To solve the problem that the vehicle monitoring technology in the bus was not perfect and few emergencies detection method were invented, a real-time detection algorithm based on image processing was proposed to detect the emergency which mainly refers to the rapid flow of the crowd in the bus. First, the main motion area was grouped according to the trajectory of the passengers. Second, an improved moving foreground extraction method was used to extract moving foreground. Then the characteristic points in the moving foreground were extracted by Harris operator, and the optical flow constraint algorithm was used to establish the motion vector filed for characteristic points. At last, the KPA (Kinetic Potential Area) model was built to recognize the emergency. Theoretical analysis and experimental results show that, in testing the emergency under different environment, the proposed algorithm has a success rate of more than 83.9%. In addition, it has advantages of real-time detection in a practical application.
Distortion of H.264 video over 802.11e is jointly caused by transmission packet loss and encoder quantization, to tackle this issue, this paper proposed a distortion-driven cross-layer video transmission optimization. The relationship between Quantization Parameter (QP) and quantization distortion was obtained firstly by a rate-distortion model. Then according to the loss rate of video data partition, the transmission and total distortions at the receiver side were estimated. Based on the total distortion, a selection algorithm of optimal quantization parameter was presented. The experimental results show that, compared with the method of up-bottom cross-layer optimization with various queue priorities for video data partitions and bottom-up cross-layer optimization with an adaptive quantization parameter selection, the proposed method gets 1~2dB average Peak Signal-to-Noise Ratio (PSNR) improvement, and it has less distortion at the receiver side.
Concerning the problem of low robustness of general watermarking algorithms in resisting JPEG compression and geometric transform attacks, a zero-watermarking algorithm based on Cellular Automata (CA) and Singular Value Decomposition (SVD) was proposed. Firstly, an image was transformed by 2-dimensional cellular automata transform and the low-frequency subband approximation image were isolated, then the CA parameters was saved as key. After that, the approximation image was sub-blocked, and the blocks were decomposed by SVD, then the zero-watermark was constructed by CA rule in SVD matrix. In image authentication, the image could be certificated by comparing the similarity of two watermarks with the threshold value. The experimental result shows that this algorithm has good invisibility and perfect robustness in resisting JPEG compression and geometric transform attacks.
Owing to that different users focus on attributes of the same item is not exactly the same, individuals' weight distribution for goods attributes are not the same. A method of the generalized interval-valued trapezoidal fuzzy soft set was proposed to deal with this kind of recommendation problems. First, the concept of generalized interval-valued trapezoidal fuzzy soft set was established by combining the concepts of generalized interval-valued trapezoidal fuzzy set and soft set, some basic operations on a generalized interval-valued trapezoidal fuzzy soft set were defined, such as “and” operation, and “or” operation. Using these operations, as well as the center of gravity method of the generalized interval-valued trapezoidal fuzzy numbers, commodities could be ranked. A group preference model from the preferences of the group members could be constructed. Finally, this paper used the car recommendation as an example to introduce the group preference aggregation algorithm and this numerical example was given to illustrate the feasibility and effectiveness of the proposed method.