Digital rice picking technology – AgriLife Today

Rice researchers at the Texas A&M AgriLife Research Center in Beaumont have begun a project to use unmanned aerial vehicles, UAVs, to speed up rice selection and reproduction.

A team of researchers at the Texas A&M AgriLife Research Center in Beaumont will use UAVs to capture images of rice crops in real time, extract phenotypic characteristics from crops, and ultimately analyze this information to determine high-yield rice genotypes. (Photo)

The team will use UAVs to capture images of rice crops in real time, extract phenotypic characteristics of crops from the images, and ultimately analyze this information to identify high-yielding rice genotypes.

Yubin Yang, Ph.D., a senior biosystems analyst at Beaumont Center, is leading the Texas A&M AgriLife Research project, funded by a three-year, $ 650,000 grant from the U.S. Department of Agriculture and the National Food and Agriculture Institute. The project aims to avoid a major hurdle in data collection: labor-intensive and time-consuming labor-intensive data collection, using skilled labor.

The Yang project team includes AgriLife Research scientist Stanley Omar Samonte, PhD, hybrid rice grower; Fugen Dou, Ph.D., crop nutrient management; Ted Wilson, Ph.D., director of the center and holder of the Jack B. Wendt Endowed Chair in Rice Growing; Tanumoy Bera, Ph.D., postdoctoral fellow, all in the Texas A&M Soil and Crop Sciences department; and Jing Zhang, Ph.D., associate professor of computer science, Lamar University, Beaumont.

The main objectives of the research are:

  • Quantify the phenotypic characteristics of rice growth and development.
  • Take UAV images of rice genotypes during the main stages of rice growth.
  • Develop advanced image processing algorithms to extract the phenological, morphological and architectural features of the main stages of rice growth.
  • Develop a digital rice selection system that analyzes the best-performing genotypes through data integration and multi-feature decision-making.

Advantages of UAV Technology

“Traditional manual measurement of the phenotypic characteristics of rice takes a long time,” Yang said. “It is becoming increasingly difficult to hire qualified and experienced staff. Advanced UAV technology and image processing can provide a cost-effective and reliable alternative. We can use UAVs to capture images of rice in the main stages of growth and to develop algorithms for extracting different phenotypic characteristics of hundreds or thousands of rice genotypes. “

Thousands of UAV images will be collected, as well as ground truth data during the rice harvest season, Yang said. Several flights of UAVs will be made to capture images of rice from different camera angles to help establish the placement of gaps between plants and gaps.

“A large amount of data needs to be integrated and analyzed,” Yang said. “This is the first year of the project and it is a learning process for us. UAV images for rice cultivation have been difficult to capture in time due to the small size of the rice plants and the wind conditions. There is a limited window you can fly. ”

Development of advanced image processing algorithms

While acquiring UAV data, the team will also develop machine learning algorithms to identify key features and select the best-performing rice genotypes.

The research project will evaluate key phenotypic characteristics for selection in breeding, such as shrub establishment, biomass growth, phenological development, and final grain yield.

“We will develop automated algorithms that can extract phenotypic characteristics from UAV images taken at critical stages of rice, including seedlings, crops, flowering, grain filling, and maturity,” Yang said. “The digital rice selection system will be developed through the integration of multiple features to identify the best-performing genotypes.”

Dou said another potential aspect of using UAV technology will be controlling plant growth for nitrogen management and disease detection.

“We have a project underway to assess the nitrogen status of rice from UAV images,” Douk said. “UAV diagnosis of plant nutrients and other stresses has tremendous potential, especially for rice with limited rural access, as a result of an overcrowded production system.”

“This proposed project involves a major effort to provide rice growers and researchers with an integrated decision-making system based on UAV imaging,” Yang said. “It will be an essential tool to greatly improve the efficiency of rice cultivation and phenotyping.”


Leave a Comment