CN112949502B - Method, system and electronic device for detecting swimming pool safety officer looking around - Google Patents
Method, system and electronic device for detecting swimming pool safety officer looking around Download PDFInfo
- Publication number
- CN112949502B CN112949502B CN202110243530.9A CN202110243530A CN112949502B CN 112949502 B CN112949502 B CN 112949502B CN 202110243530 A CN202110243530 A CN 202110243530A CN 112949502 B CN112949502 B CN 112949502B
- Authority
- CN
- China
- Prior art keywords
- preset
- angle
- horizontal angle
- swimming pool
- maximum
- 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
- 230000009182 swimming Effects 0.000 title claims abstract description 79
- 238000000034 method Methods 0.000 title claims abstract description 61
- 238000001514 detection method Methods 0.000 claims abstract description 24
- 230000008569 process Effects 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 15
- 238000012544 monitoring process Methods 0.000 claims description 15
- 238000004891 communication Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 5
- 230000000694 effects Effects 0.000 abstract description 3
- 230000008901 benefit Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 206010013647 Drowning Diseases 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000009189 diving Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000003340 mental effect Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 208000007101 Muscle Cramp Diseases 0.000 description 1
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000002243 precursor Substances 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000009183 running Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- 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
- G06V40/161—Detection; Localisation; Normalisation
-
- 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
- G08B21/22—Status alarms responsive to presence or absence of persons
Abstract
The application relates to a method, a system, an electronic device and a storage medium for detecting the looking around of a swimming pool security officer, wherein the method comprises the following steps: performing target detection on the images acquired by the camera to obtain face images of the safety personnel, and determining the horizontal angle and the vertical angle of the face of the safety personnel in each face image; according to the horizontal angle and the vertical angle of the face of the safety person in each face image, counting in a preset time period to obtain the maximum horizontal angle and the maximum vertical angle of the face of the safety person; and under the condition that the maximum horizontal angle is smaller than the preset horizontal angle and/or the maximum vertical angle is smaller than the preset vertical angle, determining that the safety officer is in a non-looking-around state currently, and recording a current non-looking-around event. Through this application, can't confirm among the correlation technique whether the security person looks around the swimming pool and whether the problem that the swimming pool security is low that the negligence led to appears has been realized can confirm whether the security person is looking around the swimming pool continuously and then the technological effect of the security of swimming pool is improved.
Description
Technical Field
The application relates to the technical field of video monitoring, in particular to a method, a system, an electronic device and a storage medium for detecting the looking around of a swimming pool security member.
Background
Along with the increasing standard of living of people, more and more people choose to swim in a swimming pool to strengthen the body, however, from related reports, swimming accidents such as drowning, sliding and falling injury and the like are known to be frequent. At present, beginners in indoor swimming pools are often unfamiliar with water, lose body balance in water easily and choke water, and then cause drowning accidents, and some learned swimmers are also very likely to have drowning conditions due to cramps, sudden collision among the swimmers, sudden diseases, mental stress and the like. However, playing, diving, running, diving and other actions are all precursors of accidents, so that when a security person discovers the conditions or takes place, the security person needs to warn or rescue in time.
At present, the early warning of swimming pool accidents is often completed through looking around by a safety person, the safety person monitors the state of the whole swimming pool through a camera on water or a swimmer looking around in a responsibility area on a lookout chair of the swimming pool, and when a suspected drowner is found, the swimming pool is immediately rescued. Such methods are low cost and widely used, however, the security personnel need to maintain concentration for a long time, endure prolonged mental stress, and are prone to work fatigue.
The safety officer is used as a first responsible person for the safety of the swimming pool, and plays a role in pre-judging in advance and giving out a warning before an accident occurs. When a safety person is tired to cause negligence in looking around the swimming pool, or unauthorized guard, fool, mobile phone playing and the like can cause the occurrence frequency of the swimming pool accident to be increased, thereby affecting the safety of the swimmer.
At present, aiming at the problem that whether a safety person looks around a swimming pool or not is negligent, the safety of the swimming pool is low, which is caused by the fact that the related technology cannot be used for determining, no effective solution is proposed.
Disclosure of Invention
The embodiment of the application provides a method, a system, an electronic device and a storage medium for detecting the looking around of a swimming pool safety member, which are used for at least solving the problem that in the related art, whether the safety member looks around the swimming pool or not is negligent, so that the safety of the swimming pool is low.
In a first aspect, an embodiment of the present application provides a method for detecting a swimming pool security member looking around, where at least one camera is disposed in the swimming pool, including: performing target detection on the images acquired by the camera to obtain face images of the safety personnel, and determining the horizontal angle and the vertical angle of the face of the safety personnel in each face image; according to the horizontal angle and the vertical angle of the face of the security personnel in each face image, the maximum horizontal angle and the maximum vertical angle of the face of the security personnel are obtained through statistics in a preset time period; and under the condition that the maximum horizontal angle is smaller than a preset horizontal angle and/or the maximum vertical angle is smaller than a preset vertical angle, determining that the safety officer is in a non-looking-around state currently, and recording a current non-looking-around event.
