![](bg8.png)
6 CONCLUSIONS
We have built a web-based innovative system for au-
tomatic recognition of structures like wells and farm
ponds. Our system has better accuracy as well as
faster detection time compared to earlier systems. We
have introduced two new public datasets, using which
we explore the trade-off between object detection ac-
curacy and inference time. We find FasterRCNN to
be giving the best accuracy though very high infer-
ence time, tinyYOLOv3 to be the fastest but lagging
in accuracy, and RetinaNet providing the golden mean
having both good accuracy as well as reasonable in-
ference time.
REFERENCES
Abhay N (2016). How to get shettale subsidy for farm pond
in 2016. URL: http://indiamicrofinance.com/shettale-
subsidy-farm-pond-2016.htm. Online; Accessed 15-
02-2019.
Anjali Marar, T. I. E. (2019). Explained: Jalyukta shivar key
for maharashtra, but still has a long road ahead. URL:
https://indianexpress.com/article/explained/jalyukta-
shivar-key-for-maharashtra-but-still-has-a-long-road-
ahead/. Online; Accessed: 2019-12-20.
Audebert, N., Le Saux, B., and Lef
`
evre, S. (2017).
Segment-before-detect: Vehicle detection and classi-
fication through semantic segmentation of aerial im-
ages. Remote Sensing, 9(4).
Cheng, G. and Han, J. (2016). A survey on object detection
in optical remote sensing images. ISPRS Journal of
Photogrammetry and Remote Sensing, 117.
Dorrer, G., Koriukin, M., Yushkova, S., and Sviridova, L.
(2019). Vehicle detection in aerial images. IOP Conf.
Series: Earth and Environmental Science.
Everingham, M., Van Gool, L., Williams, C. K. I., Winn,
J., and Zisserman, A. (2012). The PASCAL Visual
Object Classes Challenge 2012 Results.
Frenken, K. (2012). Irrigation in Southern and Eastern Asia
in figures - AQUASTAT Survey 2011.
Girshick, R. (2015). Fast r-cnn. In 2015 IEEE Intl. Conf.
on Computer Vision.
Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014).
Rich feature hierarchies for accurate object detection
and semantic segmentation. In IEEE Conf. on Com-
puter Vision and Pattern Recognition.
Google Static Maps (2019). Google maps javascript api
v3 reference. URL: https://developers.google.com/
maps/documentation/ javascript/reference/3.37. On-
line;Accessed 04-January-2020.
He, K., Zhang, X., Ren, S., and Sun, J. (2014). Spatial pyra-
mid pooling in deep convolutional networks for visual
recognition. Lecture Notes in Computer Science.
Kirpich, P. Z., Haman, D. Z., and Styles, S. W. (1999). Prob-
lems of irrigation in developing countries. Journal of
Irrigation and Drainage Engineering, 125(1).
Lin, T., Doll
´
ar, P., Girshick, R., He, K., Hariharan, B., and
Belongie, S. (2017). Feature pyramid networks for
object detection. In IEEE Conf. on Computer Vision
and Pattern Recognition.
Lin, T.-Y., Goyal, P., Girshick, R., He, K., and Dollar, P.
(2017). Focal loss for dense object detection. In The
IEEE Intl. Conf. on Computer Vision.
Lin, T.-Y., Maire, M., Belongie, S., Bourdev, L., Girshick,
R., Hays, J., Perona, P., Ramanan, D., Zitnick, C. L.,
and Doll
´
ar, P. (2014). Microsoft coco: Common ob-
jects in context.
MRSAC (2015). Maharashtra remote sensing ap-
plication centre. jalyukt shivar , water con-
servation department, mantralaya, mumbai.
URL:http://mrsac.maharashtra.gov.in/jalyukt/. On-
line; Accessed: 2019-09-15.
NIC , MeitY. (2014). National informatics centre. fifth
census of minor irrigation schemes. URL: http://
mi5census-data.nic.in/nologin/introduction.action.
Online; Accessed: 2019-09-20.
Prasad, P. and Sohoni, M. (2018). Farmponds for horticul-
ture: Boon or curse? analysing impact on farm prof-
itability, resource sustainability and social welfare. In
Proc., 36th Intl. Conf. of the System Dynamics Society.
Redmon, J., Divvala, S., Girshick, R., and Farhadi, A.
(2016). You only look once: Unified, real-time ob-
ject detection. In Conf. on Computer Vision & Pattern
Recognition.
Redmon, J. and Farhadi, A. (2018). Yolov3: An incremental
improvement. arXiv.
Ren, S., He, K., Girshick, R., and Sun, J. (2017). Faster
r-cnn: Towards real-time object detection with region
proposal networks. volume 39.
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S.,
Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bern-
stein, M., Berg, A. C., and Fei-Fei, L. (2015). Im-
agenet large scale visual recognition challenge. Intl.
Journal of Computer Vision (IJCV), 115(3).
Saito, S. and Aoki, Y. (2015). Building and road detection
from large aerial imagery. In Lam, E. Y. and Niel,
K. S., editors, Image Processing: Machine Vision Ap-
plications VIII, volume 9405. SPIE.
Uijlings, J., Sande, K., Gevers, T., and Smeulders, A.
(2013). Selective search for object recognition. Intl.
Journal of Computer Vision, 104.
V. K. Bhatia, et. al (2010). Evaluation of Rationalization
of Minor Irrigation Statistics (RMIS) Scheme, Indian
Agriculture Statistice Research Institute, New Delhi.
Vakalopoulou, M., Karantzalos, K., Komodakis, N., and
Paragios, N. (2015). Building detection in very high
resolution multispectral data with deep learning fea-
tures. In 2015 IEEE Intl. Geoscience and Remote
Sensing Symposium (IGARSS).
Wagh, P., Das, D., and Damani., O. (2019). Well detec-
tion in satellite images using convolutional neural net-
works. In Proc., 5th Intl. Conf. on Geographical Infor-
mation Systems Theory, Applications & Management.
Yang, F., Chen, H., Li, J., Li, F., Wang, L., and Yan, X.
(2019). Single shot multibox detector with kalman
filter for online pedestrian detection in video. IEEE
Access, 7.
Yuan, J. (2018). Learning building extraction in aerial
scenes with convolutional networks. IEEE Transac-
tions on Pattern Analysis and Machine Intelligence.
Yuan, J., Yang, H. L., Omitaomu, O. A., and Bhaduri, B. L.
(2016). Large-scale solar panel mapping from aerial
images using deep convolutional networks. In 2016
IEEE Intl. Conf. on Big Data.
Aiding Irrigation Census in Developing Countries by Detecting Minor Irrigation Structures from Satellite Imagery
215