Vinobot and vinoculer: from real to simulated platforms

Shafiekhani, Ali; Fritschi, Felix B.; DeSouza, Guilherme N.

doi:10.1117/12.2316341

Cited by 6 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Filtering the point cloud based on the vegetation height allows reducing the interference of unwanted vegetation, such as weeds. Thus, the collection of such data from the farm greatly speeds up the phenotyping process [103]. Comparison between the 3D reconstruction of a corn plant by VisualSFM generated using different ways of collecting data, described in detail in [102].…”

Section: Robotic Applications In Agriculture For Yield Estimation Andmentioning

confidence: 99%

Advances in Agriculture Robotics: A State-of-the-Art Review and Challenges Ahead

2021

View full text Add to dashboard Cite

The constant advances in agricultural robotics aim to overcome the challenges imposed by population growth, accelerated urbanization, high competitiveness of high-quality products, environmental preservation and a lack of qualified labor. In this sense, this review paper surveys the main existing applications of agricultural robotic systems for the execution of land preparation before planting, sowing, planting, plant treatment, harvesting, yield estimation and phenotyping. In general, all robots were evaluated according to the following criteria: its locomotion system, what is the final application, if it has sensors, robotic arm and/or computer vision algorithm, what is its development stage and which country and continent they belong. After evaluating all similar characteristics, to expose the research trends, common pitfalls and the characteristics that hinder commercial development, and discover which countries are investing into Research and Development (R&D) in these technologies for the future, four major areas that need future research work for enhancing the state of the art in smart agriculture were highlighted: locomotion systems, sensors, computer vision algorithms and communication technologies. The results of this research suggest that the investment in agricultural robotic systems allows to achieve short—harvest monitoring—and long-term objectives—yield estimation.

show abstract

Section: Robotic Applications In Agriculture For Yield Estimation Andmentioning

confidence: 99%

Advances in Agriculture Robotics: A State-of-the-Art Review and Challenges Ahead

2021

View full text Add to dashboard Cite

show abstract

“…In fact, without robots that can operate such sensors automatically and with high availability in collection of both structural and environmental characteristics, true HTPP is impossible. So, in our research, we developed two phenotyping platforms [34,35] for in-situ characterization of plant responses to changes in their environment (e.g., management practices, drought, flood, heat, etc.). These platforms consist of two robotic systems: a mobile, observation tower, Vinoculer, for canopy characterization and general inspection of the crop; and a ground vehicle, Vinobot, for individual plant phenotyping.…”

Section: Developed Phenotyping Systemmentioning

confidence: 99%

Spatio-temporal acquisition, reconstruction, and visualization of dynamic scenes for plant phenotyping

Shafiekhani¹

Self Cite

View full text Add to dashboard Cite

Recent advances in robotic vision are permitting breakthrough solutions to various agriculture-related problems, including farming, field phenotyping, food security, etc. Among these technological advancements, autonomous data collection for field phenotyping enables plant scientists to further correlate plant behavior to environmental conditions using a large amount of high-quality data captured throughout the growing season. In that sense, the ability to process such a large amount of image data must be made possible via computer vision techniques that fuse raw data in order to extract relevant changes during the growing season. For instance, correlating 3D models of plants over time enables scientists to analyze phenotypical data and identify favorable traits in terms of maximum growth, yielding, response to abiotic stressors, etc. Furthermore, the fusion of 3D models of individual plants into larger and cohesive models of the entire crop over time can lead to important discoveries in plant genomics by biology researchers. In this work, we propose an end-to-end system to acquire, fuse, and visualize multimodal data collected over time from an agricultural field. The system consists of two field robots and a visualization tool. The robots can collect and process RGB, Thermal, and 3D information from close proximity or from above ground. The visualization tool allows users to select and process the same data in order to create Spatio-temporal, high dimensional models that describe the physical and temporal structure, color, and temperature of plants in crop fields. Once created, users can visualize the same N-dimensional models using a newly proposed GUI, named VisND. Technically speaking, the proposed system registers time-stamped 5D models (3D plus RGB and IR) of the field as observed by the robots into a single-registered Spatio-temporal model. This process requires a non-rigid (ie. deformable) registration of the 3D structures so that plant behavior (e.g. growth, leaf angle, response to stress, etc) can be visualized over time.

show abstract