Computer Vision for Structural Dynamics and Health Monitoring
3. Performance Evaluation Through Laboratory and Field Tests
Download citation file:
- Ris (Zotero)
- Reference Manager
This chapter describes a wide range of experiments conducted in both controlled laboratory and challenging field environments to evaluate the performance of the computer vision sensor system for measuring dynamic displacement. Laboratory shaking table tests are carried out to compare the accuracy of displacements measured by vision sensors that track high-contrast artificial targets and low-contrast natural targets, respectively, on the structural surface as well as by reference sensors. The robustness of the vision sensor is examined in unfavorable environmental conditions such as dim light, background image disturbance, and partial template occlusion.