EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Run Your 3D Object Detector on NVIDIA Jetson Platforms:A Benchmark Analysis

Chungjae Choe, Minjae Choe, Sungwook Jung iD

Sensors · 15.04.2023 · 23 (8) · 4005

DOI: 10.3390/s23084005 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 15.04.2023. Verfasst von Chungjae Choe und 2 weiteren Autor:innen. Beteiligte Einrichtung: Autonomous IoT Research Center, Korea Electronics Technology Institute, Seongnam 13509, Republic of Korea. Die Arbeit wurde bisher 34-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Institute for Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government(MSIT), Institute for Information & communications Technology Planning & Evaluation (IITP).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents a benchmark analysis of NVIDIA Jetson platforms when operating deep learning-based 3D object detection frameworks. Three-dimensional (3D) object detection could be highly beneficial for the autonomous navigation of robotic platforms, such as autonomous vehicles, robots, and drones. Since the function provides one-shot inference that extracts 3D positions with depth information and the heading direction of neighboring objects, robots can generate a reliable path to navigate without collision. To enable the smooth functioning of 3D object detection, several approaches have been developed to build detectors using deep learning for fast and accurate inference. In this paper, we investigate 3D object detectors and analyze their performance on the NVIDIA Jetson series that contain an onboard graphical processing unit (GPU) for deep learning computation. Since robotic platforms often require real-time control to avoid dynamic obstacles, onboard processing with a built-in computer is an emerging trend. The Jetson series satisfies such requirements with a compact board size and suitable computational performance for autonomous navigation. However, a proper benchmark that analyzes the Jetson for a computationally expensive task, such as point cloud processing, has not yet been extensively studied. In order to examine the Jetson series for such expensive tasks, we tested the performance of all commercially available boards (i.e., Nano, TX2, NX, and AGX) with state-of-the-art 3D object detectors. We also evaluated the effect of the TensorRT library to optimize a deep learning model for faster inference and lower resource utilization on the Jetson platforms. We present benchmark results in terms of three metrics, including detection accuracy, frame per second (FPS), and resource usage with power consumption. From the experiments, we observe that all Jetson boards, on average, consume over 80% of GPU resources. Moreover, TensorRT could remarkably increase inference speed (i.e., four times faster) and reduce the central processing unit (CPU) and memory consumption in half. By analyzing such metrics in detail, we establish research foundations on edge device-based 3D object detection for the efficient operation of various robotic applications.

Schlagwörter

Stichwörter der Autor:innen

3D object detectionJetson platformsbenchmarkdeep learning

Autor:innen und Institutionen

  • Autonomous IoT Research Center, Korea Electronics Technology Institute, Seongnam 13509, Republic of Korea.
  • Caterpillar Inc., Peoria, IL 61629, USA.

ORCID-Profile: Sungwook Jung

Förderung

  • Institute for Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government(MSIT)
  • Institute for Information & communications Technology Planning & Evaluation (IITP)

Zitieren

APA

Choe, C., Choe, M., & Jung, S. (2023). Run Your 3D Object Detector on NVIDIA Jetson Platforms:A Benchmark Analysis. Sensors, 23(8), 4005. https://doi.org/10.3390/s23084005

Vancouver

Choe C, Choe M, Jung S. Run Your 3D Object Detector on NVIDIA Jetson Platforms:A Benchmark Analysis. Sensors. 2023;23(8):4005. doi:10.3390/s23084005

BibTeX
@article{Choe2023,
  author = {Choe, Chungjae and Choe, Minjae and Jung, Sungwook},
  title = {Run Your 3D Object Detector on NVIDIA Jetson Platforms:A Benchmark Analysis},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {8},
  pages = {4005},
  doi = {10.3390/s23084005}
}
Kostenlos starten →