Application of Augmented Reality Technology in the SDN 1 Sanur Building Recognition Application

This study aims to build an application to introduce the Sumerta 1 public elementary school building. This research uses AR (Augmented Reality) technology, which with this technology makes it possible to display an object in virtual form in a real world view. The method used in this application is marker-based which identifies the pattern of a marker, in the application development itself the model used is the waterfall model. In the process of building this application, using the Vuforia software development kit (SDK) and Unity as the engine.

Building Recognition System Based on Improved SIFT Algorithm and Positioning Information

In order to solve the general problem, that is, the accurate recognition rate is low in a small extent or when the image resources are few and scattered. This article puts forward a building recognition system that combines GPS positioning information with an improved SIFT algorithm, and adds a pre-processing mechanism to predict the possibility of the building existence in the system, which further reduces mismatch and improves response speed. The final verification shows that this research is actually effective.

Rancang Bangun Aplikasi Mobile Pengenalan Gedung dengan Teknologi Augmented Reality Berbasis Marker

<p>Universitas atau kampus merupakan institusi pendidikan tinggi dan penelitian yang memberikan gelar akademik dalam berbagai bidang. Kampus tentunya memiliki beberapa gedung yang dapat digunakan sebagai ruangan kelas, laboratorium, ruang dosen, dll. Pada waktu tertentu sebuah kampus tidak jarang dikunjungi oleh tamu, yang berkeliling kampus dan mengunjungi gedung-gedung di lingkungan kampus. Tidak hanya tamu, Kampus juga kedatangan mahasiswa baru setiap tahun ajaran baru. Setiap kegiatan tur kampus yang dilakukan tamu maupun mahasiswa baru, harus selalu dituntun oleh dosen maupun mahasiswa. Berdasarkan kasus tersebut, penelitian ini bertujuan untuk mengimplementasikan Teknologi <em>Augmented reality</em> (AR) dengan menggunakan metode <em>Marker</em>-<em>Based</em>. Aplikasi ini menjadi aplikasi yang dapat digunakan sebagai pengenalan gedung kampus. Setiap gedung akan mempunyai <em>marker</em> atau penanda unik khusus yang berbeda pada setiap gedung. Konsep dari pengimplementasian aplikasi ini adalah, dengan mengarahkan kamera yang dibuka melalui aplikasi ini dan mengarahkan kamera tersebut ke <em>marker</em> yang ditemui di gedung yang sedang dikunjungi. Kamera akan mengidentifikasi <em>marker</em>, jika <em>marker</em> dikenali maka objek 3D dari gedung tersebut akan muncul tepat diatas <em>marker</em> untuk memberikan pengguna bagaimana bentuk keseluruhan gedung. Tidak hanya objek 3D, aplikasi juga menyediakan informasi mengenai gedung tersebut dan juga gambar dari posisi <em>user</em> beserta dua gedung terdekat yang dapat dikunjungi pengguna setelahnya. Dengan menggunakan aplikasi ini, pengunjung tidak memerlukan seseorang untuk menuntunnya berkeliling di sekitaran kampus. Aplikasi ini sudah diuji dengan <em>usability testing </em>dan kepuasan pengguna mencapai 83,4 % yang berarti bahwa aplikasi dapat digunakan dan berfungsi bagi pengguna</p><p><strong><em>Abstract</em></strong></p><p><em>The university or campus is a higher education and research institution that provides academic degrees in various fields. The university certainly has several buildings that can be used as classrooms, laboratories, lecturers' rooms, etc. At a certain time, a university is not infrequently visited by guests, who tour the campus and visit buildings in the university environment. Not only guests, but the University also has new students every new school year. Every campus tour activity carried out by guests or new students, must always be guided by both lecturers and students. Based on these cases, this study aims to implement Augmented reality (AR) Technology using the Marker-Based method. This application is a building recognition application that can be used at a University. Each building will have a unique marker on each building. The concept of implementing this application is, by directing the camera opened through this application and directing the camera to the marker found in the building being visited. The camera will identify the marker, if the marker is recognized then the 3D object of the building will appear directly above the marker to give the user what the overall shape of the building looks like. Not only 3D objects, but the application also provides information about the building and also a picture of the user's position along with the two closest buildings that the user can visit afterward. By using this application, visitors do not need someone to guide them around the campus. This application has been tested with usability testing and user satisfaction reaches 83,4% which means that the application can be used and functioning for the user.</em></p>

