Development of Marker-Free Night-Vision Displacement Sensor System by Using Image Convex Hull Optimization

Abstract

Vision-based displacement sensors (VDSs) have the potential to be widely used in the structural health monitoring field, because the VDSs are generally easier to install and have higher applicability to the existing structures compared to the other conventional displacement sensors. However, the VDS also has disadvantages, in that ancillary markers are needed for extracting displacement data and data reliability is significantly lowered at night. In this study, a night vision displacement sensor (NVDS) was proposed to overcome the aforementioned two limitations. First, a non-contact NVDS system is developed with the installation of the infrared (IR) pass filter. Since it utilizes the wavelength of the infrared region and it is not sensitive to the change of a visible ray, it can precisely extract the shape information of the structure even at night. Second, a technique to extract the feature points from the images without any ancillary marker was formulated through an image convex hull optimization. Finally, the experimental tests of a three-story scaled model were performed to investigate the effectiveness of proposed NVDS at night. The results demonstrate that the NVDS has sufficiently high accuracy even at night and it can precisely measure the dynamic characteristics such as mode shapes and natural frequencies of the structure. The proposed system and formulation would extend the applicability of vision sensor not only into night-time measure but also marker-free measure.

Measuring the interstory drift of buildings by a smartphone using a feature point matching algorithm

“…If smartphones could be used at night, then the goal of continuous monitoring could be achieved. The next step in the advancement of this research will be to use night‐vision equipment, or image enhancement algorithms to monitor in the variation of light environment . Ultimately, the programming of a smartphone application will truly fulfill this function.…”

“…They proposed a target‐less method that would allow the scaling factor to be calculated with the angular distance, pixel pitch, and focal length. Choi et al also developed the method used in this study, and this method could be used at night via night vision. Xu et al used three different methods (correlation‐based template matching, Lucas Kanade optical flow estimation, and scale‐invariant feature transform) to measure the vibration of a railway bridge and suspension bridge.…”

A Literature Review on the Role of Internet of Things, Computer Vision, and Sound Analysis in a Smart Poultry Farm

“…Computer vision is an interdisciplinary field that can extract information from digital images or videos to create autonomous models, mimicking the capabilities of the human visual system . Computer vision technology can be used to study the behavior of chickens on any poultry farm.…”

“…Computer vision is an interdisciplinary field that can extract information from digital images or videos to create autonomous models, mimicking the capabilities of the human visual system. 55 Computer vision technology can be used to study the behavior of chickens on any poultry farm. Moreover, this technology can be employed on a farm for sick bird identification, disease detection, weight gain, egg size and weight monitoring, etc.…”

Underexposed Vision-Based Sensors’ Image Enhancement for Feature Identification in Close-Range Photogrammetry and Structural Health Monitoring

“…An SHM using a smartphone camera with a laser device was reported by Li et al [20]. Choi et al [21] proposed a night vision camera equipped with an IR pass filter to remove the red-eye effect in the infrared region. Digital cameras with LED lights as targets were used for night monitoring as evaluated by Feng et al [22].…”