Key points are not available for this paper at this time.
To address poor crop extraction results in mountainous regions using single-feature data in previous research, this study employed a quadcopter to capture aerial orthophoto imagery and image-matching point cloud data from a pitaya cultivation site in the rugged mountainous terrain of southwestern China. The authors identified three critical features: the visible-band difference vegetation index (VDVI), excess green – excess red (ExG-ExR), and canopy height model (CHM) and then integrated them to build a multi-dimensional feature dataset, namely VDVI+CHM and ExG-ExR+CHM. Through a rule-based object-oriented technique, they conducted identification extraction specifically for pitayas plants. The study yielded impressive extraction accuracies, with VDVI, ExG-ExR, CHM segmentation, VDVI+CHM, and ExG-ExR+CHM achieving overall accuracies of 92.34%, 91.05%, 89.08%, 97.56%, and 96.86%, respectively. Furthermore, to validate the accuracy of the extraction results, a regression analysis was conducted to compare the actual canopy area of the pitayas plants determined through human-computer interaction with the extraction results. The root mean square error (RMSE) for VDVI+CHM and ExG-ExR+CHM were found to be 18 dm2 and 25 dm2, respectively, while the coefficient of determination (R2) was 0.81 and 0.67, respectively. Notably, the comparative analysis revealed that VDVI + CHM, which fused multi-dimensional features, exhibited the highest recognition accuracy, demonstrating that integrating multi-dimensional plant features effectively enhanced the accuracy of pitaya plant identification and extraction. By overcoming the limitations of single spectral or spatial structural features, this approach provides valuable insights into the identification and extraction of characteristic economic crops in mountainous regions.
Yin et al. (2024) studied this question.