Abstract
The detection of buildings in the city is essential in several geospatial domains and for decision-making regarding intelligence for city planning, tax collection, project management, revenue generation, and smart cities, among other areas. In the past, the classical approach used for building detection was by using the imagery and it entailed human–computer interaction, which was a daunting proposition. To tackle this task, a novel network based on an end-to-end deep learning framework is proposed to detect and classify buildings features. The proposed CNN has three parallel stream channels: the first is the high-resolution aerial imagery, while the second stream is the digital surface model (DSM). The third was fixed on extracting deep features using the fusion of channel one and channel two, respectively. Furthermore, the channel has eight group convolution blocks of 2D convolution with three max-pooling layers. The proposed model’s efficiency and dependability were tested on three different categories of complex urban building structures in the study area. Then, morphological operations were applied to the extracted building footprints to increase the uniformity of the building boundaries and produce improved building perimeters. Thus, our approach bridges a significant gap in detecting building objects in diverse environments; the overall accuracy (OA) and kappa coefficient of the proposed method are greater than 80% and 0.605, respectively. The findings support the proposed framework and methodologies’ efficacy and effectiveness at extracting buildings from complex environments.
Highlights
The numerical growth of the population in urban centers through the migration of the population from rural to urban areas is a defining feature of today’s society
The main contributions are listed as follows: (i) We propose a deep learning-based approach for building extraction from light detection and ranging (LiDAR) data and high-resolution aerial imagery. (ii) We developed and trained our network from scratch for our peculiar extraction framework. (iii) Our detected building outline was tested on diversified building forms found within our study area to test the transferability of the model, and the output attains the best performance of building extraction
This study proposes a deep learning model to detect building objects from fused, very high-resolution aerial imagery and digital surface model (DSM) derived from LiDAR
Summary
The numerical growth of the population in urban centers through the migration of the population from rural to urban areas is a defining feature of today’s society. Humans continue to move to major cities from rural regions, pushing for accelerated urban growth, leading to high demand for living space and working space, and increasing the potential for precise, accurate, and up-to-date 3D city models. The production of such models is still a challenging task. In this context, generating automatic and accurate building maps as quickly as possible and with excellent accuracy of results is an increasingly stringent requirement taken into account by local public authorities and decision-makers. The results obtained have many uses, among which is the need for integrated and responsible planning of the city following the principles of sustainable development [1,2,3,4,5].
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: 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.
