Utilizing intrinsic dimension estimation methods or etracti ecific ura eature ui AA iaer high resolution satellite imagery, and LIDAR data

Nowadays, integrating different kinds of data and images, achieved by the different remote sensing sensors are known as a suitable solution for extracting more useful information. This because of large range of aqucition images, digital format, and high temporal resoulation enable scinentits to extract information form land surface. The passive optical sensors have been used extensively in mapping horizontal structures. However, radar data could be used as a complementary data, since these data would be gathered in different climatic conditions in 24 hours of a day, as well as some geo and manmade structures have a specific response in the radar frequency. Furthermore, LiDAR data could gather precise measurements from vertical structures. On the other hand incorporating these variety of information and data for extracting specific urban features is curucial and challenging task. Hence, by integrating optical, radar, and LiDAR data more features and information would be prepared for different kinds of applications. For example some object may easily find in optic imagery but it is difficult to extract that object form LiDAR or RADAR images. Therefore utilizing procdure for fusing and extracting these object is inevitable. In this research, we used these datasets to detect buildings, roads, and trees in a complex city sense, i.e., San Francisco, by generating 57 features, and also by using the PCA and ICA feature extraction methods, as well as the well-known intrinsic dimension methods, including SML and NWHFC. Finally, the K-NN classifier was utilized in order to detect buildings, roads, and trees and grouping features according to the earned accuracies. Results show the high performance of the proposed approach and support our analyses.