CN117596366B - Personnel state monitoring system - Google Patents
Personnel state monitoring system Download PDFInfo
- Publication number
- CN117596366B CN117596366B CN202410075307.1A CN202410075307A CN117596366B CN 117596366 B CN117596366 B CN 117596366B CN 202410075307 A CN202410075307 A CN 202410075307A CN 117596366 B CN117596366 B CN 117596366B
- Authority
- CN
- China
- Prior art keywords
- initial
- personnel
- person
- preset
- monitoring
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 57
- 238000005070 sampling Methods 0.000 claims abstract description 121
- 230000000694 effects Effects 0.000 claims abstract description 36
- 238000012806 monitoring device Methods 0.000 claims abstract description 25
- 238000000034 method Methods 0.000 claims abstract description 19
- 238000004590 computer program Methods 0.000 claims abstract description 15
- 101000872083 Danio rerio Delta-like protein C Proteins 0.000 claims description 10
- 238000012512 characterization method Methods 0.000 claims description 9
- 230000000877 morphologic effect Effects 0.000 claims description 7
- 230000003321 amplification Effects 0.000 claims description 2
- 230000000977 initiatory effect Effects 0.000 claims description 2
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 2
- 230000035945 sensitivity Effects 0.000 abstract description 7
- 238000012545 processing Methods 0.000 abstract description 2
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 238000013480 data collection Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/188—Capturing isolated or intermittent images triggered by the occurrence of a predetermined event, e.g. an object reaching a predetermined position
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/62—Extraction of image or video features relating to a temporal dimension, e.g. time-based feature extraction; Pattern tracking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- 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
- G08B21/18—Status alarms
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Alarm Systems (AREA)
Abstract
The application relates to the technical field of monitoring data processing, in particular to a personnel state monitoring system, which comprises: the method comprises the following steps of an initial personnel identification list, a preset maximum sampling interval duration list, an initial monitoring device set, a processor and a memory storing a computer program, wherein when the computer program is executed by the processor, the following steps are realized: according to a plurality of initial monitoring devices, acquiring a target personnel image set corresponding to any initial personnel in a preset period and an initial sampling time stamp list corresponding to each target personnel image, then acquiring a sampling interval duration list, further acquiring an intermediate sampling time stamp list, and finally judging whether to update the preset maximum sampling interval duration according to the proportion of the intermediate sampling time stamp to the initial sampling time stamp. The invention can flexibly adjust the preset maximum sampling interval duration of each initial personnel according to the monitoring condition, and has the effects of reducing false alarms or improving alarm sensitivity.
Description
Technical Field
The invention relates to the technical field of monitoring data processing, in particular to a personnel state monitoring system.
Background
In a traditional personal activity monitoring system, for example, in various occasions such as community management, old man monitoring, staff efficiency monitoring and the like, monitoring data of related staff are obtained through monitoring equipment, whether normal activity of a monitored staff is lost or not is judged according to a set static time (such as 72 hours), for example, if the activity data of the monitored staff are not monitored for 72 hours continuously, the situation that the staff is considered to have abnormal activity is considered, but the method can cause a large number of false alarms, and particularly, under the condition that a daily activity mode is irregular or data collection is intermittent, the monitoring accuracy and reliability are low.
Disclosure of Invention
Aiming at the technical problems, the invention adopts the following technical scheme:
a personnel status monitoring system, the system comprising: initial person identification list a= { a 1 ，A 2 ，……，A i ，……，A m Preset maximum sampling interval duration list b= { B corresponding to } and a 1 ，B 2 ，……，B i ，……，B m A set of initial monitoring devices, a processor and a memory storing a computer program, wherein A i For the ith initial personnel mark, B i Is A i The corresponding preset maximum sampling interval duration, i=1, 2, … …, m, m is the number of initial personnel identifiers, the initial monitoring equipment set comprises a plurality of initial monitoring equipment, and when the computer program is executed by the processor, the following steps are realized:
s100, according to a plurality of initial monitoring devices, obtaining A in a preset period i Corresponding target person image set C i ={C i1 ，C i2 ，……，C ij ，……，C in Sum C i Corresponding initial sample timestamp list C 0 i ={C 0 i1 ，C 0 i2 ，……，C 0 ij ，……，C 0 in }，C ij Is A i Corresponding j-th target person image, C 0 ij Is C ij Corresponding initial sampling timestamp, j=1, 2, … …, n, n is a i The number of corresponding target person images.
