End-to-end Learning of Multi-sensor 3D Tracking by Detection
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:ZWNZRMVIrecord.jsonopen to challenge →
classification
cs.CV
cs.LGcs.RO
keywords
detectionend-to-endtrackingverywellaccurateapproachcameras
read the original abstract
In this paper we propose a novel approach to tracking by detection that can exploit both cameras as well as LIDAR data to produce very accurate 3D trajectories. Towards this goal, we formulate the problem as a linear program that can be solved exactly, and learn convolutional networks for detection as well as matching in an end-to-end manner. We evaluate our model in the challenging KITTI dataset and show very competitive results.
This paper has not been read by Pith yet.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.