CN109815828A - Realize the system and method for initiative alarming or help-seeking behavior detection control - Google Patents
Realize the system and method for initiative alarming or help-seeking behavior detection control Download PDFInfo
- Publication number
- CN109815828A CN109815828A CN201811620890.0A CN201811620890A CN109815828A CN 109815828 A CN109815828 A CN 109815828A CN 201811620890 A CN201811620890 A CN 201811620890A CN 109815828 A CN109815828 A CN 109815828A
- Authority
- CN
- China
- Prior art keywords
- help
- module
- behavior
- detection control
- backstage
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Abstract
The present invention relates to a kind of system for realizing initiative alarming or help-seeking behavior detection control, including the predefined module of behavior, the simple action sought help for pre-defined alarm；Behavioral value module is connected with the predefined module of the behavior, for detecting the movement predetermined occurred in video image；Backstage cue module is connected with the behavioral value module, prompts for being issued according to the movement detected to backstage personnel, and provides scene video in real time so that backstage personnel's human assistance judges that the state of affairs is in progress.The invention further relates to a kind of methods for realizing initiative alarming or help-seeking behavior detection control.Using the system and method for realizing initiative alarming or help-seeking behavior detection control of the invention, the present invention can be compatible with various Face datections and behavioral value algorithm, process simple computation expense is small, and slightly upgrading to current all kinds of monitoring cameras can be realized the alarm/help function.We test several scenes, including subway, escalator, indoor passageway etc., and behavioral value accuracy reaches 95% or more.
Description
Technical field
The present invention relates to protection and monitor field more particularly to the field of video detection, in particular to a kind of reality of safety monitoring
Existing initiative alarming or the system and method for help-seeking behavior detection control.
Background technique
The all uses of current nearly all prior art regard for people (detected target) occurs for behavior, passively
Frequency determination method.There are common technological deficiencies for this kind of technology: the randomness of detected object makes detection complexity height
While detection accuracy it is lower.This set alarm method that we develop, is thus made to the detection of prespecified movement
It obtains detection algorithm difficulty to substantially reduce, detection accuracy also just greatly improves therewith.
The technical solution for simply in short summarizing us is exactly: alarm people does defined alarm against video camera or seeks help dynamic
Make, equipment detects this action notice correlation backstage personnel.
Summary of the invention
The purpose of the present invention is overcoming the above-mentioned prior art, provide it is a kind of it is high-efficient, accuracy rate is high, cost
The low system and method for realizing initiative alarming or help-seeking behavior detection control.
To achieve the goals above, the system and method that realization initiative alarming of the invention or help-seeking behavior detection control is such as
Under:
The realization initiative alarming or the system of help-seeking behavior detection control, are mainly characterized by, the system includes:
The predefined module of behavior, the simple action sought help for pre-defined alarm；
Behavioral value module is connected with the predefined module of the behavior, for detect occur in video image it is pre-
The movement first defined；
Backstage cue module is connected with the behavioral value module, for according to the movement that detects to backstage people
Member issues prompt, and provides scene video in real time so that backstage personnel's human assistance judges that the state of affairs is in progress.
Preferably, the behavioral value module includes:
Face datection and hand position detection unit are connected with the predefined module of the behavior and backstage cue module,
For being detected according to feature and Face datection algorithm；
Action behavior judging unit is connected with the predefined module of the behavior and backstage cue module, is used for basis
The face of involved party and the position of hand and hand face position retention time length judge whether to constitute prespecified alarm and seek help movement
Behavior.
Preferably, the feature includes face characteristic and the colour of skin.
Preferably, the Face datection algorithm includes the machine learning algorithms such as deep neural network.
Preferably, the face of the involved party and position include relative position and hand face relative position between two palms of the hand.
The method for realizing initiative alarming or help-seeking behavior detection control based on above system, is mainly characterized by, described
Method the following steps are included:
(1) simple action that the pre-defined alarm of the predefined module of behavior described in is sought help；
(2) movement predetermined whether occurred in the behavioral value module detection video image described in, if it is,
Continue step (3)；Otherwise, continue according to video images detection；
(3) the backstage cue module described in, which is issued according to the movement detected to backstage personnel, to be prompted, and provides field in real time
Scape video is so that backstage personnel's human assistance judges that the state of affairs is in progress.
