Szczegóły publikacji
Opis bibliograficzny
Hardware-software implementation of the PointPillars network for 3D object detection in point clouds / Joanna STANISZ, Konrad LIS, Tomasz KRYJAK, Marek GORGOŃ // W: DASIP 2021 [Dokument elektroniczny] : workshop on Design and Architectures for Signal and Image Processing - 14th edition : January 18–20 2021, Budapest, Hungary : proceedings. — Wersja do Windows. — Dane tekstowe. — [Nowy Jork] : Association for Computing Machinery, cop. 2021. — e-ISBN: 978-1-4503-8901-3. — S. 44–51. — Wymagania systemowe: Adobe Reader. — Bibliogr. s. 51, Abstr.
Autorzy (4)
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 132404 |
|---|---|
| Data dodania do BaDAP | 2021-02-04 |
| Tekst źródłowy | URL |
| DOI | 10.1145/3441110.3441150 |
| Rok publikacji | 2021 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Wydawca | Association for Computing Machinery (ACM) |
Abstract
In this paper, we present a hardware-software implementation of a deep neural network for object detection based on a point cloud obtained by a LiDAR sensor. The Brevitas / PyTorch tools were used for network quantisation and the FINN tool for hardware implementation in the reprogrammable Zynq UltraScale+ MPSoC device. The PointPillars network was used in the research, as it is a reasonable compromise between detection accuracy and calculation complexity. The obtained results show that quite a significant computation precision limitation along with a few network architecture simplifications allows the solution to be implemented on an heterogeneous embedded platform with reasonable detection accuracy.
