Abstract
In this paper, a building extraction method is proposed based on a stacked sparse autoencoder with an optimized structure and training samples. Building extraction plays an important role in urban construction and planning. However, some negative effects will reduce the accuracy of extraction, such as exceeding resolution, bad correction and terrain influence. Data collected by multiple sensors, as light detection and ranging (LIDAR), optical sensor etc., are used to improve the extraction. Using digital surface model (DSM) obtained from LIDAR data and optical images, traditional method can improve the extraction effect to a certain extent, but there are some defects in feature extraction. Since stacked sparse autoencoder (SSAE) neural network can learn the essential characteristics of the data in depth, SSAE was employed to extract buildings from the combined DSM data and optical image. A better setting strategy of SSAE network structure is given, and an idea of setting the number and proportion of training samples for better training of SSAE was presented. The optical data and DSM were combined as input of the optimized SSAE, and after training by an optimized samples, the appropriate network structure can extract buildings with great accuracy and has good robustness.
Highlights
Nowadays, aerial optical images and digital surface model (DSM) obtained from Light detection and ranging (LIDAR) are main high resolution data for citizien remote sensing applications [1,2,3,4].As the most typical features of artificial landscapes, buildings play an important role in urban planning, urban development and military affairs [5].How to extract buildings quickly and accurately from high-resolution remote sensing data has become the primary problem that needs to be studied
The results of Area 30 and Area 37 were shown in Tables 5 and 6 and Figures 10 and 11, it this paper, wewith proposed remote sensing building extraction based on anSVM
We proposed a remote sensing building method, on an effective sub-total way of thinking is suitable for building detectionextraction with LIDAR
Summary
Aerial optical images and digital surface model (DSM) obtained from Light detection and ranging (LIDAR) are main high resolution data for citizien remote sensing applications [1,2,3,4].As the most typical features of artificial landscapes, buildings play an important role in urban planning, urban development and military affairs [5].How to extract buildings quickly and accurately from high-resolution remote sensing data has become the primary problem that needs to be studied. With the rapid development of remote sensing technology, multiple sensors remote sensing data show high-resolution features. This provides a good condition for the analysis of interested objects [6]. The traditional remote sensing image building extraction methods can be summarized as the following three categories [7]: (1) The line and corner extraction-based methods. These methods usually first draw straight lines on the basis of the straight line, and the lines are grouped, merged and removed, and screens out the exact outline of the building [8,9,10]; (2) Region segmentation—based methods-these methods extract the image characteristics, and get the building areas. The texture feature of the building can be obtained by using the gray level co-occurrence matrix, the gray-difference matrix and the
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.