FIELD-OF-VIEW DETERMINATION FOR A BINDWEED DETECTION SENSOR

Autor: R. W. Whitney, Marvin L. Stone, John B. Solie, B. R. Criner
Rok vydání: 1999
Předmět:
Zdroj: Transactions of the ASAE. 42:1485-1492
ISSN: 2151-0059
DOI: 10.13031/2013.13313
Popis: Data from a photoelectric diode sensor, equipped with 670 and 780 nm interference filters, were analyzed to determine the maximum field-of-view and minimum percentage of soil covered by bindweed (Convolvulus arvensis) that could be distinguished from bare soil. Images containing one 150-mm bindweed could be distinguished from images of adjacent bare soil for all fields-of-view implying that adaptive thresholding would enable use of a field-of-view as large as 0.71 m2. Detection was 100% for nine of the 11 fields-of-view evaluated and 98% for the other two. When bare soil images were not paired with adjacent bindweed images, a single NDVI threshold could be used to distinguish between the two images with error. Results indicated that the required percentage of bindweed cover within an image was 12% for a 5% error in falsely detecting or failing to detect the presence of bindweed. Error for a fixed NDVI threshold decreased when classified by apparent soil moisture when compared with unclassified data.
Databáze: OpenAIRE