Development of a Low-Cost Distributed Computing Pipeline for High-Throughput Cotton Phenotyping
In this paper, we present the development of a low-cost distributed computing pipeline for cotton plant phenotyping using Raspberry Pi, Hadoop, and deep learning. Specifically, we use a cluster of several Raspberry Pis in a primary-replica distributed architecture using the Apache Hadoop ecosystem a...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/3/970 |
| _version_ | 1797318213283872768 |
|---|---|
| author | Vaishnavi Thesma Glen C. Rains Javad Mohammadpour Velni |
| author_facet | Vaishnavi Thesma Glen C. Rains Javad Mohammadpour Velni |
| author_sort | Vaishnavi Thesma |
| collection | DOAJ |
| description | In this paper, we present the development of a low-cost distributed computing pipeline for cotton plant phenotyping using Raspberry Pi, Hadoop, and deep learning. Specifically, we use a cluster of several Raspberry Pis in a primary-replica distributed architecture using the Apache Hadoop ecosystem and a pre-trained Tiny-YOLOv4 model for cotton bloom detection from our past work. We feed cotton image data collected from a research field in Tifton, GA, into our cluster’s distributed file system for robust file access and distributed, parallel processing. We then submit job requests to our cluster from our client to process cotton image data in a distributed and parallel fashion, from pre-processing to bloom detection and spatio-temporal map creation. Additionally, we present a comparison of our four-node cluster performance with centralized, one-, two-, and three-node clusters. This work is the first to develop a distributed computing pipeline for high-throughput cotton phenotyping in field-based agriculture. |
| first_indexed | 2024-03-08T03:49:08Z |
| format | Article |
| id | doaj.art-c172eb3ba56b4dab98c97ee941e8e797 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-08T03:49:08Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-c172eb3ba56b4dab98c97ee941e8e7972024-02-09T15:22:26ZengMDPI AGSensors1424-82202024-02-0124397010.3390/s24030970Development of a Low-Cost Distributed Computing Pipeline for High-Throughput Cotton PhenotypingVaishnavi Thesma0Glen C. Rains1Javad Mohammadpour Velni2School of Electrical and Computer Engineering, University of Georgia, Athens, GA 30602, USADepartment of Entomology, University of Georgia Tifton Campus, Tifton, GA 31793, USADepartment of Mechanical Engineering, Clemson University, Clemson, SC 29634, USAIn this paper, we present the development of a low-cost distributed computing pipeline for cotton plant phenotyping using Raspberry Pi, Hadoop, and deep learning. Specifically, we use a cluster of several Raspberry Pis in a primary-replica distributed architecture using the Apache Hadoop ecosystem and a pre-trained Tiny-YOLOv4 model for cotton bloom detection from our past work. We feed cotton image data collected from a research field in Tifton, GA, into our cluster’s distributed file system for robust file access and distributed, parallel processing. We then submit job requests to our cluster from our client to process cotton image data in a distributed and parallel fashion, from pre-processing to bloom detection and spatio-temporal map creation. Additionally, we present a comparison of our four-node cluster performance with centralized, one-, two-, and three-node clusters. This work is the first to develop a distributed computing pipeline for high-throughput cotton phenotyping in field-based agriculture.https://www.mdpi.com/1424-8220/24/3/970big datadistributed computingcotton phenotypingcomputer vision |
| spellingShingle | Vaishnavi Thesma Glen C. Rains Javad Mohammadpour Velni Development of a Low-Cost Distributed Computing Pipeline for High-Throughput Cotton Phenotyping Sensors big data distributed computing cotton phenotyping computer vision |
| title | Development of a Low-Cost Distributed Computing Pipeline for High-Throughput Cotton Phenotyping |
| title_full | Development of a Low-Cost Distributed Computing Pipeline for High-Throughput Cotton Phenotyping |
| title_fullStr | Development of a Low-Cost Distributed Computing Pipeline for High-Throughput Cotton Phenotyping |
| title_full_unstemmed | Development of a Low-Cost Distributed Computing Pipeline for High-Throughput Cotton Phenotyping |
| title_short | Development of a Low-Cost Distributed Computing Pipeline for High-Throughput Cotton Phenotyping |
| title_sort | development of a low cost distributed computing pipeline for high throughput cotton phenotyping |
| topic | big data distributed computing cotton phenotyping computer vision |
| url | https://www.mdpi.com/1424-8220/24/3/970 |
| work_keys_str_mv | AT vaishnavithesma developmentofalowcostdistributedcomputingpipelineforhighthroughputcottonphenotyping AT glencrains developmentofalowcostdistributedcomputingpipelineforhighthroughputcottonphenotyping AT javadmohammadpourvelni developmentofalowcostdistributedcomputingpipelineforhighthroughputcottonphenotyping |