Meeting present and future challenges in sustainable horticulture using virtual plants

Buck-Sorlin, Gerhard; Delaire, Mickaël

doi:10.3389/fpls.2013.00443

Cited by 4 publications

(5 citation statements)

References 4 publications

(3 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Virtual plant modeling have been used in agricultural and plant sciences to simulate plant behaviour and analyze interactions of the plants with their environment [37][38][39]. There exists many platforms for constructing virtual plant models such as L+C modelling language [40,41] and L-Py framework [42], which are based on the formalism of L-systems [24].…”

Section: Related Workmentioning

confidence: 99%

Segmentation of structural parts of rosebush plants with 3D point-based deep learning methods

et al. 2022

View full text Add to dashboard Cite

Background Segmentation of structural parts of 3D models of plants is an important step for plant phenotyping, especially for monitoring architectural and morphological traits. Current state-of-the art approaches rely on hand-crafted 3D local features for modeling geometric variations in plant structures. While recent advancements in deep learning on point clouds have the potential of extracting relevant local and global characteristics, the scarcity of labeled 3D plant data impedes the exploration of this potential. Results We adapted six recent point-based deep learning architectures (PointNet, PointNet++, DGCNN, PointCNN, ShellNet, RIConv) for segmentation of structural parts of rosebush models. We generated 3D synthetic rosebush models to provide adequate amount of labeled data for modification and pre-training of these architectures. To evaluate their performance on real rosebush plants, we used the ROSE-X data set of fully annotated point cloud models. We provided experiments with and without the incorporation of synthetic data to demonstrate the potential of point-based deep learning techniques even with limited labeled data of real plants. Conclusion The experimental results show that PointNet++ produces the highest segmentation accuracy among the six point-based deep learning methods. The advantage of PointNet++ is that it provides a flexibility in the scales of the hierarchical organization of the point cloud data. Pre-training with synthetic 3D models boosted the performance of all architectures, except for PointNet.

show abstract

Section: Related Workmentioning

confidence: 99%

Segmentation of structural parts of rosebush plants with 3D point-based deep learning methods

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The research first challenges the initial scepticism related to using computer modelling in horticulture education. Some literature criticizes that the initial keen interest coupled with high expectations on ARVR was frequently followed by disillusionment since the high hopes were not satisfied [13]. At times, advanced modelling as a scientific technique has been considered remote from practice, unreliable, or too complicated to use.…”

Section: Methodsmentioning

confidence: 99%

“…As virtual plant modelling has reached its mature development [13] and students are now granted easier access to immersive systems and devices [14], virtual experiential learning of plantation management is now widely used to supplement traditional teaching in horticultural education [15][16][17][18]. As a signature pedagogy of horticultural education, team-based learning has already been widely adopted where students complete pre-work and attempt in-class activities individually and then work together in teams to solve applicational case studies [19].…”

Section: Introductionmentioning

confidence: 99%

Digital Experiential Learning for Sustainable Horticulture and Landscape Management Education

Kee

Zhang

2022

Sustainability

View full text Add to dashboard Cite

During the COVID-19 pandemic, horticulture and landscape management programmes in higher education experienced a huge drawback because of the impossibility of organising field studies and conducting site research. To pursue a more sustainable method of teaching, immersive technology such as augmented reality (AR) and virtual reality (VR) has been increasingly adopted as an effective approach for multimodal experiential learning. This study examines student perceptions on the use of digital technology in team-based hybrid learning to achieve sustainability in tree management using data collected from students of horticulture and landscape management in a higher education institute in Hong Kong. Key theoretical principles on Kolb’s experiential learning cycle as an interactive process are discussed, followed by an empirical analysis of student survey results. This research deepens the understanding of how immersive technology enhances both environmental sustainability and learning innovation. The results demonstrate that innovative ideas in instructional methods such as ARVR simulation can enhance the environmental sustainability of how tree management can be conducted, promoting a more environmentally conscious, experiential, collaborative and digital learning experience in higher education.

show abstract

“…Since design education in higher education sees the global influence of collaborative online international learning (COIL) (Vahed & Rodriguez, 2021), synchronous hybrid learning can blur geographical boundaries in contemporary T&L. Secondly, the design team defined the PBL activities utilising immersive technology as the artefacts to generate disciplinary knowledge. With more development in education technology (Buck-Sorlin & Delaire, 2013) and increasing access to immersive systems (Renganayagalu et al, 2021), synchronous hybrid T&L activities become the supplement to traditional teaching (Atkins et al, 1996;Weber & Penn, 1995;Wu et al, 2019;Xia et al, 2009) to embrace knowledge related to humanity. The co-create project spanning the semesters helped develop better knowledge in discipline-specific content, skills in communication and group collaboration to enhance experiential learning, and its process of developing knowledge as artefacts, knowledge, activities, and humanity would be tested by the mixed method analysis.…”

Section: Development Of Hybrid Experiential Learningmentioning

confidence: 99%

An empirical study on immersive technology in synchronous hybrid learning in design education

Kee,

Zhang,

King

2023

Int J Technol Des Educ

View full text Add to dashboard Cite

Immersive technology plays an increasingly important role in design education, supporting digital literacy and experiential learning in higher education, particularly in the post-COVID-19 context. Many design disciplines, such as Architecture and Landscape Design, which used to rely heavily on physical field trips, and dialogic studios as signature pedagogies, had to adapt to the proliferation of innovative educational technologies due to the suspension of face-to-face teaching and learning. Augmented reality and virtual reality are now extensively used in technology and design education to support a more interactive, collaborative, and student-centred approach to learning. This paper expands on a pilot research study on the transition from traditional signature pedagogies of studio-based design education to technology-enhanced collaborative learning to support experiential learning. Based on Kolb’s experiential learning framework concerning four learning modes, namely, concrete experience (CE), reflective observation (RO), abstract conceptualisation (AC), and active experimentation (AE), this paper analyses data from 75 undergraduate students across four cohorts in three different higher education institutions in Hong Kong. They were surveyed on their experiences of synchronous hybrid virtual experiential learning with design and technology curricula. Furthermore, six students were interviewed about their experiences. The research findings confirm two research hypotheses showing that immersive experiential learning could constructively align RO and AE, thus bringing an overall positive impact on the experiential learning process, but shows no conclusive influence on promoting CE, especially AC. The quantitative findings and qualitative results gave new insights into the discussion of the theoretical and practical implications of the study.

show abstract

Meeting present and future challenges in sustainable horticulture using virtual plants

Cited by 4 publications

References 4 publications

Segmentation of structural parts of rosebush plants with 3D point-based deep learning methods

Segmentation of structural parts of rosebush plants with 3D point-based deep learning methods

Digital Experiential Learning for Sustainable Horticulture and Landscape Management Education

An empirical study on immersive technology in synchronous hybrid learning in design education

Contact Info

Product

Resources

About