Extraction of Broad-Leaved Tree Crown Based on UAV Visible Images and OBIA-RF Model: A Case Study for Chinese Olive Trees

Chinese olive trees (Canarium album L.) are broad-leaved species that widely planted in China. Accurately obtaining tree crown information provides important data for evaluating growth status, water and fertilizer management, yield estimation. To this end, study first used unmanned aerial vehicle (UAV) images the visible band as source of remote sensing (RS) data. Second, based on spectral features image object, vegetation index, shape, texture, terrain were introduced. Finally, extraction effect different feature dimensions was analyzed random forest (RF) algorithm, performance classifiers compared after dimensionality reduction. The results showed difference importance main factor led to a change accuracy. RF has best among current mainstream machine learning (ML) algorithms. In comparison with pixel-based (PB) classification method, object-based analysis (OBIA) method can extract each element RS images, which certain advantages. Therefore, combination OBIA algorithms is good solution (COTC) UAV images.