Skip to main content
ARS Home » Research » Publications at this Location » Publication #96114
Title: A METHOD FOR USING IMAGES FROM A COLOR DIGITAL CAMERA TO ESTIMATE FLOWER NUMBER

Author
item Adamsen, Floyd
item Coffelt, Terry
item NELSON, JOHN - UNIV OF AZ, TUCSON, AZ
item Barnes, Edward
item Rice, Robert

Submitted to: Crop Science
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 7/10/1999
Publication Date: N/A
Citation: N/A

Interpretive Summary: Flowering is a basic process in plants. It responds to environmental factors such as day length, soil fertility, water stress, and many other factors. Flowering influences productivity, and the time of flowering influences harvest dates. Therefore, counting flowers is useful for estimating yields, optimizing harvest dates, and improving plant models. Manually counting flowers is labor intensive, and mechanical damage can be done to the plants. A nonintrusive method of counting flowers remotely with a digital camera has been developed. Automation of the counting procedure reduces labor costs, and because the images are taken without physical contact with plants, it is possible to count flowers from the same spot in the field without damaging the plants. The flower counting system uses off- the-shelf software on an IBM PC compatible computer. The camera used for this work costs less than $1000. This technology will be of value to researchers, consultants, and farm managers.

Technical Abstract: In many plants, flowering is conspicuous in the field, but enumerating flowers is labor intensive, especially when flowers need to be counted on a daily basis. Frequent trips into plot areas and the physical contact with the plants can result in mechanical damage to plants which can affect results. The objectives of this work were to develop methods using color digital images to estimate the number of flowers present in a scene captured in a digital image, and to do all of the processing in a fully automated mode that would allow the counting of flowers in large numbers of images. Images of flowers were made using a color digital camera in an experiment to determine the effects of seeding rate and nitrogen fertilizer rate on lesquerella yield at the University of Arizona's Maricopa Agricultural Center, 40 km south of Phoenix, AZ, during the 1996 to 1997 growing season. An automated system that identifys all of the pixels in an image that were flowers and counts the number of flower spots in a image i described. Processing time for individual images was 3.5 min on a Pentium 133 computed with 32 mega bytes of memory compared to a minimum of 45 min for manual counts. The automated methods produced results that were highly correlated to the number of flowers in an image as counted by hand. Results of the automated methods accurately tracked the temporal changes of flower number. Multiple counts of the same plants were made using the automated methods without damage to the plots or plants counted. This method has the potential of being used to predict harvest dates from peak flowering, tracking the response of flowering to environmental conditions and to evaluate the effects of cultural practices on flowering.