More eyes on the prize: open-source data, software and hardware for advancing plant science through collaboration. Issue 2 (9th March 2023)

• Record Type: Journal Article
• Authors: Coleman, Guy R Y; Salter, William T
• Editors: Martin, Adam
• Is Part Of: AoB plants. Volume 15:Issue 2(2023)
• Publication Date: 2023-03-09
• Subjects: Computer vision -- machine learning -- open-source -- phenotyping -- site-specific weed control -- sustainable agriculture; Plants -- Periodicals; Botany -- Periodicals; 580.5
• DOI: 10.1093/aobpla/plad010
• Languages: English
• ISSNs: 2041-2851

Abstract

Abstract: Automating the analysis of plants using image processing would help remove barriers to phenotyping and large-scale precision agricultural technologies, such as site-specific weed control. The combination of accessible hardware and high-performance deep learning (DL) tools for plant analysis is becoming widely recognised as a path forward for both plant science and applied precision agricultural purposes. Yet, a lack of collaboration in image analysis for plant science, despite the open-source origins of much of the technology, is hindering development. Here, we show how tools developed for specific attributes of phenotyping or weed recognition for precision weed control have substantial overlapping data structure, software/hardware requirements and outputs. An open-source approach to these tools facilitates interdisciplinary collaboration, avoiding unnecessary repetition and allowing research groups in both basic and applied sciences to capitalise on advancements and resolve respective bottlenecks. The approach mimics that of machine learning in its nascence. Three areas of collaboration are identified as critical for improving efficiency, (1) standardized, open-source, annotated dataset development with consistent metadata reporting; (2) establishment of accessible and reliable training and testing platforms for DL algorithms; and (3) sharing of all source code used in the research process. The complexity of imaging plants and cost of annotating image datasets means that collaboration from typically distinct fields will be necessary to capitalize on the benefits of DL for both applied and basic science purposes. Abstract : Using image processing to automate plant analysis can help overcome barriers in precision agriculture and plant science for improved crop breeding. Despite shared goals and similar methods for image-based plant analysis, there is limited collaboration and sharing of tools, holding back progress. The field of machine learning has demonstrated how open-source and collaborative approaches result in rapid improvement. An open-source approach to tools for plant phenotyping or weed recognition can facilitate collaboration, avoid duplication and improve research reach and efficiency. Three critical areas of collaboration are identified: developing standardized, open-source, labeled datasets; creating accessible and reliable platforms for training and testing deep learning algorithms; and sharing all source code used in research.