CN114821961B - Indoor children missing prevention method, electronic equipment and storage medium - Google Patents
Indoor children missing prevention method, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN114821961B CN114821961B CN202210737854.2A CN202210737854A CN114821961B CN 114821961 B CN114821961 B CN 114821961B CN 202210737854 A CN202210737854 A CN 202210737854A CN 114821961 B CN114821961 B CN 114821961B
- Authority
- CN
- China
- Prior art keywords
- child
- children
- fellow
- persons
- monitoring range
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/0202—Child monitoring systems using a transmitter-receiver system carried by the parent and the child
- G08B21/0233—System arrangements with pre-alarms, e.g. when a first distance is exceeded
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/0202—Child monitoring systems using a transmitter-receiver system carried by the parent and the child
- G08B21/0205—Specific application combined with child monitoring using a transmitter-receiver system
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
Landscapes
- Health & Medical Sciences (AREA)
- Child & Adolescent Psychology (AREA)
- General Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Image Analysis (AREA)
- Alarm Systems (AREA)
Abstract
The embodiment of the application relates to the technical field of video monitoring, and discloses an indoor children missing prevention method, electronic equipment and a storage medium. The method comprises the steps of acquiring the current position of a child and the current position of a fellow person in a target area in real time based on a monitoring video of the target area; the fellow passenger is an adult who has close action with the child when entering the target area; determining a monitoring range containing the positions of the children and the fellow staff in real time according to the current position of the children and the current position of the fellow staff, performing behavior analysis on at least one of the children, the fellow staff and other staff in the monitoring range, and acquiring an analysis result of whether dangerous behaviors aiming at the children exist or not; the other persons are adults, except the fellow persons, in the monitoring range, and the stay time of the adults exceeds a preset first time threshold; and when the children are determined to have the loss risk according to the analysis result, generating corresponding early warning information based on the loss risk grade indicated by the analysis result so as to effectively prevent the children from being lost.
Description
Technical Field
The embodiment of the application relates to the technical field of video monitoring, in particular to an indoor children missing prevention method, electronic equipment and a storage medium.
Background
In indoor public places such as large shopping malls, railway stations or tourist attractions, the condition that children are lost is easy to occur due to a plurality of factors such as large area, dense population, complex terrain and the like.
The method for preventing children from getting lost commonly adopted at present is to wear a positioning device for children, the positioning device performs real-time information interaction with a terminal device of a guardian, and once the distance between the positioning device and the terminal device of the guardian is detected to exceed a preset safe distance, an alarm is triggered to remind. However, the method cannot guarantee that similar positioning equipment is worn by each child for dense scenes such as superstores, railway stations and subway stations, and once the child falls into the hands of criminals, the positioning equipment worn by the child is damaged or discarded, so that the purpose of preventing the child from getting lost cannot be really realized.
Disclosure of Invention
An object of the embodiments of the present application is to provide an indoor method, an electronic device, and a storage medium for preventing children from being lost, which adjust a monitoring range in real time through a current position of a child and a current position of a fellow passenger, so as to improve analysis efficiency and analysis accuracy when performing behavior analysis on the passenger within the monitoring range, thereby really and effectively preventing children from being lost.
In order to solve the technical problem, an embodiment of the present application provides an indoor method for preventing a child from getting lost, including: acquiring the current position of a child and the current position of a fellow person in a target area in real time based on a monitoring video of the target area; wherein the peer is an adult having close movement with the child upon entering a target area; determining a monitoring range containing the positions of the child and the fellow staff in real time according to the current position of the child and the current position of the fellow staff, performing behavior analysis on at least one of the child, the fellow staff and other staff in the monitoring range, and acquiring an analysis result of whether dangerous behaviors aiming at the child exist or not; wherein the other persons are adults with stay time exceeding a preset first time threshold value except the fellow persons within the monitoring range; and when the children are determined to have the loss risk according to the analysis result, generating corresponding early warning information based on the loss risk grade indicated by the analysis result so as to effectively prevent the children from being lost.
An embodiment of the present application also provides an electronic device, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the indoor child-resistant method as set forth in the above embodiments.
Embodiments of the present application also provide a computer-readable storage medium storing a computer program, which when executed by a processor implements the indoor child-loss prevention method mentioned in the above embodiments.
The indoor children loss prevention method provided by the embodiment of the application determines the monitoring range in real time based on the current position of the children and the current position of the fellow passengers in the target area acquired by the monitoring video, namely the monitoring range is changed and adjusted in real time according to the current positions of the children and the fellow passengers, so that the latest state of the children can be confirmed in time, the monitoring personnel can avoid monitoring more irrelevant passengers which are far away from the children and appear around the children in short time through the continuously adjusted monitoring range, and the monitoring efficiency and the monitoring accuracy are improved. And performing behavior analysis on at least one of the children, the fellow passengers and other persons in the monitoring range to obtain an analysis result, determining whether the children have the loss risk and the loss risk level according to the analysis result, and generating corresponding early warning information based on the loss risk level. That is to say, this application selects suitable one or more types of personnel to carry out behavioral analysis in monitoring range, so both can obtain the analysis result fast under simple scene, can guarantee again to have the accuracy of missing the risk to children and carry out the analysis under the complicated scene.
