Resource-constrained onboard inference of 3D object detection and localisation in point clouds targeting self-driving applications

Research about deep learning applied in object detection tasks in LiDAR data has been massively widespread in recent years, achieving notable developments, namely in improving precision and inference speed performances. These improvements have been facilitated by powerful GPU servers, taking advanta...

ver descrição completa

Detalhes bibliográficos
Autor principal: Silva, António José Linhares (author)
Outros Autores: Fernandes, Duarte (author), Névoa, Rafael Augusto Cunha Costinha (author), Monteiro, João L. (author), Novais, Paulo (author), Girão, Pedro (author), Afonso, Tiago (author), Melo-Pinto, Pedro (author)
Formato: article
Idioma:eng
Publicado em: 2021
Assuntos:
Autonomous driving
Deep learning methods
LiDAR scanners
3D object detection
Onboard inference
Quantisation methods
Science & Technology
Texto completo:https://hdl.handle.net/1822/76714
País:Portugal
Oai:oai:repositorium.sdum.uminho.pt:1822/76714

Texto Completo

https://hdl.handle.net/1822/76714

Registos relacionados