Generative Learning for Postprocessing Semantic Segmentation Predictions: A Lightweight Conditional Generative Adversarial Network Based on Pix2pix to Improve the Extraction of Road Surface Areas

Calimanut-Ionut Cira, Miguel-Ángel Manso-Callejo, Ramón Alcarria, Teresa Fernández Pareja, Borja Bordel Sánchez and Francisco Serradilla
Additional contact information
Calimanut-Ionut Cira: Departamento de Ingeniería Topográfica y Cartografía, E.T.S.I. en Topografía, Geodesia y Cartografía, Universidad Politécnica de Madrid, 28031 Madrid, Spain
Miguel-Ángel Manso-Callejo: Departamento de Ingeniería Topográfica y Cartografía, E.T.S.I. en Topografía, Geodesia y Cartografía, Universidad Politécnica de Madrid, 28031 Madrid, Spain
Ramón Alcarria: Departamento de Ingeniería Topográfica y Cartografía, E.T.S.I. en Topografía, Geodesia y Cartografía, Universidad Politécnica de Madrid, 28031 Madrid, Spain
Teresa Fernández Pareja: Departamento de Ingeniería Topográfica y Cartografía, E.T.S.I. en Topografía, Geodesia y Cartografía, Universidad Politécnica de Madrid, 28031 Madrid, Spain
Borja Bordel Sánchez: Departamento de Sistemas Informáticos, E.T.S.I. de Sistemas Informáticos, Universidad Politécnica de Madrid, 28031 Madrid, Spain
Francisco Serradilla: Departamento de Inteligencia Artificial, E.T.S.I. de Sistemas Informáticos, Universidad Politécnica de Madrid, 28031 Madrid, Spain

Land, 2021, vol. 10, issue 1, 1-15

Abstract: Remote sensing experts have been actively using deep neural networks to solve extraction tasks in high-resolution aerial imagery by means of supervised semantic segmentation operations. However, the extraction operation is imperfect, due to the complex nature of geospatial objects, limitations of sensing resolution, or occlusions present in the scenes. In this work, we tackle the challenge of postprocessing semantic segmentation predictions of road surface areas obtained with a state-of-the-art segmentation model and present a technique based on generative learning and image-to-image translations concepts to improve these initial segmentation predictions. The proposed model is a conditional Generative Adversarial Network based on Pix2pix, heavily modified for computational efficiency (92.4% decrease in the number of parameters in the generator network and 61.3% decrease in the discriminator network). The model is trained to learn the distribution of the road network present in official cartography, using a novel dataset containing 6784 tiles of 256 × 256 pixels in size, covering representative areas of Spain. Afterwards, we conduct a metrical comparison using the Intersection over Union (IoU) score (measuring the ratio between the overlap and union areas) on a novel testing set containing 1696 tiles (unseen during training) and observe a maximum increase of 11.6% in the IoU score (from 0.6726 to 0.7515). In the end, we conduct a qualitative comparison to visually assess the effectiveness of the technique and observe great improvements with respect to the initial semantic segmentation predictions.

Keywords: conditional Generative Adversarial Network; generative learning; postprocessing semantic segmentation predictions; road extraction; road surface areas (search for similar items in EconPapers)
JEL-codes: Q15 Q2 Q24 Q28 Q5 R14 R52 (search for similar items in EconPapers)
Date: 2021
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2073-445X/10/1/79/pdf (application/pdf)
https://www.mdpi.com/2073-445X/10/1/79/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jlands:v:10:y:2021:i:1:p:79-:d:481710

Access Statistics for this article

Land is currently edited by Ms. Carol Ma

More articles in Land from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().