Training set effect on super resolution for automated target recognition
| Autor: | Josh Kalin, Matthew Ciolino, David Noever |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Contextual image classification Computer science business.industry Computer Vision and Pattern Recognition (cs.CV) Deep learning Computer Science - Computer Vision and Pattern Recognition ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Process (computing) Pattern recognition Ontology (information science) Object detection Automatic target recognition Binary classification Artificial intelligence business Image resolution |
| Zdroj: | Automatic Target Recognition XXX. |
| DOI: | 10.1117/12.2557845 |
| Popis: | Single Image Super Resolution (SISR) is the process of mapping a low-resolution image to a high resolution image. This inherently has applications in remote sensing as a way to increase the spatial resolution in satellite imagery. This suggests a possible improvement to automated target recognition in image classification and object detection. We explore the effect that different training sets have on SISR with the network, Super Resolution Generative Adversarial Network (SRGAN). We train 5 SRGANs on different land-use classes (e.g. agriculture, cities, ports) and test them on the same unseen dataset. We attempt to find the qualitative and quantitative differences in SISR, binary classification, and object detection performance. We find that curated training sets that contain objects in the test ontology perform better on both computer vision tasks while having a complex distribution of images allows object detection models to perform better. However, Super Resolution (SR) might not be beneficial to certain problems and will see a diminishing amount of returns for datasets that are closer to being solved. 10 pages, 19 figures, 26 references |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|