深度学习
卷积神经网络
计算机科学
人工智能
过程(计算)
图像(数学)
机器学习
样板房
特征提取
人工神经网络
知识库
信息抽取
量子力学
操作系统
物理
作者
Yan Li,Yiqun Chen,Abbas Rajabifard,Kourosh Khoshelham,Mitko Aleksandrov
标识
DOI:10.4230/lipics.giscience.2018.40
摘要
Building databases are a fundamental component of urban analysis. However such databases usually lack detailed attributes such as building age. With a large volume of building images being accessible online via API (such as Google Street View), as well as the fast development of image processing techniques such as deep learning, it becomes feasible to extract information from images to enrich building databases. This paper proposes a novel method to estimate building age based on the convolutional neural network for image features extraction and support vector machine for construction year regression. The contributions of this paper are two-fold: First, to our knowledge, this is the first attempt for estimating building age from images by using deep learning techniques. It provides new insight for planners to apply image processing and deep learning techniques for building database enrichment. Second, an image-base building age estimation framework is proposed which doesn't require information on building height, floor area, construction materials and therefore makes the analysis process simpler and more efficient.
科研通智能强力驱动
Strongly Powered by AbleSci AI