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

Police-calling and help-seeking processing method and apparatus based on speech recognition and face recognition

A technology of face recognition and speech recognition, which is applied in speech analysis, image data processing, character and pattern recognition, etc. It can solve problems such as follow-up and response, staff workload, and easy false positives and missed positives.

Inactive Publication Date: 2017-12-01
广州市迪士普音响科技有限公司
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The main purpose of the present invention is to provide a method and device for alarm and intercom processing based on voice recognition and face recognition, aiming to solve the problem that the existing manual operation method and device cannot timely follow up and respond to abnormal behaviors , and it is easy to produce false positives and negative negatives, which will cause a great burden and interference to the work of the staff in the control center, and cause a lot of technical problems such as waste of police resources

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
  • Police-calling and help-seeking processing method and apparatus based on speech recognition and face recognition
  • Police-calling and help-seeking processing method and apparatus based on speech recognition and face recognition
  • Police-calling and help-seeking processing method and apparatus based on speech recognition and face recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0062] It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0063] A mobile terminal implementing various embodiments of the present invention will now be described with reference to the accompanying drawings. In the following description, use of suffixes such as 'module', 'part' or 'unit' for denoting elements is only for facilitating description of the present invention and has no specific meaning by itself. Therefore, "module" and "component" may be mixedly used.

[0064] The alarm and help intercom processing method and device based on voice recognition and face recognition can be implemented in various forms. For example, the processing method and apparatus described in the present invention may include mobile terminals and fixed terminals. In the following, it is assumed that the terminal is a mobile terminal. However, those skilled in the art will understand that the...

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 invention discloses a police-calling and help-seeking processing method and apparatus based on speech recognition and face recognition. The method includes: converting an onsite video to a picture sequence, and obtaining an onsite audio data frame sequence; then obtaining a target area of the picture sequence, obtaining a face area through discrimination, obtaining a video characteristic vector of a target figure according to the position of the target figure obtained through discrimination, and extracting an audio characteristic vector of the audio data frame sequence; and respectively calculating a probability of an emergency situation corresponding to the video characteristic vector and a probability of the emergency situation corresponding to the audio characteristic vector to obtain a comprehensive probability P, and determining the emergency situation occurs and sending alarm information to a control center if the probability P is determined to be greater than a preset probability threshold. According to the method and apparatus, defects of low accuracy of face recognition and failure of discrimination of the non-login target figure are avoided, the emergency situations are determined with the combination of audio and video characteristics, and the accuracy and the robustness are improved.

Description

technical field [0001] The invention relates to the field of alarm and help processing, in particular to a method and device for alarm and help processing based on voice recognition and face recognition. Background technique [0002] With the development of social economy and rapid urbanization, the density of urban population is gradually increasing and the flow of population is accelerating, which in turn leads to a series of urban management problems such as urban transportation and social security. It is an important means to solve the social security problem to set up the intercom device for calling the police and asking for help in public places. However, the existing alarm intercom device is usually provided with an emergency button, and only through the button can the alarm and help information be sent to the management center in case of an emergency. But in some emergency occasions, it is impossible to send alarm and help information in time by using this button mo...

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
IPC IPC(8): G06K9/00G06T7/246G06T7/254G10L25/51
CPCG06T7/251G06T7/254G10L25/51H04M2242/04G06T2207/30201G06T2207/30241G06V40/164G06V40/172G06V20/41
Inventor 王齐祥郭嘉斌
Owner 广州市迪士普音响科技有限公司