Skip to content

Commit

Permalink
Merge pull request #25 from PUTvision/bill_dataset
Browse files Browse the repository at this point in the history
Add UAV Billboards article and dataset
  • Loading branch information
bartoszptak authored Jul 9, 2024
2 parents 4cdeef2 + ebfda85 commit 1be9f30
Show file tree
Hide file tree
Showing 2 changed files with 23 additions and 0 deletions.
23 changes: 23 additions & 0 deletions _posts/2024/07/2024-07-09-uav-billboards-detection.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,23 @@
---
layout: single
title: "Mapping urban large-area advertising structures using drone imagery and deep learning-based spatial data analysis"
author: [ptak-bartosz, kraft-marek]
modified: 2024-07-09
tags: [uav, object detection, deep learning, gis, billboards]
category: [publication, dataset]
teaser: "/assets/images/posts/2024/07/uavbilly-thumb.webp"
---

<iframe width="1280" height="720" src="https://www.youtube.com/embed/Q6tZfh7PukI" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe>

## Abstract:

> The problem of visual pollution is a growing concern in urban areas, characterised by intrusive visual elements that can lead to overstimulation and distraction, obstructing views and causing distractions for drivers. Large-area advertising structures, such as billboards, by being effective mediums, are significant contributors to visual pollution. Illegally placed or huge billboards can also exacerbate those issues and pose safety hazards. Therefore, there is a pressing need for effective and efficient methods to identify and manage advertising structures in urban areas. This paper proposes a deep-learning-based system for automatically detecting billboards using consumer-grade unmanned aerial vehicles. Thanks to the geospatial information from the device's sensors, the position of billboards can be estimated. Side by side with the system, we share the very first dataset for billboard detection from a drone view. It contains 1361 images supplemented with spatial metadata, together with 5210 annotations.
Link to the publication: [https://doi.org/10.1111/TGIS.13208](https://doi.org/10.1111/TGIS.13208)

Link to the code and UAVBillboards dataset: [https://putvision.github.io/UAVBillboards/](https://putvision.github.io/UAVBillboards/)

## Promo video

<iframe width="1280" height="720" src="https://www.youtube.com/embed/bb1CdrZIdI4" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe>
Binary file added assets/images/posts/2024/07/uavbilly-thumb.webp
Binary file not shown.

0 comments on commit 1be9f30

Please sign in to comment.