Applied Mechanics and Materials Vols. 321-324

Abstract: Although Geographic information system has just developed for decades, the course of its development is very rapid. The application and services of GIS technology have almost extended all the fields related to spatial information. Map, as the basis of GIS, its important position is self-evident. Map symbol is the language of the GIS map, which is the expression of the map content, the main medium of spatial-data information transferring, and an important feature differs from other images referring to the geographical environment. The function of Dynamic electronic map based on modern visualization tools, is far more superior to the traditional static map. Its expression is more rich and vivid, and introduces interactive operation into loading images, which enhanced the initiative and adaptability. The dynamic symbol is the basis of powerful visualization capabilities of dynamic map. With the support of the dynamic symbol, dynamic map is even more vivid and detailed. This paper is mainly about design method of dynamic map symbols based on rich Internet applications (Rich Internet Applications, abbreviation RIA). Take Flex as the case,which focus on the animation effect in Flex and achieves the dynamical substitution of point symbols on the map published by ArcGIS Server with ArcGIS API for Flex. Furthermore, look forward to the combined applications with web service.

Abstract: Depth video has attracted great attention recently with the trend of MVD (Multiview plus depth) being the main 3D representation format. In order to improve depth video coding efficiency, we propose a novel depth video coding algorithm based on static region skipping. Firstly, based on the corresponding color video, depth video is segmented into two regions: motion regions and static regions. The blocks in static regions are skipped without encoding. The skipped blocks are predicted from the neighboring depth images. Experimental results show that the proposed algorithm not only saves the bitrate up to 56.83% but also improves virtual view quality and saves the encoding time.

Abstract: This paper mainly researches on the TI company fixed-point digital signal processor TMS320DM642 video capture technology for CMOS image sensors, sensor interface and video mini-driver carried out a detailed analysis, established different levels of peripheral structures under different CMOS Sensor, the research in this field has flexible characteristics and high practical value.

Abstract: Vehicle detection is very important for Advanced Driver Assistance System. This paper focused on improving the performance of vehicle detection system with single camera and proposed a multi-feature fusion method for forward vehicle detection. The shadow and edges of the vehicle are the most important features, so they can be utilized to detect vehicle at daytime. The shadow and edge features were segmented accurately by using histogram analysis method and adaptive dual-threshold method respectively. The initial candidates were generated by combining edge and shadow features, and these initial candidates were further verified using an integrated feature based on the fusion of symmetry, texture and shape matching degree features. The weight of each feature was determined by the Fisher criterion, and the non-vehicle initial candidates were rejected by a threshold. The experimental results show that the proposed method could be adapt to different illumination circumstances robustly and improve the accuracy of forward vehicle detection.

Abstract: Distributed video coding (DVC) is a novel video coding paradigm. One approach to DVC is Wyner-Ziv distributed video coding. Quantization step (QS) is one of the most important factors deciding encoder’s coding efficiency. In this paper, an edge classification based Discrete Cosine Transform (DCT) coefficients reorganization method was proposed. The block was first classified into horizontal-edge block, vertical-edge block and other block. Then different scanning order was applied to each class of blocks. In this way, larger coefficients might be grouped together and QS for Alternating Current (AC) coefficients might be reduced. Experimental results show that compared with DISCOVER’s method, the proposed method makes PSNR of reconstructed image increase about 0.5dB at high bit rate.

Abstract: In view of randomness and fuzziness of digital image semantics, a new semantic representation of digital image based on cloud model is proposed and a semantic vector space is constructed. In the space, semantic classifications of digital images are completed by calculating the semantic class certainty degree (SCCD). In addition, we propose cloud support vector machine based on image semantics (CSVM-IS) model, which can effectively utilize the knowledge of SCCD. This method can effectively classify the multi-semantic information and eliminate the rejection of the classification samples. Experimental results show that CSVM-IS is superior to the Nesting Algorithm in terms of classification performance.

Abstract: In the field of detecting for defects of railroad track surface, computer vision method for detection has been widely used. An online real-time image processing system for defects of railroad track surface is introduced in the paper. Results show that: if the number of pixels in each railroad track surface image is 512×240, the train speed can be 50 Km/h while the image processing system can real-time detect the railway track surface defects, the number of pixels in in each railroad track surface image is 320×250, the train speed can be 100 Km/h while the image processing system can real-time detect the railway track surface defects.

Abstract: In this paper, we analyze the object tracking task of mean-shift algorithm. A spatial-color and similarity based mean-shift tracking algorithm is proposed. The spatial-color feature is used to replace the color histogram, and an enhanced algorithm is derived by adopting a new similarity measure. We also introduce Lucas-Kanade algorithm to design a template update strategy, propose a template update algorithm for mean-shift. Experimental results show that these two improved mean-shift tracking algorithms have high tracking accuracy and good robustness to the change of appearance of the object.

Abstract: In this paper we propose a powerful visual event pattern learning method to address the issue of high-level video understanding. We first model the deformable temporal structure of the action event in videos by a temporal composition of several primitive motions. Moreover, we describe each action class by multiple temporal models to deal with the significant intra-class variability. We implement a multiple instance learning method to train the models in the weakly supervised setting. We have conducted experiments on three major benchmarks. The results are comparative to the state-of-the-arts.

Abstract: A reconstruction program of slice image based on SolidRocket Motor (SRM) skiagrams is put forward to overcome the deficiency of artificial radiographic interpretation. The algebraic reconstruction algorithmbased on compressed sensing technology is designed. The influence of radiographic interval angle and skiagram sizes on reconstructed slice image is studied. Radiographic interval angle has a great impact on the quality of the reconstructed image. Slender defects are not sensitive to changes in the length of the skiagram, but circular defects are sensitive to changes in the length of the skiagram. The reconstruction tests of model SRM skiagrams show that the sizes and locations of the debonded defects can be easily ascertained and the efficiency of radiographic interpretation can be greatly improved.