MAVNet: An effective semantic segmentation micro-network for MAV-based tasks

Ty Nguyen, Shreyas S. Shivakumar, Ian D. Miller, James Keller, Elijah S. Lee, Alex Zhou, Tolga Özaslan, Giuseppe Loianno, Joseph H. Harwood, Jennifer Wozencraft, Camillo J. Taylor, Vijay Kumar

Research output: Contribution to journalArticlepeer-review

Abstract

Real-time semantic image segmentation on platforms subject to size, weight, and power constraints is a key area of interest for air surveillance and inspection. In this letter, we propose MAVNet: a small, light-weight, deep neural network for real-time semantic segmentation on micro aerial vehicles (MAVs). MAVNet, inspired by ERFNet [E. Romera, J. M. lvarez, L. M. Bergasa, and R. Arroyo, "ErfNet: Efficient residual factorized convnet for real-time semantic segmentation," IEEE Trans. Intell. Transp. Syst., vol. 19, no. 1, pp. 263-272, Jan. 2018.], features 400 times fewer parameters and achieves comparable performancewith somereference models in empirical experiments. Additionally,we provide two novel datasets that represent challenges in semantic segmentation for real-timeMAVtracking and infrastructure inspection tasks and verify MAVNet on these datasets. Our algorithm and datasets are made publicly available.

Original languageEnglish (US)
Article number8764006
Pages (from-to)3908-3915
Number of pages8
JournalIEEE Robotics and Automation Letters
Volume4
Issue number4
DOIs
StatePublished - Oct 2019

Keywords

  • Aerial systems: perception and autonomy
  • Object detection
  • Recognition
  • Segmentation and categorization
  • Semantic scene understanding
  • Semantic segmentation

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Biomedical Engineering
  • Human-Computer Interaction
  • Mechanical Engineering
  • Computer Vision and Pattern Recognition
  • Computer Science Applications
  • Control and Optimization
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'MAVNet: An effective semantic segmentation micro-network for MAV-based tasks'. Together they form a unique fingerprint.

Cite this