Cross-Modal Learning of Housing Quality in Amsterdam
This work addresses the challenge of assessing housing quality for urban planning, offering incremental improvements by identifying viable alternatives to GSV for liveability prediction.
The study tackled the problem of predicting housing quality in Amsterdam by comparing ground-level and aerial imagery sources, finding that Google StreetView (GSV) performed best with a 30% improvement over aerial images alone, but Flickr images combined with aerial features reduced this gap to 15%.
In our research we test data and models for the recognition of housing quality in the city of Amsterdam from ground-level and aerial imagery. For ground-level images we compare Google StreetView (GSV) to Flickr images. Our results show that GSV predicts the most accurate building quality scores, approximately 30% better than using only aerial images. However, we find that through careful filtering and by using the right pre-trained model, Flickr image features combined with aerial image features are able to halve the performance gap to GSV features from 30% to 15%. Our results indicate that there are viable alternatives to GSV for liveability factor prediction, which is encouraging as GSV images are more difficult to acquire and not always available.