Unlock instant, AI-driven research and patent intelligence for your innovation.

Violence video detection method based on mosift and csd features

A video detection and video technology, applied in the field of violent video detection algorithm, can solve the problem of different color space distribution

Active Publication Date: 2019-01-25
SHANGHAI JIAOTONG UNIV +1
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For example, a window with a size of 8×8 pixels slides on the entire image and counts the color types that appear in the window. The CSD feature is extracted in the HMMD (Hue, Min, Max, Difference) color space. The main advantage is that it can distinguish the color histogram Pairs of images that are similar but have relatively different color space distributions

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Violence video detection method based on mosift and csd features
  • Violence video detection method based on mosift and csd features
  • Violence video detection method based on mosift and csd features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0070] The present invention will be described in detail below in conjunction with specific embodiments. The following examples will help those skilled in the art to further understand the present invention, but do not limit the present invention in any form. It should be noted that those skilled in the art can make several modifications and improvements without departing from the concept of the present invention. These all belong to the protection scope of the present invention.

[0071] Specifically, such as figure 1 Shown, according to the detection method of the violent terrorism video based on MoSIFT and CSD feature provided by the present invention, comprise the steps:

[0072] Step 1: Extract the MoSIFT features of the test video and the training video respectively;

[0073] Step 2: Reduce the number and dimension of the training video after extracting MoSIFT features;

[0074] Step 3: Cluster the MoSIFT features of the training video after the number and dimension ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The present invention provides a kind of violent terrorism video detection method based on MoSIFT and CSD feature, comprise step 1: calculate the CSD of video; Step 2: carry out the calculation of maximum dynamic density point to CSD feature; Step 3: calculate the score of CSD; Step 4: Calculate the MoSIFT of the video; Step 5: Perform vertical dimensionality reduction on MoSIFT features; Step 6: Perform horizontal dimensionality reduction on videos; Step 7: Cluster MoSIFT features; Step 8: Train SVM-1; Step 9: Calculate MoSIFT score; step 10: train SVM‑2; step 11: get classification results. The present invention better utilizes the features of video MoSIFT and CSD, reduces the complexity of the algorithm, and has better detection effect.

Description

technical field [0001] The present invention relates to a violent terrorism video detection algorithm, in particular to a violent terrorism video detection algorithm based on MoSIFT and CSD features. Background technique [0002] With the continuous development of the Internet, all kinds of video content disseminated through the Internet have become vast, and there are many violent and horror videos among them. Such videos are likely to have a bad psychological impact on minors. Therefore, it is necessary to classify and control videos on the Internet. The traditional method is to manually detect and review a large number of videos. The horror video detection method is very meaningful. [0003] There are many ways to detect violent and terrorist videos. Generally, audio signals and visual signals are used to identify abnormal sound information such as screams and explosions through audio signals, and images such as blood, darkness, and fighting are identified through visual...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06K9/46G06K9/62
CPCG06V20/44G06V20/40G06V20/46G06V10/462G06F18/2411
Inventor 蒋兴浩孙锬锋倪俊郑辉王丹阳
Owner SHANGHAI JIAOTONG UNIV