Göm meny

Independently Moving Object Trajectories from Sequential Hierarchical Ransac

Mikael Persson, Per-Erik Forssén
VISAPP21
International Conference on Computer Vision Theory and Applications (VISAPP'21)
February 2021

Abstract

Safe robot navigation in a dynamic environment, requires the trajectories of each independently moving object (IMO). We present the novel and effective system Sequential Hierarchical Ransac Estimation (Shire) designed for this purpose. The system uses a stereo camera stream to find the objects and trajectories in real time. Shire detects moving objects using geometric consistency and finds their trajectories using bundle adjustment. Relying on geometric consistency allows the system to handle objects regardless of semantic class, unlike approaches based on semantic segmentation. Most Visual Odometry (VO) systems are inherently limited to single motion by the choice of tracker. This limitation allows for efficient and robust ego-motion estimation in real time, but preclude tracking the multiple motions sought. Shire instead uses a generic tracker and achieves accurate VO and IMO estimates using track analysis. This removes the restriction to a single motion while retaining the real-time performance required for live navigation. We evaluate the system by bounding box intersection over union and ID persistence on a public dataset, collected from an autonomous test vehicle driving in real traffic. We also show the velocities of estimated IMOs. We investigate variations of the system that provide trade offs between accuracy, performance and limitations.

Full Paper

Portable document format file PDF ()
Paper available in Scitepress Digital Library. Dataset and code can be accessed from: [IMO Dataset]

Video on YouTube.


Bibtex entry

@InProceedings{persson21,
  author = {Mikael Persson and Per-Erik Forss\'en},
  title =  {Independently Moving Object Trajectories from Sequential Hierarchical Ransac},
  booktitle = {International Conference on Computer Vision Theory and Applications ({VISAPP'21})},
  month = {February},
  year = {2021},
  url =  {https://doi.org/10.5220/0010253407220731},
  isbn={978-989-758-488-6},
  issn={2184-4321},
  publisher = {Scitepress Digital Library.}
}

Per-Erik Forssén
 

Per-Erik Forssén

Contact:

Computer Vision Laboratory
Department of Electrical Engineering
Building B
Room 2D:521
SE-581 83 Linköping, Sweden
+46(0)13 285654

< >

My pages:


Informationsansvarig: Per-Erik Forss&eacute;n
Senast uppdaterad: 2023-09-06