Skip to main content
ARS Home » Midwest Area » Columbia, Missouri » Cropping Systems and Water Quality Research » Research » Publications at this Location » Publication #93187
Title: DEVELOPMENT OF A PRECISION SPRAYER FOR SITE-SPECIFIC WEED MANAGEMENT

Author
item TIAN, LEI - UNIV OF ILLINOIS
item REID, JOHN - UNIV OF ILLINOIS
item Hummel, John

Submitted to: Transactions of the ASAE
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 5/11/1999
Publication Date: N/A
Citation: N/A

Interpretive Summary: Improved application methods are needed to reduce the amounts of herbicides used in field crop production to maintain productivity while reducing environmental impact. A machine-vision-system-guided precision sprayer was developed and tested. The long-term objectives of the project were to develop novel technologies to estimate weed density and size in real time, realize site-specific weed control, and effectively reduce herbicide application amounts for corn and soybean fields. This research integrated a real-time machine vision sensing system with an automatic herbicide sprayer to create an intelligent sensing and spraying system. Multiple video images were used to cover the target area. To increase the accuracy, each individual spray nozzle was controlled separately. Instead of trying to identify each individual plant in the field, weed infestation zones were detected. Tests of the integrated system showed that weed infestation and crop plant zones cane be detected and spray decisions made in 0.37 s. With this system, approximately 48% of the herbicide normally used in broadcast applications could be saved without reducing the level of weed control. These findings should be beneficial to public and private sector researchers planning research on site-specific weed management.

Technical Abstract: A machine-vision-controlled sprayer was developed with four cameras in the vision system, each imaging one crop row. The four images were combined into a single frame for processing by a computer. Preliminary data showed that the image resolution could be reduced, and a prototype was developed using two cameras equipped with auto-iris, each imaging two crop rows. A near infrared filter was used to create high contrast vegetation images. An algorithm using a weed coverage ratio concept was able to make spray decisions in 0.037 s, which would allow a maximum sprayer travel speed of 46 km/hr. Approximately 50% of the herbicide normally used in broadcast applications could be saved using this concept, with little effect on overall efficacy. With the discrete wavelet transformation algorithm, the system was able to detect both weed infestation and crop plant zones, with a maximum sprayer speed of 4.2 km/hr. With this algorithm, approximately 48% of the herbicide normally used in a broadcast application could be saved with little effect on overall efficacy.