Estimating The Spatial Resolution of Overhead Imagery Using Convolutional Neural Networks
- Resource Type
- Conference
- Authors
- Liang, Haolin; Newsam, Shawn
- Source
- 2019 IEEE International Conference on Image Processing (ICIP) Image Processing (ICIP), 2019 IEEE International Conference onhttps://idams.ieee.org/idams/custom/properties/properties.jsp#. :370-374 Sep, 2019
- Subject
- Computing and Processing
Signal Processing and Analysis
Spatial resolution
Convolution
Training
Computational modeling
Convolutional neural networks
Deep learning
spatial resolution estimation
deep learning regression
convolutional neural network
dilated convolution
- Language
- ISSN
- 2381-8549
We focus on the novel problem of estimating the spatial resolution of overhead imagery. More and more overhead imagery is becoming available without such meta-data either because it was not collected in the first place or was not preserved with the imagery. We propose a bottom-up, data-driven approach using convolutional neural networks. We show that an extended model which incorporates dilated convolution to expand the receptive field of the network outperforms a baseline model on an evaluation dataset with a range of simulated spatial resolutions. We make a number of interesting observations to motivate future work on this novel problem.