KEYWORDS: Cameras, Calibration, 3D metrology, Imaging systems, 3D image processing, Distortion, 3D acquisition, Machine vision, 3D vision, Reverse engineering
One of the most interesting goals of machine vision is 3D structure recovery of the scenes. This recovery has many
applications, such as object recognition, reverse engineering, automatic cartography, autonomous robot navigation, etc.
To meet the demand of measuring the complex prototypes in reverse engineering, a trinocular stereo vision method based
on mesh candidates was proposed. After calibration of the cameras, the joint field of view can be defined in the world
coordinate system. Mesh grid is established along the coordinate axes, and the mesh nodes are considered as potential
depth data of the object surface. By similarity measure of the correspondence pairs which are projected from a certain
group of candidates, the depth data can be obtained readily. With mesh nodes optimization, the interval between the
neighboring nodes in depth direction could be designed reasonably. The potential ambiguity can be eliminated efficiently
in correspondence matching with the constraint of a third camera. The cameras can be treated as two independent pairs,
left-right and left-centre. Due to multiple peaks of the correlation values, the binocular method may not satisfy the
accuracy of the measurement. Another image pair is involved if the confidence coefficient is less than the preset
threshold. The depth is determined by the highest sum of correlation of both camera pairs. The measurement system was
simulated using 3DS MAX and Matlab software for reconstructing the surface of the object. The experimental result
proved that the trinocular vision system has good performance in depth measurement.
Rendering three-dimensional information of a scene from optical measurement is very important for a
wide variety of applications such as robot navigation, rapid prototyping, medical imaging, industrial
inspection, etc. In this paper, a new 3D measurement method based on mesh candidate with structured
light illuminating is proposed. The vision sensor consists of two CCD cameras and a DLP projector.
The measurement system combines the technology of binocular stereo vision and structured light, so as
to simplify the process of acquiring depth information using mesh candidates. The measurement
method is based on mesh candidates which represent the potential depth in the three dimensional scene.
First the mesh grid was created along the direction of axes in world coordinate system, and the nodes
were considered as depth candidates on the surface of object. Then each group of the mesh nodes
varying along z axis were mapped to the captured image planes of both cameras. At last, according to
the similarity measure of the corresponding pixel pairs, the depth of the object surface can be obtained.
The matching process is between the pixels in both camera planes corresponding to the spatial mesh
candidates. Aided by the structured light pattern, the accuracy of measurement system improved.
Appending the periodic sawtooth pattern on the scene by structured light made measurement easier,
while the computational cost did not increased since the projector had no need to be calibrated. The
3DS MAX and Matlab software were used to simulate measurement system and reconstruct the surface
of the object. After the positioned cameras have been calibrated using Matlab calibration toolbox, the
projector is used to project structured light pattern on the scene. Indicated by experimental results, the
mesh-candidate-based method is obviously superior in computation and accuracy. Compared with
traditional methods based on image matching, our method has several advantages: (1) the complex
feature extraction process is no longer needed; (2) the epipolar constraint is replaced by mesh
candidates so as to simplify stereo match process; (3) the candidate selection strategy makes
unnecessary the process of transformation from two dimensional coordinates to three dimensional
coordinates.
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.