S200 according to C 0 i Obtaining C 0 i Corresponding sample interval duration list deltac 0 i ={ΔC 0 i1 ，ΔC 0 i2 ，……，ΔC 0 ij ，……，ΔC 0 in }, wherein DeltaC 0 i1 Refers to C 0 i1 Time distance C of characterization i1 The duration between the moments characterized by the corresponding last initial sampling timestamp, ΔC when j+.1 0 ij Refers to C 0 ij Time distance C of characterization 0 i(j-1) The duration between the time instants of the characterization.
S300 according to B i And DeltaC 0 i From C 0 i Mid-sample timestamp list G i ={G i1 ，G i2 ，……，G ip ，……，C iq }，G ip Is C i The corresponding p-th intermediate sampling timestamp, p=1, 2, … …, q, q is C i The number of corresponding intermediate sampling time stamps, wherein the intermediate sampling time stamps refer to deltac 0 i Less than B i An initial sampling time stamp corresponding to any one of the sampling interval durations.
S400, when lambda 1 ＜q/n≤λ 2 At the time, B i Determining a target maximum sampling interval duration to realize subsequent monitoring of personnel states, wherein lambda 1 For a preset first probability lambda 2 Is a preset second probability.
S500, when q/n is less than or equal to lambda 1 When in use, an alarm prompt is sent out and according to a preset first updating duration epsilon 1 Pair B i Update and get B i UpdatingThe result is determined as the target maximum sampling interval duration so as to realize the subsequent monitoring of the personnel state.
S600 when q/n > lambda 2 In this case, the second update time epsilon is preset 2 Pair B i Update B i And determining the updated result as the target maximum sampling interval duration so as to realize the subsequent monitoring of the personnel state.
Compared with the prior art, the personnel state monitoring system provided by the invention has obvious beneficial effects, can achieve quite technical progress and practicality, has wide industrial utilization value, and has at least the following beneficial effects:
the invention provides a personnel status monitoring system, which comprises: the method comprises the following steps of an initial personnel identification list, a preset maximum sampling interval duration list, an initial monitoring device set, a processor and a memory storing a computer program, wherein when the computer program is executed by the processor, the following steps are realized: according to a plurality of initial monitoring devices, A in a preset period is obtained i The method comprises the steps that a corresponding target personnel image set and an initial sampling time stamp list corresponding to each target personnel image are obtained, then a sampling interval duration list is obtained according to the initial sampling time stamp list, a middle sampling time stamp list meeting requirements is obtained, and finally whether the preset maximum sampling interval duration is updated or not is judged according to the proportion of the middle sampling time stamp to the initial sampling time stamp; when the duty ratio of the middle sampling time stamp representing normal activity is relatively low, an alarm prompt is easy to send out, the proportion of the middle sampling time stamp can be improved by improving the preset maximum sampling interval time length, so that the updated target maximum sampling interval time length is more consistent with the activity habit of the initial personnel, false alarm is reduced, the monitoring accuracy is improved, when the duty ratio of the middle sampling time stamp representing normal activity is relatively high, the alarm prompt is difficult to send out, the alarm sensitivity is poor, the proportion of the middle sampling time stamp can be reduced by reducing the preset maximum sampling interval time length, and the alarm sensitivity and the monitoring effectiveness can be improvedAnd (3) adjusting the preset maximum sampling interval duration of each initial person, thereby achieving the effect of reducing false alarms or improving alarm sensitivity.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a personnel status monitoring system executing a computer program according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to fall within the scope of the invention.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
A personnel status monitoring system, the system comprising: initially, the method comprisesStarting person identification list a= { a 1 ，A 2 ，……，A i ，……，A m Preset maximum sampling interval duration list b= { B corresponding to } and a 1 ，B 2 ，……，B i ，……，B m A set of initial monitoring devices, a processor and a memory storing a computer program, wherein A i For the ith initial personnel mark, B i Is A i The corresponding preset maximum sampling interval duration, i=1, 2, … …, m, m is the number of initial personnel identifiers, and the initial monitoring device set includes a plurality of initial monitoring devices, when the computer program is executed by the processor, the following steps are implemented, as shown in fig. 1:
s100, according to a plurality of initial monitoring devices, obtaining A in a preset period i Corresponding target person image set C i ={C i1 ，C i2 ，……，C ij ，……，C in Sum C i Corresponding initial sample timestamp list C 0 i ={C 0 i1 ，C 0 i2 ，……，C 0 ij ，……，C 0 in }，C ij Is A i Corresponding j-th target person image, C 0 ij Is C ij Corresponding initial sampling timestamp, j=1, 2, … …, n, n is a i The number of corresponding target person images can be understood as: the ith initial personnel identifier corresponds to the ith initial personnel, C ij And representing a target person image corresponding to the ith initial person.
