Automatic Building Detection From High-Resolution Satellite Images Based on Morphology and Internal Gray Variance

Abstract

Automatic building extraction remains an open research topic in digital photogrammetry and remote sensing. While many algorithms have been proposed for building extraction, none of them solve the problem completely. This is even a greater challenge in urban areas, due to high-object density and scene complexity. Standard approaches do not achieve satisfactory performance, especially with high-resolution satellite images. This paper presents a novel framework for reliable and accurate building extraction from high-resolution panchromatic images. Proposed framework exploits the domain knowledge (spatial and spectral properties) about the nature of objects in the scene, their optical interactions and their impact on the resulting image. The steps in the approach consist of 1) directional morphological enhancement; 2) multiseed-based clustering technique using internal gray variance (IGV); 3) shadow detection; 4) false alarm reduction using positional information of both building edge and shadow; and 5) adaptive threshold based segmentation technique. We have evaluated the algorithm using a variety of images from IKONOS and QuickBird satellites. The results demonstrate that the proposed algorithm is both accurate and efficient.

Object-Based Dense Matching Method for Maintaining Structure Characteristics of Linear Buildings

“…Therefore, some work [10,23] proposed the joint criteria to improve the edge segments. In this paper, for accurate building outline, we propose an improved line correction method to achieve edge line feature fitting buildings closely, which include three steps: (1) direction correction; (2) line merging; (3) length adjustment.…”

“…In recent researches, line segments have been considered in the process of building extraction. Wang [10] made the use of line segments extracted and auxiliary vertices in the diagonal by rectangle rule to extract building outlines, which can obtain regular and accurate rectangular building shape. However, for complex and irregular linear buildings, Wang’s method by simple rectangular rule is limited.…”

Building Segmentation of Satellite Image based on Area and Perimeter using Region Growing

“…Automatic detection of physical objects such as bonds, buildings, and road in satellite images is advantageous in many significant purposes as well as formation and upkeep of accurate geographical databases, evaluation of an extent of destruction after natural disasters as floods or earthquakes and military operations [1]. Building detection is interest topics in remote sensing.…”

Building Detection Using Enhanced HOG–LBP Features and Region Refinement Processes

“…Variance (IGV) and morphology operations is proposed in [45]. IGV features are extracted and the edge pixels that do not correspond to man-made objects are rejected.…”

“…IGV features are extracted and the edge pixels that do not correspond to man-made objects are rejected. Then, shadow detection is employed to remove false alarms and the remaining edges form the candidate regions out of which, buildings are extracted [45]. We implemented their method with the exception that their proposed shadow detection technique was replaced by the algorithm of Liu et al [46] for panchromatic images as their shadow detection technique was not clear enough to be implemented.…”