Preferably, include the steps that Face datection in the step (2), specifically includes the following steps:
(2.1) it acquires image and is transformed into YCbCr color space；
(2.2) colour of skin similarity, thresholding skin color probability map are calculated；
(2.3) skin characteristic extraction and identification judgement are carried out.
Preferably, the skin characteristic in the step (2.3) extracts and identification judgement includes hand-characteristic and its and face
Portion's positional relationship and face feature and its with hand position relationship.
Using the system and method for realizing initiative alarming or help-seeking behavior detection control of the invention, the present invention can be compatible with
Various Face datections and behavioral value algorithm, process simple computation expense is small, slightly upgrades to current all kinds of monitoring cameras and is
Alarm/the help function can be achieved.We test several scenes, including subway, escalator, indoor passageway etc., behavior inspection
It surveys accuracy and reaches 95% or more.
Detailed description of the invention
Fig. 1 is the structure chart of the system for realizing initiative alarming or help-seeking behavior detection control of the invention.
Fig. 2 is the flow chart of the Face datection of the method for realizing initiative alarming or help-seeking behavior detection control of the invention.
Specific embodiment
It is further to carry out combined with specific embodiments below in order to more clearly describe technology contents of the invention
Description.
The realization initiative alarming of the invention or the system of help-seeking behavior detection control, wherein the system includes:
The predefined module of behavior, the simple action sought help for pre-defined alarm；
Behavioral value module is connected with the predefined module of the behavior, for detect occur in video image it is pre-
The movement first defined；
Backstage cue module is connected with the behavioral value module, for according to the movement that detects to backstage people
Member issues prompt, and provides scene video in real time so that backstage personnel's human assistance judges that the state of affairs is in progress.
As the preferred embodiment of the present invention, the behavioral value module includes:
Face datection and hand position detection unit are connected with the predefined module of the behavior and backstage cue module,
For being detected according to feature and Face datection algorithm；
Action behavior judging unit is connected with the predefined module of the behavior and backstage cue module, is used for basis
The face of involved party and the position of hand and hand face position retention time length judge whether to constitute prespecified alarm and seek help movement
Behavior.
As the preferred embodiment of the present invention, the feature includes face characteristic and the colour of skin.
As the preferred embodiment of the present invention, the Face datection algorithm includes the machine learning such as deep neural network
Algorithm.
As the preferred embodiment of the present invention, the face of the involved party and position include opposite position between two palms of the hand
It sets and hand face relative position.
The method for realizing initiative alarming or help-seeking behavior detection control based on above system, is mainly characterized by, described
Method the following steps are included:
(1) simple action that the pre-defined alarm of the predefined module of behavior described in is sought help；
(2) movement predetermined whether occurred in the behavioral value module detection video image described in, if it is,
Continue step (3)；Otherwise, continue according to video images detection；
(2.1) it acquires image and is transformed into YCbCr color space；
(2.2) colour of skin similarity, thresholding skin color probability map are calculated；
(2.3) skin characteristic extraction and identification judgement are carried out.
(3) the backstage cue module described in, which is issued according to the movement detected to backstage personnel, to be prompted, and provides field in real time
Scape video is so that backstage personnel's human assistance judges that the state of affairs is in progress.
Preferably, include the steps that Face datection in the step (2), specifically includes the following steps:
As the preferred embodiment of the present invention, the skin characteristic in the step (2.3) extracts and identification judgement packet
Include hand-characteristic and its with face location relationship and face feature and its with hand position relationship.
In a specific embodiment of the invention, in some public arenas, people often encounter some emergencies, than
As sudden cardiac sudden death disease, thief commit theft, finds that questionable person or the first idea of thing ... this when of people are to dial
Alarm call, but the mode and infeasible for alarm of sometimes making a phone call, the person of receiving a crime report also tends to that the state of affairs cannot be assessed in time can not
Take correct timely Disposal Measures.
In this set alarm/help-seeking behavior detection system that we develop, the alarm people/people that seeks help can advise against camera
Fixed movement, equipment backstage detect that alarm/help-seeking behavior that this is wanted can be issued to backstage personnel and prompt.
We this set detection method mainly include the detection that the setting of alarm/help-seeking behavior, video equipment act such
Three links such as identification, backstage prompt.
This detection system mainly includes preparatory behavior definition, behavioral value module and backstage cue module.
One, movement of alarming/seek help is defined
Type of action predetermined is to be simply advisable, for example we define one simply by experimental comparative analysis
Movement: involved party lifts towards camera, the both hands centre of the palm towards camera in parallel.