Specifically, the initial personnel identifier is a unique identity identifier of the initial personnel.
Specifically, the initial person refers to any person within a pre-recorded preset area range that meets a first preset requirement and does not meet a second preset requirement, for example, when the preset area range is a certain cell, the first preset requirement may be a resident with an age above 60 years old in the resident of the cell, and the second preset requirement may be an initial person that does not need to move in the cell for a period of time due to physical reasons or other reasons; if the preset area is the office of a certain company, the first preset requirement may be all employees of the company, and the second preset requirement may be employees who frequently go on business or sit at irregular positions.
Specifically, the preset maximum sampling interval duration refers to a maximum duration which is preset for any initial person and used for representing that the duration of the initial person between two adjacent samplings is in a normal state, and can be understood as follows: and when the time length of any initial person between two adjacent samples exceeds the preset maximum sampling interval time length, the initial person is considered to be in an abnormal state.
In a specific embodiment, the target person image is acquired in S100 by:
s101, when at least one initial monitoring device monitors initial personnel, shooting the monitored initial personnel according to a preset shooting interval to obtain an initial personnel image set, wherein the initial personnel image set comprises a plurality of initial personnel images and can be understood as follows: the initial personnel image is any personnel image shot by each initial monitoring device monitoring the initial personnel in a preset time period, and shooting is stopped when the initial personnel is not in the monitoring range.
S102, when A is identified from a plurality of initial personnel images i When the corresponding initial person is, A is identified i The initial person image of the corresponding initial person is determined as the target person image.
Specifically, one skilled in the art can know that any method for identifying a specific person from a person image in the prior art falls within the scope of the present invention, for example, a face recognition technology is adopted to identify a face in the person image.
S103, when A is not recognized from the plurality of initial personnel images i When the corresponding initial person is, an unidentified person image set D= { D is obtained 1 ，D 2 ，……，D e ，……，D f }，D e For the e-th unidentified person image, e=1, 2, … …, f, f is the number of unidentified person images.
Specifically, the unidentified personnel image refers to an initial personnel image in which any one initial personnel is unidentified in a plurality of initial personnel images.
S104, from D e Acquisition of D e The corresponding morphological information of the unidentified person comprises the height, the width and the ratio of the upper body to the lower body of the unidentified person.
S105, obtain D e Corresponding morphological information of unidentified personnel and A in target morphological database i Matching degree sigma of corresponding morphological information e 。
Specifically, the target form database refers to a database storing form information of each initial person, wherein the target form database is a database updated at regular time, for example, the target form database is updated along with seasons due to different dressing thicknesses; the target morphology database is updated regularly due to the morphology changes of the original personnel.
Specifically, sigma e Meets the following conditions:
σ e =(max(x e ,x i )/min(x e ,x i )+max(y e ,y i )/min(y e ,y i )+max(z e ,z i )/min(z e ,z i ) 3, wherein x e For D e The height, x of the corresponding unidentified person i Is A i Height, y of corresponding initial person e For D e The body width, y of the corresponding unidentified person i Is A i Corresponding body width, z of initial person e For D e The ratio of the upper body to the lower body of the corresponding unidentified person, z i Is A i The ratio of the upper body to the lower body of the corresponding original person.
S106, when sigma e When the matching degree accords with the preset matching degree range, D is determined e And determining the image as a target person image.
Specifically, sigma e The range of matching degree accords with the preset matching degree is 0.9 < sigma e ＜1.1。
According to the method, the plurality of initial personnel images are identified, the initial personnel image capable of identifying the target personnel is firstly determined to be the target personnel image, and when the target personnel is not identified, the target personnel image is determined by comparing the form information in the target form database, so that more target personnel images can be obtained, the initial sampling time stamp corresponding to each target personnel image is obtained according to each target personnel image, and further the evaluation of the activity range and the activity state of the target personnel is more accurate.
