초록

용어보기논문에서 용어와 풀이말을 자동 추출한 결과로, 시범 서비스 중입니다. AI-Helper

Abstract ▼ AI-Helper

Unmanned aerial vehicles (UAV) can provide the ability to monitor urban areas efficiently in very fine detail. Building extraction is a major topic in urban monitoring that can be used to update maps, detect illegal buildings, create 3D city models. This study proposes an object-based building extra...

Unmanned aerial vehicles (UAV) can provide the ability to monitor urban areas efficiently in very fine detail. Building extraction is a major topic in urban monitoring that can be used to update maps, detect illegal buildings, create 3D city models. This study proposes an object-based building extraction method using only RGB images of UAV. Object-based approaches can be more effective at UAV image processing, because pixel-based or edge-based analysis can prove insufficient for high-resolution imagery due to its inability to handle the internal variability of complex scenes. First, objects are generated from an orthoimage and DSM using a multiresolution segmentation technique. Segmented objects are then separated by the DSM into high objects such as buildings or trees and low objects such as roads and the ground. High objects are classified as either buildings or non-buildings using spectral indices such as the normalized excessive green index (nEGI) and spatial features. The final buildings are generated by region-growing adjacent objects that are classified as buildings. This method's usability was evaluated by performing experiments with various UAV images.

주제어