In addition, before performing behavior analysis on at least one of the child, the fellow passenger, and other persons within the monitoring range, the indoor method for preventing the child from being lost further includes: acquiring the age of the child and the person density of the monitoring range; and determining the person to be analyzed needing behavior analysis according to the age of the child and the person density in the monitoring range. The children of different ages have different cognitive ability, and the region of different personnel density has different contact condition and shelters from the condition, and the guardian all has different attention nurse degree to the children of different ages, the region of different personnel density. Therefore, the method and the device determine the appropriate person to be analyzed based on the age of the child and the person density in the monitoring range, so that the monitoring efficiency and the monitoring accuracy are improved.
In addition, the indoor method for preventing children from getting lost, which is provided by the embodiment of the present application, the method for determining the person to be analyzed who needs to perform behavior analysis according to the age of the child and the person density in the monitoring range includes: when the age of the child is larger than a preset age threshold, taking the other persons as persons to be analyzed; when the age of the child is smaller than or equal to a preset age threshold and the person density is larger than a preset density threshold, taking the child and the other persons as persons to be analyzed; and when the age of the child is smaller than or equal to a preset age threshold value and the person density is smaller than or equal to a preset density threshold value, taking the child and the fellow person as the person to be analyzed. Older children have certain cognitive competence and are not judgment ability, such child guardians usually cannot give much care, and the probability that the children lose or get lost is small, and the children are likely to lose only by other persons taking cheating or forcing measures. Child-loss prevention is therefore more effectively achieved for such children by analyzing the behavior of other persons within their monitoring range. And determining the person to be analyzed according to the person density in the monitoring range of the child for the younger child. When the personnel density is high, a large number of other personnel exist in the monitoring range where the child is located, and the sight of the personnel in the same row can be shielded, so that the other personnel and the child are used as the personnel to be analyzed. When the personnel density is low, other personnel around the children are fewer, and only the children and the fellow persons are subjected to behavior analysis.
In addition, the indoor method for preventing children from being lost provided by the embodiment of the present application, the performing behavior analysis on at least one type of person among the children, the fellow persons, and other persons in the monitoring range to obtain an analysis result of whether dangerous behaviors aiming at the children exist, includes: when the other people are subjected to behavior analysis, acquiring the distance between the other people and the child; when the distance between the other people and the child is smaller than a preset distance threshold, acquiring the time when the distance between the other people and the child is smaller than the distance threshold, the time when the other people gaze at the child and the behavior action of the other people; when the other people have a first dangerous action on the child, determining that the child has a loss risk, wherein the loss risk level is one level; and when the distance between the other people and the child is smaller than the distance threshold value and the time when the other people gaze the child is larger than the first time threshold value, determining that the child has the risk of losing, wherein the risk level of losing is two levels. This application is when carrying out behavioral analysis to other personnel, and the time that is less than apart from the threshold value through obtaining the distance between other personnel and the children, other personnel watch children's time and other personnel's action carry out all-round analysis to other personnel by the action of far and near to this acquires accurate analysis result.
Drawings
One or more embodiments are illustrated by way of example in the accompanying drawings, which correspond to the figures in which like reference numerals refer to similar elements and which are not to scale unless otherwise specified.
Fig. 1 is a first flowchart of an indoor child-resistant method provided by an embodiment of the present application;
fig. 2 is a second flowchart of an indoor child-resistant method according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an electronic device provided in an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the following describes each embodiment of the present application in detail with reference to the accompanying drawings. However, it will be appreciated by those of ordinary skill in the art that numerous technical details are set forth in various embodiments of the present application in order to provide a better understanding of the present application. However, the technical solution claimed in the present application can be implemented without these technical details and various changes and modifications based on the following embodiments.
The details of the implementation of the facial expression recognition according to the present embodiment will be described below by way of example. The following disclosure provides implementation details for the purpose of facilitating understanding, and is not necessary to practice the present solution.
The embodiment of the application relates to an indoor children-losing prevention method, as shown in fig. 1, comprising the following steps:
In this embodiment, the target area is indoor public places such as superstores, railway stations, tourist attractions, supermarkets, and the like, and such places are often provided with a large number of cameras to realize all-around dead-corner-free monitoring of all areas. Specifically, when a person enters a target area, a camera near an entrance acquires a person image, features of the person image, such as clothing, height, age, and the like, are extracted and identified, and whether a child enters the target area is determined, wherein the person image may only contain one person or a plurality of persons. When a child is determined to enter the target area, the child and an adult who has close action with the child are marked with the same label, that is, the adult who has close action with the child is taken as a fellow person (or guardian) of the child.
When an adult who has close action with a child is obtained, the multi-frame image of the child outside the entrance, the multi-frame image of the child at the entrance and the multi-frame image of the child which has entered the target area and is near the entrance are identified and analyzed, and whether the adult has close action with the child is determined. Wherein the intimate action comprises: pulling hands, hugging, carrying children, wearing masks for children and other close limbs. Such as: the method comprises the steps of taking an entrance of a target area as a central line, taking an area which is 3 meters away from the central line as an area outside the entrance, taking an area which is 3 meters away from the central line as an area inside the entrance, obtaining multi-frame images of children contained in the area outside the entrance, the area at the entrance and the area inside the entrance, identifying and analyzing the images, and determining that an adult is a member of the same child when the same adult has close action on the child in the multi-frame images of at least two areas. That is to say, according to the method and the device, the area outside the entrance and the area inside the entrance can be determined according to the preset identification distance, and the image of the area outside the entrance, the image of the area inside the entrance and the image of the area inside the entrance are identified and analyzed to determine the co-workers. Of course, different target regions may correspond to different recognition distances. There may be more than one peer identified for a single child.