S200 according to C 0 i Obtaining C 0 i Corresponding sample interval duration list deltac 0 i ={ΔC 0 i1 ，ΔC 0 i2 ，……，ΔC 0 ij ，……，ΔC 0 in }, wherein DeltaC 0 i1 Refers to C 0 i1 Time distance C of characterization i1 The duration between the moments characterized by the corresponding last initial sampling timestamp, ΔC when j+.1 0 ij Refers to C 0 ij Time distance C of characterization 0 i(j-1) The duration between the time instants of the characterization.
Specifically, C i1 The corresponding last initial sampling time stamp refers to A obtained in the last preset period corresponding to the preset period i The corresponding last sample timestamp can be understood as: c (C) i1 The corresponding last initial sampling time stamp is at C i1 Previously photographed A i And a sampling time stamp corresponding to the last target personnel image.
On the basis of acquiring the plurality of initial sampling time stamps, the method can acquire the time length of each initial person between any two adjacent activities, so as to acquire the plurality of time lengths, judge the activity interval condition of the initial person, and acquire the times of the normal activity state and the abnormal activity state.
S300 according to B i And DeltaC 0 i From C 0 i Mid-sample timestamp list G i ={G i1 ，G i2 ，……，G ip ，……，C iq }，G ip Is C i The corresponding p-thIntermediate sampling timestamp, p=1, 2, … …, q, q is C i The number of corresponding intermediate sampling time stamps, wherein the intermediate sampling time stamps refer to deltac 0 i Less than B i The initial sampling time stamp corresponding to any sampling interval duration can be understood as: ΔC 0 ij The corresponding initial sampling time stamp is C 0 ij 。
According to the sampling interval duration corresponding to each initial person and the preset maximum sampling interval duration preset for each initial person, all sampling interval durations which are smaller than the preset maximum sampling interval duration and correspond to each initial person can be obtained, so that initial sampling time stamps which correspond to the sampling interval durations which are smaller than the preset maximum sampling interval duration are obtained, the proportion of time stamps of normal activities of the initial person is judged according to the number of the obtained intermediate sampling time stamps, and further adjustment of the preset maximum sampling interval durations is completed according to the proportion, so that the subsequent monitoring of the personnel state is achieved, and false alarms are reduced.
S400, when lambda 1 ＜q/n≤λ 2 At the time, B i Determining a target maximum sampling interval duration to realize subsequent monitoring of personnel states, wherein lambda 1 For a preset first probability lambda 2 Is a preset second probability.
Specifically lambda 1 The range of the value of (2) is not less than 0.7 lambda 1 ＜0.8。
Specifically lambda 2 The range of the value of (2) is not less than 0.8 lambda 2 ＜0.9。
When the ratio of the time stamp of the normal activity corresponding to the initial person to the initial sampling time stamp corresponding to the initial person is smaller than and close to the preset second probability, that is, the ratio occupied by the time stamp of the normal activity is higher, the preset maximum sampling interval duration corresponding to the initial person is indicated to be reasonable, so that updating is not needed, and the current preset maximum sampling interval duration is maintained.
S500, when q/n is less than or equal to lambda 1 When in use, an alarm prompt is sent out and according to a preset first updating duration epsilon 1 Pair B i Update and get B i And determining the updated result as the target maximum sampling interval duration so as to realize the subsequent monitoring of the personnel state.
In a specific embodiment, B is performed in S500 by the following steps i Updating:
s501, update B i Is (B) i +ε 1 ）。
S502, according to the updated B i And DeltaC 0 i From C 0 i L first sampling time stamps are obtained, wherein the first sampling time stamps refer to delta C 0 i Less than updated B i An initial sampling timestamp corresponding to any one of the sampling interval durations; it can be understood that: updated B i Refers to (B) i +ε 1 ）。
S503, when L/n is less than or equal to lambda 1 At this time, return to execution S501 until lambda 1 ＜L/n≤λ 2 B at this time i As a result of the update; it can be understood that: b at this time i Is referred to as lambda 1 ＜L/n≤λ 2 Corresponding latest updated B i Is a value of (2).
