A Review of High-Throughput Field Phenotyping Systems: Focusing on Ground Robots

Xu, Rui; Li, Changying

doi:10.34133/2022/9760269

Cited by 35 publications

(21 citation statements)

References 109 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…), plant phenotype screening is widely used for decision-making in agricultural farming. [109,110] The highthroughput image-based phenotyping can image nondestructively plant physiology, and growth status and can collect environmental (light intensity, water supply, temperature, humidity), disease tolerance, and physical (plant weight) data to quantify genotype in the presence of ecological interactions. Robot-assisted and satellite-based imaging platforms, highperformance drowning with high-resolution cameras, and other sophisticated tools have been employed for high-throughput plant phenotyping.…”

Section: High-throughput Plant Phenotyping and Stress Sensingmentioning

confidence: 99%

Internet of Things‐Enabled Food and Plant Sensors to Empower Sustainability

Ataei Kachouei,

Kaushik,

Ali

2023

Advanced Intelligent Systems

View full text Add to dashboard Cite

To promote sustainability, this review explores: 1) the utilization of affordable high‐performance sensors that can enhance food safety and quality, plant growth, and disease management and 2) the Internet of Things (IoT)‐supported sensors to empower farmers, stakeholders, and agro‐food industries via rapid testing and predictive analysis based on sensing generated informatics using artificial intelligence (AI). The performance of such sensors is noticeable, but this technology is still not suitable to be used in real applications owing to the lack of focus, scalability, well‐coordinated research, and regulations. To cover this gap, this review carefully and critically analyzes state‐of‐the‐art sensing technologies developed for food quality assurance (i.e., contaminants, toxins, and packaging testing) and plant growth monitoring (i.e., phenotyping, stresses, volatile organic components, nutrient levels, hormones, and pathogens) along with the possible challenges. The following has been proposed for future research: 1) promoting the optimized combination of green sensing units supported by IoT to perform testing at the location, considering the remote and urban areas as a key focus, and 2) analyzing generated informatics via AI should also be a focus for risk assessment understanding and optimizing necessary safety majors. Finally, the perspectives of IoT‐enabled sensors, along with their real‐world limitations, are discussed.

show abstract

Section: High-throughput Plant Phenotyping and Stress Sensingmentioning

confidence: 99%

Internet of Things‐Enabled Food and Plant Sensors to Empower Sustainability

Ataei Kachouei,

Kaushik,

Ali

2023

Advanced Intelligent Systems

View full text Add to dashboard Cite

show abstract

“…Portions of the data collected have been published online ( https://weed-ai.sydney.edu.au/datasets/aa0cb351-9b5a-400f-bb2e-ed02b2da3699 ). Ground-based systems for plant phenotyping have been reviewed previously ( Xu and Li, 2022 ), with the authors concluding that dedicated systems were often prohibitively expensive to obtain for most plant breeding programs. Further, these systems are identified as too slow for large-scale breeding operations.…”

Section: From Data To Decisionmentioning

confidence: 99%

More eyes on the prize: open-source data, software and hardware for advancing plant science through collaboration

Coleman

Salter

2023

AoB PLANTS

View full text Add to dashboard Cite

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) standardised, 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 capitalise on the benefits of DL for both applied and basic science purposes.

show abstract

“…The problem they solve is the difficulty of labeling training data for AI algorithms. Similarly, references [ 31 , 32 , 33 , 34 , 35 ] are about environmental classification, not navigation.…”

Section: Related Workmentioning

confidence: 99%

Hyperspectral Imaging for Mobile Robot Navigation

Jakubczyk

Siemiątkowska

Więckowski

et al. 2022

Sensors

View full text Add to dashboard Cite

The article presents the application of a hyperspectral camera in mobile robot navigation. Hyperspectral cameras are imaging systems that can capture a wide range of electromagnetic spectra. This feature allows them to detect a broader range of colors and features than traditional cameras and to perceive the environment more accurately. Several surface types, such as mud, can be challenging to detect using an RGB camera. In our system, the hyperspectral camera is used for ground recognition (e.g., grass, bumpy road, asphalt). Traditional global path planning methods take the shortest path length as the optimization objective. We propose an improved A* algorithm to generate the collision-free path. Semantic information makes it possible to plan a feasible and safe path in a complex off-road environment, taking traveling time as the optimization objective. We presented the results of the experiments for data collected in a natural environment. An important novelty of this paper is using a modified nearest neighbor method for hyperspectral data analysis and then using the data for path planning tasks in the same work. Using the nearest neighbor method allows us to adjust the robotic system much faster than using neural networks. As our system is continuously evolving, we intend to examine the performance of the vehicle on various road surfaces, which is why we sought to create a classification system that does not require a prolonged learning process. In our paper, we aimed to demonstrate that the incorporation of a hyperspectral camera can not only enhance route planning but also aid in the determination of parameters such as speed and acceleration.

show abstract

A Review of High-Throughput Field Phenotyping Systems: Focusing on Ground Robots

Cited by 35 publications

References 109 publications

Internet of Things‐Enabled Food and Plant Sensors to Empower Sustainability

Internet of Things‐Enabled Food and Plant Sensors to Empower Sustainability

More eyes on the prize: open-source data, software and hardware for advancing plant science through collaboration

Hyperspectral Imaging for Mobile Robot Navigation

Contact Info

Product

Resources

About