Automatic Pine Cone Pollination Bag Counting Using Drones
About Airwyse
Airwyse develops systems for precision agriculture, golf course turf management, object detection and other applications. Airwyse’s systems have the capability to autonomously detect problematic areas (known as “hotspots”), identify the root cause of those hotspots, generate a prescription to resolve the hotspot, apply the prescription, verify the results of the treatment, and perform follow-up procedures to eliminate the problem.
Overview
In March 2025, we partnered with Airwyse, an innovator in autonomous drone technology, to address a critical challenge in yield prediction for pine orchards. The initiative aimed to automate the counting process of pollination indicators—originally pine cones, later adapted to pollination bags—to support more accurate forecasting of harvest yield.
Problem Statement
The client manages pine orchards where selective pollination is performed using pollination bags. Traditionally, the team manually counts these bags at various growth stages to estimate end-of-season yield—a labor-intensive and time-consuming task, especially as visibility and accessibility of cones and bags on tall pine trees pose significant difficulties.
Project Goal
To develop and deploy a solution that automates the counting of pollination bags in pine orchards using aerial imagery captured by autonomous drones, thereby increasing efficiency, accuracy, and scalability of yield estimation.
Solution
Airwyse deployed autonomous drones capable of navigating through the pine orchard and capturing high-resolution images of the treetops. Saiwa contributed its expertise in computer vision and deep learning by developing an advanced tracking and counting algorithm tailored to detect and count pollination bags in the collected imagery.
Originally planned for pine cone detection, the scope of the algorithm was later adjusted to detect pollination bags, which are more visible and representative for tracking pollinated groups.
Outcome
The collaborative system was successfully tested on a sample of 44 pine trees, achieving acceptable accuracy in pollination bag counting and operating with efficient time complexity. This proof of concept validated the potential of drone-based automation in orchard management and opened up opportunities for future scaling and refinement.