Above-mentioned, when the time stamp of the normal activity that initial personnel corresponds and the initial sampling time stamp that this initial personnel corresponds are less than the first probability of predetermineeing, namely the time stamp of normal activity occupies when the proportion is lower, indicate that this initial personnel corresponds the biggest sampling interval duration of predetermineeing is unreasonable, send alarm suggestion easily, through improving the biggest sampling interval duration of predetermineeing, can promote the proportion of time stamp of normal activity, make the biggest sampling interval duration of target after the update more accord with this initial personnel's activity custom, so that the proportion of time stamp of the normal activity of monitoring is less than and is close to the second probability of predetermineeing, thereby reduce the false alarm, the accuracy of control has been improved.
S600 when q/n > lambda 2 In this case, the second update time epsilon is preset 2 Pair B i Update B i The updated result is determined as the target maximum sampling interval durationSo as to realize the subsequent monitoring of personnel status.
In a specific embodiment, B is performed in S600 by the following steps i Updating:
s601, update B i Is (B) i -ε 2 ）。
S602, according to updated B i And DeltaC 0 i From C 0 i T second sampling time stamps are obtained, wherein the second sampling time stamps refer to delta C 0 i Less than updated B i An initial sampling timestamp corresponding to any one of the sampling interval durations; it can be understood that: updated B i Refers to (B) i -ε 2 ）。
S603, when T/n > lambda 2 At this time, return to execution S601 until lambda 1 ＜T/n≤λ 2 B at this time i As a result of the update; it can be understood that: b at this time i Is referred to as lambda 1 ＜L/n≤λ 2 Corresponding latest updated B i Is a value of (2).
When the ratio of the time stamp of the normal activity corresponding to the initial person to the initial sampling time stamp corresponding to the initial person is greater than the preset second probability, that is, the ratio of the time stamp of the normal activity occupied is very high, the preset maximum sampling interval duration corresponding to the initial person is unreasonable, and the alarm prompt is not easy to be sent out, so that the alarm sensitivity is poor.
In another specific embodiment, the system further comprises: key person identification list h= { H 1 ，H 2 ，……，H r ，……，H s Distance between each initial monitoring device and any initial monitoring device except the initial monitoring device, wherein H r For the r-th key person identification, r=1, 2, … …, s, s is offThe number of key person identities, the computer program, when executed by the processor, further performs the steps of:
s1, acquiring theta before the current moment according to a preset auditing period r Length of time ×η H r Liveness u of the corresponding key person r Wherein θ r Represents H r The corresponding preset maximum sampling interval duration of the key personnel, wherein eta is an amplification factor; it can be understood that: in the time of checking, if the registration time from the key personnel at the current moment is less than theta r X eta, acquiring H in the time period from the current time to the registration time r Liveness u of the corresponding key person r 。
Specifically, the key personnel identifier is a unique identity identifier of the key personnel.
Specifically, the key personnel refer to any initial personnel meeting the second preset requirement in the range of the preset area recorded in advance.
Specifically, u r Meets the following conditions:
when gamma is not equal to 1, u r =u 0 +(∑ γ-1 ρ=1 W rρ ) Phi, wherein u 0 For the preset initial activity level, W rρ To monitor H r Rho initial monitoring equipment and monitoring H of corresponding key personnel r The distance between the (p+1) th initial monitoring equipment of the corresponding key personnel, phi is the distance between the two initial monitoring equipment farthest away, and gamma is the monitored distance H r The number of initial monitoring devices of the corresponding key personnel; when γ=1, u r =u 0 。
According to the method, the system and the device, the activity state of each key person is screened regularly every one auditing period, when monitoring data corresponding to each key person are obtained, the preset maximum sampling interval duration corresponding to the key person is amplified, more monitoring data can be obtained, and the activity of the key person is determined according to the monitored times of the obtained key person, so that the obtained activity is more accurate.
S2, when u r When > ζ, H r From HDelete and put H r And adding the activity value to the A, wherein ζ is a preset activity threshold.
Above-mentioned, when the liveness of key personnel exceeds the liveness threshold value of predetermineeing, indicate that the liveness of key personnel is higher, delete this key personnel sign from key personnel sign list, no longer obtain its liveness to add it in initial personnel sign list, in order to monitor its activity state, guarantee that this key personnel send the warning suggestion when the activity state is unusual.
