Qiu Guan

Real-time three-dimensional surface measurement by color encoded light projection

Existing noncontact methods for surface measurement suffer from the disadvantages of poor reliability, low scanning speed, or high cost. The authors present a method for real-time three-dimensional data acquisition by a color-coded vision sensor composed of common components. The authors use a digital projector controlled by computer to generate desired color light patterns. The unique indexing of the light codes is a key problem and is solved in this study so that surface perception can be performed with only local pattern analysis of the neighbor color codes in a single image. Experimental examples and performance analysis are provided.

Adaptive immune algorithm for solving job-shop scheduling problem

Based on the information processing mechanism of immune system in biotic science, the process of the vaccination was analyzed. Then a new approach of immune algorithm problems for job-shop scheduling was proposed. This method can make self-adjustment of the immune responses along with the cultivation period of antibodies, and accelerate or suppress the generation of antibodies. Furthermore, it can gradually enhance recovery ability of the system, and find the optimal solution with more efficiency. Simulation results show that it is an effective approach.

Neural network based 3d model reconstruction with highly distorted stereoscopic sensors

In stereoscopic vision, there are two artificial eyes implemented so that it can obtain two separate views of the scene and simulate the binocular depth perception of human beings. Traditionally, camera calibration and 3D reconstruction of such a vision sensor are performed by geometrical solutions. However, the traditional camera model is very complicated since nonlinear factors in it and needs to approximate the light projection scheme by a number of parameters. It is even very difficult to model some highly distorted vision sensors, such as fish-eye lens. In order to simplify both the camera calibration and 3D reconstruction procedures, this work presents a method based on neural networks which is brought forward according to the characteristics of neural network and stereoscopic vision. The relation between spatial points and image points is established by training the network without the parameters of the cameras, such as focus, distortions besides the geometry of the system. The training set for our neural network consists of a variety of stereo-pair images and corresponding 3D world coordinates. Then the 3D reconstruction of a new s cene is simply using the trained network. Such a method is more similar to how humans eyes work. Simulations and real data are used to demonstrate and evaluate the procedure. We observe that the errors obtained our experimentation are accurate enough for most machine-vision applications.

A visual automatic incident detection method on freeway based on RBF and SOFM neural networks

This paper proposes a novel visual automatic incident detection method on freeway based on RBF and SOFM neural networks. Two stages are involved. First, get the freeway traffic flow model based on the RBF neural networks and use the model to obtain the output prediction. The residuals will be gotten from the comparison between the actual and prediction. Second, use a SOFM neural networks to classify the residuals to detect the incident. Because the SOFM has the character of topological ordering, the winning neurons running trajectory on SOFM neuron array corresponds to the actual traffic state on freeway. We can observe the trajectory to detect the incident and achieve the visual traffic incident detection.

An ART2/RBF hybrid neural networks research

The radial basis function (RBF) neural networks have been widely used for approximation and learning due to its structural simplicity. However, there exist two difficulties in using traditional RBF networks: How to select the optimal number of intermediate layer nodes and centers of these nodes? This paper proposes a novel ART2/RBF hybrid neural networks to solve the two problems. Using the ART2 neural networks to select the optimal number of intermediate layer nodes and centers of these nodes at the same time and further get the RBF network model. Comparing with the traditional RBF networks, the ART2/RBF networks have the optimal number of intermediate layer nodes , optimal centers of these nodes and less error.

Grid-pattern design for fast scene reconstruction by a 3D vision sensor

This paper presents a method of pattern design for a 3D vision sensor, which is based on the principles of color-encoded structured light, to improve the reconstruction efficiency. Since an ordinary structured light system using an LCD projector needs to take several images (usually 8-12 images) for recovering the 3D scene, as a result its speed is limited and applications are restricted in acquisition of static environment. For dynamic cases, the 3D measurement is desired to only capture a single image. To realize this, a new method is to use a color projector which can be controlled by a computer to generate arbitrary desired color patterns. A problem of the color encoded projection is the unique indexing of the light codes in the image. It is essential that each light grid be uniquely identified by incorporating the local neighborhoods in the light pattern so that 3D reconstruction can be performed with only local analysis of the single image. This paper proposes a method in design of such grid patterns. Experiments are provided to demonstrate the proposed method with two, three, and four different colors. The maximum possible square matrices are illustrated.

Easy calibration of a structured light vision system based on neural networks

The structured light vision system consists of a CCD camera and a digital projector. Calibration of such a vision system plays an important means of accurate 3D reconstruction of a scene. However, the projection model for both the camera and projector is very complicated because of distorted and nonlinear factors in it. It is unlikely to accurately model a camera with only a few parameters even considering some lens distortions. In order to simplify the system calibration and 3D reconstruction, this work presents a new calibration method that is based on neural network and brought forward according to the characteristics of neural network and vision measurement. The relation between spatial points and image points is established by training the network without the parameters of the camera and the projector, such as focus, distortions besides the geometry of the system. The training set for the neural network consists of a variety of lighting patterns and their projected images and the corresponding 3D world coordinates. Such a calibration method has two distinct advantages. It possesses the complicated nonlinear relation between two-dimensional information and three-dimensional information with the neural network, which can include various kinds of distortion and other nonlinear factors during the imaging period. Experiments are carried out to demonstrate and evaluate the procedure. From the result of training we can find out that through the neural network, it may avoid non-linear operation and obtaining the three-dimensional coordinates directly.