A Robust Framework to Estimate the Spatial Resolution of Overhead Images Using Off-the-Shelf Object Detectors
- Resource Type
- Conference
- Authors
- Liang, Haolin; Newsam, Shawn
- Source
- 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS Geoscience and Remote Sensing Symposium IGARSS , 2021 IEEE International. :8229-8232 Jul, 2021
- Subject
- Aerospace
Geoscience
Photonics and Electrooptics
Signal Processing and Analysis
Training
Geoscience and remote sensing
Detectors
Metadata
Distance measurement
Automobiles
Spatial resolution
Object Detection
Ground Sample Distance
- Language
- ISSN
- 2153-7003
We propose a robust framework for estimating the ground sample distance (GSD) of overhead images using off-the-shelf object detectors. Knowing the GSD of an overhead image is important for many tasks yet images are increasingly being distributed without such meta data due to the advent of drones. We make our framework robust by performing detections over a number of scales and orientations. We derive a reference curve from a large number of training images that relates GSD to object size. This reference curve is used to estimate the GSD of a test image. We demonstrate the effectiveness of our framework on drone imagery ranging from 2 to 32cm GSD using an off-the-shelf car detector.