University of Twente Student Theses
DumpingMapper : illegal dumping detection from high spatial resolution satellite imagery
Helvoort, L.F.A. van (2023) DumpingMapper : illegal dumping detection from high spatial resolution satellite imagery.
|
PDF
2MB |
| Abstract: | The illegal dumping of waste materials presents a significant challenge for environmental conservation efforts due to the potential risks it poses to human health and natural habitats. The timely localization and disposal of illegal dumping sites can help prevent further contamination of its surroundings. Currently, the predominantly used method for detecting illegal dumping sites involves manual interpretation of satellite imagery, which is time-consuming, error-prone, and expensive for certain communities. To address this issue, there is a need for more efficient and accurate automated detection methods using satellite imagery. This study aimed to investigate the viability of Adversarial Autoencoder (AAE) models for detecting illegal dumping sites from satellite imagery. Initially, experiments were conducted using Generative Adversarial Networks (GANs), including vanilla GAN, Wasserstein GAN (WGAN) and Wasserstein GAN with gradient penalty (WGAN-GP). However, the study later pivoted towards AAE models, which were found to produce more informative embeddings that improved anomaly detection. The AAE model was trained to produce embeddings that represent the unique features of each satellite image. These embeddings were then visualized using certain techniques, such as dimensionality reduction methods and clustering techniques, to better understand the patterns and structure within the data. The results of this study demonstrate the promising potential of using AAE models for detecting illegal dumping sites from satellite imagery. By providing a more efficient and cost-effective approach to monitoring and identifying potential illegal dumping sites, this technology can help promote sustainable environmental management and public health. |
| Item Type: | Essay (Bachelor) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 54 computer science |
| Programme: | Creative Technology BSc (50447) |
| Link to this item: | https://purl.utwente.nl/essays/94646 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page