Fully automated region of interest segmentation pipeline for UAV based RGB images

Sadashivan, Shreeshan and Bhattacherjee, Subhra S. and Priyanka, Gattu and Rajalakshmi, P and et al, . (2021) Fully automated region of interest segmentation pipeline for UAV based RGB images. Biosystems Engineering, 211. pp. 192-204. ISSN 1537-5110

Text
Biosystems_Engineering.pdf - Published Version
Restricted to Registered users only
Download (3MB) | Request a copy

Abstract

Unmanned Aerial Vehicles (UAVs) have exhibited its potential for efficient and non-invasive crop data acquisition in high throughput crop phenotyping. In general, for analysis of phenotypic traits, there is a need for extracting the region of interest (RoI) from images captured by UAVs. It involves the generation of orthomosaic, which is a complicated and time-intensive process. In this study, a fully automated AI-based pipeline has been proposed for the RoI segmentation from raw RGB images acquired via UAV. The proposed pipeline achieves a near real-time processing speed compared to the other baseline methods. The key feature of the pipeline is the introduction of Sub-Paths, in which the original UAV flight path is divided into several small paths which facilitates parallel processing. The image quality of the extracted RoI has been examined using blind/referenceless image spatial quality evaluator (BRISQUE) and natural image quality evaluator (NIQE). The performance of the proposed pipeline is exemplified with the Leaf Area Index (LAI) estimation on five datasets containing three different crop types and growth stages. Regression analysis has also been performed on the estimated LAI values. Average R2, RMSE, and correlation scores of the estimates are observed to be 0.68, 0.033, and 0.83, respectively. © 2021 IAgrE

[error in script]

IITH Creators:

IITH Creators	ORCiD
Rajalakshmi, P	UNSPECIFIED

Item Type:

Article

Additional Information:

This work was supported and funded by Ministry of Electronics and Information Technology (MeitY) India under the project” AI Driven High Throughput Phenotyping to Accelerate Crop Improvement Through Crop Images Captured from Unmanned Aerial Vehicle (UAV) with On-vehicle Sensors” project no: DIT/EE/F002/2018-19/G174 .

Uncontrolled Keywords:

High throughput phenotyping; LAI; Parallel processing; Sub-Path detection; Sub-Plot; UAV

Subjects:

Electrical Engineering

Divisions:

Department of Electrical Engineering

Depositing User:

. LibTrainee 2021

Date Deposited:

24 Aug 2022 10:24

Last Modified:

24 Aug 2022 10:24