Sensor-Based Evaluation of Architectural Traits in Tree Fruits

Mugilan Govindasamy Raman

doi:10.7273/000005260

Tree fruit industries play a significant role in many aspects of global food security. They provide recognized vitamins, antioxidants, and other nutritional supplements packed in fresh fruits and other processed commodities such as juices, jams, pies, and other products. However, many fruit crops including peaches (Prunus persica (L.) Batsch) and pear (Pyrus communis L.) are perennial trees requiring dedicated orchard management. The architectural and morphological traits of fruit trees, notably tree height, canopy area, and canopy crown volume, help to determine yield potential and precise orchard management. Thus, the use of unmanned aerial vehicles (UAVs) coupled with RGB sensors and ground-based 3D LiDAR can play an important role in the high-throughput acquisition of data for evaluating architectural traits. One of the main factors that define UAV-RGB data quality are sensor imaging angles, which are important for extracting architectural characteristics from the trees. Two studies have been conducted at different orchard systems, namely peach and pear, to extract the precise architectural trait information. The goal was to optimize the sensor imaging angles and find out the effect of these angles and integration of the data acquired at nadir and oblique angles, on the prediction accuracy. In the first study, UAV integrated with an RGB imaging sensor at three different angles (90º, 65º, and 45º) and a 3D light detection and ranging (LiDAR) system was used to acquire images of peach trees located at the Washington State University’s Tukey Horticultural Orchard, Pullman, WA, USA. A total of three approaches, comprising the use of 2D data (from UAV-RGB) and 3D point cloud (from UAV-RGB and LiDAR), were utilized to segment and measure the individual tree height and canopy crown volume. Overall, the features extracted from the images acquired at 45º and integrated nadir and oblique images showed a strong correlation with the ground reference tree height data, while the latter was highly correlated with canopy crown volume. In the second study, five UAV missions were conducted at the pear rootstock breeding plot to acquire high-resolution RGB imagery at different sensor inclination angles (90º, 65º, and 45º) and directions (forward and backward) at Washington State University (WSU) Tree Fruit Research and Extension Center in Wenatchee, WA, USA. The study evaluated the tree height and canopy volume extracted from four different integrated datasets and validated the accuracy with the ground reference data. The results indicated that 3D point cloud precisely measured the traits compared to 2D datasets and the integration of different angles especially without nadir angles improved the accuracy in extracting the tree height and canopy volume data. Thus, the selection of the sensor angles during UAV flight is critical for improving the accuracy of extracting architectural traits and may be useful for further precision orchard management.

Sensor-Based Evaluation of Architectural Traits in Tree Fruits

Files and links (1)

Abstract

Metrics

Details