Advanced Materials Research Vols. 271-273

Abstract: To investigate whether both the sources of visual information tau cue and depth cue were utilized to guide braking, in the present study we used the virtual reality technology which could decouple the dilation rate of visual object and depth cue. Participants were instructed to park a car to an obstacle as closely as possible and avoid making collision. Results showed: (1) on the condition of same initial distance from car to an obstacle, participants tended to brake in advance on tau speed-up condition, which caused longer distance from braking to an obstacle than on control condition(tau and depth cue couple);While participants tended to postpone braking on tau speed-down condition, which caused the shorter distance from braking to an obstacle than on control condition; (2) On tau speed-up and tau speed-down condition, participants automatically fine-tuned the actual braking position to avoid making collision. These results suggested that both tau cue and depth cue were processed and utilized to direct the behavior of braking by our visual perceptual system.

Abstract: In order to overcome these deficiencies that computation of recognition algorithm based on template matching is very high and the recognition rate of recognition algorithms based on skin-color segmentation is low, and is vulnerable to the impact of background which is similar with skin-color, face recognition algrithom based on skin color segmentation and template matching is presented in this paper. According to the clustering properties that the skin-color of human faces have emerged in the YCbCr color space, the regions closing to facial skin color are separated from the image by using Gaussian mixture model in order to achieve the purpose of rapidly detecting the external face of human face. Adaptive template matching is used to overcome the affect of the backgrounds which are similar with skin color on face recognition. Computation in the matching process is reduced by using the second matching algorithm. Extraction of face images by using singular value features is used to identify faces and to reduce the dimensions of the eigenvalue matrix in the course of facial feature extraction. Experimental results show that proposed method can rapidly recongnise human faces, and improve the accuracy of face recognition.

Abstract: The purpose of this paper is to describe a processing system on multi-view registration minimizing error propagation for 3D geometry modelling.In the geometry modelling stage, the algorithm based on graph and metaview method is used . In order to enhance its robustness, a method for judging bad pairwise registration is proposed based on the computation of two views’ overlapping percentage. In order to enrich its completeness, combined the graph analysis with the metaview method is used to deal with the measurement data for local details. Results show that the processing system can provide 3D geometry model with low distortion successfully.

Abstract: Due to special characteristics of Carboform material, there are many difficulties to exam such material with traditional methods. Infrared thermal imaging technology shoots carboform to obtain infrared thermal images. With variation of time and temperature, the change principle of thermal performance difference of carboform in different temperature can be compared and analyzed. Effective data and reasonable fitting time can be extracted to fit for data with power exponential function. Then, imaging functions were utilized to perform gray change, median filter, fuzzy contrast enhancement, edge detection so as to output images on fitted data. Defects of specimen can be found. Example of some carboform sample based on infrared thermal wave verified feasibility of the proposed method.

Abstract: Aiming at the inadequacy of existing web map labeling system, this paper try to design a lightweight system which can be combined with different business rapidly, expect to improve the capacity of geographic information services and save the cost of software development.

Abstract: Nowadays, the idea of recognition based on image sets looms so large in real world applications. From the view of manifold learning, each image set has commonly been regarded as a manifold, and we formulate the problem of set recognition as manifold recognition (MR). Since it is impossible to directly compute the distance between nonlinear manifolds, constructing local linear subspaces is brought into our focus. Among methods offering of subspace matching, canonical correlations have recently drawn intensive attention. For the task of MR, we propose a method of Manifold Recognition Based On Discriminative-analysis of Canonical Correlations (MRDCC). The proposed method is evaluated on two datasets: Honda/UCSD face video database and ETH-80 object database. Comprehensive comparisons and results demonstrate the effectiveness of our method.

Abstract: With the rapid development of network technology, network-based humanoid robot technology will also be open to the development of gradual and orderly progress. This article is based on the C / S architecture, the server responsible for controlling the record of news and information network transit between paragraphs; through remote interaction, real-time client to complete the real humanoid robot control functions. Interoperability between the client, first to sign the server. Server information of all registered users to return to the client process, then the client users will be able to get online users to select the remote robot interaction. .When a user operation, the client program as a virtual robot through the virtual robot laboratory will be displayed in real-time robot control results.

Abstract: This article mainly introduces the face recognition technology in its development, the present situation and common applications, and also discusses the facing problems and solutions, finally it makes a brief outlook for the future of face recognition technology in development and application.

Abstract: According to the lack of Harris corner detection algorithm in corner detection, positioning, detection speed and anti-noise ,this paper improves Harris operator to make up for the bad stability of original operator, so as to realize accurate inspection, Strong anti-noise, fast, good stability and the exact match of image.

Abstract: Cloud is an important factor affect the quality of optical remote sensing image. How to automatically detect the cloud cover of an image, reduce of useless data transmission, make great significance of higher data rate usefulness. This paper represent a method based on Lansat5 data, which can automatically mark the location of clouds region in each image, and effective calculated for each cloud cover, remove useless remote sensing images.