CN116246417A - Drowning prevention alarm method, device, equipment and storage medium - Google Patents
Drowning prevention alarm method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN116246417A CN116246417A CN202111487892.9A CN202111487892A CN116246417A CN 116246417 A CN116246417 A CN 116246417A CN 202111487892 A CN202111487892 A CN 202111487892A CN 116246417 A CN116246417 A CN 116246417A
- Authority
- CN
- China
- Prior art keywords
- water area
- human body
- area
- alarm
- frame
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 206010013647 Drowning Diseases 0.000 title claims abstract description 155
- 238000000034 method Methods 0.000 title claims abstract description 76
- 230000002265 prevention Effects 0.000 title claims abstract description 47
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 328
- 238000001514 detection method Methods 0.000 claims abstract description 125
- 238000012544 monitoring process Methods 0.000 claims abstract description 36
- 230000001960 triggered effect Effects 0.000 claims abstract description 12
- 238000013459 approach Methods 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 6
- 230000003405 preventing effect Effects 0.000 claims description 4
- 230000008859 change Effects 0.000 description 22
- 238000003709 image segmentation Methods 0.000 description 21
- 230000006399 behavior Effects 0.000 description 9
- 230000009471 action Effects 0.000 description 8
- 231100001261 hazardous Toxicity 0.000 description 7
- 239000003643 water by type Substances 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000001788 irregular Effects 0.000 description 2
- 241000251468 Actinopterygii Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/0202—Child monitoring systems using a transmitter-receiver system carried by the parent and the child
- G08B21/0205—Specific application combined with child monitoring using a transmitter-receiver system
- G08B21/0208—Combination with audio or video communication, e.g. combination with "baby phone" function
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/0202—Child monitoring systems using a transmitter-receiver system carried by the parent and the child
- G08B21/0261—System arrangements wherein the object is to detect trespassing over a fixed physical boundary, e.g. the end of a garden
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/08—Alarms for ensuring the safety of persons responsive to the presence of persons in a body of water, e.g. a swimming pool; responsive to an abnormal condition of a body of water
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A50/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE in human health protection, e.g. against extreme weather
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Child & Adolescent Psychology (AREA)
- General Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Emergency Alarm Devices (AREA)
Abstract
The invention discloses a drowning prevention alarm method, a device, equipment and a storage medium, belonging to the technical field of computers, wherein the method comprises the following steps: monitoring a preset area to obtain a video picture; identifying a water area from the video picture, and generating a corresponding water area frame according to the outline of the water area; when a human body appears in the video picture, a human body detection frame is generated according to the human body position corresponding to the human body; when an intersection exists between the human body detection frame and the water area frame, an alarm prompt is triggered. According to the scheme, the water area frame and the human body detection frame are determined according to the video pictures monitored in real time, a person is judged to be close to a dangerous water area under the condition that the two have an intersection, and an alarm prompt is triggered, so that drowning alarm is timely prevented when drowning danger possibly exists, the probability that the person enters the dangerous water area can be reduced, and a drowning event is avoided.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a drowning prevention alarm method, apparatus, device, and storage medium.
Background
In recent years, students often have drowned in the summer holidays. The occurrence of such events is likely to be the occurrence of tragedy caused by untimely rescue due to lack of a drowning prevention alarm mechanism because no caretaker or life-saving equipment is arranged at the water area side.
The foregoing is provided merely for the purpose of facilitating understanding of the technical solutions of the present invention and is not intended to represent an admission that the foregoing is prior art.
Disclosure of Invention
The invention mainly aims to provide a drowning prevention alarm method, a device, equipment and a storage medium, which aim to solve the technical problem of timely performing drowning prevention alarm when drowning danger possibly exists and avoid drowning events.
