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 M. Wozencraft, Camillo J. Taylor, Vijay Kumar

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,” <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">IEEE Trans. Intell. Transp. Syst.</i> , vol. 19, no. 1, pp. 263–272, Jan. 2018.], features 400 times fewer parameters and achieves comparable performance with some reference models in empirical experiments. 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.