New paper: Machine Vision System for 3D Plant Phenotyping


#1

Here’s a new research paper describing a system for phenotyping plants in an automated growth chamber. As far as I can tell, these folks don’t have any affiliation with MIT or OpenAg. The connection is that they are already doing things that OpenAg aspires to do. For folks who are interested in learning about the state of the art in automated phenotyping, this paper’s citations might be a good place to start.

Machine Vision System for 3D Plant Phenotyping (https://arxiv.org/abs/1705.00540)

Abstract:

Machine vision for plant phenotyping is an emerging research area for producing high throughput in agriculture and crop science applications. Since 2D based approaches have their inherent limitations, 3D plant analysis is becoming state of the art for current phenotyping technologies. We present an automated system for analyzing plant growth in indoor conditions. A gantry robot system is used to perform scanning tasks in an automated manner throughout the lifetime of the plant. A 3D laser scanner mounted as the robot’s payload captures the surface point cloud data of the plant from multiple views. The plant is monitored from the vegetative to reproductive stages in light/dark cycles inside a controllable growth chamber. An efficient 3D reconstruction algorithm is used, by which multiple scans are aligned together to obtain a 3D mesh of the plant, followed by surface area and volume computations. The whole system, including the programmable growth chamber, robot, scanner, data transfer and analysis is fully automated in such a way that a naive user can, in theory, start the system with a mouse click and get back the growth analysis results at the end of the lifetime of the plant with no intermediate intervention. As evidence of its functionality, we show and analyze quantitative results of the rhythmic growth patterns of the dicot Arabidopsis thaliana(L.), and the monocot barley (Hordeum vulgare L.) plants under their diurnal light/dark cycles.

cc @webbhm @Paul


Can I help OpenAg without building a PFC?
#2

Thanks @wsnook hey @Eddie @spaghet @rbaynes check this out


#3

Good old Arabidopsis (model research organism).
Interesting paper, a spin off of LIDAR mapping on a small scale. There are always trade offs, but Photogrametry (creating point clouds with camera images) has been doing this sort of stuff also.
While the research is good with a single plant (and a lot of space around it), things get tricky real fast in an actual field or any place that the plants start touching each other as they grow.
This is some good work on identify plant notes, though it is interesting that they stop before flowering; I wonder if the complexity to be too much after that time.
Thanks for posting.

Rough point cloud of Whitecliff Quarry (via MeshLab) from a series of photos.


#4

Thanks for your post, it looks very useful. I’m new here, so the following may be old news. Although published in 2014, this Open Source Leibniz Institute greenhouse phenotyping system has a great review of the many issues involved in automated phenotyping: http://www.plantphysiol.org/content/165/2/506.full


MVP - Product Design
#5

Arabidopsis Chamber or plant growth chambers is an important equipment of biological laboratory. It is specially designed for the agricultural research applications like plant pathology, germination studies, plant genetic research and plant tissue culture studies. Arabidopsis Chamber makes possible animal, plant and culture studies in the classroom. There are different shapes and sizes of these chambers are available in the market and buyer and collect the best model according to their requirements.
http://newmeditech.com/arabidopsis-chamber/