Reducing farmer uncertainty in spring forage harvests: image recognition to predict alfalfa-grass stand composition

Reducing farmer uncertainty in spring forage harvests: image recognition to predict alfalfa-grass stand composition

Summary

Perennial forages use large quantities of nutrients, minimizing the risk of nutrient leaching or runoff. High quality forage is also very competitive economically compared to grains. Although it is possible to make hay during spring in the Northeast, the odds are against it. Spring forage harvest for silage is the most crucial time of the year, and sets the stage for good harvest management throughout the year. There is a relatively small range in optimal fiber content (NDF) for lactating dairy cows, making quality-related harvest management decisions critical. The purpose of this project is to improve the timing and nutritive value of spring forage harvests for dairy operations. Accurate prediction equations exist for estimating NDF content of mixed alfalfa-grass stands in spring, and estimating the optimal harvest date, but the weak link is estimating the proportion of grass (or alfalfa) in a stand. This project is acquiring numerous digital images of alfalfa-grass stands and relating the images to the actual percentage of alfalfa and grass in the image area. An alfalfa-grass recognition system is being designed to allow farmers and consultants to accurately estimate alfalfa-grass proportion, stand NDF, and optimum harvest date. A digital picture of the stand and a measure of maximum alfalfa height will be the only required inputs to an internet program, accessible by computer or smart phone. Such a tool will allow farmers and consultants to prioritize the order of harvest of alfalfa-grass fields to maximize chances of obtaining optimal forage NDF for lactating dairy cow diets.

Objectives/Performance Targets

Ultimate Objective:
Improve the timing and quality of spring forage harvests for Northeast dairy farms by reducing uncertainty in the estimation of alfalfa-grass stand composition.

Proximate Objectives:
1) Capture digital images from representative samples of mixed stands of alfalfa-grass in Northeast farmers’ fields.
-580 digital images were acquired from representative samples of mixed stands of alfalfa-grass in Northeast farmers’ fields in May 2011

2) Determine known stand composition values for each sample.
-The 580 samples of alfalfa-grass were cut, separated into alfalfa and grass fractions, and dried to determine known stand composition percentages

3) Create an alfalfa-grass recognition system that can filter and normalize a mixed stand image, evaluate the image, and return the percentage grass and alfalfa in the stand.
-Image filters and feature extraction algorithms are currently being designed from the 580 digital images.

4) Generate a free web service on http://www.forages.org that will allow farmers to upload images acquired from their fields and receive stand composition results and predictions of optimal forage quality and harvest timing in a rapid manner.
-This objective will be undertaken following successful completion of the alfalfa-grass recognition system.

Accomplishments/Milestones

Spring 2011
Certified Crop Advisors in Tompkins and Cortland Counties of New York State assisted in the selection of appropriate farmers’ fields for sample acquisition. In each field, representative samples were selected and delineated using a 66cm diameter round hoop. A digital image was taken at five megapixels resolution using a Canon PowerShot A3100 IS digital camera. In each sample, alfalfa maximum height, grass maximum height, and grass canopy height were measured using a meter stick.

Following digital photo acquisition, a 10cm high quadrat was inserted under the hoop to define the cutting height and the hoop was lowered to ground level. The forage within each hoop (sample) was cut at 10cm above ground level by cutting at the height of the quadrat using battery-operated grass clippers. Harvested forage from each sample was labeled, transported back to the laboratory, and manually separated into alfalfa and grass fractions. Any plant species other than alfalfa and grass were removed from the sample. Samples were dried until stable weight was reached at 60°C in a forced air oven. Samples were weighed directly after removal from the oven to determine dry matter weight of alfalfa and grass fractions from each sample. Dry matter weights determined known percentages of alfalfa and grass associated with each sample and its corresponding digital image.

A total of 580 digital images were acquired. Samples included four varieties of grass in mixed stands with alfalfa.

August 2011 to 2012
The spring 2011 sample set is now being used to develop and calibrate an alfalfa-grass recognition system (Figure 1) that will determine the percentage of alfalfa and grass in a given digital image. The system consists of six modules: 1) web interface, 2) recognition controller, 3) image filters, 4) feature extraction, 5) classification system, and 6) results.

First, the system user (farmer or extensionist) uploads an image to the web interface. The image is fed through a recognition controller that serves as the control system for the image processing modules described below. The image filters module enhances important features in the image and normalizes it to a format that permits image processing by the feature extraction module. The feature extraction module uses a mathematical algorithm to extract important features in the image such as the hoop defining the processing area and geometric attributes of alfalfa and grass leaves. This image is also subdivided into many smaller blocks to improve the accuracy of the classification system. The classification system then further processes the filtered, extracted images using geometric pattern matching and artificial intelligence. Finally, the results module uses information from the classification system to generate the percentage of alfalfa and the percentage of grass within the hoop in each image.

The timeline for image processing system development is to finish an initial iteration of the image filters and feature extraction modules prior to collecting a second sample set in spring 2012. The alfalfa-grass recognition system will then be completed by finalizing the classification system module and the results model. The system will be tested and validated using 2012 samples before adding the 2012 set to the calibration dataset to increase recognition system robustness across production years.

2013
After successful generation of the alfalfa-grass recognition system, the software will be developed into a farmer-friendly web application for inclusion as a free web service on http://www.forages.org by spring 2013. The image recognition software will be linked to automated calculators that employ equations to determine optimal forage quality and harvest timing (Parsons et al., 2006). Farmers will be able to simply acquire digital images from representative samples of mixed stands using a camera or smart phone, upload images acquired from their fields to the web application as well as the alfalfa maximum height parameter, and receive stand composition estimates and harvest timing predictions to achieve optimal forage quality from mixed stands at a given stubble height.

Parsons, D., Cherney, J. H., and Gauch, H. G., Jr. 2006. Estimation of Preharvest Fiber Content of Mixed Alfalfa–Grass Stands in New York. Agron. J. 98:1081-1089.

• Figure 1 Alfalfa-grass recognition system

Impacts and Contributions/Outcomes

The success of sample acquisition during year one activities and the initial development of image filters supports the idea that this application could reduce farmer uncertainty in the timing of spring forage harvest to ensure optimal quality.

Collaborators: