@Article{LotteHaaKarAraShi:2018:CaStUs,
               author = "Lotte, Rodolfo Georjute and Haala, Norbert and Karpina, Mateusz 
                         and Arag{\~a}o, Luiz Eduardo Oliveira e Cruz de and Shimabukuro, 
                         Yosio Edemir",
          affiliation = "{Instituto Nacional de Pesquisas Espaciais (INPE)} and {University 
                         of Stuttgart} and {Wroclaw University of Environmental and Life 
                         Sciences} and {Instituto Nacional de Pesquisas Espaciais (INPE)} 
                         and {Instituto Nacional de Pesquisas Espaciais (INPE)}",
                title = "3D Fa{\c{c}}ade Labeling over Complex Scenarios: A Case Study 
                         Using Convolutional Neural Network and Structure-From-Motion",
              journal = "Remote Sensing",
                 year = "2018",
               volume = "10",
               number = "9",
                pages = "e1435",
                month = "Sept.",
             keywords = "fa{\c{c}}ade feature detection, 3D reconstruction, deep-learning, 
                         structure-from-motion.",
             abstract = "Urban environments are regions in which spectral variability and 
                         spatial variability are extremely high, with a huge range of 
                         shapes and sizes, and they also demand high resolution images for 
                         applications involving their study. Due to the fact that these 
                         environments can grow even more over time, applications related to 
                         their monitoring tend to turn to autonomous intelligent systems, 
                         which together with remote sensing data could help or even predict 
                         daily life situations. The task of mapping cities by autonomous 
                         operators was usually carried out by aerial optical images due to 
                         its scale and resolution; however new scientific questions have 
                         arisen, and this has led research into a new era of 
                         highly-detailed data extraction. For many years, using artificial 
                         neural models to solve complex problems such as automatic image 
                         classification was commonplace, owing much of their popularity to 
                         their ability to adapt to complex situations without needing human 
                         intervention. In spite of that, their popularity declined in the 
                         mid-2000s, mostly due to the complex and time-consuming nature of 
                         their methods and workflows. However, newer neural network 
                         architectures have brought back the interest in their application 
                         for autonomous classifiers, especially for image classification 
                         purposes. Convolutional Neural Networks (CNN) have been a trend 
                         for pixel-wise image segmentation, showing flexibility when 
                         detecting and classifying any kind of object, even in situations 
                         where humans failed to perceive differences, such as in city 
                         scenarios. In this paper, we aim to explore and experiment with 
                         state-of-the-art technologies to semantically label 3D urban 
                         models over complex scenarios. To achieve these goals, we split 
                         the problem into two main processing lines: first, how to 
                         correctly label the fa{\c{c}}ade features in the 2D domain, where 
                         a supervised CNN is used to segment ground-based fa{\c{c}}ade 
                         images into six feature classes, roof, window, wall, door, balcony 
                         and shop; second, a Structure-from-Motion (SfM) and 
                         Multi-View-Stereo (MVS) workflow is used to extract the geometry 
                         of the fa{\c{c}}ade, wherein the segmented images in the previous 
                         stage are then used to label the generated mesh by a reverse 
                         ray-tracing technique. This paper demonstrates that the proposed 
                         methodology is robust in complex scenarios. The fa{\c{c}}ade 
                         feature inferences have reached up to 93% accuracy over most of 
                         the datasets used. Although it still presents some deficiencies in 
                         unknown architectural styles and needs some improvements to be 
                         made regarding 3D-labeling, we present a consistent and simple 
                         methodology to handle the problem.",
                  doi = "10.3390/rs10091435",
                  url = "http://dx.doi.org/10.3390/rs10091435",
                 issn = "2072-4292",
             language = "en",
           targetfile = "lotte_3d.pdf",
        urlaccessdate = "27 abr. 2024"
}