FSRSS-Net: High-Resolution Mapping of Buildings from Middle-Resolution Satellite Images Using a Super-Resolution Semantic Segmentation Network

Satellite mapping of buildings and built-up areas used to be delineated from high spatial resolution (e.g., meters or sub-meters) and middle spatial resolution (e.g., tens of meters or hundreds of meters) satellite images, respectively. To the best of our knowledge, it is important to explore a deep-learning approach to delineate high-resolution semantic maps of buildings from middle-resolution satellite images. The approach is termed as super-resolution semantic segmentation in this paper. Specifically, we design a neural network with integrated low-level image features of super-resolution and high-level semantic features of super-resolution, which is trained with Sentinel-2A images (i.e., 10 m) and higher-resolution semantic maps (i.e., 2.5 m). The network, based on super-resolution semantic segmentation features is called FSRSS-Net. In China, the 35 cities are partitioned into three groups, i.e., 19 cities for model training, four cities for quantitative testing and the other 12 cities for qualitative generalization ability analysis of the learned networks. A large-scale sample dataset is created and utilized to train and validate the performance of the FSRSS-Net, which includes 8597 training samples and 766 quantitative accuracy evaluation samples. Quantitative evaluation results show that: (1) based on the 10 m Sentinel-2A image, the FSRSS-Net can achieve super-resolution semantic segmentation and produce 2.5 m building recognition results, and there is little difference between the accuracy of 2.5 m results by FSRSS-Net and 10 m results by U-Net. More importantly, the 2.5 m building recognition results by FSRSS-Net have higher accuracy than the 2.5 m results by U-Net 10 m building recognition results interpolation up-sampling; (2) from the spatial visualization of the results, the building recognition results of 2.5 m are more precise than those of 10 m, and the outline of the building is better depicted. Qualitative analysis shows that: (1) the learned FSRSS-Net can be also well generalized to other cities that are far from training regions; (2) the FSRSS-Net can still achieve comparable results to the U-Net 2 m building recognition results, even when the U-Net is directly trained using both 2-meter resolution GF2 satellite images and corresponding semantic labels.

Inferring Mixed Use of Buildings with Multisource Data Based on Tensor Decomposition

Information on the mixed use of buildings helps understand the status of mixed-use urban vertical land and assists in urban planning decisions. Although a few studies have focused on this topic, the methods they used are quite complex and require manual intervention in extracting different function patterns of buildings, while building recognition rates remain unsatisfying. In this paper, we propose a new method to infer the mixed use of buildings based on a tensor decomposition algorithm, which integrates information from both high-resolution remote sensing images and social sensing data. We selected the Tianhe District of Guangzhou, China to validate our method. The results show that the recognition rate of buildings can reach 98.67%, with an average recognition accuracy of 84%. Our study proves that the tensor decomposition algorithm can extract different function patterns of buildings unsupervised, while remote sensing data can provide key information for inferring building functions. The tensor decomposition-based method can serve as an effective and efficient way to infer the mixed use of buildings, which can achieve better results with simpler steps.

An Improved 3D Registration Method of Mobile Augmented Reality for Urban Built Environment

3D registration plays a pivotal role in augmented reality (AR) system. The existing methods are not suitable to be applied directly in the mobile AR system for the built environment, with the reasons of poor real-time performance and robustness. This paper proposes an improved 3D registration method of mobile AR for built environment, which is based on SURFREAK and KLT. This method increases the building efficiency of algorithm descriptors and maintains the robustness of the algorithms. To implement and evaluate the registration method, a smart phone-based mobile AR system for built environment is developed. The experimental result shows that the improved method is endowed with higher real-time performance and robustness, and the mobile AR 3D registration can realize a favorable performance and efficiency in the complex built environment. The mobile AR system could be used in building recognition and information augmentation for built environment and further to facilitate location-based games, urban heritage tourism, urban planning, and smart city.