The agriculture arm of Deere & Company has signed a definitive agreement to acquire Blue River Technology, an innovative applied learning technology firm that has coupled precision computer vision with machine learning to recognize and take action on very specific objects.
John May, president of Deere Agricultural Solutions and CIO, said the investment in Blue River Technology is similar to Deere's acquisition of NavCom Technology in 1999 that established Deere as a leader in the use of GPS technology for agriculture and accelerated machine connectivity and optimization.
"We welcome the opportunity to work with the Blue River Technology team that is highly skilled and intensely dedicated to rapidly advancing the implementation of machine learning," said May. "As Deere recognizes the importance of technology to our customers. Machine learning is an important capability for Deere's future."
The Sunnyvale, California tech firm's primary market has been focused on grower's precision agriculture needs, applying its technology for weed control. Blue River has developed a system that uses facial recognition-type technology that teaches ag spraying equipment to precisely recognize specific types of weeds, then target those weeds with control substances, while leaving other plants in the sprayer's range completely undisturbed. The result for growers is a reduction in herbicide use.
"Blue River is advancing precision agriculture by moving farm management decisions from the field level to the plant level," said Jorge Heraud, co-founder and CEO of Blue River Technology. "We are using computer vision, robotics, and machine learning to help smart machines detect, identify, and make management decisions about every single plant in the field."
The company also works with drone technology for phenotyping environmental factors.
Deere will invest $305 million to fully acquire Blue River Technology and plans to keep the 60-person firm in Sunnyvale. The transaction is expected to close in September.
To watch Blue River Technology in action, click here: