# Fine-Grained Land Use Classification at the City Scale Using Ground-Level Images

arXiv: https://arxiv.org/abs/1802.02668 · HTML: https://mlsanity.com/paper/1802.02668/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Feb 2018.

## Built on by (most cited first, 8 of 8)

- [OmniCity: Omnipotent City Understanding with Multi-level and Multi-view Images](https://mlsanity.com/paper/2208.00928/) (2022)
- [Revisiting Near/Remote Sensing with Geospatial Attention](https://mlsanity.com/paper/2204.01807/) (2022)
- [Using Social Media Images for Building Function Classification](https://mlsanity.com/paper/2202.07315/) (2022)
- [Geo-Information Harvesting from Social Media Data](https://mlsanity.com/paper/2211.00543/) (2022)
- [Urban land-use analysis using proximate sensing imagery: a survey](https://mlsanity.com/paper/2101.04827/) (2021)
- [Exploration and Exploitation of Unlabeled Data for Open-Set Semi-Supervised Learning](https://mlsanity.com/paper/2306.17699/) (2023)
- [Unsupervised Urban Land Use Mapping with Street View Contrastive Clustering and a Geographical Prior](https://mlsanity.com/paper/2504.17551/) (2025)
- [Designing Deep Networks for Scene Recognition](https://mlsanity.com/paper/2303.07402/) (2023)

## Abstract (arXiv)

We perform fine-grained land use mapping at the city scale using ground-level images. Mapping land use is considerably more difficult than mapping land cover and is generally not possible using overhead imagery as it requires close-up views and seeing inside buildings. We postulate that the growing collections of georeferenced, ground-level images suggest an alternate approach to this geographic knowledge discovery problem. We develop a general framework that uses Flickr images to map 45 different land-use classes for the City of San Francisco. Individual images are classified using a novel convolutional neural network containing two streams, one for recognizing objects and another for recognizing scenes. This network is trained in an end-to-end manner directly on the labeled training images. We propose several strategies to overcome the noisiness of our user-generated data including search-based training set augmentation and online adaptive training. We derive a ground truth map of San Francisco in order to evaluate our method. We demonstrate the effectiveness of our approach through geo-visualization and quantitative analysis. Our framework achieves over 29% recall at the individual land parcel level which represents a strong baseline for the challenging 45-way land use classification problem especially given the noisiness of the image data.