In some of these embodiments, the method further comprises: and carrying out target detection on the image acquired by the camera, determining that the security personnel is in an off-duty state currently under the condition that the face image of the security personnel and the human body image of the security personnel are not detected within a preset time period, and recording a current off-duty event.
In some of these embodiments, the method further comprises: under the condition that the occurrence times of the non-looking-around events reach a preset threshold value, determining that the safety officer is in a non-looking-around state; under the condition that the occurrence times of off-duty events reach a preset threshold value, determining that the security officer is in an off-duty state; triggering an early warning process under the condition that the safety officer is in an unobscured state or an off-duty state, wherein the early warning process comprises at least one of the following steps: sending reminding information to the safety officer, sending reminding information to the manager, sending early warning voice and sending early warning light.
In some of these embodiments, the maximum horizontal angle comprises a maximum left horizontal angle and a maximum right horizontal angle, and the maximum vertical angle comprises a maximum vertical upward angle and a maximum vertical downward angle; the preset horizontal angle comprises a preset left horizontal angle and a preset right horizontal angle, and the preset vertical angle comprises a preset vertical upward angle and a preset vertical downward angle; in the case that the maximum horizontal angle is smaller than a preset horizontal angle and/or the maximum vertical angle is smaller than a preset vertical angle, determining that the safety officer is currently in an unobscured state includes: and determining that the safety guard is in an unbroken state currently under the condition that the maximum left horizontal angle is smaller than a preset left horizontal angle, the maximum right horizontal angle is smaller than a preset right horizontal angle, the maximum vertical upward angle is smaller than a preset vertical upward angle, or the maximum vertical downward angle is smaller than a preset vertical downward angle.
In some of these embodiments, prior to object detection of the image acquired by the camera, the method further comprises: configuring a plurality of preset points in the video camera, wherein each preset point corresponds to each safety person, and a human body target in a monitoring picture corresponding to each preset point only comprises the safety person corresponding to the preset point; and polling each preset point at preset intervals, and controlling the camera to start image acquisition under the current preset point.
In some embodiments, polling each of the preset points at intervals of a preset time, and controlling the camera to start image acquisition at the current preset point includes: judging whether the current time is in the business time period of the swimming pool or not; and under the condition that the current time is in the business time period of the swimming pool, polling each preset point at intervals of preset time, and controlling the camera to start image acquisition under the current preset point.
In some embodiments, after the maximum horizontal angle and the maximum vertical angle of the face of the security officer are obtained through statistics in a preset time period, the method further comprises: and under the condition that the maximum horizontal angle is larger than a preset horizontal angle and the maximum vertical angle is larger than a preset vertical angle, determining that the safety officer is in a looking-around state currently, and emptying the safety officer from looking-around events.
In a second aspect, an embodiment of the present application provides a system for detecting a swimming pool security person looking around, a camera, configured to acquire a face image and/or a body image of the security person, and perform the method for detecting a swimming pool security person looking around as described in the first aspect above; the edge storage video recorder is in communication connection with the video camera and is used for storing the monitoring image of the security personnel, recording the non-looking-around event and off-duty event of the security personnel, and processing and forwarding the non-looking-around event and the off-duty event of the security personnel; the client is in communication connection with the edge storage video recorder and is used for inquiring and playing back the monitoring image and inquiring the non-looking-around event and off-duty event of the security personnel; and the terminal early warning device is in communication connection with the camera and is used for executing an early warning process.
In a third aspect, embodiments of the present application also provide an electronic device comprising a memory and a processor, the memory having stored therein a computer program, the processor being arranged to run the computer program to perform the method of detecting a swimming pool security officer looking around as described in the first aspect above.
In a fourth aspect, embodiments of the present application further provide a storage medium having a computer program stored therein, where the computer program is configured to perform, when executed, the method for detecting a swimming pool security officer looking around as described in the first aspect above.
Compared with the related art, the method, the system, the electronic device and the storage medium for detecting the looking around of the swimming pool security personnel provided by the embodiment of the application are characterized in that the camera is arranged in the swimming pool to perform target detection on the image acquired by the camera to obtain the face image of the security personnel, the horizontal angle and the vertical angle of the face of the security personnel in each face image are determined, the maximum horizontal angle and the maximum vertical angle of the face of the security personnel are obtained through statistics in a preset time period according to the horizontal angle and the vertical angle of the face of the security personnel in each face image, then the security personnel are determined to be in an unobscured state under the condition that the maximum horizontal angle is smaller than the preset horizontal angle and/or the maximum vertical angle is smaller than the preset vertical angle, and the current unobscured event is recorded, so that the problem that the security personnel have low security of the swimming pool caused by negligence in the prior art can not be determined whether the security personnel look around the swimming pool is continuously is solved, and the technical effect that whether the security personnel can continuously look around the swimming pool is improved is achieved.
