Exploring the Potential of Unmanned Aerial Vehicle (UAV) Remote Sensing for Mapping Plucking Area of Tea Plantations

Abstract

Mapping plucking areas of tea plantations is essential for tea plantation management and production estimation. However, on-ground survey methods are time-consuming and labor-intensive, and satellite-based remotely sensed data are not fine enough for plucking area mapping that is 0.5–1.5 m in width. Unmanned aerial vehicles (UAV) remote sensing can provide an alternative. This paper explores the potential of using UAV-derived remotely sensed data for identifying plucking areas of tea plantations. In particular, four classification models were built based on different UAV data (optical imagery, digital aerial photogrammetry, and lidar data). The results indicated that the integration of optical imagery and lidar data produced the highest overall accuracy using the random forest algorithm (94.39%), while the digital aerial photogrammetry data could be an alternative to lidar point clouds with only a ~3% accuracy loss. The plucking area of tea plantations in the Huashan Tea Garden was accurately measured for the first time with a total area of 6.41 ha, which accounts for 57.47% of the tea garden land. The most important features required for tea plantation mapping were the canopy height, variances of heights, blue band, and red band. Furthermore, a cost–benefit analysis was conducted. The novelty of this study is that it is the first specific exploration of UAV remote sensing in mapping plucking areas of tea plantations, demonstrating it to be an accurate and cost-effective method, and hence represents an advance in remote sensing of tea plantations.

Plant phenotyping relevance

UAV画像・写真測量・LiDARを組み合わせ、茶園の摘採面積を分類・定量化する手法を比較検証しており、植物キャノピーの状態測定が中心である。

Code and data availability

The supplied blocks describe UAV lidar/imagery data collection and classification for tea plucking area mapping, but contain no public phenotype dataset, imagery deposit, author code, or trained model release. The only URLs are the article DOI, the CC BY license link, and Pix4D's generic support documentation, none of

No evidence-backed public reproduction asset is currently recorded.