Two, behavioral value module
The major function of this module is to detect whether occur defined movement in video image.
We illustrate that specific detecting step is as follows for acting defined in first segment,
1, Face datection and hand position detection
There are many kinds of the methods of Face datection, using the detection of face characteristic, using the colour of skin detection ... in addition can use
More complicated and accurate Face datection algorithm (such as deep neural network machine learning algorithm).For the sake of for convenience of explanation,
We add the detection method of shape at this with the simple colour of skin.
A kind of fast method flow chart of Face datection is as shown in Figure 2.
2, alarm/help-seeking behavior judgement
The purpose of this step operation judges to be according to the face position of involved party, hand position and position retention time length
It is no to constitute prespecified alarm/help-seeking behavior.
It, both can Gao Zhun typically according to the relative position between two palms of the hand, hand face relative position, hand face position retention time
True rate judges whether to constitute a defined behavior act.
Three, backstage cue module
The function of this module is according to the alarm/help-seeking behavior detected to one prompt of backstage personnel sending, and in real time
It provides scene video and judges that the state of affairs is in progress for backstage personnel's human assistance.
The protection point of the technical program is: 1, alarm/help-seeking behavior movement definition type, including and is not limited to aforementioned
The action definition mentioned, i.e., under the video detection frame, it is intended to all behavior acts alarmed/sought help.2, the behavior is realized
The complete set of equipments of motion detection.
Using the system and method for realizing initiative alarming or help-seeking behavior detection control of the invention, the present invention can be compatible with
Various Face datections and behavioral value algorithm, process simple computation expense is small, slightly upgrades to current all kinds of monitoring cameras and is
Alarm/the help function can be achieved.We test several scenes, including subway, escalator, indoor passageway etc., behavior inspection
It surveys accuracy and reaches 95% or more.
In this description, the present invention is described with reference to its specific embodiment.But it is clear that can still make
Various modifications and alterations are without departing from the spirit and scope of the invention.Therefore, the description and the appended drawings should be considered as illustrative
And not restrictive.
Claims (8)
1. a kind of system for realizing initiative alarming or help-seeking behavior detection control, which is characterized in that the system includes:
The predefined module of behavior, the simple action sought help for pre-defined alarm；
Behavioral value module is connected with the predefined module of the behavior, for detect occur in video image it is preparatory fixed
The movement of justice；
Backstage cue module is connected with the behavioral value module, for being sent out according to the movement detected to backstage personnel
It prompts out, and provides scene video in real time so that backstage personnel's human assistance judges that the state of affairs is in progress.
2. the system according to claim 1 for realizing initiative alarming or help-seeking behavior detection control, which is characterized in that described
Behavioral value module include:
Face datection and hand position detection unit are connected with the predefined module of the behavior and backstage cue module, are used for
It is detected according to feature and Face datection algorithm；
Action behavior judging unit is connected with the predefined module of the behavior and backstage cue module, for according to behavior
The face of people and the position of hand and hand face position retention time length judge whether to constitute prespecified alarm and seek help action behavior.
3. the system according to claim 2 for realizing initiative alarming or help-seeking behavior detection control, which is characterized in that described
Feature include face characteristic and the colour of skin.
4. the system according to claim 2 for realizing initiative alarming or help-seeking behavior detection control, which is characterized in that described
Face datection algorithm include the machine learning algorithms such as deep neural network.
5. the system according to claim 2 for realizing initiative alarming or help-seeking behavior detection control, which is characterized in that described
Involved party face and position include relative position and hand face relative position between two palms of the hand.
6. a kind of method for realizing initiative alarming or help-seeking behavior detection control based on system described in claim 1, feature
Be, the method the following steps are included:
(1) simple action that the pre-defined alarm of the predefined module of behavior described in is sought help；
(2) movement predetermined whether occurred in the behavioral value module detection video image described in, if it is, continuing
Step (3)；Otherwise, continue according to video images detection；
(3) the backstage cue module described in, which is issued according to the movement detected to backstage personnel, to be prompted, and provides scene visual in real time
Frequency is so that backstage personnel's human assistance judges that the state of affairs is in progress.
7. the method according to claim 6 for realizing initiative alarming or help-seeking behavior detection control, which is characterized in that described
The step of (2) in include the steps that Face datection, specifically includes the following steps:
(2.1) it acquires image and is transformed into YCbCr color space；
(2.2) colour of skin similarity, thresholding skin color probability map are calculated；
(2.3) skin characteristic extraction and identification judgement are carried out.