In addition, when the current position of the child and the current position of the fellow traveler are obtained, the determination can be performed according to the positions of cameras for shooting the child and the fellow traveler, external reference and internal reference of the cameras, a pre-stored electronic map of a target area and the like.
102, determining a monitoring range including the positions of the child and the fellow staff in real time according to the current position of the child and the current position of the fellow staff, and performing behavior analysis on at least one of the child, the fellow staff and other staff in the monitoring range to obtain an analysis result of whether dangerous behaviors aiming at the child exist; wherein the other persons are adults, who stay within the monitoring range for a time period exceeding a preset first time threshold, except for the fellow persons.
In this embodiment, the monitoring range is determined according to the current position of the child and the current position of the fellow passenger, and the current positions of the child and the fellow passenger are changed in real time, so that the monitoring range is also changed in real time. Such as: when the target area is a shopping mall, the child and the fellow passengers may move ceaselessly, and the monitoring range also changes along with the movement of the child and the fellow passengers; if the child or the fellow person stays at the checkout counter to purchase a certain item, the monitoring range remains unchanged for that period of time.
Wherein the monitoring range is an area containing the positions of the children and the fellow passengers. Specifically, the monitoring range may be a minimum area including the current position of the child and the current position of the fellow passenger, and the minimum area may be a circle, a rectangle area, or other shape area.
In one embodiment, the monitoring range may be determined according to the following formula:
S=α 1 (1/age)+α 2 ρ+c
wherein S is a monitoring range, c is a minimum area containing the positions of the child and the fellow passenger, rho is the passenger density of the target area, age is the age of the child, and alpha 1 、α 2 Are coefficients.
It should be noted that the monitoring range of each child is calculated based on the age of the child and the person density of the target area based on the minimum area including the positions of the child and the co-workers of the child. Such as: if the minimum area is a circle, the minimum area is a circle having a diameter equal to the distance between the child and the fellow person. If the minimum area is a rectangle, the minimum area is a rectangular area having the distance between the child and the fellow passenger as the long side, and the midpoint of the two short sides of the rectangular area is the position of the child and the position of the fellow passenger, respectively. The personnel density of the target area is determined according to the area of the target area and the total number of personnel in the target area, alpha 2 The coefficient related to the personnel density in the target area can be set according to empirical values, the personnel density value is in different numerical ranges, and alpha 2 The corresponding are of different sizes. The age is the age of the child, and the value can be determined comprehensively according to the height of the child determined by an image recognition technology and the age of the child recognized by an age prediction model based on deep learning, so that the final age of the child is obtained. Alpha is alpha 1 The coefficient is related to the age of the child, and can also be set according to empirical values, wherein the age of the child is in different numerical ranges, alpha 1 The corresponding are of different sizes. It will be appreciated that the larger the age, the smaller the monitored area, and the greater the density of persons in the target area.
In addition, for the case that there are a plurality of persons in the same row as the child, there are two methods for determining the monitoring range of the child: the first is to take the peer closest to the child as the target peer, and determine the monitoring range according to the current position of the child and the current position of the target peer. And secondly, determining a peer region according to the positions of a plurality of peers, taking the central position of the peer region as the position of the target peer, and determining a monitoring range according to the position of the target peer and the position of the child.
Since the positions of the children and the fellow passengers are constantly changed, the minimum area is also constantly changed, and the monitoring range is changed according to the change of the minimum area and the change of the density of the passengers in the target area. In practice, once the minimum area is determined to be a circular area with the diameter being the distance between the child and the fellow passenger, the minimum area is subsequently determined according to the method.
In an embodiment, when performing behavior analysis on at least one of children, fellow persons, and other persons within the monitoring range, the persons performing behavior analysis may be determined according to factors such as the age of the children, the density of the persons within the monitoring range, the fellow persons (including the number and the persons) corresponding to the children, and the like. Specifically, the determination may be made only by a single factor, or may be made by combining a plurality of factors. Such as: if 3 persons in the same group correspond to one child, only the behaviors of other persons in the monitoring range can be analyzed. If the peer corresponding to the child a is the person a, and the peer corresponding to the child B is also the person a, two children responsible for monitoring by the explanation person a are provided: children A and children B then can all carry out behavioral analysis to children, peer personnel and other personnel in children A monitoring range, all carry out behavioral analysis to children, peer personnel and other personnel in children B monitoring range.
It is worth mentioning that the family relationship between the children and the fellow persons can be determined according to the fellow persons corresponding to different children, that is, the children and the fellow persons belonging to one family are determined; updating the peer personnel corresponding to each child according to the family relationship between the child and the peer personnel; and determining the monitoring range of each child and the personnel for behavior analysis according to the updated peer personnel corresponding to each child.
Such as: determining the persons in the same row as the person a and the person B for the child A, determining the persons in the same row as the person B, the person c and the person d for the child B, and if the child A, the child B, the person a, the person B, the person c and the person d are considered as a family, updating the persons in the same row as the person a, the person B, the person c and the person d for the child A, and updating the persons in the same row as the person a, the person B, the person c and the person d for the child A.
For another example: determining that the fellow persons of the child a are person a, person B and person c, and determining that the fellow persons of the child B are person B, the fellow persons of the child B may be considered to include person a, person B and person c, or the child a, the child B, the person a, the person B and the person c may be considered to be a family. Child B is similar to child a analyst. Of course, the above example can also be determined in combination with the age of the child and the person density within the monitoring range when determining the person to be analyzed within the monitoring range.
And 103, when the children are determined to have the loss risk according to the analysis result, generating corresponding early warning information based on the loss risk level indicated by the analysis result.
In this embodiment, when the analysis result indicates that the child has the risk of getting lost, the corresponding early warning information is generated based on the risk level of getting lost indicated by the analysis result, and the higher the risk level of getting lost, the higher the intensity of the early warning information. Such as: the loss risk level has three levels, namely a first level, a second level and a third level from high to low, when the loss risk level is the first level, the analysis result can be sent to the entrance and exit security personnel and the security personnel nearest to the child, and meanwhile, related conditions can be alarmed to police to collect more resources for processing.
The indoor child loss prevention method provided by the embodiment of the application comprises the steps that the current position of a child and the current position of a fellow passenger in a target area obtained based on a monitoring video determine the monitoring range in real time, namely the monitoring range is changed and adjusted in real time according to the current positions of the child and the fellow passenger, so that the latest state of the child can be confirmed in time, the monitoring staff can avoid monitoring more irrelevant persons which are far away from the child and appear around the child in a short time through the continuously adjusted monitoring range, and the monitoring efficiency and the monitoring accuracy are improved. And performing behavior analysis on at least one of the children, the fellow passengers and other persons in the monitoring range to obtain an analysis result, determining whether the children have the loss risk and the loss risk level according to the analysis result, and generating corresponding early warning information based on the loss risk level. That is to say, this application selects suitable one or more types of personnel to carry out behavioral analysis in monitoring range, so both can obtain the analysis result fast under simple scene, can guarantee again to have the accuracy of missing the risk to children and carry out the analysis under the complicated scene.
The embodiment of the application relates to an indoor children-losing prevention method, as shown in fig. 2, comprising the following steps:
In this embodiment, the specific implementation details of step 201 are substantially the same as those of step 101, and are not described herein again.
And step 203, acquiring the age of the child and the personnel density in the monitoring range.
In this embodiment, the age of the child may be determined comprehensively according to the height of the child determined by the image recognition technology and the age of the child identified by the age prediction model based on deep learning, and the person density in the monitoring range is determined according to the area of the monitoring range and the total number of persons in the monitoring range. It should be noted that, in determining the total number of persons in the monitoring range, the number of children and persons in the same row is generally kept constant, while the number of other persons is determined according to adults who stay in the monitoring range for a time period exceeding a preset first time threshold value except for the persons in the same row, so that the number of other persons is kept constant for a short time, but the density of persons in the monitoring range is changed continuously for a long time.
And step 204, determining the person to be analyzed, which needs to perform behavior analysis, according to the age of the child and the person density in the monitoring range.
Specifically, the person density in the monitoring range is kept constant for a short time and is changed continuously for a long time, so that the person to be analyzed in the application is kept constant for a short time and is changed dynamically for a long time. Therefore, the behavior analysis of the person to be analyzed can be consistent, and the behavior analysis can be changed along with the change of the surrounding conditions of the children.
In one embodiment, step 204 includes: when the age of the child is larger than a preset age threshold, taking other people as the people to be analyzed; when the age of the child is smaller than or equal to a preset age threshold and the person density is larger than a preset density threshold, taking the child and other persons as persons to be analyzed; and when the age of the child is less than or equal to the preset age threshold and the person density is less than or equal to the preset density threshold, taking the child and the fellow person as the persons to be analyzed.
In this embodiment, children of different ages have different cognitive competence, and the region of different personnel density has different contact condition and the condition of sheltering from, and the guardian all has different attention and nurse the degree to children of different ages, the region of different personnel density. Therefore, the method and the device determine the appropriate person to be analyzed based on the age of the child and the person density in the monitoring range, so that the monitoring efficiency and the monitoring accuracy are improved. Older children have certain cognitive ability and are not judgment ability, such child guardians usually do not give much nursing, and the children have little possibility of losing and getting lost, and the children are possible to lose only by other persons who take a cheating or forcing means. Therefore, the children can be effectively prevented from being lost by analyzing the behaviors of other persons in the monitoring range of the children. And determining the person to be analyzed according to the person density in the monitoring range of the child for the younger child. When the personnel density is high, a large number of other personnel exist in the monitoring range where the child is located, and the sight of the personnel in the same row can be shielded, so that the other personnel and the child are used as the personnel to be analyzed. When the personnel density is low, other personnel around the children are fewer, and only the children and the fellow persons are subjected to behavior analysis.
In this embodiment, the person to be analyzed performs behavior analysis, and determines whether the person to be analyzed has a behavior that constitutes a potential risk or a direct risk to the child, and if so, determines that the child has a risk of losing.
In one embodiment, when performing behavioral analysis on other persons, the analyzing step includes: (1) acquiring the distance between other persons and the child; (2) When the distance between other people and the child is smaller than a preset distance threshold, acquiring the time when the distance between other people and the child is smaller than the distance threshold, the time when other people gaze the child and the behavior of other people; (3) When other people have first dangerous actions on the children, determining that the children have the loss risk, wherein the loss risk level is first grade; (4) When the time that the distance between other personnel and the child is smaller than the distance threshold value and the time that other personnel gaze the child are both larger than the first time threshold value, it is determined that the child has the risk of being lost, and the risk level of being lost is two levels.
Specifically, the distance between other people and the child is judged in real time, and when the distance between other people and the child is smaller than a distance threshold, the time smaller than the distance threshold, the time when other people gaze at the child, and behavior actions of other people are respectively counted for each other person. That is, the application monitors the behavior of other people from far to near. When other people have first dangerous actions on the child, the child is determined to have the risk of losing and the risk level of losing is first grade. Wherein the first dangerous action comprises: hugging, embracing, dragging, kicking, beating and the like.
For acquiring the time when other people gaze at the child, the method specifically comprises the following steps: (1) Acquiring the current head postures of other people and time points corresponding to the head postures; (2) Determining the visual field range of other people according to the head postures of the other people, and judging whether the visual field range contains the current position of the child; (3) If the visual field range of other people contains the current position of the child, marking the starting time mark on the time point corresponding to the head posture; if the vision range of other people does not contain the current position of the child, no processing is performed; (4) And if the head postures of other persons are kept unchanged all the time, determining that the watching time exceeds a first time threshold according to the starting time mark, and determining that the child has the risk of losing.
In addition, in the process of the steps, when the head postures of other persons are monitored to change, the latest head posture and the time point corresponding to the head posture are obtained; updating the visual field ranges of other people according to the latest head posture, and judging whether the current visual field range contains the current position of the child; if the visual field range of other people contains the current position of the child, determining whether the watching time exceeds a first time threshold value according to the starting time mark; if the vision range of other people does not contain the current position of the child, marking the time point corresponding to the latest head posture with an ending time mark; and determining whether the time for other people to watch the child exceeds a first time threshold according to the starting time mark and the ending time mark, and if so, determining that the child has the risk of losing. Otherwise, the child is determined not to be at risk of loss.
Further, after obtaining the analysis result of whether there is dangerous behavior for the child, the method further includes: when the loss risk level is one level, acquiring monitoring videos of other people with first dangerous actions on the children in real time; the method comprises the steps of obtaining appearance clothing characteristics, walking tracks and walking speeds of other people who have first dangerous actions on the basis of monitoring video analysis, and sending the appearance clothing characteristics, the walking tracks and the walking speeds to terminal equipment corresponding to security personnel.
Specifically, when the level of the loss risk of the child is determined to be one level, the monitoring video of other people who cause the first-level loss risk to the child is identified and analyzed, the appearance clothing features of the other people are obtained through a series of technologies such as image processing, feature extraction and face identification, the walking tracks and the walking speeds of the other people are obtained through shooting the positions of cameras of the other people, the time when the cameras shoot the other people and an electronic map of a pre-stored target area, and the features are sent to terminal equipment corresponding to security personnel.
In one embodiment, when performing behavioral analysis on a child, the analyzing step comprises: (1) Acquiring the emotional state and the behavior and the action of the child; (2) When the emotional state of the child is a negative emotion and the time of the negative emotion is greater than a preset second time threshold, determining that the child has a risk of losing, and the risk level of losing is three levels; (3) When the behavior of the child is taken as a second dangerous behavior, the child is determined to have the risk of losing, and the risk level of losing is two levels.
Specifically, the behavior and the action of the child can be determined through an image recognition technology, the emotional state of the child can be determined through an emotion recognition algorithm based on deep learning, when the emotional state of the child is a negative emotion, the time of the negative emotion is greater than a preset second time threshold, the child is determined to have the risk of losing, and the risk level of losing is three levels, wherein the negative emotion comprises: crying, anxiety, fear, etc., the second time threshold being greater than or equal to the first time threshold. When the action of children is moved as the dangerous action of second, it has the risk of wandering away to confirm children, and the risk level of wandering away is the second grade, and wherein the dangerous action of second includes: children stay at an elevator entrance, children are at the edge of a step or a high place, children are at the edge of a charged object, etc., and when the children have such actions, it can be considered that no fellow passenger is around the children or that the fellow passenger is not concerned about the current situation of the children.
Further, after obtaining the analysis result of whether there is dangerous behavior for the child, the method further includes: when the loss risk level is two-level or three-level, the user can be reminded through the broadcast notification of the target area, and the user can also be notified to the security personnel nearest to the child to process.
In one embodiment, when performing behavior analysis on peer personnel, the analyzing step includes: (1) Acquiring behavior actions of the fellow passengers and time for the fellow passengers to watch the children; (2) And when the close action of the fellow staff does not exist on the child and the time for the fellow staff to watch the child is less than the second time threshold value, determining that the child has the risk of getting lost, and setting the risk level of getting lost to be two levels.
Specifically, the behavior of the peer is similar to the behavior of the child and other people, and the time for the peer to watch the child is similar to the time for the other people to watch the child, which is not described herein again.
And step 206, when the children are determined to have the loss risk according to the analysis result, generating corresponding early warning information based on the loss risk level indicated by the analysis result.