The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below to provide a more thorough understanding of the other features, objects, and advantages of the application.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute an undue limitation to the application. In the drawings:
FIG. 1 is a flow chart of a method of detecting a swimming pool security member looking around in accordance with an embodiment of the present application;
FIG. 2 is a flow chart of a method of detecting a swimming pool security member looking around in accordance with a preferred embodiment of the present application;
FIG. 3 is a block diagram of a system for detecting the presence of a swimming pool security member in accordance with an embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described and illustrated below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden on the person of ordinary skill in the art based on the embodiments provided herein, are intended to be within the scope of the present application. Moreover, it should be appreciated that while such a development effort might be complex and lengthy, it would nevertheless be a routine undertaking of design, fabrication, or manufacture for those of ordinary skill having the benefit of this disclosure, and thus should not be construed as having the benefit of this disclosure.
Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is to be expressly and implicitly understood by those of ordinary skill in the art that the embodiments described herein can be combined with other embodiments without conflict.
Unless defined otherwise, technical or scientific terms used herein should be given the ordinary meaning as understood by one of ordinary skill in the art to which this application belongs. Reference to "a," "an," "the," and similar terms herein do not denote a limitation of quantity, but rather denote the singular or plural. The terms "comprising," "including," "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, article, or apparatus that comprises a list of steps or modules (elements) is not limited to only those steps or elements but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus. The terms "connected," "coupled," and the like in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The term "plurality" as used herein means greater than or equal to two. "and/or" describes an association relationship of an association object, meaning that there may be three relationships, e.g., "a and/or B" may mean: a exists alone, A and B exist together, and B exists alone. The terms "first," "second," "third," and the like, as used herein, are merely distinguishing between similar objects and not representing a particular ordering of objects.
The embodiment provides a method for detecting the swimming pool security personnel looking around, fig. 1 is a flowchart of a method for detecting the swimming pool security personnel looking around according to an embodiment of the application, as shown in fig. 1, the method includes:
step S101, performing target detection on the images acquired by the camera to obtain face images of the safety personnel, and determining the horizontal angle and the vertical angle of the face of the safety personnel in each face image.
Step S102, according to the horizontal angle and the vertical angle of the face of the security personnel in each face image, the maximum horizontal angle and the maximum vertical angle of the face of the security personnel are obtained through statistics in a preset time period.
Step S103, under the condition that the maximum horizontal angle is smaller than the preset horizontal angle and/or the maximum vertical angle is smaller than the preset vertical angle, determining that the safety officer is in a non-looking-around state currently, and recording a current non-looking-around event.
In this embodiment, the camera may employ an AI (artificial intelligence, artificial Intelligence, abbreviated as AI) camera for data acquisition and security personnel look-around detection or off-duty detection.
In other embodiments, other cameras may be used.
In some of these embodiments, the method further comprises: and carrying out target detection on the image acquired by the camera, determining that the security personnel is in an off-duty state currently under the condition that the face image of the security personnel and the human body image of the security personnel are not detected within a preset time period, and recording a current off-duty event.
In this embodiment, the camera may call a target detection algorithm, such as an R-CNN (Region-CNN) algorithm or an SSD (Single Shot MultiBox Detector, SSD) algorithm, to detect whether a face target and a human target exist in an image through the target detection algorithm, and at the same time, a unique ID exists for each face of a security person in the image acquired by the camera f Value, facilitate subsequent passing of ID f Value inquiry is carried out on monitoring video, non-looking-around event, off-duty event and the like of the corresponding security personnel.
When the face target and the human body target are not detected within a preset time period, namely, when the face image of the safety person and the human body image of the safety person are not detected, determining that the safety person is in an off-duty state currently, and simultaneously recording a current off-duty event, wherein the number of times of the off-duty warning mark of the safety person is increased by one.
When the face target and the human body target are detected, outputting the current face ID f Wherein the horizontal angle includes a left horizontal angle θ fl And right horizontal angle θ fr The vertical angle includes a vertical upward angle θ fu And a vertical downward angle theta fd 。
The preset time period may be 10 seconds, 5 seconds, etc., which is not limited in this application.
In some of these embodiments, the method further comprises: under the condition that the occurrence times of the non-looking-around events reach a preset threshold value, determining that the security personnel is in a non-looking-around state; under the condition that the occurrence times of off-duty events reach a preset threshold value, determining that the security officer is in an off-duty state; triggering an early warning process under the condition that a safety officer is in an unobscured state or an off-duty state, wherein the early warning process comprises at least one of the following steps: sending reminding information to a safety officer, sending reminding information to a manager, sending early warning voice and sending early warning light.
In this embodiment, the preset threshold may be 5 times, 3 times, etc., which is not limited in this application.
After judging that the safety officer is in an unobscured state or an off-duty state, the early warning process can be triggered by the camera, and the early warning process is executed by the terminal early warning device, for example, the terminal early warning device can comprise mobile equipment such as a mobile phone, an LED (light-emitting diode) display, an acousto-optic warning device and the like, the mobile equipment such as the mobile phone can be preloaded with appointed application software, the functions of remote consulting of early warning, parameter setting of front-end equipment (such as a camera) and the like are realized, the acousto-optic warning device can send early warning voice and early warning light outwards, the terminal early warning device can also send a warning message to the safety officer and a manager, prompt the safety officer to change the duty in time or inform the manager to manage on site in a swimming pool, and the safety of the swimmer in the swimming pool is improved.
