Title:
CROP PLANTING DISTRIBUTION PREDICTION METHOD BASED ON TIME SERIES REMOTE SENSING DATA AND CONVOLUTIONAL NEURAL NETWORK
Document Type and Number:
WIPO Patent Application WO/2021/068176
Kind Code:
A1
Abstract:
A crop planting distribution prediction method based on time series remote sensing data and a convolutional neural network. The method comprises the following steps: step 1: carrying out ground survey and training sample establishment; step 2: constructing a crop planting distribution prediction model based on time series remote sensing data and a convolutional neural network, wherein the convolutional neural network carries out prediction by means of data of a target pixel point and surrounding pixel points thereof in a multi-temporal image, and an input value is a multi-temporal high-resolution multi-spectral image, and an output value is classification information of crop types and crop rotation modes; and step 3: inputting the time series remote sensing data of a statistical area into the constructed model to acquire a recognition result. A ground survey of only a small number of representative parcels of land is required, a prediction model fusing time series features of remote sensing data and the local features of remote sensing images is constructed, and the context information of decision points is introduced, thereby improving the accuracy of a prediction result.
Inventors:
ZHANG WEI (CN)
HUANG HE (CN)
SHI YANG (CN)
WU XIAOWEI (CN)
HUANG HE (CN)
SHI YANG (CN)
WU XIAOWEI (CN)
Application Number:
PCT/CN2019/110509
Publication Date:
April 15, 2021
Filing Date:
October 11, 2019
Export Citation:
Assignee:
ANHUI ZHONGKE INTELLIGENT PERCEPTION INDUSTRIAL TECH RESEARCH INSTITUTE CO LTD (CN)
International Classes:
G06K9/00
Foreign References:
| CN109063660A | 2018-12-21 | |||
| CN109409261A | 2019-03-01 | |||
| CN109145885A | 2019-01-04 | |||
| US10430691B1 | 2019-10-01 |
Attorney, Agent or Firm:
WUHU SICHENG INTELLECTUAL PROPERTY AGENCY CO., LTD. (CN)
Download PDF: