Invisible structures exposed

May 7, 2018, Osaka University
Fig.1. Estimated 3D plant branch structure. Credit: Osaka University

Thoroughly understanding the growth of branches and leaves of individual fruit-bearing trees and adequately managing them are important in improving their quality. However, daily observation and advanced knowledge are necessary for proper management and cultivation of trees, so tree management systems using cameras are drawing attention. The automatic 3-D modeling of plant shapes and branch structures from images is an indispensable technology for pursuing both labor-saving cultivation and improvement of product quality.

Three-dimensional (3-D) from multiple images obtained from different viewpoints has been actively examined. However, it was difficult to reconstruct the of objects that have hidden portions, such as with branch structures hidden under their leaves.

By combining the original image-to-image translation approach in a Bayesian deep learning framework and 3-D reconstruction, a group of researchers led by Fumio Okura estimated the existence probability of branches that are hidden under leaves in images. Using these estimated branch positions, they achieved accurate 3-D reconstruction of branch structures, including those hidden under leaves. Specifically, they converted images of leafy plants to images showing branch existence probability, thereby achieving 3-D reconstruction.

The results of this study will be presented at the EEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2018) to be held from June 18 through June 22, 2018. The paper presented at the conference will be published in Computer Vision Foundation Open Access as part of the conference proceedings on June 4, 2018.

Fig.2. Flow of the proposed approach. Credit: Osaka University

The results will contribute to the cultivation and management of plants by artificial intelligence (AI) and image analysis. They will be helpful in realizing future technology to allow for (a) detailed daily of branch/leaf level process of growing plants in places where cultivators' vision can't reach by filming with a drone or robot, (b) coming up with best trimming or pruning methods for plants, and (c) forecasting future growth of plants.

Fig.3. Future cultivation via plant structure estimation. Credit: Osaka University

Explore further: Researchers report overnight cycle of water movement in trees

More information: Probabilistic plant modeling via multi-view image-to-image translation. IEEE/CVF Conference on Computer Vision and Pattern Recognition (2018)

Related Stories

Development of an artificial orchid cultivation kit

September 22, 2017

Orchids are loved by gardeners around the world but are notoriously difficult to cultivate. Japanese researchers have developed a new orchid cultivation kit that allows seed germination, flowering, and fruiting, and have ...

Downed trees not necessarily a lost cause

September 19, 2017

Among the devastation wrought by Hurricane Irma last week, many downed trees and uprooted plants were left in the storm's wake. Those in a rush to get things back to normal have been quick to break out the chainsaws and remove ...

The 3-D selfie is here

September 26, 2017

Computer scientists at the University of Nottingham and Kingston University have solved a complex problem that has, until now, defeated experts in vision and graphics research. They have developed technology capable of producing ...

Recommended for you

What can snakes teach us about engineering friction?

May 21, 2018

If you want to know how to make a sneaker with better traction, just ask a snake. That's the theory driving the research of Hisham Abdel-Aal, Ph.D., an associate teaching professor from Drexel University's College of Engineering ...

Flexible, highly efficient multimodal energy harvesting

May 21, 2018

A 10-fold increase in the ability to harvest mechanical and thermal energy over standard piezoelectric composites may be possible using a piezoelectric ceramic foam supported by a flexible polymer support, according to Penn ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.