KO | EN

GitLite

Minimalist Open Source Repository Search Engine

gitlite — search

#dsh #dsh-plugin #typescript #ai-agent #developer-tools #claude-code #codex #deepseek-harness #ai-agents #cli #react #mcp

OpenCV_Competition2021

★ 34 Open GitHub ↗

No description available.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# About this Repo

We are the BenchBotics! An amazing team working together from several different locations around the United States and the world. We have deployed a great use case for the OAK-D Camera system for one of our main projects: "The BenchBot".

Please take a look at the folders within the "Code Section" to replicate the use of the camera in similar conditions. This system is totally open-source. For more details and a longer description per section, please visit our [Wiki](https://github.com/precision-sustainable-ag/OpenCV_Competition2021/wiki/1.-Background) page.

Here is a brief description, enjoy this repo as much as we enjoyed this deployment.

# BenchBot

The BenchBot is a plant phenotyping platform, which consists of two major components: a semi-automatic image acquisition device and a central processing unit to control the platform and camera movement. The BenchBot is low-cost, modular, upgradeable, portable, and easy to use. Specifically, the BenchBot can be adjusted to work in benches of different dimensions and the camera height can be changed to accommodate plants of different heights and sizes. We are currently examining image acquisition and processing approaches that work best under greenhouse conditions(i.e. high levels of light and heat). Furthermore, we are developing image-processing algorithms needed to detect and identify plants, detect leaves, determine leaf area and estimate plant biomass.

Our first prototype consisted of a frame that can be moved along greenhouse benches with a mounted camera system (camera and lights) that stops at each potted plant to take individual RGB and depth images. We are currently developing the semi-autonomous system, which requires minimal human intervention. Expected products include a stable control application and a suitable database that enables biomass measurements and plant detection algorithms. We are also working on full automation of the platform and image acquisition. We anticipate broad adoption of this technology among public and private plant breeders.

It is possible to install different kind of cameras under 5 kg directly to the top slider. First testing was with D-435 Intel RGB-D camera, and now we are submitting the results using the OAK-D camera within the second OpenCV AI competition.

![](https://lh5.googleusercontent.com/tHdXvMbHdc3JykFLDBgbhk_In4KXHa-Onu5khKwsVgKnKEjiw-9lHYCDIXmlkehCP7DSMlgtfk2aMkZyOmYPPvjAjiR3NqenPyKa1MjXKKUp1cqY0jNawHkdeBwmlO6qgtbFMeMM)
Figure 1. Phenotyping prototype, RGB-D image, mounted camera, and light source. Parts of the phenotyping prototype (yellow boxes) and movements (blue arrows).

The second BenchBot version has integrated a mechanical system to adjust the BenchBot structure to different bench sizes. Also, this new design has motorized wheels with control system to automatize its movement along the bench.

<p align="center">
  <img width="300" src="https://lh4.googleusercontent.com/RVCFwbj2_s7OGirMTMOMG2b8EWb5M9PlDNIKfn7Jp1NuNTBwlvlcRs-GC7MivzObQDDFD564f5Q5PdjUvxcimARJOtnuBsaPXGWz3Q1wN3j0QgZ1RsPoC3OvP0LWgA">
  <img width="300" src="https://lh3.googleusercontent.com/8jJAcJXyjxXKO9xnlexA6BAQtWPNoqYF365rfe1BY3A3lTKZme3bIjkYDXfQ-diRKFd37oux9q9YqZCzRepcV2jO4sYB1S_U9FlzO22I-g9DWDhvzt2PJfftX5F0Ug">
</p>
Figure 2. New BenchBot design

OpenCV_Competition2021

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README