For disparity information acquisition tasks, phase-shift profilometry can achieve high disparity accuracy, but it is a stereo matching technique based on phase unwrapping. The phase unwrapping depends on the fringe pattern of multifrequency. Recent work also shows that deep learning can obtain disparity from a stereo pair of images, but it is difficult to obtain high accuracy. To tackle these problems, we propose a stereo matching method of obtaining high-accuracy disparity using a combination of the fringe pattern stereo matching network and the phase-shift method. First, the coarse disparity is obtained by using the fringe pattern stereo matching network, and then the wrapped phase map obtained by the 3 steps phase-shift method is used to optimize the coarse disparity to obtain a high-accuracy disparity map. This method rectifies the left and right fringe patterns in advance and eliminates the influence of the calibration parameters without loss of generality. It also avoids the challenge of phase unwrapping compared with phase-shift profilometry. We prove that the sinusoidal fringe pattern stereo matching can obtain a better coarse disparity effect than the stereo matching of the texture image, especially in the textureless area. Experiments show that high-precision disparity can be obtained with only three frames of high-frequency fringe patterns.
Existing motion-capture technologies are implemented through expensive and specialized equipment, which typically requires the wearable devices or the mark of human body joint. This leads to a distinct limitation on the accessibility and popularity for mass market consumer. To address these problems, we present a pipeline for 3D human motion capture from binocular stereo vision, which is based on MobilePose, a supervised learning method for 2D skeletal joint detection in real time. Due to the short time of 2D joint detection and 3D reconstruction, our approach can fulfill 3D human motion capture in real time. Besides, we use the captured 3D motion information to implement a simple application on human body animation. Compared with Microsoft's Kinect method using depth camera, our method is implemented with the available cameras, which is low cost and widely used.
For Line-Laser sensor products that CCD images are unknown, we present a method for the calibration of Line-Laser sensor measurement system using multi-directional and non-featured planes, and a method for system calibration optimization using multi-angle standard spheres. By building a mathematical model, we convert the line laser sensor measurement data into CMM measurement points. According to the constraint relationships of planes or spheres, the point measured by the Line-Laser sensor and the CMM should conform to the same equation, then we can solve the calibration matrix of the line laser sensor and the coordinate measuring machine by nonlinear optimization. Both simulation analyses and real experiments were conducted. A line laser sensor was used to measure a frosted standard ball with a radius of 12.696 mm. The radius deviation measured by the line laser sensor system and the center deviation of the sphere comparing with the CMM were observed. The experimental results show that the radius deviation of the calibration laser sensor measurement system is less than 0.02mm, and the center distance deviation of the sphere is less than 0.02mm. This method utilizing non-featured planes simplifies the calibration equipment and can reduce the fitting error when using standard ball from multiple angles for calibration. This method is different from the method of calibrating the single direction of the laser sensor. It can simultaneously calibrate the rotation matrix and translation matrix of the two-dimensional line laser sensor to the coordinate measuring machine, and optimize the global optimal calibration parameters.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.