CPS: Medium: Collaborative Research: Using Computer Vision to Improve Data Input for Precision Thinning Models in Apples
Lead PI:
George Kantor
Abstract
Commercial apple growers must remove a portion of new apple fruitlets every year in order maintain fruit size, and prevent trees from develop a pattern of alternative year bearing, where some years there are many fruit, and other years very few. The challenge for a commercial grower is to remove a number fruitlets in the first three to four weeks after they form so as to optimize size and number of harvested fruit later in the year. To do this, commercial growers spray chemicals, generally two to four applications per year. The impact of a chemical thinner depends on weather and other factors. Thinning has historically been as much art as science, and growers often remove too few fruit, or occasionally, too many. In either case, production and profitability are less than they might be.Recently, horticultural researchers have developed a way for growers to more precisely determine if and when to apply chemical thinners. Basically, it requires that the new fruitlets be measured to see how fast they are growing. Some grow more slowly than others, or not at all, and these are the fruitlets that will drop. The method requires that the same fruitlets be measured two or more times over a two- to three-week period, and that many fruitlets be evaluated for each apple variety and block. The measurements are done by hand, with calipers, and each measurement has to be carefully recorded. While it makes thinning much more accurate, it takes a great deal of time, and growers are reluctant to do it.Computer technology in the form of smart-phones or robotically manipulated cameras offer a solution. This project will use pictures taken with phones and other cameras as a substitute for caliper measurements. Initially, many images will be used to build a measuring program using artificial intelligence. It's a challenge, as the computer has to pick out small apple fruitlets from among leaves, branches and other objects. It then has to determine how big the fruitlet is, and finally, make sure that measurements are taken from the same fruitlets when needed. However, if successful, growers will be able to quickly evaluate the need to thin using a set of cell-phone photos. This in turn, should improve production, and potentially reduce chemical use.
Performance Period: 06/01/2020 - 05/31/2024
Institution: Carnegie Mellon University
Sponsor: USDA
Award Number: 1932498