Applying a particle filtering technique for canola crop growth stage estimation in Canada

Abhijit Sinha; Weikai Tan; Yifeng Li; Heather McNairn; Xianfeng Jiao; Mehdi Hosseini

doi:10.1117/12.2277968

2 November 2017 Applying a particle filtering technique for canola crop growth stage estimation in Canada

Abhijit Sinha, Weikai Tan, Yifeng Li, Heather McNairn, Xianfeng Jiao, Mehdi Hosseini

Proceedings Volume 10421, Remote Sensing for Agriculture, Ecosystems, and Hydrology XIX; 104211F (2017) https://doi.org/10.1117/12.2277968
Event: SPIE Remote Sensing, 2017, Warsaw, Poland

Abstract

Accurate crop growth stage estimation is important in precision agriculture as it facilitates improved crop management, pest and disease mitigation and resource planning. Earth observation imagery, specifically Synthetic Aperture Radar (SAR) data, can provide field level growth estimates while covering regional scales. In this paper, RADARSAT-2 quad polarization and TerraSAR-X dual polarization SAR data and ground truth growth stage data are used to model the influence of canola growth stages on SAR imagery extracted parameters. The details of the growth stage modeling work are provided, including a) the development of a new crop growth stage indicator that is continuous and suitable as the state variable in the dynamic estimation procedure; b) a selection procedure for SAR polarimetric parameters that is sensitive to both linear and nonlinear dependency between variables; and c) procedures for compensation of SAR polarimetric parameters for different beam modes. The data was collected over three crop growth seasons in Manitoba, Canada, and the growth model provides the foundation of a novel dynamic filtering framework for real-time estimation of canola growth stages using the multi-sensor and multi-mode SAR data. A description of the dynamic filtering framework that uses particle filter as the estimator is also provided in this paper.

Citation Download Citation

Abhijit Sinha, Weikai Tan, Yifeng Li, Heather McNairn, Xianfeng Jiao, and Mehdi Hosseini "Applying a particle filtering technique for canola crop growth stage estimation in Canada ", Proc. SPIE 10421, Remote Sensing for Agriculture, Ecosystems, and Hydrology XIX, 104211F (2 November 2017); https://doi.org/10.1117/12.2277968

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available