- Fruits: apples
- Crop Production: application rate management
Thinning is an important routine for apple growers to manage crop load and improve fruit quality, which is commonly done through manual fruitlet thinning or chemical blossom thinning. Despite chemical thinning is a cheaper and more effective method, traditionally it relies on human experts’ visual evaluation of tree blooming intensity to guide chemical spraying, which is inefficient and prone to errors. In this proposed project, we aim to establish an objective methodology that quantifies apple tree blossom density utilizing drone imagery and photogrammetry, and develop an apple blossom density mapping algorithm that allows users to define tree height region and generates corresponding top-view blossom density maps. The study will be conducted in the apple orchards located at Russell E. Larson Agricultural Research Center of Penn State in the growing season of 2022. During first bloom and full bloom growth stages, apple tree red-green-blue (RGB) images will be collected using DJI Mavic 2 Zoom. With the assistance of the proposed tree blocking structures, blossoms of the same apple trees will also be manually counted as ground truth. Tree point cloud reconstruction will be completed using Pix4Dmapper. Tree point clouds processing algorithm will be developed based on color thresholding and point cloud voxelization. Estimated blossom counting accuracy will be evaluated through regression analysis. The outcome of the study will be disseminated to farmers, industry stakeholders and researchers through convention presentation, extension publication and in-person demonstration.
Project objectives from proposal:
The overall goal of the project is to develop a point cloud processing and mapping algorithm that can assist farmers in the decision-making of precise blossom thinning by allowing convenient blossom density estimation and direct orchard blossom density visualization with drone technology. Specifically, the project objectives include:
1. Reconstruct dense point cloud models of apple trees during blooming using aerial RGB images and photogrammetry software.
2. Develop and evaluate a point cloud-based apple tree blossom density estimation method.
3. Develop a flexible apple tree blossom density mapping algorithm that allows the visualization of blossom density at various tree heights.