Image-based high-throughput phenotyping of agri-photonics
DAN WU1, LINGBO LIU1, LEJUN YU1, 3, WANNENG YANG2 AND QIAN LIU3
1 Britton Chance Center for Biomedical Photonics, Wuhan National Laboratory for Optoelectronics, and Key Laboratory of Ministry of Education for Biomedical Photonics, Department of Biomedical Engineering, Huazhong University of Science and Technology, People’s Republic of China
2 National Key Laboratory of Crop Genetic Improvement, National Center of Plant Gene Research, Huazhong Agricultural University, People’s Republic of China
3 School of biomedical engineering, Hainan University, People’s Republic of China
Abstract
In the past decade, the development of phenotypic detection was greatly promoted by advanced photonics-based technologies. A variety of imaging techniques, including visible light imaging, hyperspectral imaging, structured light, X-ray computed tomography, have been applied in the case of rice, maize, rape, cotton and grapevine. Phenotypic data were extracted from crop images using specialized algorithm, which generally adopted classical image processing and machine learning methods. Traditional phenotyping that depends largely on manual measuring were tend to be replaced by automatic, non-destructive image-based phenotyping, bringing the functional analysis of crop genome into a high-throughput stage.
File with abstract
Speaker
Qian Liu
Huazhong University of Science and Technology, HHainan Universityuazhong Agricultural University,
China
Discussion
Ask question