In summary, the present invention provides a personnel status monitoring system, the system comprising: the method comprises the following steps of an initial personnel identification list, a preset maximum sampling interval duration list, an initial monitoring device set, a processor and a memory storing a computer program, wherein when the computer program is executed by the processor, the following steps are realized: according to a plurality of initial monitoring devices, A in a preset period is obtained i The method comprises the steps that a corresponding target personnel image set and an initial sampling time stamp list corresponding to each target personnel image are obtained, then a sampling interval duration list is obtained according to the initial sampling time stamp list, a middle sampling time stamp list meeting requirements is obtained, and finally whether the preset maximum sampling interval duration is updated or not is judged according to the proportion of the middle sampling time stamp to the initial sampling time stamp; when the duty ratio of the middle sampling time stamp representing normal activities is relatively low, an alarm prompt is easy to send out, the proportion of the middle sampling time stamp can be improved by improving the preset maximum sampling interval time length, so that the updated target maximum sampling interval time length is more consistent with the activity habit of the initial personnel, false alarms are reduced, the monitoring accuracy is improved, when the duty ratio of the middle sampling time stamp representing normal activities is very high, the alarm prompt is difficult to send out, the alarm sensitivity is poor, the proportion of the middle sampling time stamp can be reduced by reducing the preset maximum sampling interval time length, and therefore the alarm sensitivity and the monitoring effectiveness can be improved.
While certain specific embodiments of the invention have been described in detail by way of example, it will be appreciated by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the invention. Those skilled in the art will also appreciate that many modifications may be made to the embodiments without departing from the scope and spirit of the invention. The scope of the invention is defined by the appended claims.
Claims (7)
1. A personnel condition monitoring system, the system comprising: initial person identification list a= { a 1 ，A 2 ，……，A i ，……，A m Preset maximum sampling interval duration list b= { B corresponding to } and a 1 ，B 2 ，……，B i ，……，B m A set of initial monitoring devices, a processor and a memory storing a computer program, wherein A i For the ith initial personnel mark, B i Is A i The corresponding preset maximum sampling interval duration, i=1, 2, … …, m, m is the number of initial personnel identifiers, the initial monitoring equipment set comprises a plurality of initial monitoring equipment, and when the computer program is executed by the processor, the following steps are realized:
s100, according to a plurality of initial monitoring devices, obtaining A in a preset period i Corresponding target person image set C i ={C i1 ，C i2 ，……，C ij ，……，C in Sum C i Corresponding initial sample timestamp list C 0 i ={C 0 i1 ，C 0 i2 ，……，C 0 ij ，……，C 0 in }，C ij Is A i Corresponding j-th target person image, C 0 ij Is C ij Corresponding initial sampling timestamp, j=1, 2, … …, n, n is a i The number of corresponding target person images;
s200 according to C 0 i Obtaining C 0 i Corresponding sample interval duration list deltac 0 i ={ΔC 0 i1 ，ΔC 0 i2 ，……，ΔC 0 ij ，……，ΔC 0 in }, wherein DeltaC 0 i1 Refers to C 0 i1 Time distance C of characterization i1 The duration between the moments characterized by the corresponding last initial sampling timestamp, ΔC when j+.1 0 ij Refers to C 0 ij Time distance C of characterization 0 i(j-1) The duration between the time instants of the characterization;
s300 according to B i And DeltaC 0 i From C 0 i Mid-sample timestamp list G i ={G i1 ，G i2 ，……，G ip ，……，C iq }，G ip Is C i The corresponding p-th intermediate sampling timestamp, p=1, 2, … …, q, q is C i The number of corresponding intermediate sampling time stamps, wherein the intermediate sampling time stamps refer to deltac 0 i Less than B i An initial sampling timestamp corresponding to any one of the sampling interval durations;
s400, when lambda 1 ＜q/n≤λ 2 At the time, B i Determining a target maximum sampling interval duration to realize subsequent monitoring of personnel states, wherein lambda 1 For a preset first probability lambda 2 A second probability which is preset;
s500, when q/n is less than or equal to lambda 1 When in use, an alarm prompt is sent out and according to a preset first updating duration epsilon 1 Pair B i Update and get B i The updated result is determined as the target maximum sampling interval duration so as to realize the subsequent monitoring of the personnel state;
in S500, the method comprises the following steps of i Updating:
s501, update B i Is (B) i +ε 1 ）；
S502, according to the updated B i And DeltaC 0 i From C 0 i L first sampling time stamps are obtained, wherein the first sampling time stamps refer to delta C 0 i Less than updated B i Corresponding to any sampling interval duration ofIs used for the initial sampling time stamp of (a);
s503, when L/n is less than or equal to lambda 1 At this time, return to execution S501 until lambda 1 ＜L/n≤λ 2 B at this time i As a result of the update;
s600 when q/n > lambda 2 In this case, the second update time epsilon is preset 2 Pair B i Update B i The updated result is determined as the target maximum sampling interval duration so as to realize the subsequent monitoring of the personnel state;
in S600, pair B is prepared by i Updating:
s601, update B i Is (B) i -ε 2 ）；
S602, according to updated B i And DeltaC 0 i From C 0 i T second sampling time stamps are obtained, wherein the second sampling time stamps refer to delta C 0 i Less than updated B i An initial sampling timestamp corresponding to any one of the sampling interval durations;
s603, when T/n > lambda 2 At this time, return to execution S601 until lambda 1 ＜T/n≤λ 2 B at this time i As a result of the update.
