The measurement of plant community structure provides an extensive understanding of its function, succession, and ecological process. The detection of plant community boundary is rather a challenge despite in situ work. Recent advances in object-based image analysis (OBIA) and machine learning algorithms offer new opportunities to address this challenge. This study presents a multi-scale segmentation OBIA approach to accurately identify the boundaries of each vegetation and plant community for mapping plant community structure. Initially, a very high resolution Worldview-2 image of a desert area is hierarchically segmented from scale 2 to 500. Afterward, the peak values of the standard deviation of brightness and normalized difference vegetation index (NDVI) across the segmentation scales are detected to determine the optimal segmentation scales of homogeneous single vegetation and plant community boundaries. A multi-scale classification of vegetation characterization with features of multiple bands, NDVI, grey-level co-occurrence matrix entropy, and shape index is performed to identify desert vegetation types. Finally, the six vegetation structural features on the diversity, richness, and morphology are calculated within the plant community boundaries and classified into plant community categories. Comparing the results with the object fitting index of the reference data, the validation indicates that the optimal segmentations of tree, shrub, and plant communities are consistent with the identified peak values.