Learn More
Comparing with the research of pornographic content filtering on Web, Web horror content filtering, especially horror video scene recognition is still on the stage of exploration. Most existing methods identify horror scene only from independent frames, ignoring the context cues among frames in a video scene. In this paper, we propose a Multi-view(More)
Crowd density estimation, is much valuable in intelligent crowd monitoring. The traditional approach based on static texture analysis of single frame, is not adept to complex background, and the rule based statistic approaches are short of robustness for background noise. In this paper, a crowd density estimation approach fusing statistic features and(More)
Recently, crowd estimation techniques in real-time are more popular research field using computer vision. here understand the behavior of the system using Linear Quadratic Estimation or kalman filter with new proposed index parameter which will help to understand the accuracy of the system still no more parameter discover to judge the accuracy of the system(More)
Along with the ever-growing Web, horror video sharing through the Internet has affected our children's psychological health. Most of current horror video filtering researches pay more attention to the extraction of global features or selection of an optimal classifier, while neglecting the underlying contexts in a scene. In this paper, a novel(More)
The mine surveillance system can record the information of the production field timely and accurately. In order to reduce the production cost, the resolution of the system is lower. High resolution image can provide more information. In addition, surveillance images contain a lot of noise because of the poor quality of air and inadequate lighting. This(More)
—Measuring particle size distribution through calculating light scattering intensity is a typical inverse problem. This paper builds an inverse mathematical model based on Mie scattering, deduces the inversion formulas for particle size, and calculates the relative coefficients through programming with built-in functions in MATLAB. In order to improve the(More)
To improve the clearness of images captured in the low illumination environment, a new enhancement algorithm was presented based on the popular histogram equalization method. It can transform the histogram to the ordered shape to highlight the contrast of selected interest gray level and fit for the human visual. The experiment has shown that the new(More)
Drilling grouting repair technology is an important direction of development in landfill liner leakage detection and repair, the difficulty and keystone of this technology is that how to detect the gravel layer, in order to avoid damaging the HDPE membrane. According to the different responses of the vibration signal in the different media of landfill site,(More)
The paper proposed a clustering method of decade observation data based on k-means algorithm, which adjusted the weight influence to similarity function by the missing values handling and scaling of range fields. This paper discussed the way to select initial cluster centers and the process of calculating cluster centers and assigning records to clusters.(More)
  • 1