8. the method according to claim 7 for realizing initiative alarming or help-seeking behavior detection control, which is characterized in that described
The step of (2.3) in skin characteristic extract and identification judgement include hand-characteristic and its with face location relationship and face feature
And its with hand position relationship.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811620890.0A CN109815828A (en) | 2018-12-28 | 2018-12-28 | Realize the system and method for initiative alarming or help-seeking behavior detection control |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811620890.0A CN109815828A (en) | 2018-12-28 | 2018-12-28 | Realize the system and method for initiative alarming or help-seeking behavior detection control |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109815828A true CN109815828A (en) | 2019-05-28 |
Family
ID=66602628
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811620890.0A Pending CN109815828A (en) | 2018-12-28 | 2018-12-28 | Realize the system and method for initiative alarming or help-seeking behavior detection control |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109815828A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110996052A (en) * | 2019-11-26 | 2020-04-10 | 绍兴天宏激光科技有限公司 | Emergency alarm method and system based on image recognition |
| CN111382723A (en) * | 2020-03-30 | 2020-07-07 | 北京云住养科技有限公司 | Method, device and system for identifying help |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101901339A (en) * | 2010-07-30 | 2010-12-01 | 华南理工大学 | Hand movement detecting method |
| CN207440970U (en) * | 2017-08-29 | 2018-06-01 | 来邦科技股份公司 | A kind of alarm terminal based on Mouth-Shape Recognition |
-
2018
- 2018-12-28 CN CN201811620890.0A patent/CN109815828A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101901339A (en) * | 2010-07-30 | 2010-12-01 | 华南理工大学 | Hand movement detecting method |
| CN207440970U (en) * | 2017-08-29 | 2018-06-01 | 来邦科技股份公司 | A kind of alarm terminal based on Mouth-Shape Recognition |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110996052A (en) * | 2019-11-26 | 2020-04-10 | 绍兴天宏激光科技有限公司 | Emergency alarm method and system based on image recognition |
| CN111382723A (en) * | 2020-03-30 | 2020-07-07 | 北京云住养科技有限公司 | Method, device and system for identifying help |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108734055B (en) | Abnormal person detection method, device and system | |
| KR101309366B1 (en) | System and Method for Monitoring Emergency Motion based Image | |
| US10419728B2 (en) | Monitoring system having personal information protection function and method thereof | |
| KR102260120B1 (en) | Apparatus for Performing Recognition of Activity Based on Deep Learning and Driving Method Thereof | |
| CN109993946A (en) | A kind of monitoring alarm method, camera, terminal, server and system | |
| KR20160074208A (en) | System and method for providing safety service using beacon signals | |
| US20110253486A1 (en) | Device and method for elevator monitoring | |
| EP2000998B1 (en) | Flame detecting method and device | |
| CN109815828A (en) | Realize the system and method for initiative alarming or help-seeking behavior detection control | |
| CN106448055B (en) | Monitoring alarm method and device | |
| CN111985428A (en) | Security detection method and device, electronic equipment and storage medium | |
| CN109858400A (en) | Database matching system is captured in recognition of face | |
| CN112364696A (en) | Method and system for improving family safety by using family monitoring video | |
| CN111908288A (en) | TensorFlow-based elevator safety system and method | |
| KR20220078893A (en) | Apparatus and method for recognizing behavior of human in video | |
| CN104392201A (en) | Human fall identification method based on omnidirectional visual sense | |
| CN111524318A (en) | Intelligent health condition monitoring method and system based on behavior recognition | |
| CN113420739B (en) | Intelligent emergency monitoring method and system based on neural network and readable storage medium | |
| CN113705357A (en) | Method, system, device and storage medium for identifying electric vehicle based on camera | |
| KR20200059628A (en) | Skeleton image learning based old people behavior pattern monitoring method | |
| Zhang et al. | Falling detection of lonely elderly people based on NAO humanoid robot | |
| CN112836689A (en) | Dangerous area personnel management and control system and method based on image recognition | |
| CN110334669A (en) | A kind of method and apparatus of morphological feature identification | |
| CN112307920A (en) | High-risk work-type operator behavior early warning device and method | |
| CN115412706B (en) | Monitor based on eyeball tracking and motion detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |