Improving regression performance on monocular 3D object detection using bin-mixing and sparse voxel data

Name: Improving regression performance on monocular 3D object detection using bin-mixing and sparse voxel data
Author: Balatkan, Eren, Kıraç, Mustafa Furkan

İsim	Improving regression performance on monocular 3D object detection using bin-mixing and sparse voxel data
Yazar	Balatkan, Eren, Kıraç, Mustafa Furkan
Basım Tarihi:	2021
Basım Yeri	- IEEE
Konu	3D object detection, Bin mixing, Sparse voxel grid, Sub-manifold sparse convolution
Tür	Belge
Dil	İngilizce
Dijital	Evet
Yazma	Hayır
Kütüphane:	Özyeğin Üniversitesi
Demirbaş Numarası	2-s2.0-85125842056
Kayıt Numarası	e5410971-9a53-4eca-9546-3bb861a86210
Lokasyon	Computer Science
Tarih	2021
Örnek Metin	Accurate and fast 3D object detection plays a role of paramount importance for safe and capable autonomous machines. LiDAR point cloud based methods have demonstrated impressive results, yet expensive LiDAR sensors make such approaches infeasible for wide-scale adaptation. Camera based methods on the other hand are performing sub-optimally given safety and accuracy requirements. Traditionally, camera based 3D object detection is performed by generating pseudo-LiDAR point clouds from RGB-D data and using point-cloud based models, however, irregular nature of point cloud data representation makes it challenging to exploit spatial local correlations on 3D space and point cloud based models generally suffer from this. To this end, we propose Sparse Voxel based 3D Object Detection, our approach differs from traditional approaches by converting point cloud information to sparse voxel grid and utilizing sub-manifold sparse convolutions to extract information instead of PointNet based models. Furthermore, we propose Bin-Mixing layers. Bin-Mixing replaces the output layer of a neural network and boosts performance by representing the problem of regression in a fashion that is easier for network to learn.
DOI	10.1109/UBMK52708.2021.9558880

Kaynağa git Özyeğin Üniversitesi

Aramaya Dön

Özyeğin Üniversitesi

Kaynağa git

Improving regression performance on monocular 3D object detection using bin-mixing and sparse voxel data

Yazar Balatkan, Eren, Kıraç, Mustafa Furkan

Basım Tarihi 2021

Basım Yeri - IEEE

Konu 3D object detection, Bin mixing, Sparse voxel grid, Sub-manifold sparse convolution

Tür Belge

Dil İngilizce

Dijital Evet

Yazma Hayır

Kütüphane Özyeğin Üniversitesi

Demirbaş Numarası 2-s2.0-85125842056

Kayıt Numarası e5410971-9a53-4eca-9546-3bb861a86210

Lokasyon Computer Science

Tarih 2021

Örnek Metin Accurate and fast 3D object detection plays a role of paramount importance for safe and capable autonomous machines. LiDAR point cloud based methods have demonstrated impressive results, yet expensive LiDAR sensors make such approaches infeasible for wide-scale adaptation. Camera based methods on the other hand are performing sub-optimally given safety and accuracy requirements. Traditionally, camera based 3D object detection is performed by generating pseudo-LiDAR point clouds from RGB-D data and using point-cloud based models, however, irregular nature of point cloud data representation makes it challenging to exploit spatial local correlations on 3D space and point cloud based models generally suffer from this. To this end, we propose Sparse Voxel based 3D Object Detection, our approach differs from traditional approaches by converting point cloud information to sparse voxel grid and utilizing sub-manifold sparse convolutions to extract information instead of PointNet based models. Furthermore, we propose Bin-Mixing layers. Bin-Mixing replaces the output layer of a neural network and boosts performance by representing the problem of regression in a fashion that is easier for network to learn.

DOI 10.1109/UBMK52708.2021.9558880