In some of these embodiments, the maximum horizontal angle comprises a maximum left horizontal angle and a maximum right horizontal angle, and the maximum vertical angle comprises a maximum vertical upward angle and a maximum vertical downward angle; the preset horizontal angle comprises a preset left horizontal angle and a preset right horizontal angle, and the preset vertical angle comprises a preset vertical upward angle and a preset vertical downward angle; in the case that the maximum horizontal angle is smaller than the preset horizontal angle and/or the maximum vertical angle is smaller than the preset vertical angle, determining that the safety officer is currently in the non-looking around state includes: and determining that the safety guard is in a non-looking-around state currently under the condition that the maximum left horizontal angle is smaller than the preset left horizontal angle, or the maximum right horizontal angle is smaller than the preset right horizontal angle, or the maximum vertical upward angle is smaller than the preset vertical upward angle, or the maximum vertical downward angle is smaller than the preset vertical downward angle.
In this embodiment, when the face target and the human target are detected, the current face ID is output f Wherein the horizontal angle includes a left horizontal angle θ fl And right horizontal angle θ fr The vertical angle includes a vertical upward angle θ fu And a vertical downward angle theta fd After continuously counting the preset time period, the current face ID in the preset time period can be analyzed and obtained f Maximum left horizontal angle θ of (2) flm And maximum rightSide horizontal angle theta frm And a maximum vertical upward angle θ fum And a maximum vertical downward angle θ fdm . The preset time period may be 10 seconds, 20 seconds, 1 minute, etc., which is not limited herein.
The preset horizontal angle comprises a preset left horizontal angle theta lm And a preset right horizontal angle theta rm The preset vertical angle comprises a preset vertical upward angle theta um And a preset vertical downward angle theta dm The preset horizontal angle and the preset vertical angle are preset into the camera when any one of the following occurs: θ flm ＜θ lm ，θ frm ＜θ rm ，θ fum ＜θ um ，θ fdm ＜θ dm And judging that the safety person is in the non-looking-around state currently, and recording the current non-looking-around event, wherein the number of times of the non-looking-around warning mark of the safety person is increased by one.
In this embodiment, after the maximum horizontal angle and the maximum vertical angle of the face of the security personnel are obtained by statistics in the preset time period, the method further includes: and under the condition that the maximum horizontal angle is larger than the preset horizontal angle and the maximum vertical angle is larger than the preset vertical angle, determining that the safety officer is in a looking-around state currently, and emptying the non-looking-around event of the safety officer.
Namely theta flm ＞θ lm ，θ frm ＞θ rm ，θ fum ＞θ um ，θ fdm ＞θ dm When all four conditions are met, determining that the safety person is in the looking-around state currently, and clearing the non-looking-around event of the safety person, wherein the number of times of clearing the non-looking-around warning mark of the safety person is cleared.
In some of these embodiments, prior to object detection of the image acquired by the camera, the method further comprises: configuring a plurality of preset points in the video camera, wherein each preset point corresponds to each safety person, and the human body target in the monitoring picture corresponding to the preset point only comprises the safety person corresponding to the preset point; each preset point is polled at intervals of preset time, and the camera is controlled to start image acquisition under the current preset point.
In this embodiment, a plurality of preset points are further configured in the camera, the preset points are in one-to-one correspondence with all the security personnel in the swimming pool, only one human body target corresponding to the security personnel in the monitoring picture of each preset point is ensured, the target detection in the monitoring picture is ensured not to be affected by other targets, and meanwhile, the preset horizontal angle and the preset vertical angle of the human face when the security personnel corresponding to each preset point look around the whole swimming pool are required to be configured in the camera.
In this embodiment, it is also necessary to determine whether the current time is within the business time period of the swimming pool; under the condition that the current time is in the business time period of the swimming pool, each preset point is polled at intervals of preset time, the camera is controlled to start to acquire images under the current preset point, and in the non-business time period, the camera is in a low-power consumption mode, so that energy is saved.
Through the steps S101 to S103, the camera is set in the swimming pool, the image acquired by the camera is subjected to target detection to obtain the face image of the safety person, the horizontal angle and the vertical angle of the face of the safety person in each face image are determined, the maximum horizontal angle and the maximum vertical angle of the face of the safety person are obtained through statistics in a preset time period according to the horizontal angle and the vertical angle of the face of the safety person in each face image, then the safety person is determined to be in an unobserved state under the condition that the maximum horizontal angle is smaller than the preset horizontal angle and/or the maximum vertical angle is smaller than the preset vertical angle, the current unobserved event is recorded, the safety person is reminded to timely change the post or inform the management person to the scene of the swimming pool, the safety of the swimming person in the swimming pool is improved, the problem that the safety of the swimming pool is low due to the fact that whether the safety person is negligence occurs in the surrounding of the swimming pool cannot be determined in the related technology is solved, and the technical effect that whether the safety person can continuously look around the swimming pool is further improved is achieved.
Fig. 2 is a flow chart of a method of detecting a swimming pool security member looking around in accordance with a preferred embodiment of the present application, as shown in fig. 2, in one embodiment the method comprises:
in step S201, a plurality of preset points are configured in the camera, each preset point corresponds to each security person, and the human body target in the monitoring picture corresponding to the preset point only includes the security person corresponding to the preset point.
