Coal resources play a crucial role in societal development. However, intensive coal mining frequently leads to environmental degradation. Monitoring surface crop growth in mining areas is essential for ecological assessments and a critical component of evaluating mining disturbances. In this study, sunflowers growing on the first mining face of the Xinjie Mine were selected to explore an efficient crop extraction method. Visible-band imagery was captured using a UAV, and the spectral characteristics of the sunflowers were analyzed. A red-blue difference index was developed, and the histogram threshold segmentation was employed for sunflower extraction. Four supervised classification methods containing maximum likelihood, minimum distance, support vector machine, and random forest method were compared to evaluate the performance of each extraction technique.