Computer Vision Ground Settlement Monitoring via Prism Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for monitoring ground settlement during underground construction are limited by high costs, low precision, limited monitoring frequency, and difficulty in maintaining long-term, all-weather monitoring in complex urban environments.
Innovation Solution
A computer vision-based method using an industrial camera, optical lens, and digital image processing for multi-point monitoring, which includes fast device arrangement, all-weather operation, and simultaneous monitoring of multiple points with reduced equipment costs and improved accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If digital level and leveling rod are used for settlement monitoring, then measurement precision is improved, but monitoring frequency is limited due to manual operation requirements
Solution Approach 1:
The patent replaces the mechanical manual leveling system with an automated optical measurement system. The total station automatically captures images of prism targets and calculates settlement data through image processing, eliminating the need for manual level erection and rod positioning while maintaining measurement precision and enabling continuous automated monitoring.
Solution Approach 2:
The system implements self-service automation where the total station autonomously performs target acquisition, image capture, coordinate calculation, and settlement analysis without human intervention. The automated image processing algorithm automatically identifies prism positions and calculates settlement data, transforming the manual measurement process into a self-operating system that achieves both high precision and frequent monitoring.
2Duration of action of stationary object
If fiber Bragg grating hydrostatic level is used for all-weather on-line monitoring, then monitoring duration is improved, but device complexity increases due to breather pipes and liquid pipes
Solution Approach 1:
The patent extracts and eliminates the complex breather pipe and liquid pipe infrastructure from the monitoring system. By using optical prism targets mounted on building structures combined with automated total station imaging, the system achieves all-weather long-term monitoring capability without the physical connectivity requirements that complicated the hydrostatic level system.
3Area of stationary object
If GPS receiver is installed at each measured point for positioning, then monitoring coverage is improved, but cost increases due to multiple receivers and electromagnetic interference susceptibility
Solution Approach 1:
The patent introduces passive prism targets as intermediaries between the building structures and the total station. These passive optical targets reflect light back to the total station without requiring power sources or active electronics, enabling reliable multi-point monitoring coverage while avoiding the electromagnetic interference and cost issues associated with multiple active GPS receivers.
4Measurement precision
If total station scans prisms one by one to obtain settlement change, then measurement precision is improved, but monitoring frequency is limited due to sequential scanning requirement
Solution Approach 1:
The patent transitions from one-dimensional sequential scanning to two-dimensional parallel imaging. The total station captures images of multiple prism targets simultaneously within its field of view, and the automated image processing algorithm extracts coordinates of all prisms from a single image frame. This dimensional transformation enables both high precision measurement and frequent monitoring by eliminating the time-consuming sequential scanning process.
Data Source
AI summary
Disclosed is a method for monitoring ground settlement based on computer vision. Before monitoring starts, the first image frame is captured. For one measuring point, the area of the top LED lamp is defined as a tracking template, its pixel center is the reference point for settlement calculation, and a monitoring area is defined by an estimated range. After monitoring starts, the best matched of the lamp template is searched for in the monitoring area of a second image frame. When the best matched area is obtained, its pixel center is obtained as the new lamp position, and it is selected as the new template; the pixel displacement between two adjacent image frames can be obtained by comparison. The total pixel displacement of multiple points during the monitoring period is calculated through the accumulated displacement, and the actual settlement is calculated through a pixel-physical ratio.