Step S202, under each preset point, configuring a preset horizontal angle and a preset vertical angle of a human face when a safety person corresponding to each preset point looks around the whole swimming pool in a camera, wherein the preset horizontal angle comprises a preset left horizontal angle theta lm And a preset right horizontal angle theta rm The preset vertical angle comprises a preset vertical upward angle theta um And a preset vertical downward angle theta dm 。
Step S203, judging whether the current time is in the business time period of the swimming pool.
Step S204, when the current time is within the business time of the swimming pool, polling each preset point at intervals of preset time, and controlling the camera to start image acquisition and target detection under the current preset point.
Step S205, judging whether the human face target and the human body target can be detected within a preset time period.
Step S206, under the condition that the face image of the security personnel and the human body image of the security personnel are not detected within a preset time period, determining that the security personnel are in an off-duty state currently, and recording a current off-duty event.
Step S207, when the face target and the human body target are detected, outputting the current face ID f And clear the security guard of off duty events, wherein the horizontal angle includes a left horizontal angle θ fl And right horizontal angle θ fr The vertical angle includes a vertical upward angle θ fu And a vertical downward angle theta fd 。
Step S208, after continuously counting the preset time period, analyzing and obtaining the current face ID in the preset time period f Maximum left horizontal angle θ of (2) flm And a maximum right horizontal angle θ frm And a maximum vertical upward angle θ fum And a maximum vertical downward angle θ fdm 。
Step S209, when any one of the following occurs: θ flm ＜θ lm ，θ frm ＜θ rm ，θ fum ＜θ um ，θ fdm ＜θ dm JudgingAnd when the safety is in the non-looking around state, recording the current non-looking around event, adding one to the number of times of the non-looking around warning mark of the safety, otherwise, emptying the non-looking around event of the safety.
Step S210, judging whether the non-looking-around event of the security personnel reaches a preset threshold value.
Step S211, judging whether the off-duty event of the security personnel reaches a preset threshold.
Step S212, triggering an early warning process under the condition that the non-looking-around event or the off-duty event reaches a preset threshold, wherein the early warning process comprises at least one of the following steps: sending reminding information to a safety officer, sending reminding information to a manager, sending early warning voice and sending early warning light.
It should be noted that, specific examples in this embodiment may refer to examples described in the foregoing embodiments and alternative implementations, and this embodiment is not repeated herein.
The present embodiment provides a system for detecting a swimming pool security member looking around, and fig. 3 is a block diagram of a system for detecting a swimming pool security member looking around according to an embodiment of the present application, as shown in fig. 3, and the system includes: a camera 30 for acquiring a face image and/or a body image of a security person and performing the inspection detection method of the swimming pool security person according to the above-described embodiment; an edge storage video recorder 31, which is in communication connection with the video camera 30, and is used for storing the monitoring image of the security officer, recording the non-patrol event and the off-duty event of the security officer, and processing and forwarding the non-patrol event and the off-duty event of the security officer; a client 32, communicatively connected to the edge storage video recorder 31, for querying and playing back the monitoring image, and querying the security personnel for non-patrol events and off-duty events; the terminal early warning device 33 is connected to the camera 30 in a communication manner, and is used for executing an early warning process.
In some embodiments, the camera 30 is configured to perform target detection on the images acquired by the camera 30, obtain face images of the security personnel, and determine a horizontal angle and a vertical angle of the face of the security personnel in each face image; according to the horizontal angle and the vertical angle of the face of the safety person in each face image, counting in a preset time period to obtain the maximum horizontal angle and the maximum vertical angle of the face of the safety person; and under the condition that the maximum horizontal angle is smaller than the preset horizontal angle and/or the maximum vertical angle is smaller than the preset vertical angle, determining that the safety officer is in a non-patrol state currently, and recording a current non-patrol event.
In some of these embodiments, the camera 30 is configured to perform object detection on images acquired by the camera 30, determine that the security officer is currently off duty if no face image of the security officer or no body image of the security officer is detected within a preset period of time, and record a current off duty event.
In some of these embodiments, the camera 30 is configured to determine that the security officer is in the non-patrol state if the number of non-patrol event occurrences reaches a preset threshold; under the condition that the occurrence times of off-duty events reach a preset threshold value, determining that the security officer is in an off-duty state; triggering an early warning process under the condition that the security officer is in an unobserved state or an off-duty state, wherein the early warning process comprises at least one of the following steps: sending reminding information to a safety officer, sending reminding information to a manager, sending early warning voice and sending early warning light.
In some of these embodiments, the maximum horizontal angle comprises a maximum left horizontal angle and a maximum right horizontal angle, and the maximum vertical angle comprises a maximum vertical upward angle and a maximum vertical downward angle; the preset horizontal angle comprises a preset left horizontal angle and a preset right horizontal angle, and the preset vertical angle comprises a preset vertical upward angle and a preset vertical downward angle; the camera 30 is configured to determine that the security officer is currently in an unverified state in the event that the maximum left horizontal angle is less than the preset left horizontal angle, or the maximum right horizontal angle is less than the preset right horizontal angle, or the maximum vertical upward angle is less than the preset vertical upward angle, or the maximum vertical downward angle is less than the preset vertical downward angle.
