Abstract

In the light of the constantly expanding technological advancements concerning high-resolution satellites and imaging techniques for investigative and information uses it is important to look at how these algorithms progress to acquire more reliable data in a much efficient manner. This study aims to (1) investigate the ability to use remote sensing and geographic information system techniques to extract the detecting building edges in the City of Makkah and (2) investigate new machine learning techniques to derive the illegal building fences in the study area. Two WorldView-3 images will be the first obtained for the City of Makkah in 2016 and 2018. Convolutional neural networks algorithm will be investigated to detect all the fences within the two images. These traits have been utilized to create automated object detection techniques, which are a core requirement of information extraction and large frame analysis of images covering large expanses of land. In high-resolution images, object detection identifies objects belonging to a class, locating them using a bounding box. Based on satellite images time series, the outputs will detect the changes that occurred during 2016 and 2018. A web map application will be designed as the primary tool to make it easier, illustrating the differences between the main changes. Evaluation of binary classifiers approach will be used to evaluate the outcomes of building fences based on several performances that measure data interpretation. Preliminary findings will illustrate the precision and accuracy of the used machine learning algorithm. The research findings can contribute to the federal/municipal authorities and act as a generic indicator for targeting building fences for urban areas and/or suburban areas.

中文翻译：

---

从高分辨率图像中检测建筑物围栏的自动方法：沙特阿拉伯麦加的案例研究

摘要

鉴于有关用于调查和信息用途的高分辨率卫星和成像技术的不断扩大的技术进步，重要的是要研究这些算法如何以更有效的方式获取更可靠的数据。本研究旨在 (1) 研究使用遥感和地理信息系统技术提取麦加市检测建筑物边缘的能力，以及 (2) 研究新的机器学习技术以推导出研究区域内的非法建筑围栏。两幅 WorldView-3 图像将在 2016 年和 2018 年首次为麦加市获得。将研究卷积神经网络算法以检测两幅图像中的所有围栏。这些特征已被用于创建自动对象检测技术，这是大面积图像信息提取和大帧分析的核心需求。在高分辨率图像中，对象检测识别属于一个类的对象，使用边界框定位它们。基于卫星图像时间序列，输出将检测 2016 年和 2018 年期间发生的变化。网络地图应用程序将被设计为主要工具，以使其更容易，说明主要变化之间的差异。二元分类器的评估方法将用于基于测量数据解释的几种性能来评估构建围栏的结果。初步发现将说明所用机器学习算法的精度和准确性。