Detecting Pipeline Pathways in Landsat 5 Satellite Images With Deep Learning

Kurzfassung

We present a detection model for the automatic recognition of pipeline pathways using a Convolutional Neural Network (CNN). The model was trained with historic low-resolution satellite images of the construction phase of British gas transport pipelines, made with the Landsat 5 Thematic Mapper instrument. The satellite images have been automatically labeled with the help of high-resolution pipeline route data provided by the respective Transmission System Operator (TSO). We have used data augmentation on the training data and subsequently trained our model with 4 different initial learning rates. The model and the different learning rates have been validated with 5-fold cross-validation using the Intersection over Union (IoU) metric. We show that our model is capable of reliably identifying pipeline pathways despite the comparably low resolution of the used satellite images. Further, we have successfully tested the model's capability to generalize to other geographic regions with the deployment of satellite images of the NEL pipeline located in Northern Germany.

Verfügbare Versionen dieses Eintrags

• Detecting Pipeline Pathways in Landsat 5 Satellite Images With Deep Learning. (deposited 19 Jul 2021 16:25) [Gegenwärtig angezeigt]
  • Detecting Pipeline Pathways in Landsat 5 Satellite Images With Deep Learning. (deposited 05 Okt 2021 15:51)