Search

The typical Mean Shift tracking algorithm was introduced and an improved Mean Shift algorithm based on probability distribution was presented. This algorithm uses color information and motion information to express target model. Compared with typical Mean Shift algorithm's, target expression and operation process are more simple and it is easy to integrate different target characteristics, which enhances tracking performance. Finally, tracking strategies were made aiming at problems of multi-objects and target lost.

With the development of ship industry, pipeline system has been more and more widely used. However, the pipeline site space is narrow. Mechanical and electrical equipments are of all kinds. The pipeline cable is densely distributed. All problems mentioned above seriously affects the pipeline construction. In order to solve the problem of pipeline docking, the method of making model and comprehensive lofting is usually adopted. However, this method is technically backward. The operation is inconvenient due to the narrow onsite space. The required period is long. With low information utilization and accuracy, the method of making model and comprehensive lofting has a great influence on the development cycle and design quality. In order to solve these problems, this paper presents a design method and system of flange pipe docking. A binocular camera is used to obtain the image of the pipe joint. The center position of the flange surface and array holes on the flange surface are extracted from the image, which is bias of subsequent work. First, the path of the intermediate connecting pipe is calculated. Then, according to the pipe standards of intermediate connection pipe and production specification of enterprise, the model of intermediate connecting pipe is automatically generated by using secondary development technology of CAD. In this paper, the binocular vision technology is combined with pipeline docking design, which significantly improves the utilization rate of field space information and design efficiency, and solves the problems of inconvenient operation and safety risk of traditional profiling method.

This paper presents a method for extracting and recognizing the billet numbers according to the feature of each number. Its advantages lie in that no template image is required, the requirement to the number in the image is low, and the anti-interference performance is strong. This method is able to recognize the numbers on the billet with a high efficiency

Recently, it is still difficult to extract interested object from complex background. In this field, interactive image segmentation method has attracted much attention in the vision. In this paper, we propose a new algorithm to segment the interested object from complex background. In the algorithm, we use the improved K-means clustering in the LUV color space to get more accurate classifications of the labeled pixels. Then, build up energy function model and calculate the energy of segmentation properly. Finally, we get the perfect result through graph cuts and denoising algorithm based on connected components.

In order to study the seismic performance of steel frame with semi-rigid connections. Steel frames finite element model of engineering design was found using ANSYS finite element analysis software. Simulate to dynamic responses of steel frame with semi-rigid connections under seismic load. Numerical results show that seismic performance of steel frame with semi-rigid connections is well, and increase the ductility of steel frame, increase the natural periods of the lower modes, decrease the integral rigidity of steel frame, raise the structure lateral displacement within a certain range, reduce the column base shear.

An automatic recognition method for steel billet images with different orientations is proposed in this paper. A crucial part of this method is to segment the image firstly, and then use the projection features of the segmented image to distinguish the different orientations of the steel billet in production line. After the string is segmented into individual characters, the segmented characters can be recognized by template matching. Experiments on steel billet image recognition demonstrate that the proposed method can distinguish the steel billet image orientation and recognize the characters automatically, which shows the effectiveness of the proposed method.

Since the threshold segmentation methods can't divide the interested objects from intricate background perfectly, in this paper, we proposed a new method that combined graph theory with optimal threshold method. With this method we have made a good integration of the two methods above to ensure that the segment results have smooth boundary and complete regions. Through a lot of experiments, we can draw the conclusion that the proposed method can extract the objects from intricate background perfectly and meet the need of applications.