Documents
Poster
Poster
Poster: Generative-Discriminative Crop Type Identification using Satellite Images
- Citation Author(s):
- Submitted by:
- Nan Qiao
- Last updated:
- 9 November 2019 - 7:23pm
- Document Type:
- Poster
- Document Year:
- 2019
- Event:
- Categories:
- Log in to post comments
Crop type identification refers to distinguishing certain crop from other landcovers, which is an essential and crucial task in agricultural monitoring. Satellite images are good data input for identifying different crops since satellites capture relatively wider area and more spectral information. Based on prior knowledge of crop phenology, multi-temporal images are stacked to extract the growth pattern of varied crops. In this paper, we proposed a machine learning model which combines generative and discriminative models and achieved averaged AP score of 0.903 overall tested crops and regions under the limitation of small datasets and label noise using satellite images taken at different times.