Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Deep Convolutional Network to Extract Real-Time Landmarks for UAV Navigation

Osman Tokluoglu, Mustafa Ozturk

TL;DR

A convolution-based deep learning approach is proposed for the extraction of appropriate landmarks, and its effectiveness is examined.

Abstract

Recent advances in satellite and communication technologies have significantly improved geographical information and monitoring systems. Global System for Mobile Communications (GSM) and Global Navigation Satellite System (GNSS) technologies, which rely on electromagnetic signals transmitted from satellites and base stations, have long been utilized for geolocation applications. However, signal attenuation due to environmental conditions or intentional interference such as jamming may lead to severe degradation or complete loss of positioning capability. In such GNSS-denied environments, landmark extraction becomes critical for the navigation of unmanned aerial vehicles (UAVs) used in monitoring applications. By processing images captured from onboard UAV cameras, reliable visual landmarks can be identified to enable navigation without GNSS support. In this study, a convolution-based deep learning approach is proposed for the extraction of appropriate landmarks, and its effectiveness is examined.

A Deep Convolutional Network to Extract Real-Time Landmarks for UAV Navigation

TL;DR

A convolution-based deep learning approach is proposed for the extraction of appropriate landmarks, and its effectiveness is examined.

Abstract

Recent advances in satellite and communication technologies have significantly improved geographical information and monitoring systems. Global System for Mobile Communications (GSM) and Global Navigation Satellite System (GNSS) technologies, which rely on electromagnetic signals transmitted from satellites and base stations, have long been utilized for geolocation applications. However, signal attenuation due to environmental conditions or intentional interference such as jamming may lead to severe degradation or complete loss of positioning capability. In such GNSS-denied environments, landmark extraction becomes critical for the navigation of unmanned aerial vehicles (UAVs) used in monitoring applications. By processing images captured from onboard UAV cameras, reliable visual landmarks can be identified to enable navigation without GNSS support. In this study, a convolution-based deep learning approach is proposed for the extraction of appropriate landmarks, and its effectiveness is examined.
Paper Structure (7 sections, 3 figures, 1 table)

This paper contains 7 sections, 3 figures, 1 table.

Table of Contents

  1. Introduction
  2. Method
  3. Approach
  4. Dataset and Training
  5. Proposed Method
  6. Results and Discussion
  7. Conclusion

Figures (3)

  • Figure 1: The dataset used for network training was adapted from MnihThesis. (a) Sample input aerial images; (b) corresponding ground-truth building segmentation maps.
  • Figure 2: Proposed deep convolutional neural network architecture. A $192 \times 192$ input image is processed through parallel convolutional branches with different kernel sizes and dilation rates to capture multi-scale representations. The concatenated feature maps are subsequently refined by hierarchical convolutional layers and compressed via a bottleneck structure for dimensionality reduction. Skip connections connect early and deeper layers to preserve spatial information and facilitate gradient propagation.
  • Figure 3: The input images shown in (a) and (c) were used to evaluate the proposed method. The corresponding output predictions obtained from the network are presented in (b) and (d).