Abstract
| Original language | English |
|---|---|
| Pages (from-to) | 129-143 |
| Journal | Remote Sensing of Environment |
| Volume | 228 |
| DOIs | |
| Publication status | Published - Jul 2019 |
Fingerprint
Cite this
}
Understanding urban landuse from the above and ground perspectives: A deep learning, multimodal solution. / Srivastava, Shivangi; Vargas-Muñoz, John E.; Tuia, Devis.
In: Remote Sensing of Environment, Vol. 228, 07.2019, p. 129-143.Research output: Contribution to journal › Article › Academic › peer-review
TY - JOUR
T1 - Understanding urban landuse from the above and ground perspectives: A deep learning, multimodal solution
AU - Srivastava, Shivangi
AU - Vargas-Muñoz, John E.
AU - Tuia, Devis
PY - 2019/7
Y1 - 2019/7
N2 - Landuse characterization is important for urban planning. It is traditionally performed with field surveys or manual photo interpretation, two practices that are time-consuming and labor-intensive. Therefore, we aim to automate landuse mapping at the urban-object level with a deep learning approach based on data from multiple sources (or modalities). We consider two image modalities: overhead imagery from Google Maps and ensembles of ground-based pictures (side-views) per urban-object from Google Street View (GSV). These modalities bring complementary visual information pertaining to the urban-objects. We propose an end-to-end trainable model, which uses OpenStreetMap annotations as labels. The model can accommodate a variable number of GSV pictures for the ground-based branch and can also function in the absence of ground pictures at prediction time. We test the effectiveness of our model over the area of Île-de-France, France, and test its generalization abilities on a set of urban-objects from the city of Nantes, France. Our proposed multimodal Convolutional Neural Network achieves considerably higher accuracies than methods that use a single image modality, making it suitable for automatic landuse map updates. Additionally, our approach could be easily scaled to multiple cities, because it is based on data sources available for many cities worldwide.
AB - Landuse characterization is important for urban planning. It is traditionally performed with field surveys or manual photo interpretation, two practices that are time-consuming and labor-intensive. Therefore, we aim to automate landuse mapping at the urban-object level with a deep learning approach based on data from multiple sources (or modalities). We consider two image modalities: overhead imagery from Google Maps and ensembles of ground-based pictures (side-views) per urban-object from Google Street View (GSV). These modalities bring complementary visual information pertaining to the urban-objects. We propose an end-to-end trainable model, which uses OpenStreetMap annotations as labels. The model can accommodate a variable number of GSV pictures for the ground-based branch and can also function in the absence of ground pictures at prediction time. We test the effectiveness of our model over the area of Île-de-France, France, and test its generalization abilities on a set of urban-objects from the city of Nantes, France. Our proposed multimodal Convolutional Neural Network achieves considerably higher accuracies than methods that use a single image modality, making it suitable for automatic landuse map updates. Additionally, our approach could be easily scaled to multiple cities, because it is based on data sources available for many cities worldwide.
U2 - 10.1016/j.rse.2019.04.014
DO - 10.1016/j.rse.2019.04.014
M3 - Article
VL - 228
SP - 129
EP - 143
JO - Remote Sensing of Environment
JF - Remote Sensing of Environment
SN - 0034-4257
ER -