In some embodiments, the camera 30 is configured to configure a plurality of preset points in the camera 30, each preset point corresponding to each security officer, and the human target in the monitoring screen corresponding to the preset point includes only the security officer corresponding to the preset point; each preset point is polled at preset intervals to control the camera 30 to begin image acquisition at the current preset point.
In some of these embodiments, the camera 30 is configured to determine if the current time is within a swimming pool operating period; in the case where the current time is within the operating period of the swimming pool, each preset point is polled at intervals of preset time, and the camera 30 is controlled to start image acquisition at the current preset point.
In some of these embodiments, camera 30 is configured to determine that the security officer is currently in a looking-around state and clear the security officer of non-looking-around events if the maximum horizontal angle is greater than the preset horizontal angle and the maximum vertical angle is greater than the preset vertical angle.
It should be noted that, specific examples in this embodiment may refer to examples described in the foregoing embodiments and alternative implementations, and this embodiment is not repeated herein.
The present embodiment also provides an electronic device, fig. 4 is a schematic diagram of a hardware structure of the electronic device according to the embodiment of the present application, and as shown in fig. 4, the electronic device includes a memory 404 and a processor 402, where the memory 404 stores a computer program, and the processor 402 is configured to execute the computer program to perform the steps in any one of the method embodiments described above.
In particular, the processor 402 may include a Central Processing Unit (CPU), or an application specific integrated circuit (Application Specific Integrated Circuit, abbreviated as ASIC), or may be configured to implement one or more integrated circuits of embodiments of the present application.
Memory 404 may include, among other things, mass storage for data or instructions. By way of example, and not limitation, memory 404 may comprise a Hard Disk Drive (HDD), floppy Disk Drive, solid state Drive (Solid State Drive, SSD), flash memory, optical Disk, magneto-optical Disk, tape, or universal serial bus (Universal Serial Bus, USB) Drive, or a combination of two or more of the foregoing. Memory 404 may include removable or non-removable (or fixed) media, where appropriate. Memory 404 may be internal or external to the data processing apparatus, where appropriate. In a particular embodiment, the memory 404 is a Non-Volatile (Non-Volatile) memory. In a particular embodiment, the Memory 404 includes Read-Only Memory (ROM) and random access Memory (Random Access Memory, RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (Programmable Read-Only Memory, abbreviated PROM), an erasable PROM (Erasable Programmable Read-Only Memory, abbreviated EPROM), an electrically erasable PROM (Electrically Erasable Programmable Read-Only Memory, abbreviated EEPROM), an electrically rewritable ROM (Electrically Alterable Read-Only Memory, abbreviated EAROM), or a FLASH Memory (FLASH), or a combination of two or more of these. The RAM may be Static Random-Access Memory (SRAM) or dynamic Random-Access Memory (Dynamic Random Access Memory DRAM), where the DRAM may be a fast page mode dynamic Random-Access Memory (Fast Page Mode Dynamic Random Access Memory FPMDRAM), extended data output dynamic Random-Access Memory (Extended Date Out Dynamic Random Access Memory EDODRAM), synchronous dynamic Random-Access Memory (Synchronous Dynamic Random-Access Memory SDRAM), or the like, as appropriate.
Memory 404 may be used to store or cache various data files that need to be processed and/or used for communication, as well as possible computer program instructions for execution by processor 402.
The processor 402 implements any of the above-described embodiments of the method for detecting a swimming pool security member looking around by reading and executing computer program instructions stored in the memory 404.
Optionally, the electronic apparatus may further include a transmission device 406 and an input/output device 408, where the transmission device 406 is connected to the processor 402 and the input/output device 408 is connected to the processor 402.
Alternatively, in this embodiment, the processor 502 may be configured to execute the following steps by a computer program:
s1, performing target detection on images acquired by a camera to obtain face images of the safety personnel, and determining the horizontal angle and the vertical angle of the face of the safety personnel in each face image.
S2, counting according to the horizontal angle and the vertical angle of the face of the security personnel in each face image, and obtaining the maximum horizontal angle and the maximum vertical angle of the face of the security personnel in a preset time period.
And S3, determining that the safety officer is in a non-patrol state currently and recording a current non-patrol event under the condition that the maximum horizontal angle is smaller than a preset horizontal angle and/or the maximum vertical angle is smaller than a preset vertical angle.
It should be noted that, specific examples in this embodiment may refer to examples described in the foregoing embodiments and alternative implementations, and this embodiment is not repeated herein.
In addition, in combination with the method for detecting the swimming pool security personnel in the above embodiment, the embodiments of the present application may provide a storage medium for implementation. The storage medium has a computer program stored thereon; the computer program, when executed by a processor, implements the look-around detection method of any of the swimming pool security personnel of the above embodiments.
It should be understood by those skilled in the art that the technical features of the above embodiments may be combined in any manner, and for brevity, all of the possible combinations of the technical features of the above embodiments are not described, however, they should be considered as being within the scope of the description provided herein, as long as there is no contradiction between the combinations of the technical features.
