# Non-target Structural Displacement Measurement Using Reference Frame Based Deepflow

## TL;DR

This paper introduces a reference frame based Deepflow algorithm with masking and filtering for accurate, cost-effective, and flexible non-target structural displacement measurement using computer vision, validated on a cantilevered beam.

## Contribution

It presents a novel CV method that overcomes feature detection issues and drift, enabling precise displacement measurement without natural features.

## Key findings

- Validated on a cantilevered beam under various conditions
- Achieved high accuracy compared to laser displacement sensors
- Flexible in measuring any region without natural features

## Abstract

Structural displacement is crucial for structural health monitoring, although it is very challenging to measure in field conditions. Most existing displacement measurement methods are costly, labor intensive, and insufficiently accurate for measuring small dynamic displacements. Computer vision (CV) based methods incorporate optical devices with advanced image processing algorithms to accurately, cost-effectively, and remotely measure structural displacement with easy installation. However, non-target based CV methods are still limited by insufficient feature points, incorrect feature point detection, occlusion, and drift induced by tracking error accumulation. This paper presents a reference frame based Deepflow algorithm integrated with masking and signal filtering for non-target based displacement measurements. The proposed method allows the user to select points of interest for images with a low gradient for displacement tracking and directly calculate displacement without drift accumulated by measurement error. The proposed method is experimentally validated on a cantilevered beam under ambient and occluded test conditions. The accuracy of the proposed method is compared with that of a reference laser displacement sensor for validation. The significant advantage of the proposed method is its flexibility in extracting structural displacement in any region on structures that do not have distinct natural features.

---
Source: https://tomesphere.com/paper/1903.08831