In this embodiment, when the analysis result indicates a plurality of loss risk levels, the highest loss risk level may be used as the final loss risk level; and generating corresponding early warning information based on the final lost risk grade.
The indoor children loss prevention method provided by the embodiment of the application determines the monitoring range in real time based on the current position of the children and the current position of the fellow passengers in the target area acquired by the monitoring video, namely the monitoring range is changed and adjusted in real time according to the current positions of the children and the fellow passengers, so that the latest state of the children can be confirmed in time, the monitoring personnel can avoid monitoring more irrelevant passengers which are far away from the children and appear around the children in short time through the continuously adjusted monitoring range, and the monitoring efficiency and the monitoring accuracy are improved. And performing behavior analysis on at least one of the children, the fellow passengers and other persons in the monitoring range to obtain an analysis result, determining whether the children have the loss risk and the loss risk level according to the analysis result, and generating corresponding early warning information based on the loss risk level. That is to say, this application selects suitable one or more types of personnel to carry out behavioral analysis in monitoring range, so both can obtain the analysis result fast under simple scene, can guarantee again to have the accuracy of missing the risk to children and carry out the analysis under the complicated scene.
The steps of the above methods are divided for clarity, and the implementation may be combined into one step or split some steps, and the steps are divided into multiple steps, so long as the same logical relationship is included, which are all within the protection scope of the present patent; it is within the scope of the patent to add insignificant modifications to the algorithms or processes or to introduce insignificant design changes to the core design without changing the algorithms or processes.
Embodiments of the present application relate to an electronic device, as shown in fig. 3, including:
at least one processor 301; and a memory 302 communicatively coupled to the at least one processor 301; wherein the memory 302 stores instructions executable by the at least one processor 301, the instructions being executable by the at least one processor 301 to enable the at least one processor 301 to perform the indoor child-resistant method as mentioned in the above embodiments.
The electronic device includes: one or more processors 301 and a memory 302, with one processor 301 being illustrated in fig. 3. The processor 301 and the memory 302 may be connected by a bus or other means, and fig. 3 illustrates the connection by a bus as an example. Memory 302, which is a non-volatile computer-readable storage medium, may be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. The processor 301 executes various functional applications and data processing of the device by running non-volatile software programs, instructions and modules stored in the memory 302, i.e. implements the above-mentioned indoor child-resistant method.
The memory 302 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store a list of options, etc. Further, the memory 302 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some embodiments, memory 302 may optionally include memory located remotely from processor 301, which may be connected to an external device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
One or more modules are stored in the memory 302, and when executed by the one or more processors 301, perform the indoor child-resistant method of any of the embodiments described above.
The product can execute the method provided by the embodiment of the application, has corresponding functional modules and beneficial effects of the execution method, and can refer to the method provided by the embodiment of the application without detailed technical details in the embodiment.
Embodiments of the present application relate to a computer-readable storage medium storing a computer program. The computer program realizes the above-described method embodiments when executed by a processor.
That is, as can be understood by those skilled in the art, all or part of the steps in the method according to the above embodiments may be implemented by a program instructing relevant hardware, where the program is stored in a storage medium and includes several instructions to enable a device (which may be a single chip, a chip, or the like) or a processor (processor) to execute all or part of the steps in the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
It will be understood by those of ordinary skill in the art that the foregoing embodiments are specific examples for carrying out the present application, and that various changes in form and details may be made therein without departing from the spirit and scope of the present application in practice.
Claims (8)
1. An indoor method for preventing children from getting lost, which is characterized by comprising the following steps:
acquiring the current position of a child and the current position of a fellow person in a target area in real time based on a monitoring video of the target area; wherein the peer is an adult having close movement with the child upon entering a target area;
determining a monitoring range containing the positions of the child and the fellow staff in real time according to the current position of the child and the current position of the fellow staff, and performing behavior analysis on at least one of the child, the fellow staff and other staff in the monitoring range to obtain an analysis result of whether dangerous behaviors aiming at the child exist; wherein the other persons are adults with stay time exceeding a preset first time threshold value except the fellow persons within the monitoring range;
when the children are determined to have the loss risk according to the analysis result, generating corresponding early warning information based on the loss risk level indicated by the analysis result;
before performing behavior analysis on at least one of the child, the fellow passenger, and other persons in the monitoring range, the method further includes:
acquiring the age of the child and the person density of the monitoring range;
when the age of the child is larger than a preset age threshold, taking the other persons as persons to be analyzed;
when the age of the child is smaller than or equal to a preset age threshold and the person density is larger than a preset density threshold, taking the child and the other persons as persons to be analyzed;
and when the age of the child is smaller than or equal to a preset age threshold value and the person density is smaller than or equal to a preset density threshold value, taking the child and the fellow person as the person to be analyzed.
2. The indoor method for preventing children from getting lost according to claim 1, wherein the performing behavior analysis on at least one of the children, the fellow persons and other persons in the monitoring range to obtain an analysis result of whether dangerous behaviors exist for the children comprises:
when the other people are subjected to behavior analysis, acquiring the distance between the other people and the child;
when the distance between the other people and the child is smaller than a preset distance threshold, acquiring the time when the distance between the other people and the child is smaller than the distance threshold, the time when the other people gaze at the child and the behavior action of the other people;
when the other people have a first dangerous action on the child, determining that the child has a loss risk, wherein the loss risk level is one level;
and when the distance between the other people and the child is smaller than the distance threshold value and the time when the other people gaze the child is larger than the first time threshold value, determining that the child has the risk of losing, wherein the risk level of losing is two levels.