In order to achieve the above object, the present invention provides a drowning prevention alarm method, which includes:
monitoring a preset area to obtain a video picture;
identifying a water area from the video picture, and generating a corresponding water area frame according to the outline of the water area;
when a human body appears in the video picture, a human body detection frame is generated according to the human body position corresponding to the human body;
when an intersection exists between the human body detection frame and the water area frame, an alarm prompt is triggered.
Optionally, when there is an intersection between the human body detection frame and the water area frame, triggering an alarm prompt, including:
when an intersection exceeding a preset number of pixels exists between the human body detection frame and the water area frame, judging that a person approaches the water area;
when a person approaches a water area, acquiring warning prompt information and alarm information;
and sending out an alarm to the human body according to the alarm prompt information, and giving an alarm to a monitoring room according to the alarm information.
Optionally, when there is an intersection between the human body detection frame and the water area frame, after triggering the alarm prompt, the method further includes:
and stopping alarming prompt when no intersection exists between the human body detection frame and the water area frame.
Optionally, when there is an intersection between the human body detection frame and the water area frame, after triggering the alarm prompt, the method further includes:
detecting the intersection area between the human body detection frame and the water area frame when the intersection time between the human body detection frame and the water area frame exceeds the preset time;
judging whether a person enters a water area according to the intersection area;
When a person enters a water area, throwing the life-saving equipment to the person.
Optionally, the determining whether a person enters the water area according to the intersection area includes:
acquiring the detection frame area of the human body detection frame;
and judging whether a person enters the water area according to the intersection area and the detection frame area.
Optionally, the determining whether a person enters the water area according to the intersection area and the detection frame area includes:
calculating the area to be compared according to the area of the detection frame and a preset percentage value;
comparing the intersection area with the area to be compared;
and judging whether a person enters the water area according to the comparison result.
Optionally, after judging whether a person enters the water area according to the comparison result, the method further includes:
and when the comparison result shows that the intersection area exceeds the area to be compared, judging that a person enters the water area.
Optionally, when a person enters the water area, throwing the life-saving equipment to the person, including:
detecting action information of a human body when the human body enters a water area;
judging whether the human body has drowning behavior according to the action information;
When the human body has drowning behavior, throwing the life-saving equipment to the human body according to the position of the human body.
Optionally, the throwing the life saving device to the human body according to the human body position includes:
acquiring device positions of a plurality of throwing devices;
calculating the position distance between the human body position and each equipment position;
selecting a target throwing device from a plurality of throwing devices according to the position distance;
and throwing the life saving equipment to the human body through the target throwing equipment according to the human body position.
Optionally, the throwing the life saving device to the human body through the target throwing device according to the human body position includes:
determining the position and distance of the human body relative to the target throwing device according to the human body position and the target device position of the target throwing device;
and controlling the target throwing device to throw the life-saving device to the human body according to the azimuth and the distance.
Optionally, the controlling the target throwing apparatus to throw the life saving apparatus to the human body according to the azimuth and the distance includes:
determining a throwing direction according to the azimuth, and determining throwing force according to the distance;
Generating a throwing instruction according to the throwing direction and the throwing force;
and controlling the target throwing device to throw the life-saving device to the human body according to the throwing instruction.
Optionally, the identifying the water area from the video picture, and generating a corresponding water area frame according to the outline of the water area, includes:
identifying a water area from the video picture;
when the water area is a dangerous water area, image segmentation is carried out according to the outline of the water area;
and generating a water area frame corresponding to the water area according to the image segmentation result.
Optionally, the identifying a water area from the video frame includes:
detecting the change degree of the video picture;
and when the change degree exceeds the preset change degree, identifying a water area from the video picture.
Optionally, the image segmentation according to the contour of the water area includes:
performing scene recognition on the video picture, and respectively distributing corresponding category labels for each element in the video picture;
performing scene annotation on the video picture according to the category label;
determining the outline of the water area in the video picture according to the scene annotation result;
And image segmentation is carried out according to the outline of the water area.
