Medical Plant Yield Monitoring
Automating Medicinal Plant Growth Monitoring with AI-Powered Computer Vision
problem
Our client, a pharmaceutical company that is operating automated plantations of medicinal plants, experiments with various agricultural-technical schemes (a different scheme for each bush) on their plantations. They currently use robots with cameras for regular plant observation. However, the business required more automation and modernization to reduce the human factor and achieve complete market security. Also, it was essential to control and monitor tops growth process and anomalies on the top level for the schemes of further analysis and enhancement.
problem
Our client, a pharmaceutical company that is operating automated plantations of medicinal plants, experiments with various agricultural-technical schemes (a different scheme for each bush) on their plantations. They currently use robots with cameras for regular plant observation. However, the business required more automation and modernization to reduce the human factor and achieve complete market security. Also, it was essential to control and monitor tops growth process and anomalies on the top level for the schemes of further analysis and enhancement.
solution
We used robots with cameras for periodical plant observation. We created a computer vision solution that takes images coming from different zones with some time intervals. It detects growing tops and identifies them, providing information on the growth process as a result of each unique growing top. During this project, we used the CRISP-DM methodology. The team decided to choose YOLO as the fastest and the most popular way to get high-level accuracy and fast processing. We spent approximately 12 hours on transfer learning for 30,000 iterations. In the end, we got 90% of accuracy. It takes approximately 20 seconds per image to analyze and detect many tops with an embedded device on one image.
solution
We used robots with cameras for periodical plant observation. We created a computer vision solution that takes images coming from different zones with some time intervals. It detects growing tops and identifies them, providing information on the growth process as a result of each unique growing top. During this project, we used the CRISP-DM methodology. The team decided to choose YOLO as the fastest and the most popular way to get high-level accuracy and fast processing. We spent approximately 12 hours on transfer learning for 30,000 iterations. In the end, we got 90% of accuracy. It takes approximately 20 seconds per image to analyze and detect many tops with an embedded device on one image.
results
We deployed the solution on Jetson TX2. The data was labeled using the LabelImg tool. After getting bounding boxes from the tool, the YOLO model was trained to detect grow tops. We implemented a custom Python algorithm that used a special distances vector to describe every grow top on the image. Thanks to the work of the team, the software achieved 80% accuracy for hemp detection and 90% for disease classification. The client was impressed with the innovation and flexibility.
results
We deployed the solution on Jetson TX2. The data was labeled using the LabelImg tool. After getting bounding boxes from the tool, the YOLO model was trained to detect grow tops. We implemented a custom Python algorithm that used a special distances vector to describe every grow top on the image. Thanks to the work of the team, the software achieved 80% accuracy for hemp detection and 90% for disease classification. The client was impressed with the innovation and flexibility.
tech stack
tech stack
