**6. Conclusions**

In this paper, we propose an end-to-end architecture that takes LR satellite imagery as input and gives object detection results as outputs. Our architecture contains a SR network and a detector network. We have used a different combination of SR systems and detectors to compare the AP values for detection using two different datasets. Our experimental results show that the proposed SR network with faster R-CNN has yielded the best results for small objects on satellite imagery. However, we need to add more diverse training data in the OGST dataset to make our model robust in detecting oil and gas storage tanks. We also need to explore diverse datasets and the techniques to create more realistic LR images. In conclusion, our method has combined different strategies to provide a better solution to the task of small-object detection on LR imagery.

**Author Contributions:** Conceptualization, J.R., N.R. and M.S.; methodology, J.R., N.R. and M.S.; software, J.R.; validation, J.R.; formal analysis, J.R.; investigation, J.R.; resources, N.R.; data curation, J.R., S.C. and D.C.; writing–original draft preparation, J.R.; writing–review and editing, J.R., N.R., M.S., S.C. and D.C.; visualization, J.R.; supervision, N.R. and M.S.; project administration, N.R.; funding acquisition, N.R., S.C. and D.C. All authors have read and agreed to the published version of the manuscript.

**Funding:** This research was partially supported by Alberta Geological Survey (AGS) and NSERC discovery grant.

**Acknowledgments:** The first and the second authors acknowledge support from the Department of Computing Science, University of Alberta and Compute Canada.

**Conflicts of Interest:** The authors declare no conflict of interest.
