Details

Autor(en) / Beteiligte

• Berriel, Rodrigo F.
• Teixeira Lopes, Andre
• de Souza, Alberto F.
• Oliveira-Santos, Thiago

Titel

Deep Learning-Based Large-Scale Automatic Satellite Crosswalk Classification

Ist Teil von

• IEEE geoscience and remote sensing letters, 2017-09, Vol.14 (9), p.1513-1517

Ort / Verlag

Piscataway: IEEE

Erscheinungsjahr

2017

Quelle

IEEE

Beschreibungen/Notizen

• High-resolution satellite imagery has been increasingly used on remote sensing classification problems. One of the main factors is the availability of this kind of data. Despite the high availability, very little effort has been placed on the zebra crossing classification problem. In this letter, crowdsourcing systems are exploited in order to enable the automatic acquisition and annotation of a large-scale satellite imagery database for crosswalks related tasks. Then, this data set is used to train deep-learning-based models in order to accurately classify satellite images that contain or not contain zebra crossings. A novel data set with more than 240000 images from 3 continents, 9 countries, and more than 20 cities was used in the experiments. The experimental results showed that freely available crowdsourcing data can be used to accurately (97.11%) train robust models to perform crosswalk classification on a global scale.