3. The indoor child loss prevention method according to claim 2, wherein after obtaining the analysis result of whether there is dangerous behavior for the child, the method further comprises:
when the loss risk level is first grade, acquiring monitoring videos of other people with first dangerous actions on the child in real time;
and analyzing and acquiring the appearance clothing characteristics, the walking track and the walking speed of other personnel with first dangerous actions on the basis of the monitoring video, and sending the appearance clothing characteristics, the walking track and the walking speed to terminal equipment corresponding to security personnel.
4. The indoor method for preventing children from getting lost according to claim 1, wherein the performing behavior analysis on at least one of the children, the fellow persons and other persons in the monitoring range to obtain an analysis result of whether dangerous behaviors exist for the children comprises:
when the child is subjected to behavior analysis, acquiring the emotional state of the child and the behavior action of the child;
when the emotional state of the child is a negative emotion and the time of the negative emotion is greater than a preset second time threshold, determining that the child has a risk of getting lost, and the risk level of getting lost is three levels;
and when the behavior of the child is taken as a second dangerous behavior, determining that the child has the risk of getting lost, wherein the risk level of getting lost is two levels.
5. The indoor method for preventing children from getting lost according to claim 1, wherein the performing behavior analysis on at least one of the children, the fellow persons and other persons in the monitoring range to obtain an analysis result of whether dangerous behaviors of the children exist comprises:
when the behavior analysis is carried out on the fellow staff, the behavior action of the fellow staff and the time of the fellow staff watching the child are obtained;
and when the close action of the fellow staff to the child does not exist and the time of the fellow staff gazing at the child is less than a second time threshold value, determining that the child has the risk of losing, wherein the risk level of losing is two levels.
6. The indoor child loss prevention method according to claim 1, wherein the generating corresponding early warning information based on the loss risk level indicated by the analysis result comprises:
when the analysis result indicates a plurality of loss risk levels, taking the highest loss risk level as a final loss risk level;
and generating corresponding early warning information based on the final lost risk grade.
7. An electronic device, comprising:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the indoor child resistant method of any one of claims 1 to 6.
8. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the indoor child-loss prevention method of any one of claims 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210737854.2A CN114821961B (en) | 2022-06-28 | 2022-06-28 | Indoor children missing prevention method, electronic equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210737854.2A CN114821961B (en) | 2022-06-28 | 2022-06-28 | Indoor children missing prevention method, electronic equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114821961A CN114821961A (en) | 2022-07-29 |
CN114821961B true CN114821961B (en) | 2022-11-22 |
Family
ID=82522510
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210737854.2A Active CN114821961B (en) | 2022-06-28 | 2022-06-28 | Indoor children missing prevention method, electronic equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114821961B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115689297A (en) * | 2022-12-29 | 2023-02-03 | 杭州天阙科技有限公司 | Child abduction risk early warning method, device, equipment and storage medium |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2005316883A (en) * | 2004-04-30 | 2005-11-10 | Funai Electric Co Ltd | Remote watching system and terminal equipment for use in the same |
JP2013191059A (en) * | 2012-03-14 | 2013-09-26 | Dainippon Printing Co Ltd | Lost child notifying guide system and method, eyewitness information distribution server, and program |
CN107845234A (en) * | 2017-11-27 | 2018-03-27 | 浙江卓锐科技股份有限公司 | A kind of anti-anti- method of wandering away of system and scenic spot of wandering away in scenic spot |
CN108419051A (en) * | 2018-03-22 | 2018-08-17 | 安徽华普生产力促进中心有限公司 | A kind of market effectively prevent the implementation that child goes astray from the group |
CN109686049A (en) * | 2019-01-03 | 2019-04-26 | 深圳壹账通智能科技有限公司 | Children fall single based reminding method, device, medium and electronic equipment in public place |
CN109887234A (en) * | 2019-03-07 | 2019-06-14 | 百度在线网络技术(北京)有限公司 | A kind of children loss prevention method, apparatus, electronic equipment and storage medium |
CN110298293A (en) * | 2019-06-25 | 2019-10-01 | 重庆紫光华山智安科技有限公司 | One kind anti-wander away method, apparatus, readable storage medium storing program for executing and electric terminal |
CN111292502A (en) * | 2020-02-17 | 2020-06-16 | 浙江大华技术股份有限公司 | Method and device for preventing early warning of lost and storage medium |
CN111653057A (en) * | 2020-05-27 | 2020-09-11 | 惠州Tcl移动通信有限公司 | Behavior supervision method and device, storage medium and mobile terminal |
CN111860110A (en) * | 2020-06-01 | 2020-10-30 | 青岛海尔智能技术研发有限公司 | Security control method, security control device, computer equipment and storage medium |