The foregoing examples merely represent several embodiments of the present application, the description of which is more specific and detailed and which should not be construed as limiting the scope of the present application in any way. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.
Claims (9)
1. A method for detecting the presence of a swimming pool security officer, wherein at least one camera is disposed in the swimming pool, the method comprising:
performing target detection on the images acquired by the camera to obtain face images of the safety personnel, and determining the horizontal angle and the vertical angle of the face of the safety personnel in each face image;
according to the horizontal angle and the vertical angle of the face of the security personnel in each face image, the maximum horizontal angle and the maximum vertical angle of the face of the security personnel are obtained through statistics in a preset time period;
determining that the safety officer is in a non-looking-around state currently and recording a current non-looking-around event under the condition that the maximum horizontal angle is smaller than a preset horizontal angle and/or the maximum vertical angle is smaller than a preset vertical angle;
the maximum horizontal angle comprises a maximum left horizontal angle and a maximum right horizontal angle, and the maximum vertical angle comprises a maximum vertical upward angle and a maximum vertical downward angle; the preset horizontal angle comprises a preset left horizontal angle and a preset right horizontal angle, and the preset vertical angle comprises a preset vertical upward angle and a preset vertical downward angle; in the case that the maximum horizontal angle is smaller than a preset horizontal angle and/or the maximum vertical angle is smaller than a preset vertical angle, determining that the safety officer is currently in an unobscured state includes:
and determining that the safety guard is in an unbroken state currently under the condition that the maximum left horizontal angle is smaller than a preset left horizontal angle, the maximum right horizontal angle is smaller than a preset right horizontal angle, the maximum vertical upward angle is smaller than a preset vertical upward angle, or the maximum vertical downward angle is smaller than a preset vertical downward angle.
2. A method of detecting a swimming pool security member looking around as in claim 1, further comprising:
and carrying out target detection on the image acquired by the camera, determining that the security personnel is in an off-duty state currently under the condition that the face image of the security personnel and the human body image of the security personnel are not detected within a preset time period, and recording a current off-duty event.
3. A method of detecting a swimming pool security member looking around as in claim 2, further comprising:
under the condition that the occurrence times of the non-looking-around events reach a preset threshold value, determining that the safety officer is in a non-looking-around state;
under the condition that the occurrence times of off-duty events reach a preset threshold value, determining that the security officer is in an off-duty state;
triggering an early warning process under the condition that the safety officer is in an unobscured state or an off-duty state, wherein the early warning process comprises at least one of the following steps: sending reminding information to the safety officer, sending reminding information to the manager, sending early warning voice and sending early warning light.
4. A method for detecting the presence of a swimming pool security member according to claim 1, wherein, before the target detection of the image acquired by the camera, the method further comprises:
configuring a plurality of preset points in the video camera, wherein each preset point corresponds to each safety person, and a human body target in a monitoring picture corresponding to each preset point only comprises the safety person corresponding to the preset point;
and polling each preset point at preset intervals, and controlling the camera to start image acquisition under the current preset point.
5. A method of detecting a swimming pool security member looking around as in claim 4, wherein polling each of the presets at intervals of a preset time, controlling the camera to begin image acquisition at the current preset point comprises:
judging whether the current time is in the business time period of the swimming pool or not;
and under the condition that the current time is in the business time period of the swimming pool, polling each preset point at intervals of preset time, and controlling the camera to start image acquisition under the current preset point.
6. A swimming pool security guard's look-around detection method as recited in claim 1, wherein after statistically obtaining the maximum horizontal angle and the maximum vertical angle of the security guard's face within a preset period of time, the method further comprises:
and under the condition that the maximum horizontal angle is larger than a preset horizontal angle and the maximum vertical angle is larger than a preset vertical angle, determining that the safety officer is in a looking-around state currently, and emptying the safety officer from looking-around events.
7. A system for detecting the presence of a swimming pool security member, said system comprising:
a camera for acquiring a face image and/or a body image of a security person and performing the method for detecting the look-around of a swimming pool security person according to any one of claims 1 to 6;
the edge storage video recorder is in communication connection with the video camera and is used for storing the monitoring image of the security personnel, recording the non-looking-around event and off-duty event of the security personnel, and processing and forwarding the non-looking-around event and the off-duty event of the security personnel;
the client is in communication connection with the edge storage video recorder and is used for inquiring and playing back the monitoring image and inquiring the non-looking-around event and off-duty event of the security personnel;
and the terminal early warning device is in communication connection with the camera and is used for executing an early warning process.
8. An electronic device comprising a memory and a processor, wherein the memory has stored therein a computer program, the processor being arranged to run the computer program to perform the method of detecting a swimming pool security officer's look around as claimed in any one of claims 1 to 6.
