Method for acquiring action classification by combining with spacing restriction information

Abstract

The invention discloses a method for acquiring an action category by combining space constraint information, relates to the automatic monitoring field, and solves the problem of long training time and low classification precision of the existing methods for acquiring the action categories. The method comprises the following steps: reading video, tracking a target in a target profile section by snake and a particle filter, and accurately framing the target section with a rectangular frame in each frame; acquiring a target curve and a fitting function according to the width and height of the target section of each frame, and acquiring a prior probability of a current action a which is classified as a k category action by classifying support vector machines of an extracted characteristic value, dividing the video into m sections, and acquiring the coverage probabilities of all the frames in the video that a section I is trained by a k category action training set, and the probability sum of all the categories of actions in the section i; and acquiring the category number to which the current action a belongs according to the proportion of the times that the current action a covers the section i in all the times that all the video sections are covered.

Description

technical field [0001] The invention relates to the field of automatic monitoring, in particular to a method for obtaining action classification in combination with space constraint information. Background technique [0002] Abnormal behavior detection of family members is a hot research field in recent years, especially for the care of the elderly, children and disabled people with disabilities. However, most of the current smart home monitoring systems are based on sensor networks and wireless communication devices, which are expensive and not suitable for general household use. Therefore, computer vision-based smart home monitoring technology has attracted widespread attention in recent years. However, the current methods of this type of technology are very limited, most of which are based on the detection of specific rules and specific abnormal behaviors, and their poor generalization ability makes them difficult to promote. The current methods for obtaining action clas...

AI Technical Summary

Problems solved by technology

[0003] In order to solve the problems of too long training time and low classification accuracy of the current method of obtaining action classification, a method of obtaining action categories combined with spatial constraint information is proposed.

Images