CN112562260A (en) * | 2020-12-16 | 2021-03-26 | 浙江大华技术股份有限公司 | Anti-lost method and device |
CN114419481A (en) * | 2021-12-16 | 2022-04-29 | 佛山弘视智能信息科技有限公司 | Outdoor child unattended detection method and device based on community cerebellum monitoring |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP6835065B2 (en) * | 2016-03-18 | 2021-02-24 | 日本電気株式会社 | Information processing equipment, control methods, and programs |
JP2019193089A (en) * | 2018-04-24 | 2019-10-31 | 東芝テック株式会社 | Video analysis device |
-
2022
- 2022-06-28 CN CN202210737854.2A patent/CN114821961B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2005316883A (en) * | 2004-04-30 | 2005-11-10 | Funai Electric Co Ltd | Remote watching system and terminal equipment for use in the same |
JP2013191059A (en) * | 2012-03-14 | 2013-09-26 | Dainippon Printing Co Ltd | Lost child notifying guide system and method, eyewitness information distribution server, and program |
CN107845234A (en) * | 2017-11-27 | 2018-03-27 | 浙江卓锐科技股份有限公司 | A kind of anti-anti- method of wandering away of system and scenic spot of wandering away in scenic spot |
CN108419051A (en) * | 2018-03-22 | 2018-08-17 | 安徽华普生产力促进中心有限公司 | A kind of market effectively prevent the implementation that child goes astray from the group |
CN109686049A (en) * | 2019-01-03 | 2019-04-26 | 深圳壹账通智能科技有限公司 | Children fall single based reminding method, device, medium and electronic equipment in public place |
CN109887234A (en) * | 2019-03-07 | 2019-06-14 | 百度在线网络技术(北京)有限公司 | A kind of children loss prevention method, apparatus, electronic equipment and storage medium |
CN110298293A (en) * | 2019-06-25 | 2019-10-01 | 重庆紫光华山智安科技有限公司 | One kind anti-wander away method, apparatus, readable storage medium storing program for executing and electric terminal |
CN111292502A (en) * | 2020-02-17 | 2020-06-16 | 浙江大华技术股份有限公司 | Method and device for preventing early warning of lost and storage medium |
CN111653057A (en) * | 2020-05-27 | 2020-09-11 | 惠州Tcl移动通信有限公司 | Behavior supervision method and device, storage medium and mobile terminal |
CN111860110A (en) * | 2020-06-01 | 2020-10-30 | 青岛海尔智能技术研发有限公司 | Security control method, security control device, computer equipment and storage medium |
CN112562260A (en) * | 2020-12-16 | 2021-03-26 | 浙江大华技术股份有限公司 | Anti-lost method and device |
CN114419481A (en) * | 2021-12-16 | 2022-04-29 | 佛山弘视智能信息科技有限公司 | Outdoor child unattended detection method and device based on community cerebellum monitoring |
Also Published As
Publication number | Publication date |
---|---|
CN114821961A (en) | 2022-07-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Adhikari et al. | Activity recognition for indoor fall detection using convolutional neural network | |
Anderson et al. | Linguistic summarization of video for fall detection using voxel person and fuzzy logic | |
KR101390591B1 (en) | Facial image search system and facial image search method | |
CN107416629B (en) | The control method and system of elevator safety operation | |
RU2015147449A (en) | ANALYTICAL RECOGNITION AND VIDEO IDENTIFICATION SYSTEM | |
US11159769B2 (en) | Drowning detection enhanced by swimmer analytics | |
Merrouche et al. | Depth camera based fall detection using human shape and movement | |
CN114821961B (en) | Indoor children missing prevention method, electronic equipment and storage medium | |
JP7416165B2 (en) | information processing equipment | |
JP2006011728A (en) | Suspicious person countermeasure system and suspicious person detection device | |
Widhalm et al. | Top in the lab, flop in the field? Evaluation of a sensor-based travel activity classifier with the SHL dataset | |
JP5001808B2 (en) | Crime prevention device and crime prevention program | |
CN111666920A (en) | Target object wearing detection method and device, storage medium and electronic device | |
Onie et al. | The use of closed-circuit television and video in suicide prevention: narrative review and future directions | |
Kaur et al. | Violence detection in videos using deep learning: A survey | |
Merrouche et al. | Fall detection using head tracking and centroid movement based on a depth camera | |
Kolarow et al. | APFel: The intelligent video analysis and surveillance system for assisting human operators | |
JP2016143302A (en) | Information notification device, method, and program | |
De et al. | Fall detection approach based on combined displacement of spatial features for intelligent indoor surveillance | |
Guney et al. | A deep neural network based toddler tracking system | |
CN115761564A (en) | Follower list processing method, abnormal travel event detection method and system | |
KR102648004B1 (en) | Apparatus and Method for Detecting Violence, Smart Violence Monitoring System having the same | |
CN112562260B (en) | Anti-lost method and device | |
JP2023079291A (en) | Image processing device, image processing method, and program | |
Jameel et al. | Human gait recognition using preprocessing and classification techniques |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20230818 Address after: Room 799-4, 7th Floor, Building A3A4, Zhong'an Chuanggu Science and Technology Park, No. 900 Wangjiang West Road, Gaoxin District, Hefei Free Trade Experimental Zone, Anhui Province, 230031 Patentee after: Anhui Lushenshi Technology Co.,Ltd. Address before: 230091 room 611-217, R & D center building, China (Hefei) international intelligent voice Industrial Park, 3333 Xiyou Road, high tech Zone, Hefei, Anhui Province Patentee before: Hefei lushenshi Technology Co.,Ltd. |