Effectiveness of Image Augmentation Techniques on Detection of Building Characteristics from Street View Images Using Deep Learning

被引:16
作者
Han, Jongwon [1 ]
Kim, Jaejun [1 ]
Kim, Seongkyung [1 ]
Wang, Seunghyeon [1 ]
机构
[1] Hanyang Univ, Dept Architectural Engn, Seoul 133791, South Korea
关键词
Building characteristics; Urban analysis; Number of stories; Building typologies; Street view images; Image augmentation; Image processing; Deep learning; DAMAGE DETECTION;
D O I
10.1061/JCEMD4.COENG-15075
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
Two key building characteristics, namely the number of stories and typology, is vital across various domains such as construction management and architectural design. These aspects are particularly critical for disaster risk assessment and infrastructure planning. Although deep learning models are adept at extracting this information from Street view images (SVIs), their success is contingent upon the availability of large and diverse data sets with high accuracy. Image augmentation presents an alternative method to artificially broaden data set diversity. However, the impact of image augmentation techniques on identifying building stories and typologies from SVIs has not been adequately explored. This study proposes a methodology employing eight distinct image augmentation techniques-brightness, contrast, perspective, rotation, scale, shearing, and translation augmentations-as well as a combined approach using all these methods. The study evaluates the efficacy of models trained with these techniques by comparing the accuracy of different classes and architectures for each task, both with and without the application of augmentation. The findings revealed that while most augmentation methods enhance model accuracy, their effectiveness is task-dependent. Furthermore, it was observed that the most effective augmentation techniques differ among building classes and architectures within each task. This suggests that augmentation strategies need to be custom-designed to align with the unique features of each class and architectures for precise estimation of the number of stories and building typologies. While the focus of this research is on specific tasks, the evaluated augmentation techniques could also extend to related areas, such as ascertaining the age of buildings or identifying window types. In this study, the efficacy of augmentation techniques is explored within the framework of identifying the number of stories and building typologies. The models were assessed for average accuracy and class-specific accuracy across various architectures, comparing outcomes with and without the implementation of the proposed augmentation methods. A key finding is that the most effective augmentation method varies between architectures and individual classes. Contrary to common practice in deep learning, where applying multiple augmentation techniques is standard for accuracy enhancement, this study observed that such a strategy did not uniformly improve performance. Specifically, while combining augmentation methods generally resulted in higher average accuracy, this was not the case for some classes within MobileNetV3 when detecting the number of stories. Similarly, for ResNet-152, employing all augmentation techniques together led to the lowest accuracy in certain classes for building typology classification. These results indicate that augmentation strategies may require customization to cater to the distinct characteristics of each class and architecture for accurate estimation of number of stories and building typologies.
引用
收藏
页数:18
相关论文
共 50 条
[41]   A Comparative Evaluation of Deep Learning Techniques for Photovoltaic Panel Detection From Aerial Images [J].
Arnaudo, Edoardo ;
Blanco, Giacomo ;
Monti, Antonino ;
Bianco, Gabriele ;
Monaco, Cristina ;
Pasquali, Paolo ;
Dominici, Fabrizio .
IEEE ACCESS, 2023, 11 :47579-47594
[42]   Emotion Detection from Face Images Using Deep Learning Pfechniques [J].
Petean, Corina ;
Sandulescu, Virginia ;
Bica, Ovidiu .
2024 12TH E-HEALTH AND BIOENGINEERING CONFERENCE, EHB 2024, 2024, :206-209
[43]   Data Augmentation on Plant Leaf Disease Image Dataset Using Image Manipulation and Deep Learning Techniques [J].
Pandian, Arun J. ;
Geetharamani, G. ;
Annette, B. .
PROCEEDINGS OF THE 2019 IEEE 9TH INTERNATIONAL CONFERENCE ON ADVANCED COMPUTING (IACC 2019), 2019, :199-204
[44]   Rapid visual screening of soft-story buildings from street view images using deep learning classification [J].
Yu, Qian ;
Wang, Chaofeng ;
McKenna, Frank ;
Yu, Stella X. ;
Taciroglu, Ertugrul ;
Cetiner, Barbaros ;
Law, Kincho H. .
EARTHQUAKE ENGINEERING AND ENGINEERING VIBRATION, 2020, 19 (04) :827-838
[45]   Plant Disease Detection and Severity Assessment Using Image Processing and Deep Learning Techniques [J].
Verma S. ;
Chug A. ;
Singh A.P. ;
Singh D. .
SN Computer Science, 5 (1)
[46]   Rapid visual screening of soft-story buildings from street view images using deep learning classification [J].
Qian Yu ;
Chaofeng Wang ;
Frank McKenna ;
Stella X. Yu ;
Ertugrul Taciroglu ;
Barbaros Cetiner ;
Kincho H. Law .
Earthquake Engineering and Engineering Vibration, 2020, 19 :827-838
[47]   Gender Prediction from Images Using Deep Learning Techniques [J].
Bhat, Salma Fayaz ;
Lone, Ab Waheed ;
Dar, Taniya Ashraf .
2019 INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND DATA PROCESSING (IDAP 2019), 2019,
[48]   A survey of deep learning techniques for vehicle detection from UAV images [J].
Srivastava, Srishti ;
Narayan, Sarthak ;
Mittal, Sparsh .
JOURNAL OF SYSTEMS ARCHITECTURE, 2021, 117
[49]   Cell detection on digitized Pap smear images using ensemble of conventional image processing and deep learning techniques [J].
Harangi, Balazs ;
Toth, Janos ;
Bogacsovics, Gergo ;
Kupas, David ;
Kovacs, Laszlo ;
Hajdu, Andras .
PROCEEDINGS OF THE 2019 11TH INTERNATIONAL SYMPOSIUM ON IMAGE AND SIGNAL PROCESSING AND ANALYSIS (ISPA 2019), 2019, :38-42
[50]   Beyond here and now: Evaluating pollution estimation across space and time from street view images with deep learning [J].
Nathvani R. ;
D. V. ;
Clark S.N. ;
Alli A.S. ;
Muller E. ;
Coste H. ;
Bennett J.E. ;
Nimo J. ;
Moses J.B. ;
Baah S. ;
Hughes A. ;
Suel E. ;
Metzler A.B. ;
Rashid T. ;
Brauer M. ;
Baumgartner J. ;
Owusu G. ;
Agyei-Mensah S. ;
Arku R.E. ;
Ezzati M. .
Science of the Total Environment, 2023, 903