Landscape structures and process on different scale show different characteristics. In the study of specific target landmarks, the most appropriate scale for images can be attained by scale conversion, which improves the accuracy and efficiency of feature identification and classification. In this paper, the authors carried out experiments on multi-scale classification by taking the Shangri-la area in the north-western Yunnan province as the research area and the images from SPOT5 HRG and GF-1 Satellite as date sources. Firstly, the authors upscaled the two images by cubic convolution, and calculated the optimal scale for different objects on the earth shown in images by variation functions. Then the authors conducted multi-scale superposition classification on it by Maximum Likelyhood, and evaluated the classification accuracy. The results indicates that: (1) for most of the object on the earth, the optimal scale appears in the bigger scale instead of the original one. To be specific, water has the biggest optimal scale, i.e. around 25-30m; farmland, grassland, brushwood, roads, settlement places and woodland follows with 20-24m. The optimal scale for shades and flood land is basically as the same as the original one, i.e. 8m and 10m respectively. (2) Regarding the classification of the multi-scale superposed images, the overall accuracy of the ones from SPOT5 HRG and GF-1 Satellite is 12.84% and 14.76% higher than that of the original multi-spectral images, respectively, and Kappa coefficient is 0.1306 and 0.1419 higher, respectively. Hence, the multi-scale superposition classification which was applied in the research area can enhance the classification accuracy of remote sensing images .
In this paper, the decision tree classification based on the CART algorithm (Classification and Regression Tree) is used to extract the impervious surface area of Nantong city in Jiangsu Province in China. Impervious surface dynamic change nearly 25 years in Nantong city is researched using four periods Landsat images of 1990, 2003, 2008, and 2014. The results show that the classification precision based on the CART algorithm is higher, which can more accurately extract the impervious surface. During the 25 years, the trend of the impervious surface of Nantong is increased year by year. Urban construction and expansion is one of the driving forces of the impervious surface increase.
Fuxian Lake located in the middle of Yunnan Province is second deepest lake in china. The water level of Fuxian Lake descends and its water area reduces in recent years owing to the climate changing. Therefore, it is crucial for rational utilization of lake resources to study the change trend of Fuxian Lake’s area. Landsat images from 1974 to 2014 were used to monitor Fuxian Lake’s area change. Monitoring results show that there are four apparent features of Fuxian Lake’s area: (1) Years in which Fuxian Lake’s area are larger are concentrated in 2006 to 2009. (2) From 1974 to 1990, Fuxian Lake’s area change has a trend of decrease. (3) From 1990 to 2005, Fuxian Lake’s area change shows a rise trend on the whole. (4) From 2005 to 2014, there is an obvious decrease trend of Fuxian Lake’s area change.
High accuracy remote sensed image classification technology is a long-term and continuous pursuit goal of remote sensing
applications. In order to evaluate single classification algorithm accuracy, take Landsat TM image as data source,
Northwest Yunnan as study area, seven types of land cover classification like Maximum Likelihood Classification has been
tested, the results show that: (1)the overall classification accuracy of Maximum Likelihood Classification(MLC), Artificial
Neural Network Classification(ANN), Minimum Distance Classification(MinDC) is higher, which is 82.81% and 82.26%
and 66.41% respectively; the overall classification accuracy of Parallel Hexahedron Classification(Para), Spectral
Information Divergence Classification(SID), Spectral Angle Classification(SAM) is low, which is 37.29%, 38.37, 53.73%,
respectively. (2) from each category classification accuracy: although the overall accuracy of the Para is the lowest, it is
much higher on grasslands, wetlands, forests, airport land, which is 89.59%, 94.14%, and 89.04%, respectively; the SAM,
SID are good at forests classification with higher overall classification accuracy, which is 89.8% and 87.98%, respectively.
Although the overall classification accuracy of ANN is very high, the classification accuracy of road, rural residential land
and airport land is very low, which is 10.59%, 11% and 11.59% respectively. Other classification methods have their
advantages and disadvantages.
These results show that, under the same conditions, the same images with different classification methods to classify, there
will be a classifier to some features has higher classification accuracy, a classifier to other objects has high classification
accuracy, and therefore, we may select multi sub-classifier integration to improve the classification accuracy.
Estimating regional forest organic carbon pool has became a hot issue in the study of forest ecosystem carbon cycle. The forest ecosystem in Shangri-La County, Northwest Yunnan Province, are well preserved, and the area of Picea Likiangensis, Quercus Aquifolioides, Pinus Densata and Pinus Yunnanensis amounts to 80% of the total arboreal forest area in Shangri-La County. Based on the field measurements, remote sensing data and GIS analysis, three models were established for carbon storage estimation. The remote sensing information model with the highest accuracy were used to calculate the carbon storages of the four main forest ecosystems. The results showed: (1) the total carbon storage of the four forest ecosystems in Shangri-La is 302.984 TgC, in which tree layer, shrub layer, herb layer, litter layer, soil layer are 60.196TgC, 5.433TgC, 1.080TgC, 3.582TgC and 232.692TgC, accounting for 19.87%, 1.79%, 0.36%, 1.18%, 76.80% of the total carbon storage respectively. (2)The order of the carbon storage from high to low is soil layer, tree layer, shrub layer, litter layer and herb layer respectively for the four main forest ecosystems. (3)The total average carbon density of the four main forest ecosystems is 403.480 t/hm2, and the carbon densities of the Picea Likiangensis, Quercus Aquifolioides, Pinus Densata and Pinus Yunnanensis are 576.889 t/hm2, 326.947 t/hm2, 279.993 t/hm2 and 255.792 t/hm2 respectively.