2019/07/14 by T. H. Nguyen, Thanh Huy Nguyen, S. Daniel +7 · 7 citations
Computer Science · Earth and Planetary Sciences · Engineering · Environmental Science · #3D Surveying and Cultural Heritage #Active contour model #Domain (mathematical analysis) #Extraction (chemistry) #Feature extraction #Lidar #Photogrammetry #Remote Sensing and LiDAR Applications #Remote-Sensing Image Classification #Task (project management) #cs.CV #eess.IV
paper · pdf · doi:10.5194/isprs-archives-xlii-2-w16-181-2019
published in The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences XLII-2/W16, 181-188 (Copernicus Publications) · PIA19 - Photogrammetric Image Analysis 2019 which will be held in conjunction with MRSS19 - Munich Remote Sensing Symposium 2019 on September 18th-20th, 2019 in Munich, Germany. Proceeding: The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
arxiv created 2019/07/14 · openalex created_date 2019/07/23 · openalex publication_date 2019/09/17 · arxiv updated 2019/09/19 · openalex updated_date 2026/08/05
Abstract. Automatic extraction of buildings in urban scenes has become a subject of growing interest in the domain of photogrammetry and remote sensing, particularly with the emergence of LiDAR systems since mid-1990s. However, in reality, this task is still very challenging due to the complexity of building size and shape, as well as its surrounding environment. Active contour model, colloquially called snake model, which has been extensively used in many applications in computer vision and image processing, has also been applied to extract buildings from aerial/satellite imagery. Motivated by the limitations of existing snake models dedicated to the building extraction, this paper presents an unsupervised and automatic snake model to extract buildings using optical imagery and an unregistered airborne LiDAR dataset, without manual initial points or training data. The proposed method is shown to be capable of extracting buildings with varying color from complex environments, and yielding high overall accuracy.