US 11,864,552 B2
Digital detection method and system for predicting drug resistance of transgenic maize
Yong He, Hangzhou (CN); Xuping Feng, Hangzhou (CN); Mingzhu Tao, Hangzhou (CN); Rui Yang, Hangzhou (CN); Jinnuo Zhang, Hangzhou (CN); and Yongqiang Shi, Hangzhou (CN)
Assigned to Zhejiang University, Hangzhou (CN)
Filed by Zhejiang University, Hangzhou (CN)
Filed on Aug. 11, 2021, as Appl. No. 17/399,826.
Claims priority of application No. 202110029557.8 (CN), filed on Jan. 11, 2021.
Prior Publication US 2022/0217966 A1, Jul. 14, 2022
Int. Cl. A01M 7/00 (2006.01); G06T 7/136 (2017.01); G06T 7/62 (2017.01); G06T 7/11 (2017.01); G06T 7/90 (2017.01); A01G 22/20 (2018.01); G01S 17/894 (2020.01); G06T 7/00 (2017.01); G06T 17/00 (2006.01); G06N 3/044 (2023.01); G06N 3/045 (2023.01)
CPC A01M 7/0089 (2013.01) [A01G 22/20 (2018.02); G01S 17/894 (2020.01); G06N 3/044 (2023.01); G06N 3/045 (2023.01); G06T 7/0012 (2013.01); G06T 7/11 (2017.01); G06T 7/136 (2017.01); G06T 7/62 (2017.01); G06T 7/90 (2017.01); G06T 17/00 (2013.01); G06T 2207/10024 (2013.01); G06T 2207/10028 (2013.01); G06T 2207/20072 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30128 (2013.01); G06T 2207/30188 (2013.01)] 10 Claims
OG exemplary drawing
 
1. A digital detection method for predicting drug resistance of transgenic maize, comprising:
acquiring detection information of a maize plant after medicament spraying at a current moment; wherein the detection information comprises an RGB image, three-dimensional point cloud data and a chlorophyll relative content;
calculating a pixel ratio of the maize plant at the current moment according to the RGB image at the current moment; wherein the pixel ratio is a ratio of a pixel point number in a first region of the maize plant to a pixel point number in a second region of the maize plant; the first region of the maize plant is a leaf region of the maize plant that changes after the maize plant is treated by the medicament; and the second region is a region of all the leaves of the maize plant;
calculating a morphological feature of the maize plant at the current moment according to the three-dimensional point cloud data at the current moment; wherein the morphological feature comprises a plant height, a crown layer diameter, a stem thickness, a stem height, a first leaf length, a first leaf width, a second leaf length, a second leaf width, a third leaf length, and a third leaf width; the first leaf length, the second leaf length and the third leaf length are defined according to an order in which a root of the maize plant is upward and the branches and leaves are inward; and the first leaf width, the second leaf width and the third leaf width are defined according to an order in which the root of the maize plant is upward and the branches and leaves are inward;
inputting a detection parameter of the maize plant at the current moment into a series model to predict the detection parameter of the maize plant at a next moment to obtain a graph of change in the detection parameter of the maize plant in a next period; wherein the series model is constructed based on a convolutional neural network and a long-short term memory network; the detection parameter comprises a chlorophyll relative content, the pixel ratio, the plant height, the crown layer diameter, the stem thickness, the stem height, the first leaf length, the first leaf width, the second leaf length, the second leaf width, the third leaf length and the third leaf width; and the period is composed of a plurality of successive moments;
estimating a drug resistance characteristic of the maize plant according to the graph of the change in the detection parameter of the maize plant; and
inputting the detection parameter of the maize plant at the current moment into a parallel model to predict a variety of the maize plant; wherein the parallel model is constructed based on a convolutional neural network and a long-short term memory network.