Near-drowning behavior detection method based on support vector machine

Abstract

The invention discloses a near-drowning behavior detection method based on a support vector machine. According to the invention, the support vector machine is used as a classifier for the learning of a machine; the support vector machine classifier is trained through an obtained video sequence sample of near-drowning behavior and normal swimming behavior by pre-simulation; then a video image sequence of a pool is acquired in real time through a camera arranged above the water; the monitored video image sequence is inputted into the trained support vector machine classifier to determine a behavioral state of a swimmer. Therefore, a near-drowner can be automatically detected through the camera in an actual public swimming place and lives can be timely saved at the maximum. The near-drowning behavior detection method based on the support vector machine has the advantages of accurate and reliable detection, good robustness, high noise immunity and good adaption to transformation of light. Besides, through monitoring by the camera arranged above the water, the near-drowning behavior detection method based on the support vector machine lowers costs for system implementation and has great value in engineering application.

Description

technical field [0001] The invention relates to the fields of computer vision technology and video surveillance, in particular to a method for detecting drowning behavior based on a support vector machine. Background technique [0002] Swimming pool is the basic construction facility of every city and the main place for people's leisure and entertainment. However, according to a data display, drowning death is the leading cause of accidental death among young people in my country. Many drowning incidents occur in public swimming places. Even if there are professional lifeguards supervising, but because the drowning person cannot be found in time, the death incident occurs. Therefore, it is of great practical significance to develop a system that can automatically detect and detect drowning events and find drowning people in time to save lives. [0003] Research on automatic detection of drowning behavior has been carried out in foreign countries as early as 20 years ago. ...

AI Technical Summary

Problems solved by technology

However, the system also has many disadvantages. For example, the system can only detect the drowning person who has already drowned in the late stage. At this time, the life of the drowning person is already in danger. Not only the maintenance cost is high, but also the accuracy of monitoring is easily disturbed by other objects

The applicant applied for an invention patent with the application number "201110448257.X" on December 28, 2011 and titled "Video-Based Early Drowning Behavior Action Detection Method", which discloses a drowning behavior using a hidden Markov model Detection method, but the pre-training and modeling process of this method is complicated, and the real-time performance is not good in the actual execution process. At the same time, the detection accuracy is not high, and the false detection rate is high.

Images