Farm Parcel Delineation Using Spatio-Temporal Convolutional Networks

Han Lin Aung, Burak Uzkent, Marshall Burke, David Lobell, Stefano Ermon; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2020, pp. 76-77

Abstract


Farm parcel delineation (delineation of boundaries of farmland parcels/segmentation of farmland areas) provides cadastral data that is important in developing and managing climate change policies. Specifically, farm parcel delineation informs applications in downstream governmental policies of land allocation, irrigation, fertilization, greenhouse gases (GHG's), etc. This data can also be useful for the agricultural insurance sector for assessing compensations following damages associated with extreme weather events - a growing trend related to climate change. Using satellite imaging can be a scalable and cost-effective manner to perform the task of farm parcel delineation to collect this valuable data. In this paper, we break down this task using satellite imaging into two approaches: 1) Segmentation of parcel boundaries, and 2) Segmentation of parcel areas. We implemented variations of U-Nets, one of which takes into account temporal information, which achieved the best results on our dataset on farm parcels in France in 2017.

Related Material


[pdf]
[bibtex]
@InProceedings{Aung_2020_CVPR_Workshops,
author = {Aung, Han Lin and Uzkent, Burak and Burke, Marshall and Lobell, David and Ermon, Stefano},
title = {Farm Parcel Delineation Using Spatio-Temporal Convolutional Networks},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2020}
}