In addition, in order to achieve the above object, the present invention also provides an anti-drowning alarm device, which includes:
the area detection module is used for monitoring a preset area to obtain a video picture;
the water area identification module is used for identifying a water area from the video picture and generating a corresponding water area frame according to the outline of the water area;
the human body identification module is used for generating a human body detection frame according to the human body position corresponding to the human body when the human body appears in the video picture;
and the alarm prompt module is used for triggering alarm prompt when an intersection exists between the human body detection frame and the water area frame.
Optionally, the alarm prompting module is further configured to determine that a person approaches a water area when an intersection of more than a preset number of pixels exists between the human body detection frame and the water area frame; when a person approaches a water area, acquiring warning prompt information and alarm information; and sending out an alarm to the human body according to the alarm prompt information, and giving an alarm to a monitoring room according to the alarm information.
Optionally, the alarm prompting module is further configured to stop alarm prompting when there is no intersection between the human body detection frame and the water area frame.
Optionally, the anti-drowning alarm device further comprises:
the equipment control module is used for detecting the intersection area between the human body detection frame and the water area frame when the intersection time between the human body detection frame and the water area frame exceeds the preset time; judging whether a person enters a water area according to the intersection area; when a person enters a water area, throwing the life-saving equipment to the person.
In addition, in order to achieve the above object, the present invention also provides a drowning prevention alarm device, which includes: the anti-drowning alarm system comprises a memory, a processor and an anti-drowning alarm program which is stored in the memory and can run on the processor, wherein the anti-drowning alarm method is realized when the anti-drowning alarm program is executed by the processor.
In addition, in order to achieve the above object, the present invention also provides a storage medium, on which a drowning prevention alarm program is stored, which when executed by a processor, implements the drowning prevention alarm method as described above.
In the drowning prevention alarm method provided by the invention, a preset area is monitored to obtain a video picture; identifying a water area from the video picture, and generating a corresponding water area frame according to the outline of the water area; when a human body appears in the video picture, a human body detection frame is generated according to the human body position corresponding to the human body; when an intersection exists between the human body detection frame and the water area frame, an alarm prompt is triggered. According to the scheme, the water area frame and the human body detection frame are determined according to the video pictures monitored in real time, a person is judged to be close to a dangerous water area under the condition that the two have an intersection, and an alarm prompt is triggered, so that drowning alarm is timely prevented when drowning danger possibly exists, the probability that the person enters the dangerous water area can be reduced, and a drowning event is avoided.
Drawings
FIG. 1 is a schematic diagram of a drowning prevention alarm device in a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a flow chart of a first embodiment of the anti-drowning alarm method of the present invention;
FIG. 3 is a schematic diagram showing a setting position of an image capturing apparatus according to an embodiment of the drowning prevention alarm method of the present invention;
FIG. 4 is a schematic view of a circular water area frame according to an embodiment of the anti-drowning alarm method of the present invention;
FIG. 5 is a schematic view of an elliptical water area frame according to an embodiment of the anti-drowning method of the present invention;
FIG. 6 is a schematic view of an irregular-shaped water area according to an embodiment of the anti-drowning alarm method of the present invention;
FIG. 7 is a flow chart of a second embodiment of the anti-drowning alarm method of the present invention;
FIG. 8 is a flow chart of a third embodiment of the anti-drowning alarm method of the present invention;
FIG. 9 is a flow chart of an intelligent water area monitoring anti-drowning alarm system according to an embodiment of the anti-drowning alarm method of the present invention;
fig. 10 is a schematic diagram of functional modules of a first embodiment of the drowning prevention alarm device of the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a drowning prevention alarm device in a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 1, the anti-drowning alarm device may include: a processor 1001, such as a central processing unit (Central Processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, a memory 1005. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as keys, and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., wi-Fi interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
It will be appreciated by those skilled in the art that the arrangement of the apparatus shown in fig. 1 is not limiting of the anti-drowning alarm device and may include more or fewer components than shown, or may combine certain components, or a different arrangement of components.
