Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2019-05-10 Cooperative journals: 《计算机应用研究》
Abstract： Aiming at the contradiction between improving the embedded quantity and enhancing the robustness in the information hiding algorithm, this paper proposed a multi-carrier information hiding algorithm. The algorithm used multiple facial expression images as vectors, and applied local binary pattern (LBP) texture features to recognize facial expression regions to embed encrypted information. Calculating the adjacent pixel difference matrix of the carrier region, and constructing the embedded space by shifting the histogram of the corresponding element of the difference matrix , in order to realize the reversible concealment of the encrypted information and the lossless recovery of the carrier images. Algorithm analysis proves that it has greater embedding capacity and maintains higher robustness than existing algorithms. Its largest embedded capacity reaches 0.561 at same time the peak signal to noise ratio (PSNR) is 38.421dB. And the value of embedded region PSNR in the paper. reaches 46.286. The robustness experiments show that the proposed algorithm may have a similarity greater than 99% to the original information image for the filtering attack. In the face of shear and translation attacks, the minimum image normalization coefficient (NC) is 0.743 and 0.728, which is much larger than other algorithms. From the comparison experimental results with other algorithms, the proposed algorithm is effective.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-10-11 Cooperative journals: 《计算机应用研究》
Abstract： In view of the different impacts of different traffic periods on traffic congestion and single factor fail to accurately characterize the traffic congestion state, this paper proposed a multi-index fuzzy comprehensive evaluation method for traffic congestion state evaluation. The method used the particle swarm optimization algorithm to optimize the support vector regression to predict the average road speed and traffic flow, obtained the predicted values of the average speed v, traffic flow density D, and road saturation S, and input the three factor indexes to Multi-index fuzzy comprehensive evaluation model that establish the set of factors and evaluation (level) for traffic congestion. It determined the weight coefficients of three factors under the morning peak and the evening peak and other periods by the entropy method, then determined the degree of membership of each index in each period by the trapezoidal membership function. Finally, it divided爐he traffic congestion state into six levels. The results of predictive evaluation at the traffic data of the I405 highway in PeMS show that the traffic congestion state evaluated by the proposed method is basically consistent with the actual state and has a high prediction accuracy, the correct rate can reach 94.79%.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-09-12 Cooperative journals: 《计算机应用研究》
Abstract： Aiming at the problems of that the detecting module scans a large number of sub windows, which result the detection time is too long , and when the target has severious occlusion and deformation during the tracking process, the traditional tracking learning detection (TLD) target tracking algorithm will fail to track, so this paper propose the improved TLD target tracking algorithm. Before the detection module, it added the ViBe model to estimate the foreground target, which greatly reduces the detection area. The tracking module uses the Sift feature matching algorithm to replace the optical flow method in the original algorithm, accurately tracking the target to avoid the tracking drift, reducing the complexity of the calculation and improving the ability of the algorithm to adapt to the environment. The experiment results show that the improved TLD algorithm can improve the running speed, and the tracking accuracy can also be improved when the target is seriously occluded and the light intensity changes dramatically.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-08-13 Cooperative journals: 《计算机应用研究》
Abstract： Aiming at inferior anti-analysis of current information hiding algorithm, this paper proposed a zero-low-frequency information hiding algorithm based on local BRISK feature. . First, it carried out first-order CL multi-wavelet transform for carrier image. then extracted BRISK feature points in the low-frequency LL2 to generate an image feature matrix; Second, Using zig-zag scrambling and logistic chaos scrambling for the secret image to decorrelate; Again, associated the image feature with the encrypted information to form an association sequence by comparing feature values; Last, it would embed association sequence into lower three bits of high-frequency HL2 and HH2. The association information constructed by eigenmatrix of high energy region and encrypted information of two times was hidden in the high frequency region, which was beneficial to the robustness and anti-analysis of algorithm. Under the analysis of high-order statistics on 200 pictures, the maximum detection rate was less than 7.516%, which indicates that the proposed algorithm has good anti-analysis ability.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-05-20 Cooperative journals: 《计算机应用研究》
Abstract： With the rapid development of urban traffic, traffic congestion and traffic accidents occur frequently, urban traffic induction is an important part of intelligent transportation system, and its production and development without delay. Variable information board (VMS) is an important tool for traffic information transmission in traffic guidance system. For the intelligent traffic guidance system in the domestic application of immature, the improved genetic algorithm was used to optimize the location of VMS in the road network, and the coding method and selection method in the basic genetic algorithm were improved. At the same time, the dynamic decay mutation probability was used to perform the mutation operation, the multi-objective optimization was used to singulate the multi-objective function, and introduced the attenuation influence factor for the different degree of VMS on the downstream of the road segment. Then, the VMS layout simulation test was carried out with the complex virtual road network as the simulation example. It is shown that the method uses VMS utility and economic cost as the evaluation index, it can achieve the optimal distribution of VMS site in the traffic network and the purpose of saving resources, which has certain scientificity and practicability.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-04-12 Cooperative journals: 《计算机应用研究》
Abstract： For the secure transmission of confidential information, this proposed an information hiding algorithm. Using chaos scrambling transform and run-length code compression simultaneously in the secret information preprocessing, in order to improve the embedding capacity and robustness of the stego. In order to achieve the lossless hiding and improve the capacity, it used the histogram-shift technology and the AMBTC (Absolute Moment Block Truncating Coding) to hide the preprocessed secret information in high and low mean value sequence, and the capacity was larger than that of the algorithm which is only based on the AMBTC. The experimental results show that the extracted secret information can be highly identified even after some attacks, and the normalization coefficient is always lager than 0.6, which proves the advantages of the proposed algorithm in terms of robustness and hiding efficiency. Therefore, the method of information hiding in this paper achieves the goal of secure transmission of secret information and has good anti-aggression.
Hits
Hits
Downloads
Comment