2. The person state monitoring system according to claim 1, wherein the target person image is acquired in S100 by:
s101, when at least one initial monitoring device monitors initial personnel, shooting the monitored initial personnel according to a preset shooting interval to obtain an initial personnel image set, wherein the initial personnel image set comprises a plurality of initial personnel images;
s102, when A is identified from a plurality of initial personnel images i When the corresponding initial person is, A is identified i An initial personnel image of a corresponding initial personnel is determined to be a target personnel image;
s103, when A is not recognized from the plurality of initial personnel images i When corresponding initial personnel are acquiredOther person image set d= { D 1 ，D 2 ，……，D e ，……，D f }，D e For the e-th unidentified person image, e=1, 2, … …, f, f is the number of unidentified person images;
s104, from D e Acquisition of D e The method comprises the steps of obtaining form information of corresponding unidentified personnel, wherein the form information comprises the height and width of the unidentified personnel and the ratio of an upper body to a lower body;
s105, obtain D e Corresponding morphological information of unidentified personnel and A in target morphological database i Matching degree sigma of corresponding morphological information e ；
S106, when sigma e When the matching degree accords with the preset matching degree range, D is determined e And determining the image as a target person image.
3. The personnel status monitoring system of claim 2 wherein the unidentified personnel image is an initial personnel image in which none of the initial personnel images is identified.
4. The personnel status monitoring system of claim 2 wherein σ e Meets the following conditions:
σ e =(max(x e ,x i )/min(x e ,x i )+max(y e ,y i )/min(y e ,y i )+max(z e ,z i )/min(z e ,z i ) 3, wherein x e For D e The height, x of the corresponding unidentified person i Is A i Height, y of corresponding initial person e For D e The body width, y of the corresponding unidentified person i Is A i Corresponding body width, z of initial person e For D e The ratio of the upper body to the lower body of the corresponding unidentified person, z i Is A i The ratio of the upper body to the lower body of the corresponding original person.
5. The personnel status monitoring system of claim 2Characterized in that sigma e The range of matching degree accords with the preset matching degree is 0.9 < sigma e ＜1.1。
6. The personnel condition monitoring system of claim 1, wherein the system further comprises: key person identification list h= { H 1 ，H 2 ，……，H r ，……，H s Distance between each initial monitoring device and any initial monitoring device except the initial monitoring device, wherein H r For the r-th key person identifier, r=1, 2, … …, s, s is the number of key person identifiers, and when the computer program is executed by the processor, the following steps are further implemented:
s1, acquiring theta before the current moment according to a preset auditing period r Length of time ×η H r Liveness u of the corresponding key person r Wherein θ r Represents H r The corresponding preset maximum sampling interval duration of the key personnel, wherein eta is an amplification factor;
s2, when u r When > ζ, H r Delete from H and H r And adding the activity value to the A, wherein ζ is a preset activity threshold.
