MAVNet: an Effective Semantic Segmentation Micro-Network for MAV-based Tasks
This addresses the need for efficient image segmentation on resource-constrained MAVs for surveillance and inspection, though it is incremental as it builds on existing methods like ERFNet.
The authors tackled real-time semantic segmentation for micro aerial vehicles (MAVs) by proposing MAVNet, a lightweight deep neural network with 400 times fewer parameters than reference models, achieving up to 48 FPS on high-end hardware and comparable performance in empirical tests.
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.