MSU-led horticulture mechanization study to streamline inventory for growers
Contact: Meg Henderson
STARKVILLE, Miss.鈥擥rowing high-demand ornamentals and specialty crops is a time and labor-intensive profession requiring constant monitoring of inventory and health, while also handling routine maintenance. A Mississippi State scientist is looking to the sky for solutions to these ground-level tasks.
Patricia Knight, director of coastal horticulture research at MSU鈥檚 Coastal Research and Extension Center and scientist in the Mississippi Agricultural and Forestry Experiment Station, is exploring how drone technology and artificial intelligence, or AI, might help growers save time and money on labor-intensive tasks. She has partnered to test cost-effective, industry-ready solutions with Siva Kumpatla, research leader for the USDA Agricultural Research Service鈥檚 Thad Cochran Southern Horticultural Laboratory, and Prabha Sundaravadivel, associate professor of electrical engineering at the University of Texas-Tyler.
The three-part study鈥檚 first phase is training a computer vision model to conduct plant inventories.
聽鈥淚t鈥檚 important to have an accurate inventory, but during the active shipping season, that gets pushed to the side,鈥 said Knight, also a research professor in MSU鈥檚 Department of Plant and Soil Sciences. 鈥淪ending out a drone to count while your staff is busy with more immediate tasks could help you avoid selling plants you don鈥檛 have.鈥
The team has visited three South Mississippi nurseries, and the UT group has shot footage of different shrubs and trees including magnolias, azaleas, roses and more. The images are being used to train an AI model to identify every possible variation of the plants, beginning with magnolias.
鈥淚n this method, called manual labeling, we label the images for features such as 鈥榩lant鈥 and 鈥榮oil.鈥 After being fed enough images, the system learns to quickly distinguish between plant and soil and then between individual plants and counts them,鈥 Kumpatla said. 鈥淲e have repeated this process over and over, always with a manual check until we got to a high level of accuracy.鈥
To date, the model has achieved over 96% accuracy in identifying magnolias, and the team is working on transferring and tweaking the models to achieve similar accuracy in other species.
鈥淚t is challenging to distinguish young peach and plum trees through drone imaging as they have similar canopy structures and leaf shapes, and factors like humidity, strong sunlight and shadows can affect the clarity and resolution of the images,鈥 Kumpatla said. 鈥淚mproving the model鈥檚 accuracy in such scenarios is an ongoing process.鈥
Once this phase is complete, the team will investigate robotics to automate repetitive, labor-intensive tasks like moving plants, weeding and pruning. They also are exploring drones for targeted disease and pest control and identifying soil moisture and irrigation issues before the plants show signs of distress鈥攁ll measures to help growers mitigate losses and save money. 聽
鈥淭hese technologies are available, but they are mostly implemented on large farms producing a single crop,鈥 Knight said. 鈥淢ost nurseries in Mississippi are smaller operations. We鈥檙e thinking about these producers that may grow hundreds of species and how we can deliver affordable technology to meet their needs.鈥
鈥淚 also think the project shows how effectively Mississippi State leverages our resources to work with outside partners like the USDA and University of Texas-Tyler,鈥 she added. 鈥淭ogether, we鈥檙e working quickly and effectively to come up with real-world solutions that add value to the industry.鈥
Learn more about the university鈥檚 Mississippi Agricultural and Forestry Experiment Station at .
Mississippi State University is taking care of what matters. Learn more at聽.