As shown in fig. 1, an operating system, a network communication module, a user interface module, and a drowning prevention alarm program may be included in the memory 1005 as one type of storage medium.
In the anti-drowning alarm device shown in fig. 1, the network interface 1004 is mainly used for connecting to an external network and performing data communication with other network devices; the user interface 1003 is mainly used for connecting user equipment and communicating data with the user equipment; the device invokes the anti-drowning alarm program stored in the memory 1005 through the processor 1001 and executes the anti-drowning alarm method provided by the embodiment of the invention.
Based on the hardware structure, the embodiment of the drowning prevention alarm method is provided.
Referring to fig. 2, fig. 2 is a schematic flow chart of a first embodiment of the drowning prevention alarm method according to the present invention.
In a first embodiment, the anti-drowning alarm method includes:
step S10, monitoring a preset area to obtain a video picture.
It should be noted that, the execution body of the embodiment may be a drowning prevention alarm device, and the drowning prevention alarm device may be a computer device with a data processing function, or may be other devices that may implement the same or similar functions, which is not limited in this embodiment, and in this embodiment, a computer device is taken as an example for explanation.
The preset area refers to an area that needs to be monitored and may have a risk of drowning, for example, an area near a lake in a park, an area near a pool in a district, an area near a river in a river bank, and the like, and may be other types of areas having a risk of drowning, which is not limited in this embodiment.
It should be understood that, in this solution, the image capturing device may perform real-time detection on the preset area to obtain a video image corresponding to the preset area, where the image capturing device may be a camera integrated on the computer device, or may be an independent image capturing device, and after the video image is monitored, the video image is transmitted to the computer device by a wired or wireless transmission manner, that is, the image capturing module and the processing module may be integrated or may be separate, which is not limited in this embodiment. The image capturing apparatus may include, but is not limited to, a video camera, a monitoring camera, an intelligent camera, and other types of apparatuses with image capturing function, which is not limited in this embodiment.
In a specific implementation, for example, taking a park scene as an example, because the scenery close to the lake side in the park is good, many adults or children like to walk and play on the lake side, however, the lake side may have a risk of drowning, especially if the children playing alone carelessly fall into the lake, there is a high risk of drowning, and safety accidents occur. Therefore, according to the scene, the camera can be arranged at a proper position, the camera is aligned to the area close to the lake side in the park, and the area is monitored in real time through the camera, so that a video picture corresponding to the area can be obtained in real time.
Referring to fig. 3, fig. 3 is a schematic diagram of a setting position of an image capturing device, if a region in a park near a lake is required to be monitored for preventing drowning, the region in the park near the lake may be used as a preset region, and an image capturing device a is set at a suitable position in the park, and the preset region is monitored in real time by the image capturing device a, so as to obtain a video picture corresponding to the preset region.
And step S20, identifying a water area from the video picture, and generating a corresponding water area frame according to the outline of the water area.
It should be understood that, in the existing intrusion alarm system for dangerous areas, whether a human body appears in a picture or not is judged, or an intersection with a designated rectangular area is judged, and a water area is an irregular area, so that a person cannot be said to be close to the rectangular area, and then the person is indicated to be close to the water area, so that certain false alarm and false alarm are caused.
Therefore, in order to avoid the situation of false alarm and missing alarm, the accuracy and timeliness of the drowning prevention alarm are improved.
It should be noted that, unlike the prior art, the present solution is to generate a corresponding water area frame according to the contour of the water area after identifying the water area from the video image, that is, what shape the contour of the water area in the video image is, what shape the generated water area frame is, and the shape of the water area frame is consistent with the contour shape of the water area. For example, reference may be made to fig. 4, 5 and 6, wherein fig. 4 is a schematic view of a circular water area, fig. 5 is a schematic view of an elliptical water area, and fig. 6 is a schematic view of an irregular water area.
