Search

Your search keyword '"Aljosa Osep"' showing total 91 results
Start Over Author "Aljosa Osep"
91 results on '"Aljosa Osep"'

27. STEP: Segmenting and Tracking Every Pixel.

Author

Mark Weber, Jun Xie, Maxwell D. Collins, Yukun Zhu, Paul Voigtlaender, Hartwig Adam, Bradley Green, Andreas Geiger 0001, Bastian Leibe, Daniel Cremers, Aljosa Osep, Laura Leal-Taixé, and Liang-Chieh Chen

Published
2021

33. Opening up Open-World Tracking.

Author

Yang Liu, Idil Esen Zulfikar, Jonathon Luiten, Achal Dave, Aljosa Osep, Deva Ramanan, Bastian Leibe, and Laura Leal-Taixé

Published
2021

49. EagerMOT: 3D Multi-Object Tracking via Sensor Fusion

Author

Aljosa Osep, Aleksandr Kim, and Laura Leal-Taixé

Subjects
FOS: Computer and information sciences, Computer science, business.industry, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, Mobile robot, Object (computer science), Sensor fusion, Tracking (particle physics), Visualization, Computer Science - Robotics, Video tracking, Trajectory, Computer vision, Motion planning, Artificial intelligence, business, Robotics (cs.RO)
Abstract

Multi-object tracking (MOT) enables mobile robots to perform well-informed motion planning and navigation by localizing surrounding objects in 3D space and time. Existing methods rely on depth sensors (e.g., LiDAR) to detect and track targets in 3D space, but only up to a limited sensing range due to the sparsity of the signal. On the other hand, cameras provide a dense and rich visual signal that helps to localize even distant objects, but only in the image domain. In this paper, we propose EagerMOT, a simple tracking formulation that eagerly integrates all available object observations from both sensor modalities to obtain a well-informed interpretation of the scene dynamics. Using images, we can identify distant incoming objects, while depth estimates allow for precise trajectory localization as soon as objects are within the depth-sensing range. With EagerMOT, we achieve state-of-the-art results across several MOT tasks on the KITTI and NuScenes datasets. Our code is available at https://github.com/aleksandrkim61/EagerMOT., To be published at ICRA 2021. Source code available at https://github.com/aleksandrkim61/EagerMOT

Published
2021

50. 4D Panoptic LiDAR Segmentation

Author

Cyrill Stachniss, Maxim Maximov, Mark Weber, Laura Leal-Taixé, Aljosa Osep, Jens Behley, and Mehmet Aygun

Subjects
FOS: Computer and information sciences, Class (computer programming), Computer science, business.industry, Computer Vision and Pattern Recognition (cs.CV), Association (object-oriented programming), Computer Science - Computer Vision and Pattern Recognition, Object (computer science), Machine learning, computer.software_genre, Semantics, Temporal database, Computer Science - Robotics, Metric (mathematics), Robot, Segmentation, Artificial intelligence, business, Robotics (cs.RO), computer
Abstract

Temporal semantic scene understanding is critical for self-driving cars or robots operating in dynamic environments. In this paper, we propose 4D panoptic LiDAR segmentation to assign a semantic class and a temporally-consistent instance ID to a sequence of 3D points. To this end, we present an approach and a point-centric evaluation metric. Our approach determines a semantic class for every point while modeling object instances as probability distributions in the 4D spatio-temporal domain. We process multiple point clouds in parallel and resolve point-to-instance associations, effectively alleviating the need for explicit temporal data association. Inspired by recent advances in benchmarking of multi-object tracking, we propose to adopt a new evaluation metric that separates the semantic and point-to-instance association aspects of the task. With this work, we aim at paving the road for future developments of temporal LiDAR panoptic perception., CVPR 2021

Published
2021

Catalog

Books, media, physical & digital resources
See catalog results