Feature engineering is a key component contributing to the performance of the computer vision pipeline. It is fundamental to several computer vision tasks such as object recognition, image retrieval, and image segmentation. On the other hand, the emerging technology of structural health monitoring (SHM) paved the way for spotting continuous tracking of structural damage. Damage detection and severity recognition in the structural buildings and constructions are issues of great importance as the various types of damages represent an essential indicator of building and construction durability. In this chapter, the authors connect the feature engineering with SHM processes through illustrating the concept of SHM from a computational perspective, with a focus on various types of data and feature engineering methods as well as applications and open venues for further research. Challenges to be addressed and future directions of research are presented and an extensive survey of state-of-the-art studies is also included.
TopIntroduction
In recent years, Structural Health Monitoring (SHM) is an emerging field that received remarkable attention from many researchers, and its techniques have been noteworthy improved by integrating advancements in communication and sensing technology. The focus of SHM is on the condition assessment, especially structures durability, of different structure types; including civil structures, mechanical, and aerospace, using a dense deployment of various sensors. Thus, SHM is a substantial method of estimating the integrity of structures through detection, localization of damages, and estimation of structures durability, based on the appropriate analysis of the measured data in situ. The goal of SHM is not solely monitoring the integrity of structures, but also is providing an estimation for the damage at earlier stages, which results in determining the ideal repair strategies before the structural damage results in failure, increasing safety, and decreasing maintenance cost (Dorvash, Pakzad & Cheng, 2013; Fang, Liu & Teng, 2018; Bolandi et al., 2019; Abdulkarem et al., 2020).
A standard SHM system comprises three major components (Dorvash, Pakzad & Cheng, 2013; Zhou & Yi, 2013; Fang, Liu & Teng, 2018; Bolandi et al., 2019; Abdulkarem et al., 2020), as depicted in Figure 1.
- 1.
Sensor Deployment: This component aims to use the different sensors to measure the required data parameters of a structure, such as acceleration, images, stress, and displacement. Moreover, the influential environmental parameters (e.g., humidity, temperature, and wind speed) are measured. These parameters provide necessary data for structural health assessment.
- 2.
Data Processing: This component comprises data acquisition and transmission, data aggregation and processing, and storage modules. Data acquisition and transmission module is responsible for data collection from various SHM sensors and achieved by sensor nodes. Data aggregation and processing module is necessary for extracting features of SHM algorithms and can be allocated in different units such as sensor nodes and base stations. It also can take place before or after data transmission, according to the network topology and data processing strategy.
- 3.
Structural Health Evaluation: The main task of this component is to estimate the overall stability and safety of the structure.
Figure 1. General architecture of standard SHM system
Accordingly, having an SHM system helps at the following domains (Yan, Chen & Mukhopadhyay, 2017):
- 1.
Enhancement of Structural Integrity: The weak structure can be enhanced based on the conditional information of SHM.
- 2.
Avoidance of Catastrophic Failures: Early detection of structure damages can hinder the structure from catastrophic failures and secondary defects.
- 3.
Maintenance Costs Reduction: Periodical maintenance can be substituted with condition-based maintenance.
- 4.
Further Development Support: Studying the dynamic behavior of the structures over the periods of time may help to optimize the design of structures.
On the other hand, considering the rapid progress in digital cameras as well as computer vision-based sensing and monitoring technologies, major research fields are opened and attracted the attention of the structural health monitoring research community. The main reason for this is its unique characteristics and applicability in the past few years such as long-distance, high accuracy, non-contact nature, and electromagnetic interference immunity in multipoint, and structural measurement /monitoring over large-range (Ye, Dong & Liu, 2016).