A Weakly Supervised Approach for Estimating Spatial Density Functions from High-Resolution Satellite Imagery
This work addresses the challenge of fine-grained density estimation in remote sensing for applications such as urban planning, but it is incremental as it builds on existing weakly supervised methods.
The paper tackles the problem of estimating spatial density functions from high-resolution satellite imagery using only coarse-grained density aggregates, and demonstrates that their approach yields better density estimates than a common baseline across synthetic datasets and real-world applications like population and housing density estimation.
We propose a neural network component, the regional aggregation layer, that makes it possible to train a pixel-level density estimator using only coarse-grained density aggregates, which reflect the number of objects in an image region. Our approach is simple to use and does not require domain-specific assumptions about the nature of the density function. We evaluate our approach on several synthetic datasets. In addition, we use this approach to learn to estimate high-resolution population and housing density from satellite imagery. In all cases, we find that our approach results in better density estimates than a commonly used baseline. We also show how our housing density estimator can be used to classify buildings as residential or non-residential.