Show simple item record

dc.contributor.authorZarzar, Jesus
dc.contributor.authorGiancola, Silvio
dc.contributor.authorGhanem, Bernard
dc.date.accessioned2019-12-18T11:13:26Z
dc.date.available2019-12-18T11:13:26Z
dc.date.issued2019-03-25
dc.identifier.urihttp://hdl.handle.net/10754/660668
dc.description.abstractTracking vehicles in LIDAR point clouds is a challenging task due to the sparsity of the data and the dense search space. The lack of structure in point clouds impedes the use of convolution and correlation filters usually employed in 2D object tracking. In addition, structuring point clouds is cumbersome and implies losing fine-grained information. As a result, generating proposals in 3D space is expensive and inefficient. In this paper, we leverage the dense and structured Bird Eye View (BEV) representation of LIDAR point clouds to efficiently search for objects of interest. We use an efficient Region Proposal Network and generate a small number of object proposals in 3D. Successively, we refine our selection of 3D object candidates by exploiting the similarity capability of a 3D Siamese network. We regularize the latter 3D Siamese network for shape completion to enhance its discrimination capability. Our method attempts to solve both for an efficient search space in the BEV space and a meaningful selection using 3D LIDAR point cloud. We show that the Region Proposal in the BEV outperforms Bayesian methods such as Kalman and Particle Filters in providing proposal by a significant margin and that such candidates are suitable for the 3D Siamese network. By training our method end-to-end, we outperform the previous baseline in vehicle tracking by 12% / 18% in Success and Precision when using only 16 candidates.
dc.publisherarXiv
dc.relation.urlhttps://arxiv.org/pdf/1903.10168
dc.rightsArchived with thanks to arXiv
dc.titleEfficient Tracking Proposals using 2D-3D Siamese Networks on LIDAR
dc.typePreprint
dc.contributor.departmentKing Abdullah University of Science and Technology (KAUST), Saudi Arabia
dc.contributor.departmentElectrical Engineering Program
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.eprint.versionPre-print
dc.identifier.arxivid1903.10168
kaust.personZarzar, Jesus
kaust.personGhanem, Bernard
refterms.dateFOA2019-12-18T11:14:33Z


Files in this item

Thumbnail
Name:
Preprintfile1.pdf
Size:
848.6Kb
Format:
PDF
Description:
Pre-print

This item appears in the following Collection(s)

Show simple item record