Applied Mechanics and Materials Vols. 58-60

Abstract: In this contribution are presented designs of intelligent camera systems at the intelligent manufacturing-assembly cell. Intelligent manufacturing-assembly cell is situated at the Institute of production systems and applied mechanics. For this intelligent cell was designed intelligent camera system with industrial camera. All design alternatives of check station with camera system go out knowledge of intelligent systems. Intelligent systems as systems of new generation are loading gradually at mechanical production, when they remove person from production process and they shorten production times. Intelligent systems are situated to day at all production processes of large industrial companies.

Abstract: This paper proposes a new method for measuring vehicle geometric parameters, which is based on image processing. In the method, a black and white bar-cord ruler is applied to calculate the vehicle dimensions. Canny edge detection algorithm and image mosaic algorithm based on Image-Based Rendering (IBR) technique are utilized to deal with the target images. According to the relationship between the vehicle and the bar-cord ruler in the target images, the geometric parameters of the vehicle can be measured. Furthermore, the experiments indicate that the method has a good performance in measuring the dimensions of a vehicle.

Abstract: Considering noise and low contrast of infrared image，an efficient nonlinear adaptive enhancement algorithm，which is based on differential evolution (DE)algorithm and stationary wavelet transform (SWT)，is proposed. Evaluation function is constructed by combing information entropy，signal-noise-ratio with standard deviation of enhanced image. A nonlinear transformation function is designed to enhance the contrast of the infrared image. The optimal transformation parameters are determined by combing DE algorithm with the constructed evaluation function. The proposed algorithm can efficiently enhance the contrast of the infrared image while have a good robust to noise. Experimental results show that the proposed algorithm is better than multi-scale nonlinear enhancement algorithm，stationary wavelet nonlinear enhancement algorithm and histogram equalization algorithm in overall performance.

Abstract: A new generation of integrated business systems of a state-owned bank will centralize all the data from all the branchs banks to the head office bank ,the head office bank is the data collection center, it takes responsible for all the banks, such as business data storage and processing, management (Security Authentication, Security Management, Bank System Management), Access Gateway (People's Bank of China, the center of Gold Card, SWIFT, etc.).The Enterprise Channel Transaction Integration Platform(ECTIP) is the key system to realize this function. This article focuses on the DES data encryption technology in this system. Including the introduction of channel integration platform ECTIP, DES data encryption algorithm, and the use of DES encryption algorithm in this system.

Abstract: In order to solve problem that the image which is under different wavelength channels can’t match in the ice detection whit the near infrared, this paper describes a solution of image matching which based on the chain code of angle related to a tangential direction of image edge. By extracting the edge with Canny, calculating the chain code of angle and differences, computing the relative chain code of direction angle and comparing the relative chain code, the possible rotation angle between the images will be gained. After rotating the image and differencing the corresponding coordinates, the shift amount can be obtained. Ultimately image match can be achieved. Experimental results show that this method is accuracy and have certain inhibition of noise.

Abstract: A method of abnormal motion detection for intelligent video surveillance is presented, which includes object intrusion detection, object overlong stay detection and object overpopulation detection. Background subtraction algorithm is used to detect moving objects in video streams. Kalman filter is applied for object tracking. By the construction of relation matrix, the tracking process is divided into five statuses for prediction and estimation, which are object disappearing, object separating, new object appearing, object sheltering and object matching. The object parameters and predictive information in the next frame which is used to track moving objects is established by Kalman filter. Then, three types of abnormal motion detection are implemented. The relative position of alarm area or guard line with the rectangle boxes of the moving objects is used to detect whether the object is invading. The existing time of the moving objects in monitor area is counted to detect whether the object is staying too long. Moving objects in the monitor area are classified and counted to detect whether the objects are too much. Alarm will be triggered when abnormal motion detection as defined is detected in the monitor area.

Abstract: The outage probability performance is analyzed for the optimization of incremental selection decode-amplify-forward (ISDF) multi-node MIMO cooperative communication systems. Firstly, the system model for the proposed multi-node MIMO cooperative protocol. Then, the incremental selection decode-amplify-forward and optimal relay selection strategy (routing) based on the opportunistic relaying scheme is proposed. The mutual information and outage probability between source and destination nodes for the proposed scheme are formulated with the relays have the capability of maximum ratio combining (MRC) receiving and beam-forming transmitting capabilities. Finally, adaptive strategy is proposed for adaptive optimal power allocation (APA). Theoretical analysis and simulation results show that the proposed APA outperforms traditional equal power allocation (EPA) in outage performance.

Abstract: Geographic Information System (GIS) database is built by ArcGIS software based on observation data in Lanzhou city. GIS data set was analyzed, including testing data distribution, the trend analysis of spatial data, data outlier analysis. According to the analysis results, the appropriate spatial analysis model is chosen to simulate and predict thermal field. Cross validation method is used to verify simulation accuracy and validity of model. Simulation map of urban thermal in is output by optimal model and parameters eventually. Results show that urban thermal field presents regular distribution in summer. The spatial distribution characteristics of thermal field have directly relations with land use type, urban energy consumption, population density, building volume rate, and thermodynamic properties of underlying surface.

Abstract: A precise, fast, and fully automatic calibration method is proposed to address the shortcomings in currently used large-scale interactive camera-projector systems. These shortcomings include a small number of calibration points used in manual calibration, large errors, huge time consumption, and lack of professional quality operations. The proposed method applies mechanical wavelength switching in the projected image to capture multi-regional vertices. The co-linearity of each point in the projected images is calculated to determine the actual location of the interactive points in the projected image. The point-by-point computation adopted in the method promotes the automatic elimination of uncorrectable systematic errors in large-scale optical devices. The automatic error elimination not only increases the accuracy of the interactive system and reduces the complexity of system installation, but also increases the flexibility of the interactive system.

Abstract: This paper proposed five new types of facial features for face recognition. Ada-boost is used to detect face firstly. False detected faces are removed by dynamic background modeling and skin color detection. Skewed face is also calibrated to achieve higher accuracy. Based on Active Shape Modeling, the five new types of facial features including gradient histograms of facial components, vertical/horizontal projection of facial edge points, signature of facial components, multiple vertical/horizontal line segments within facial shape, and face template could be extracted. According to the classification capability, features are associated with different weights while during matching. Nearest neighbor classifier is deployed for face recognition by using the averaged of feature points of a person as the center. The size of database is 200 people which are selected from the face databases of MIT and ESSEX. Five images per person were used for training and 491 images were tested. The recognition rate was 98.3% and the processing speed reached 220ms per frame on a general personal computer.