GridTrack: Detection and Tracking of Multiple Objects in Dynamic Occupancy Grids - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year :

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

Abstract

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", to overcome this difficulty. We fuse a dynamic occupancy grid map (DOGMa) with an object detector. DOGMa is obtained by applying a Bayesian filter on raw sensor data. This improves the tracking of the partially observed / unobserved objects with the help of the Bayesian filter on raw data, which has a powerful prediction capability. We develop a network to track the objects on the grid and fuse information from previous detections in this network. The experiments show that the multi-object tracking accuracy is high with the usage of the proposed method.
Fichier principal
Vignette du fichier
Erkent-2021-ICVS_noblind.pdf (2.66 Mo) Télécharger le fichier
mytrack_lo2.mp4 (4.03 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03335282 , version 1 (06-09-2021)

Identifiers

Cite

Özgür Erkent, David Sierra Gonzalez, Anshul Paigwar, Christian Laugier. GridTrack: Detection and Tracking of Multiple Objects in Dynamic Occupancy Grids. ICVS 2021 - International Conference on Vision Systems, Oct 2021, Virtual Conference, Austria. pp.1-14, ⟨10.1007/978-3-030-87156-7_15⟩. ⟨hal-03335282⟩
344 View
566 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More