UC IPM Online UC ANR home page UC IPM home page


SKIP navigation


Research and IPM

Grants Programs: Projects Database

Project description

Development of New Technology for Nonchemical Weed Control. (92CC047)
Program UC IPM competitive research grants program
D.C. Slaughter, Biological and Agricultural Engineering, UC Davis
P. Chen, Biological and Agricultural Engineering, UC Davis
Host/habitat Unspecified
Pest Unspecified Weeds
Discipline Weed Science
Cultural Controls
Start year (duration)  1992 (One Year)
Objectives Develop an intelligent, nonchemical weed removal machine by transferring and building upon recent advances in machine vision technology, knowledge-based decision theory and robotics.

Expand the pattern recognition research initially developed for processing tomatoes to cotton and lettuce and test the feasibility of using the experimental vision guided cultivator initially developed for processing tomatoes to cotton and lettuce.

Final report An experimental, vision-guided cultivator was designed to provide precise control of close cultivation tools in order to improve the effectiveness of mechanical cultivation when the crop is at the one to two true leaf stage. The system consists of a realtime computer vision control system coupled to an electronically controlled hydraulic actuator and a steerable tool sled. The computer examines a picture of the row and surrounding bed directly preceding the cultivation tools. Using a previously developed color look-up table, the computer identifies which picture elements comprise plants. The computer analyzes the plant material in the picture to determine where the row of crop plants are located. Once the row is identified the computer can determine if the cultivation tools are centered about the crop or if the tools need to be shifted to the left or right. This system was initially developed for processing tomatoes and the steering precision in commercial tomato fields ranged from positioning the cultivation tools within 1-0.26 inches of the desired location 68% of the time under low weed loads to within +/-0.47 inches under high weed loads. Similar accuracy was achieved when the system was modified for weeds in lettuce and cotton.

When adapting the system from tomatoes to other crops several modifications were made. The field of view of the system should be optimized for crop row spacing, plant spacing within the row, tendency for missing crop plants, and crop plant size. The use of two cameras improves the performance of the system when large weeds are present that may block the camera's view. The color look-up table used to identify crop plants may need to be modified for some crops. The color look-up table developed for tomatoes performed acceptably for lettuce and cotton, however the surface texture of the cotton leaves caused a glare in the computer image when the angle of the sun was low. The glare was not observed in tomatoes or lettuce and could be eliminated by using a polarizing filter on the camera.

Top of page

Statewide IPM Program, Agriculture and Natural Resources, University of California
All contents copyright 2020 The Regents of the University of California. All rights reserved.

For noncommercial purposes only, any Web site may link directly to this page. FOR ALL OTHER USES or more information, read Legal Notices. Unfortunately, we cannot provide individual solutions to specific pest problems. See our Home page, or in the U.S., contact your local Cooperative Extension office for assistance.

Agriculture and Natural Resources, University of California

Accessibility   web template revised: July 8, 2020 Contact webmaster.