Many of us take for granted that we can enjoy fresh fruit year-round and probably have no clue just how much of a logistical feat this is for orchardists and fruit packing houses. Naturally, knowing what sort of yield to anticipate early in the season can be a gamechanger for growers, packing houses, retailers, and even consumers.
High-value crops like orchards and vineyards have received a fair amount of attention from agtech startups and venture capitalists. Growers are employing everything from biotech to precision ag to improve various aspects of their operations. There’s also a big opportunity for startups to solve fruit growers’ biggest pain: hungry insects that devour precious crops in the blink of an eye.
VCs are also making fruit-based plays. In Asia, Blue Sky Funds created a $10 million venture fund to invest in the growing demand for citrus fruit in Asia, while e-commerce giant JD.com led a $70 million financing for a Chinese-based retailer providing fresh fruits and vegetables.
Israel-based startup Fruitspec is hoping to take the mystery out of yield prediction with its hyperspectral machine vision technology. Current yield estimations are based on extrapolation from manual counts of a few sampled trees. As these estimates may vary widely in their accuracy, the results are detrimental business decisions that cause a loss of revenue to all players, from growers to retailers.
“No-one really knows how much fruit they have in their orchard until picking. As all key business decisions along the fruit value chain are based on yield estimates, not being able to accurately estimate your yield may result in poor business performance,” Raviv Kula, Fruitspec CEO, told AgFunderNews. “Using patented hyperspectral and computer vision technology, FruitSpec provides customers with an accurate prediction of the quantity of fruit they have in the orchard six-to-seven months before picking when critical decisions are made.”
FruitSpec’s technology consists of specially designed sensor pods mounted on any vehicle that scans the trees in the orchard. Applied computer vision and a hyperspectral algorithm automatically count and estimate fruit number and size, focused at the green fruit stage. Accurate yield estimates offer fruit packing houses and growers a service that enables them to make sound decisions, which impact revenues and financial stability, without adding to the workload.
Recently, the company announced that it completed successful field studies with its solution for fruit yields estimates/projections. The trials, which used FruitSpec’s hyperspectral machine vision technology, reportedly resulted in estimates that were more than 90% accurate.
We spoke with Kula to learn more about the startup’s journey.
When did you launch and what growth stage are you at currently as a company?
We have conducted multiple international pilots (South Africa, Israel, Spain, Florida, California and Chile) with large customers. So far, the results demonstrate that our accuracy is greater than 90%. We plan to launch commercially in 2019.
Who is your target customer?
FruitSpec targets packing houses and juice manufacturing customers. As the current business trend is to own the entire fruit chain or a part of the chain (i.e. a grower, packing house and juice manufacturer) these customers will benefit the most from our service.
What are some of the challenges that you’ve faced and how did you overcome them?
Beside technology development, the orchard hyperspectral ground scanning is the biggest challenge we had. Adjusting the right equipment to the right vehicle was a huge challenge, but we overcame that during our field trials.
What’s been the most surprising aspect of your startup journey so far?
The most surprising aspect is the willingness of customers and customers’ employees to assist us in what we do. “Yes, come and check it, I’ll help” was often the offer we received. My work experience is in other sectors, not agriculture, and this helpful attitude never ceases to amaze me.
What’s your fundraising experience been like? Who are your investors?
Fundraising is not easy, despite the enthusiasm in the sector for our technology. We are lucky to have Trendlines as our main seed investor. With the help of other private investors, we were able to move forward and achieve what we have today.
What do you look for in an investor?
To be part of the team! It is really great when an investor can also bring business experience and another viewpoint to the table, in addition to the money.
Have you participated in incubators or accelerators? If so was it beneficial?
FruitSpec is currently in Trendlines Agtech’s incubator. The incubator is highly recommended. As a young company, you need all the help, good advice, support and connections available. If you are in the right program you are blessed.
Any advice for other startups out there?
My experience of start-up life is that you need to be an optimistic-pessimistic person. On the one hand, you have to be optimistic that you will conquer the world with 3 people in your company and on the other hand, pessimistic, in order to predict all the things that can go wrong which you will need to worry about. In short, my advice is to enjoy the ride…
Do you have any competitors or quasi-competitors working on somewhat similar innovations?
Our main competition is manual labor. Some start-ups provide yield estimation, but toward the end of the season when the value of that data is low.
