Real-time semantic image segmentation on platforms subject to size, weight and power (SWaP) constraints is a key area of interest for air surveillance and inspection. In this work, we propose MAVNet: a small, light-weight, deep neural network for real-time semantic segmentation on micro Aerial Vehicles (MAVs). MAVNet, inspired by ERFNet, features 400 times fewer parameters and achieves comparable performance with some reference models in empirical experiments. Our model achieves a trade-off between speed and accuracy, achieving up to 48 FPS on an NVIDIA 1080Ti and 9 FPS on the NVIDIA Jetson Xavier when processing high resolution imagery. Additionally, we provide two novel datasets that represent challenges in semantic segmentation for real-time MAV tracking and infrastructure inspection tasks and verify MAVNet on these datasets. Our algorithm and datasets are made publicly available.
@article{arxiv.1904.01795,
title = {MAVNet: an Effective Semantic Segmentation Micro-Network for MAV-based Tasks},
author = {Ty Nguyen and Shreyas S. Shivakumar and Ian D. Miller and James Keller and Elijah S. Lee and Alex Zhou and Tolga Ozaslan and Giuseppe Loianno and Joseph H. Harwood and Jennifer Wozencraft and Camillo J. Taylor and Vijay Kumar},
journal= {arXiv preprint arXiv:1904.01795},
year = {2019}
}