Can We Measure Displacement of a Structure with Featureless Surface using Computer Vision?
Non-targetbased computer vision 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.
Publication: Won, J., Park, J.W., Park, K., Yoon, H. and Moon, D.S., 2019. Non-Target Structural Displacement Measurement Using Reference Frame-Based Deepflow. Sensors, 19(13), p.2992.
How can we minimize power consumption of IoT sensor while capturing unexpected events such as earthquake, failure, etc.
Despite the advantages of the Wireless sensor networks (WSNs) for large infrastructure monitoring, long-term structural health monitoring, however, is still a challenge because it requires continuous data acquisition for the detection of random events such as earthquakes and structural collapse.
To achieve long-term operation, it is necessary to reduce the power consumption of sensor nodes designed to capture random events and, thus, enhance structural safety.
In this paper, we present an event-based sensing system design based on an ultra-low-power microcontroller with programmable event-detection mechanism to allow continuous monitoring; the device is triggered by vibration, strain, or a timer and has a programmed threshold, resulting in ultra-low-power consumption of the sensor node.