Applied Mechanics and Materials Vols. 687-691

Paper Title Page

Abstract: This paper concerns the problem of frog and haze image enhancement. Images are often degreed due to the fog and haze condition. In this paper, an image enhancement method by using improved histogram equalization in HIS color space was put forward. Firstly, the image was transformed from RGB to HIS color space. Then the S and I components were treated with improved histogram equalization separately. When judging whether a gray level was to be merged with another, the weight coefficients with increased step were assigned to these low frequency gray levels according to their distance to the current gray level. Thus the excessive gray level merging was avoided. At the same time, a non-linear gray level mapping algorithm was proposed, which improved the contrast and brightness of the image. The experimental results show that our methods could keep the original colors and details of the image better, and they could improve the frog and haze image display effects significantly.
3671
Abstract: As far as the large-scale video surveillance sensor network in urban road and highway, the relay-surveillance on abnormal behavior or particular targets is one of the hot focuses of in recent researches, while the establishment of adjacency relationship of the neighbor sensor nodes is the basis of the sensor scheduling for the relay-surveillance. The topology of a road network is generated according to the road information, which has already existed in the geographic information systems (GIS) regarding the road intersections as nodes and the section between the two intersections as the edge. The initial topology of relay-adjacency relationship between sensors is built by that each video sensor is deployed at the each intersection and the section of the each two intersections is regarded as the basis of adjacency between the each two sensors. When a new video sensor is to be deployed in a section of a road, the related deployed sensors in same section are searched by using the spatial index of GIS based on its GPS information, and then the adjacency relationship between the new sensor and the related ones is generated by using the sorting algorithm according to their GPS information. By using the road network information that has already existed in the GIS system, the algorithm on establishing the relay-adjacency relationship of video sensors is simple and simpler to implement, and it can be used in the construction of sensor relay-surveillance topology such as automatic real-time tracking on abnormal behavior or the analysis of the escape routes and so on in city roads, highway, smarter cities and smarter planet.
3675
Abstract: Wireless sensor networks are widely deployed and thus are suffering increasing threats such as reactive bit jamming attacks. Such jamming can be alleviated by coded transmissions. This paper derives an optimal redundancy level required for Reed-Solomon code based transmissions and unveils the monotonic characteristic of coded transmission efficiency with respect to frame size, jamming strength, as well as communication protocol stack overhead.
3679
Abstract: In this passage is about the safety evaluation on the conveyance structure of small hydroelectric power station. Applying Binary comparative indicators to determine the weights and fuzzy recognition model on the conveyance structure of small hydroelectric power station’s assessment. Compared other models with fuzzy recognition model which will be explained in detail in the next section on a specific small hydropower station. The results show that the fuzzy recognition model is feasible and effective on safety evaluation on the conveyance structure of the hydroelectric power station.
3686
Abstract: For real-time monitoring the behavior of pigs in piggery, the method that combined the advantages of wavelet multi-scale analysis with invariant moments is proposed. Firstly, the original image is pre-processed by using ant colony algorithm to extract object contour. Then the target contour edge growth method and binary morphology are used, and the outlines of pigs are extracted by canny operator. Wavelet moment was used to get the global features of an image and increase the structural details of the image feature description. Finally, the neural network is applied to identify four behaviors including normal walking, walking down, looked up walking and lying of pigs. Experimental results show that the accuracy of the classification and identification of swine gesture reached more than 95%. This method has a better effect in the recognition of pigs and the noise resistance.
3691
Abstract: In order to segment the pig image accurately in the complex background, an image segmentation algorithm based on wavelet modulus maxima and edge growth is proposed. Firstly wavelet transformation to pig image was adopted to get local maximum value points in gray gradient, then local adaptive method was used to determine the segmentation threshold within local maximum points, and get the accurate edges. Secondly, the edge growth method based on gradient was used to link discontinuous edge points and complete the edges sealing repair. Finally, the mathematical morphology methods including connecting method and corrosion expansion operation were adopted to obtain the image area of a pig. The experimental results show that, in the complex background of piggery, the smooth and full pig image separated from background could be obtained by this algorithm. This method could improve the effectiveness of the image segmentation.
3695
Abstract: Aiming at the difference between satellite’s signal frequency spectrum and satellite signals under specific channel condition, larger fluctuation and ineffective threshold searching method by adopting traditional energy, the paper improved singular point’s performance detection of traditional wavelet transform, selected suitable searching threshold by ultimately combining with both advantages and promoted searching performance of satellite signals under specific channel condition. Based on preprocessed order-1 subspace tracing algorithm of space sign function and infinite norm normalization, the paper solved the problem of degenerating performance of regular order-1 subspace tracing algorithm under noise environment of a stationary distribution effectively.
3699
Abstract: A novel Bayesian compressive sensing (BCS) based method for multi-view radar automatic target recognition (RATR) is presented. The overcomplete dictionary is constructed by all the training sets. The sparse representation coefficient solved via BCS is used as feature vector, and recognition is implemented according to minimum construction error criterion. Performance evaluation was carried out using simulated vehicle target dataset. The results show that the proposed method can obtain promising performance and is robust to the effect of noise.
3704
Abstract: The Rayleigh approximation model is used for analyzing fog attenuation of the HAP-based communication system, the influence of transmitter elevation to fog attenuation under different temperature and liquid water density are studied, Numerical results show the optimum transmitter elevation angle in a ka-band HAP-based communication system under fog attenuation.
3709
Abstract: In this paper, we proposed a face gender recognition method based on local features and SVM. First, we divide the face image into five parts which are used to instead of the whole face for better recognition performance. Second, we use CS to extract local features of these five parts. Then, we respectively train five single SVM classifiers to achieve one to one feature recognition for local features. Finally, decision information fusion is used to achieve the final classification. Because SVM were successfully used to solve numerous pattern recognition problems and is mainly used to solve two-classification problem, selecting SVM to do gender recognition in our method has the obvious superiority. After a lot of experiments, results show that the proposed method in this paper is stable and effective, greatly improving the efficiency of face gender recognition.
3714

Showing 841 to 850 of 1182 Paper Titles