Monocular Crop Stem Measurement for High-Throughput Field Phenotyping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current agricultural phenotyping methods are labor-intensive, inaccurate, and inefficient, particularly in field conditions due to high clutter, varying lighting, and lack of suitable technologies for real-time, low-cost, high-throughput data collection, which hampers crop breeding and yield prediction.
Innovation Solution
A small, ultra-compact robot equipped with a side-facing monocular RGB camera, 2D LIDAR, and wheel encoders uses image processing and structure from motion algorithms to estimate crop stem width and phenotypic measurements in real-field conditions, providing accurate and robust data without damaging crops.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual measurements are used for plant phenotyping, then measurement accuracy can be maintained, but labor intensity and time consumption increase significantly
Solution Approach 1:
The patent replaces manual mechanical measurement systems with an automated robotic system that uses monocular vision and LIDAR sensors to capture plant phenotypic data. The robot navigates through crop rows and automatically measures stem width and other parameters without human intervention, thereby increasing throughput while maintaining measurement accuracy through calibrated sensing systems.
Solution Approach 2:
The robotic phenotyping system performs self-navigation and self-measurement tasks autonomously. The robot uses its onboard sensors (monocular camera, LIDAR, wheel encoders) to automatically detect plant stems, measure their dimensions, and record phenotypic data without requiring manual operation, thus enabling high-throughput automated phenotyping.
2Productivity
If automated phenotyping systems are deployed, then productivity increases, but device complexity and cost increase
Solution Approach 1:
The robotic platform is designed as a multi-functional system that can perform various phenotyping tasks (stem width measurement, plant height measurement, canopy coverage assessment) using a single integrated platform. The robot incorporates multiple sensors (monocular camera, LIDAR, wheel encoders) that serve multiple measurement functions, reducing the need for separate specialized devices and thereby managing complexity while maintaining high productivity.
Solution Approach 2:
The patent uses intermediate processing algorithms and data fusion techniques to bridge the gap between raw sensor data and meaningful phenotypic measurements. The system processes data from multiple sensors (camera images, LIDAR point clouds, encoder positions) through computational algorithms to produce accurate stem width and other phenotypic measurements, managing system complexity through intelligent data processing rather than hardware complexity.
3Ease of manufacture
If traditional imaging methods are used, then equipment cost is low, but measurement accuracy deteriorates in field conditions with clutter and varying lighting
Solution Approach 1:
The patent combines multiple sensing modalities (monocular RGB camera, 2D LIDAR, wheel encoders) into an integrated phenotyping system. The monocular vision provides cost-effective stem detection and width measurement, while LIDAR adds depth information for accurate distance and size estimation. This fusion of complementary sensors maintains low cost compared to complex multi-spectral systems while significantly improving measurement accuracy in challenging field conditions with clutter and varying lighting.
Solution Approach 2:
The system uses parameter calibration and transformation to convert raw sensor measurements into accurate phenotypic data. The monocular camera captures 2D images that are transformed into 3D measurements using LIDAR depth information and geometric relationships. The system adjusts measurement parameters based on robot position (from wheel encoders) and camera-LIDAR spatial relationships to compensate for varying lighting conditions and background clutter, maintaining accuracy without requiring expensive controlled environments.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The solution enables accurate and efficient phenotypic measurements, achieving 92.5% match with manual measurements for stem width estimation, and is applicable to various crops, overcoming the limitations of traditional methods by providing a low-cost, high-throughput solution for agricultural data collection.
Implementation Method 1
obtain a set of measurements from a light detection and ranging (LiDAR) sensor, wherein the set of measurements includes a first measurement corresponding to a first point on the crop stem and a second measurement corresponding to a second point on the crop stem
Data Source
Figure 1A
Figure 1B
Figure 2
AI summary
Aspects of the subject disclosure may include, for example, obtaining video data from a single monocular camera, wherein the video data comprises a plurality of frames, wherein the camera is attached to a mobile robot that is travelling along a lane defined by a row of crops, wherein the row of crops comprises a first plant stem, and wherein the plurality of frames include a depiction of the first plant stem; obtaining robot velocity data from encoder(s), wherein the encoder(s) are attached to the robot; performing foreground extraction on each of the plurality of frames of the video data, wherein the foreground extraction results in a plurality of foreground images; and determining, based upon the plurality of foreground images and based upon the robot velocity data, an estimated width of the first plant stem. Additional embodiments are disclosed.