倾斜摄影测量生成的原始正射影像存在灰度集中，局部亮度值过大等情况，对图

Photogrammetry inclination generated raw grayscale presence of concentrated ortho-image luminance value local too large, the spatial domain of the image made gray linear stretching, increases the variance of the background crown ground, and to facilitate subsequent classification of individual tree crown division; using the nearest neighbor classification method to classify the image into the canopy and ground categories, excluding the impact of the split background values ​​may arise. Image enhancement and classification results shown in Figure 4:

The original orthophoto image generated by the tilt photogrammetry has grayscale concentration, local brightness value is too large, etc. , and the image is stretched linearly in space, increasing the difference between the tree crown and the ground background, and facilitating the subsequent classification and the division of the canopy of the wood tree; Excludes the possible effect of background values on segmentation. Image enhancement and classification results are shown in Figure 4:

The original Orthophoto Image generated by tilt photogrammetry has gray concentration, local brightness value is too large and so on. The image is stretched linearly in spatial domain, which increases the difference between tree crown and ground background, so as to facilitate subsequent classification and single tree crown segmentation. The image is divided into tree crown and ground two categories by using nearest neighbor classification method, so as to eliminate the possible influence of background value on segmentation. The results of image enhancement and classification are shown in Figure 4: