4.7 Article

DroneSegNet: Robust Aerial Semantic Segmentation for UAV-Based IoT Applications

Journal

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
Volume 71, Issue 4, Pages 4277-4286

Publisher

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TVT.2022.3144358

Keywords

Image segmentation; Feature extraction; Semantics; Internet of Things; Deep learning; Drones; Computer architecture; Semantic segmentation; UAVs; aerial scene analysis; deep learning; IoT

Funding

  1. SICI SICRG through Artificial Intelligence Enabled Security Provisioning and Vehicular Vision innovations for Autonomous Vehicles Project
  2. BITS Additional Competitive Research Grant through Disaster Monitoring from Aerial Imagery using Deep Learning Project [PLN/AD/2018-19/5]
  3. NVIDIA Corporation

Ask authors/readers for more resources

This work proposes a deep learning approach for robust semantic segmentation of aerial scenes captured by UAVs. The approach utilizes a three-tier deep learning architecture and learns from aerial scenes along with elevation maps to improve the accuracy and performance of semantic segmentation.
Unmanned Aerial Vehicles (UAVs) are the promising Flying IoT devices of the future, which can be equipped with various sensors and cognitive capabilities to perform numerous tasks related to remote sensing, search and rescue operations, object tracking, segmentation of roads and buildings, surveillance, etc. However, these AI-driven tasks require heavy computation and may lead to suboptimal performance with embedded processors on a power-constrained battery-operated drone. This work proposes a novel deep learning approach for performing robust semantic segmentation of aerial scenes captured by UAVs. In our setup, the power-constrained drone is used only for data collection, while the computationally intensive tasks are offloaded to a GPU cloud server. Our architecture performs robust semantic segmentation by learning the segmentation maps from jointly utilizing of aerial scenes along with the respective elevation maps in a semi-supervised approach. We propose a three-tier deep learning architecture, wherein the first module aims at preliminary feature extraction from aerial scenes using a backbone feature extractor. The second module captures the spatial dependency between the aerial scenes and their respective elevation maps to obtain better semantic information, which is achieved by a bi-directional LSTM. The third module is aimed at enhancing the performance of semantic segmentation through a semi-supervised approach with an encoder to generate segmentation maps and a decoder to reconstruct feature maps. This semi-supervised feature learning ensures robust extraction along with scalability. The proposed architecture was validated on real-world aerial datasets and achieves state-of-the-art results for aerial image segmentation.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available