Related Experiment Video
Updated: May 26, 2026
07:12
High-Throughput, In-Field Screening of Photosynthetic Efficiency in Crop Plants Using an Autonomous Robot
Published on: January 9, 2026
Robust crop and weed segmentation under uncontrolled outdoor illumination
Hong Y Jeon1, Lei F Tian, Heping Zhu
1United State Department of Agriculture-Agricultural Research Service, Application Technology Research Unit, Wooster, OH 44691, USA. hongyoung.jeon@ars.usda.gov
Sensors (Basel, Switzerland)
|December 14, 2011
Summary
A new image processing algorithm accurately detects weeds in outdoor fields. This machine vision system achieved high accuracy for identifying crop plants, improving agricultural applications.
Area of Science:
- Agricultural Engineering
- Computer Vision
- Machine Learning
Background:
- Accurate weed detection is crucial for precision agriculture.
- Existing methods struggle with uncontrolled outdoor lighting conditions.
- Automated plant identification is needed for efficient crop management.
Purpose of the Study:
- To develop and evaluate an image processing algorithm for automated weed detection.
- To assess the algorithm's performance under variable outdoor illumination.
- To differentiate between crop plants and weeds using machine vision.
Main Methods:
- Developed an algorithm integrating normalized excessive green conversion, thresholding, segmentation, filtering, and Artificial Neural Network (ANN).
- Utilized a field robot with machine vision to capture images under natural lighting.
- Employed automated image processing without manual intervention.
Main Results:
- The algorithm demonstrated low error rates (2.1-2.9%) across 666 field images.
- Initial ANN crop plant detection accuracy was 72.6%, with improvements to 95.1% after error source correction.
- The system successfully identified plants against soil backgrounds in uncontrolled environments.
Conclusions:
- The developed algorithm offers a novel approach for plant identification and weed differentiation in outdoor settings.
- The machine vision system shows promise for applications like plant-specific direct applications (PSDA).
- This technology can enhance automated weed management strategies in agriculture.
Related Concept Videos
02:16Light Acquisition
In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.
02:00Photoreceptors and Plant Responses to Light
Light plays a significant role in regulating the growth and development of plants. In addition to providing energy for photosynthesis, light provides other important cues to regulate a range of developmental and physiological responses in plants.