7. The personnel status monitoring system of claim 6 wherein u r Meets the following conditions:
when gamma is not equal to 1, u r =u 0 +(∑ γ-1 ρ=1 W rρ ) Phi, wherein u 0 For the preset initial activity level, W rρ To monitor H r Rho initial monitoring equipment and monitoring H of corresponding key personnel r The distance between the (p+1) th initial monitoring equipment of the corresponding key personnel, phi is the distance between the two initial monitoring equipment farthest away, and gamma is the monitored distance H r The number of initial monitoring devices of the corresponding key personnel; when γ=1, u r =u 0 。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410075307.1A CN117596366B (en) | 2024-01-18 | 2024-01-18 | Personnel state monitoring system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410075307.1A CN117596366B (en) | 2024-01-18 | 2024-01-18 | Personnel state monitoring system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117596366A CN117596366A (en) | 2024-02-23 |
| CN117596366B true CN117596366B (en) | 2024-03-29 |
Family
ID=89910299
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410075307.1A Active CN117596366B (en) | 2024-01-18 | 2024-01-18 | Personnel state monitoring system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117596366B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107133142A (en) * | 2017-04-18 | 2017-09-05 | 浙江大学 | A kind of monitoring data intellegent sampling method based on association analysis |
| CN109474697A (en) * | 2018-12-11 | 2019-03-15 | 长春金阳高科技有限责任公司 | A kind of monitoring system audio/video transmission method |
| WO2019140155A1 (en) * | 2018-01-12 | 2019-07-18 | Kineticor, Inc. | Systems, devices, and methods for tracking and/or analyzing subject images and/or videos |
| CN115220034A (en) * | 2022-07-14 | 2022-10-21 | 浙江芯力微电子股份有限公司 | Personnel state monitoring method |
-
2024
- 2024-01-18 CN CN202410075307.1A patent/CN117596366B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107133142A (en) * | 2017-04-18 | 2017-09-05 | 浙江大学 | A kind of monitoring data intellegent sampling method based on association analysis |
| WO2019140155A1 (en) * | 2018-01-12 | 2019-07-18 | Kineticor, Inc. | Systems, devices, and methods for tracking and/or analyzing subject images and/or videos |
| CN109474697A (en) * | 2018-12-11 | 2019-03-15 | 长春金阳高科技有限责任公司 | A kind of monitoring system audio/video transmission method |
| CN115220034A (en) * | 2022-07-14 | 2022-10-21 | 浙江芯力微电子股份有限公司 | Personnel state monitoring method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117596366A (en) | 2024-02-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109858365B (en) | Special crowd gathering behavior analysis method and device and electronic equipment | |
| CN107169426B (en) | Crowd emotion abnormality detection and positioning method based on deep neural network | |
| CN109190588A (en) | A kind of method and device of population classification | |
| CN112308001A (en) | Data analysis method and personnel tracking method and system for smart community | |
| CN107665289B (en) | Operator data processing method and system | |
| CN109784270A (en) | A kind of processing method promoting face picture identification integrality | |
| CN111026738A (en) | Regional population monitoring method and system, electronic equipment and storage medium | |
| CN111680637A (en) | Mask detection method and detection system based on deep learning and image recognition technology | |
| US11232387B2 (en) | Time and attendance system suitable for large or mobile work forces | |
| WO2022262257A1 (en) | Method for recognizing sleep behavior of operator on duty in field of inspection | |
| Gupta et al. | Identification of age, gender, & race SMT (scare, marks, tattoos) from unconstrained facial images using statistical techniques | |
| CN112199530B (en) | Multi-dimensional face library picture automatic updating method, system, equipment and medium | |
| CN116108491B (en) | Data leakage early warning method, device and system based on semi-supervised federal learning | |
| CN111079720B (en) | Face recognition method based on cluster analysis and autonomous relearning | |
| CN117596366B (en) | Personnel state monitoring system | |
| CN110390478A (en) | Supervisory systems and monitoring and managing method after finance based on Internet of Things is borrowed | |
| CN114049658A (en) | Floating population management method and device based on face recognition, computer equipment and storage medium | |
| CN113901441A (en) | User abnormal request detection method, device, equipment and storage medium | |
| CN110705971A (en) | Attendance management system and method based on deep learning | |
| CN116884076A (en) | Appointed person early warning method, electronic equipment and storage medium | |
| CN112685473B (en) | Network abnormal flow detection method and system based on time sequence analysis technology | |
| CN113971739A (en) | Face recognition police information tracking platform based on internet | |
| CN110502992B (en) | Relation graph based fast face recognition method for fixed scene video | |
| CN113191191A (en) | Community epidemic situation management method and system based on user habit analysis | |
| CN110969209A (en) | Stranger identification method and device, electronic equipment and storage medium |
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 |