“…Considering the spectral properties of vegetation, particular NIR band can be very helpful to detect trees. Li et al employed a simplified pulse-coupled neural network (PCNN) that uses spectral features as input, postprocessed using morphological reconstruction (Li, Hayward, Zhang, Liu, & Walker, 2009). The algorithm has been shown to outperform both JSEG (Deng & Manjunath, 2001) and TreeAnalysis (Erikson, 2003) in tree crown segmentation, but the primary error source is the undersegmentation of tree clusters due to the crown overlap.…”