9. A storage medium having stored therein a computer program, wherein the computer program is arranged to perform the method of detecting a swimming pool security officer's look around as claimed in any one of claims 1 to 6 when run.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110243530.9A CN112949502B (en) | 2021-03-05 | 2021-03-05 | Method, system and electronic device for detecting swimming pool safety officer looking around |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110243530.9A CN112949502B (en) | 2021-03-05 | 2021-03-05 | Method, system and electronic device for detecting swimming pool safety officer looking around |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112949502A CN112949502A (en) | 2021-06-11 |
| CN112949502B true CN112949502B (en) | 2024-03-29 |
Family
ID=76247807
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110243530.9A Active CN112949502B (en) | 2021-03-05 | 2021-03-05 | Method, system and electronic device for detecting swimming pool safety officer looking around |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112949502B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107888875A (en) * | 2017-11-07 | 2018-04-06 | 国网重庆市电力公司江津供电分公司 | Transformer station's ground safety managing and control system and method based on mobile detection |
| JP2019506817A (en) * | 2015-11-24 | 2019-03-07 | コーニンクレッカ フィリップス エヌ ヴェＫｏｎｉｎｋｌｉｊｋｅ Ｐｈｉｌｉｐｓ Ｎ．Ｖ． | Processing multiple HDR image sources |
| CN109902669A (en) * | 2019-04-19 | 2019-06-18 | 田鸣鸣 | Artificial intelligence based on image recognition anti-drowned early warning system, device and method |
| CN209328184U (en) * | 2019-01-29 | 2019-08-30 | 李淇 | A kind of swimming pool anti-drowning artificial intelligence prior-warning device based on image recognition technology |
| KR102065516B1 (en) * | 2018-10-18 | 2020-01-13 | 조선대학교산학협력단 | Safety monitoring system using underwater camera |
| CN112001230A (en) * | 2020-07-09 | 2020-11-27 | 浙江大华技术股份有限公司 | Sleeping behavior monitoring method and device, computer equipment and readable storage medium |
-
2021
- 2021-03-05 CN CN202110243530.9A patent/CN112949502B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2019506817A (en) * | 2015-11-24 | 2019-03-07 | コーニンクレッカ フィリップス エヌ ヴェＫｏｎｉｎｋｌｉｊｋｅ Ｐｈｉｌｉｐｓ Ｎ．Ｖ． | Processing multiple HDR image sources |
| CN107888875A (en) * | 2017-11-07 | 2018-04-06 | 国网重庆市电力公司江津供电分公司 | Transformer station's ground safety managing and control system and method based on mobile detection |
| KR102065516B1 (en) * | 2018-10-18 | 2020-01-13 | 조선대학교산학협력단 | Safety monitoring system using underwater camera |
| CN209328184U (en) * | 2019-01-29 | 2019-08-30 | 李淇 | A kind of swimming pool anti-drowning artificial intelligence prior-warning device based on image recognition technology |
| CN109902669A (en) * | 2019-04-19 | 2019-06-18 | 田鸣鸣 | Artificial intelligence based on image recognition anti-drowned early warning system, device and method |
| CN112001230A (en) * | 2020-07-09 | 2020-11-27 | 浙江大华技术股份有限公司 | Sleeping behavior monitoring method and device, computer equipment and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112949502A (en) | 2021-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109166261B (en) | Image processing method, device and equipment based on image recognition and storage medium | |
| KR101825045B1 (en) | Alarm method and device | |
| CN108965826B (en) | Monitoring method, monitoring device, processing equipment and storage medium | |
| CN111083435A (en) | Security monitoring method and device and computer readable storage medium | |
| JP2006011728A (en) | Suspicious person countermeasure system and suspicious person detection device | |
| CN107977638B (en) | Video monitoring alarm method, device, computer equipment and storage medium | |
| CN116743970B (en) | Intelligent management platform with video AI early warning analysis | |
| JP5388829B2 (en) | Intruder detection device | |
| Khawandi et al. | Implementation of a monitoring system for fall detection in elderly healthcare | |
| CN107730841B (en) | Alarm processing method and related product | |
| CN113011833A (en) | Safety management method and device for construction site, computer equipment and storage medium | |
| CN111401239B (en) | Video analysis method, device, system, equipment and storage medium | |
| CN110688931A (en) | Abnormal behavior monitoring method and device, storage medium and electronic equipment | |
| CN112949502B (en) | Method, system and electronic device for detecting swimming pool safety officer looking around | |
| CN107452027A (en) | A kind of target person method for security protection based on multi-cam monitoring | |
| CN111228706A (en) | GIS-based building interior fire fighting equipment control method and device | |
| JP2008236729A (en) | Method and apparatus for generating digest | |
| US9805272B1 (en) | Storage system of original frame of monitor data and storage method thereof | |
| CN112995763B (en) | Control method of intelligent monitoring system, 5G television, system and storage medium | |
| CN113421431B (en) | Emergency channel monitoring method and device | |
| CN114973326A (en) | Fall early warning method, device, equipment and readable storage medium | |
| US10748397B2 (en) | Monitoring system | |
| CN111126100B (en) | Alarm method, alarm device, electronic equipment and storage medium | |
| JP6833556B2 (en) | Monitoring equipment, monitoring systems, monitoring methods, and programs | |
| CN111355932A (en) | Monitoring method and device, household equipment, storage medium and electronic equipment |
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 |