|Shrestha, D - IA STATE UNIVERSITY|
|Steward, B - IA STATE UNIVERSITY|
|Birrell, S - IA STATE UNIVERSITY|
Submitted to: ASAE Annual International Meeting
Publication Type: Proceedings
Publication Acceptance Date: July 31, 2002
Publication Date: July 31, 2002
Citation: SHRESTHA, D.S., STEWARD, B.L., BIRRELL, S.J., KASPAR, T.C. PLANT HEIGHT ESTIMATION USING TWO SENSING SYSTEMS. ASAE ANNUAL INTERNATIONAL MEETING. 2002. CD-ROM. ST. JOSEPH, MI. Interpretive Summary: A major limitation to identifying and mapping yield-limiting factors in agricultural fields is the availability of appropriate on-the-go sensing technologies for plant growth during the growing season. The ability to map crop height and changes in crop height over time in agricultural fields would be a useful diagnostic tool to identify where and when crop stress is occurring. Additionally, plant height or rate of plant height change could be used to evaluate spatial crop response to inputs of fertilizers, herbicides, or insecticides. In this study we developed, tested, and compared two prototype systems for measuring crop height. One system utilized a digital camera and image analysis software and the other utilized an ultrasonic sensor and signal processing. With further development either system will be capable of measuring and mapping crop height on-the-go from a tractor-mounted platform. Farmers should be able to use this system to identify areas in their fields that are stressed and require management inputs such as fertilizer or water or areas that did not respond to inputs applied earlier, such as fertilizer, herbicide, or insecticides. In general, farmers will use this information to increase profitability and reduce environmental impacts. Scientists will use this system to identify the causes of variable crop growth in fields and to find management solutions to alleviate spatially variable crop stress.
Technical Abstract: The ability to map crop height over time in agricultural fields would be a useful diagnostic tool to identify where and when crop stress is occurring. Additionally, crop height or rate of height change could be used to evaluate spatial crop response to inputs of fertilizers, herbicides, or insecticides. Two different sensing approaches, stereo vision and ultrasonic, were developed to measure corn plant height. For the stereo vision method a chain code based stereo correspondence technique was developed to determine the disparity in the stereo image pair. Images were taken using one camera from a series of precisely controlled locations to generate the stereo effect. The ultrasonic sensor measured the distance to an object by detecting the time delay of an ultrasound signal echo. The echoes from different parts of a plant were recorded and collar height of the plant was estimated. A good correlation was found between the measured and estimated height using both stereo vision and the ultrasonic sensor. For the stereovision, r**2 between the maximum plant height and estimated height was 0.76. For the ultrasonic sensor the r**2 between 25th percentile of the group height statistics and plant collar height was found to be 0.72. It was concluded that both stereo vision and ultrasonic sensing have potential as corn plant height sensing approaches. These results demonstrate the potential of stereo vision for a vehicle-mounted crop height measurement system. Farmers will use this information to increase profitability and to reduce environmental impacts. Scientists will use this system to identify the causes of variable crop growth in fields and to find management solutions to alleviate spatially variable crop stress.