/978-3-030-87156-7_15⟩

International audience; Multiple Object Tracking is an important task for autonomous vehicles. However, it gets difficult to track objects when it is hard to detect them due to occlusion or distance to the sensors. We propose a method, "GridTrack", t

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::153c4079db57f72c54d0a51c37e369a1
https://hal.inria.fr/hal-03335282

Leveraging Dynamic Occupancy Grids for 3D Object Detection in Point Clouds

Autor: Ozgur Erkent, Jilles S. Dibangoye, David Sierra-Gonzalez, Anshul Paigwar, Christian Laugier

Publikováno v: ICARCV 2020-16th IEEE International Conference on Control, Automation, Robotics and Vision
ICARCV 2020-16th IEEE International Conference on Control, Automation, Robotics and Vision, Dec 2020, Shenzhen, China. pp.1-6
ICARCV

International audience; Traditionally, point cloud-based 3D object detectors are trained on annotated, non-sequential samples taken from driving sequences (e.g. the KITTI dataset). However, by doing this, the developed algorithms renounce to exploit

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c9f9e3c644b6ef11bf5cf329f38ebb68
https://inria.hal.science/hal-03044979/document

GndNet: Fast Ground Plane Estimation and Point Cloud Segmentation for Autonomous Vehicles

Autor: Ozgur Erkent, David Sierra-Gonzalez, Anshul Paigwar, Christian Laugier

Publikováno v: IROS
IROS 2020-IEEE/RSJ International Conference on Intelligent Robots and Systems
IROS 2020-IEEE/RSJ International Conference on Intelligent Robots and Systems, Oct 2020, Las Vegas, NV, United States. pp.2150-2156, ⟨10.1109/IROS45743.2020.9340979⟩

International audience; Ground plane estimation and ground point seg-mentation is a crucial precursor for many applications in robotics and intelligent vehicles like navigable space detection and occupancy grid generation, 3D object detection, point

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9eb5b49688006f044f3b7f1c369a232d
https://doi.org/10.1109/iros45743.2020.9340979

Attentional PointNet for 3D-Object Detection in Point Clouds

Autor: Christian Wolf, Anshul Paigwar, Ozgur Erkent, Christian Laugier

Publikováno v: CVPR Workshops
CVPR 2019-Workshop on Autonomous Driving
CVPR 2019-Workshop on Autonomous Driving, Jun 2019, Long Beach, California, United States. pp.1
CVPR 2019-Workshop on Autonomous driving
CVPR 2019-Workshop on Autonomous driving, Jun 2019, Long Beach, California, United States. pp.1-10, ⟨10.1109/CVPRW.2019.00169⟩
CVPR 2019-Workshop on Autonomous driving, Jun 2019, Long Beach, California, United States. pp.1-10

International audience; Accurate detection of objects in 3D point clouds is a central problem for autonomous navigation. Most existing methods use techniques of hand-crafted features representation or multi-sensor approaches prone to sensor failure.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::addec4aa31f0fd4a629c362071123aba
https://doi.org/10.1109/cvprw.2019.00169