Investigating the Use of Street-Level Imagery and Deep Learning to Produce In-Situ Crop Type Information

Orduña-Cabrera, F. ORCID: https://orcid.org/0000-0002-8558-0053, Sandoval-Gastelum, M., McCallum, I. ORCID: https://orcid.org/0000-0002-5812-9988, See, L. ORCID: https://orcid.org/0000-0002-2665-7065, Fritz, S. ORCID: https://orcid.org/0000-0003-0420-8549, Karanam, S., Sturn, T., Javalera Rincón, V. ORCID: https://orcid.org/0000-0001-8743-9777, & Gonzalez-Navarro, F.F. (2023). Investigating the Use of Street-Level Imagery and Deep Learning to Produce In-Situ Crop Type Information. Geographies 3 (3) 563-573. 10.3390/geographies3030029.

Preview	Text geographies-03-00029.pdf - Published Version Available under License Creative Commons Attribution. Download (1MB) | Preview
Preview	Text preprints202307.0724.v1.pdf - Submitted Version Available under License Creative Commons Attribution. Download (718kB) | Preview

Abstract

The creation of crop type maps from satellite data has proven challenging and is often impeded by a lack of accurate in situ data. Street-level imagery represents a new potential source of in situ data that may aid crop type mapping, but it requires automated algorithms to recognize the features of interest. This paper aims to demonstrate a method for crop type (i.e., maize, wheat and others) recognition from street-level imagery based on a convolutional neural network using a bottom-up approach. We trained the model with a highly accurate dataset of crowdsourced labelled street-level imagery using the Picture Pile application. The classification results achieved an AUC of 0.87 for wheat, 0.85 for maize and 0.73 for others. Given that wheat and maize are two of the most common food crops grown globally, combined with an ever-increasing amount of available street-level imagery, this approach could help address the need for improved global crop type monitoring. Challenges remain in addressing the noise aspect of street-level imagery (i.e., buildings, hedgerows, automobiles, etc.) and uncertainties due to differences in the time of day and location. Such an approach could also be applied to developing other in situ data sets from street-level imagery, e.g., for land use mapping or socioeconomic indicators.

Item Type:	Article
Uncontrolled Keywords:	crop type recognition; deep learning; crowdsourcing; street-level imagery
Research Programs:	Advancing Systems Analysis (ASA) Advancing Systems Analysis (ASA) > Exploratory Modeling of Human-natural Systems (EM) Advancing Systems Analysis (ASA) > Novel Data Ecosystems for Sustainability (NODES)
Depositing User:	Luke Kirwan
Date Deposited:	07 Sep 2023 12:33
Last Modified:	07 Sep 2023 12:55
URI:	https://pure.iiasa.ac.at/19041

Actions (login required)

View Item