Detection of plant characteristics and a comparison of effectiveness between 2d and 3d data visualization in supporting human perception of plant characteristics

Efficient agriculture requires the assessment of plant characteristics. A higher crop yield can be achieved with good quality plant characteristic data. In this research, a system was developed using the algorithms presented here to automatically extract plant characteristics. The automatically extracted values were compared with ground-truth data to evaluate the accuracy of the system. As well, the effectiveness of using 2 or 3-dimensional data visualization for determining these characteristics is studied. An experiment was conducted to investigate how effective plant characteristics are evaluated when using 2D or 3D data visualizations. Participants were presented with either plant pictures (2D) or 3D plant models and tasked with identifying plant height and the number of leaves. Task completion times and accuracy rates were gathered for performance analysis.