DATASET

FlevoVision

Collection: DRLL : Digital Rural Landscape Lab 

Description

Monitoring crop phenology with streer-level imagery using computer vision

Contact

Email
Raphael.DANDRIMONT (at) ec.europa.eu

Contributors

How to cite

European Commission, Joint Research Centre (JRC) (2021): FlevoVision. European Commission, Joint Research Centre (JRC) [Dataset] PID: http://data.europa.eu/89h/343b89a6-14c0-4602-b62e-a94eb8d8fddc

Data access

Training data
URL 

Publications

Publication
Monitoring crop phenology with street-level imagery using computer vision
D`andrimont, R., Yordanov, M., Martinez Sanchez, L. and Van Der Velde, M., Monitoring crop phenology with street-level imagery using computer vision, COMPUTERS AND ELECTRONICS IN AGRICULTURE, ISSN 0168-1699 (online), 196, 2022, p. 106866, JRC128056.
  • ELSEVIER SCI LTD, OXFORD, ENGLAND
  • Abstract

    Street-level imagery holds a significant potential to scale-up in-situ data collection. This is enabled by combining the use of cheap high quality cameras with recent advances in deep learning compute solutions to derive relevant thematic information. We present a framework to collect and extract crop type and phenological information from street level imagery using computer vision. Each month in 2018, a fixed 200-km route was surveyed collecting one picture per second resulting in a total of 400,000 geo-tagged pictures. At 220 specific parcel locations detailed on the spot crop phenology observations were recorded. Classification was done using TensorFlow with a well-known image recognition model, based on transfer learning with convolutional neural networks (MobileNet). A hypertuning methodology was developed to obtain the best performing model among 160 models. This best model was applied on an independent inference set discriminating crop type with a Macro F1 score of 88.1% and main phenological stage at 86.9% at the parcel level. Potential and caveats of the approach along with practical considerations for implementation and improvement are discussed. The proposed framework speeds up high quality in-situ data collection and suggests avenues for massive data collection via automated classification using computer vision.

Geographic areas

Netherlands

Temporal coverage

From date To date
2018-01-01 2018-12-31

Additional information

Published by
European Commission, Joint Research Centre
Created date
2021-10-01
Modified date
2022-04-04
Issued date
2021-10-01
Data theme(s)
Agriculture, fisheries, forestry and food
Update frequency
monthly
Identifier
http://data.europa.eu/89h/343b89a6-14c0-4602-b62e-a94eb8d8fddc
Popularity