Vision Based Automated Point-Cloud Processing Pipeline For High Throughput Phenotyping

Shreeshan, S and Bhattacherjee, S S and Gattu, P and Rajalakshmi, P and Kholova, J and Choudhary, S (2020) Vision Based Automated Point-Cloud Processing Pipeline For High Throughput Phenotyping. In: IEEE International Conference on Image Processing, Oct 25–28, 2020, Abu Dhabi, United Arab Emirates. (Unpublished)

[img] PDF - Presentation
Download (1MB)


High throughput phenotyping is rapidly gaining widespread popularity due to its non-destructive approach for plant traits extraction. In this study, we focus on developing a vision based automated 3D point cloud processing pipeline for accurate estimation of plant traits, namely - plant height, leaf area index(LAI), and leaf inclination. Furthermore, the obtained estimates are validated by comparing the results with LeasyScan data in terms of coefficient of determination (R2), root mean squared error (RMSE), and correlation coefficient. These metrics are found to be around 0.90, 0.10, and 0.96, respectively, for each of the traits. Regression analysis has also been performed to gain some analytical insights on the data.

Item Type: Conference or Workshop Item (Speech)
Divisions: Research Program : Innovation Systems for the Drylands (ISD)
Uncontrolled Keywords: High throughput phenotyping, Crop Physiology
Subjects: Others > Crop Modelling
Others > Crop Physiology
Others > Food Security
Depositing User: Mr Arun S
Date Deposited: 15 Jun 2020 07:10
Last Modified: 15 Jun 2020 07:30
Acknowledgement: UNSPECIFIED
    View Statistics

    Actions (login required)

    View Item View Item