In fig. 4, since the water area in the video screen is recognized as a circular water area, a circular dotted frame shown in fig. 4, which is a water area frame, can be generated from the outline of the circular water area. In fig. 5, it is recognized that there are two elliptical water areas in the video frame, so the two elliptical dashed boxes shown in fig. 5 can be generated according to the outlines of the two elliptical water areas, and the two elliptical dashed boxes are water area boxes, wherein the number of the water area boxes in the video frame is not limited, and how many water area boxes are generated according to the embodiment. In fig. 6, since the water area in the video screen is recognized as an irregularly shaped water area, an irregularly shaped dashed frame shown in fig. 6, which is a water area frame, can be generated from the outline of the irregularly shaped water area.
Further, in order to more accurately divide the water area frame corresponding to the water area from the video image and remove some disturbances of the water area which basically does not cause drowning danger, the step S20 includes:
identifying a water area from the video picture; when the water area is a dangerous water area, image segmentation is carried out according to the outline of the water area; and generating a water area frame corresponding to the water area according to the image segmentation result.
It can be understood that the water area can be identified from the video picture, then whether the water area is a dangerous water area is determined according to the outline and the area of the water area, if the water area in the video picture is a dangerous water area, the subsequent detection and judgment steps are performed, if the water area in the video picture is not a dangerous water area, the situation that the drowning risk is not existed is directly judged, and the drowning prevention monitoring is not needed.
In a specific implementation, for example, a small area of a fish pond or fountain landscape may be provided in a park, and such a similar area, although belonging to a water area, is not substantially at risk of drowning due to its small area, and may be viewed at a close distance due to the fact that the areas are specifically designed for viewing by the tourists, and if a drowning prevention alarm is performed in this case, it is not only unnecessary to give an alarm to prompt the tourists to leave, but also reduces the play experience of the tourists, which is not desirable. In addition, some drainage ditches can be arranged in the park to facilitate drainage in rainy days, water is reserved in the drainage ditches, but normally, tourists are not drowned, the drainage ditches are arranged on the roadside in many cases, the tourists can possibly stride from the drainage ditches in the walking process, and anti-drowning alarm is not needed for the water area.
Therefore, in order to avoid the situation that the problem is done greatly due to false alarm, the drowning alarm is only carried out under the situation that the drowning danger is actually possibly generated, and the drowning alarm is not carried out under the situation that the drowning danger is not generated, so that the drowning alarm is prevented more pertinently, the better drowning alarm preventing effect is achieved, the water area identified in the video picture can be divided into the dangerous water area and the common water area, the drowning monitoring and the alarm are only carried out for the dangerous water area, and the operation is not carried out for the common water area. For example, the contour and the area of the water area can be combined to determine whether the water area belongs to a dangerous water area or a normal water area, and a water area which does not cause drowning danger, such as a water area with a small area or a water area with a slender contour shape, can be divided into normal water areas, and a water area which does not belong to a normal water area can be divided into dangerous water areas.
It should be understood that when the water area in the video picture is a dangerous water area, image segmentation can be performed according to the outline of the water area, and then a water area frame corresponding to the water area can be generated according to the image segmentation result.
It can be understood that, in order to make the image segmentation more accurate, improve the precision of waters area frame, and then make prevent drowning detection more accurate, improve the accuracy of preventing drowning warning, avoid the false alarm, in the in-process of carrying out the image segmentation, can carry out scene recognition to the video picture, assign corresponding category label for each element in the video picture respectively according to scene recognition result to carry out scene annotation to the video picture according to category label, obtain the video picture after annotating. The scene with the water area annotation in the video picture can be used as a water area scene, the outline of the water area is determined according to the shape of the water area scene, and then the image segmentation is carried out according to the outline of the water area, so that a water area frame corresponding to the water area is generated according to the image segmentation result.
It should be understood that, because the image capturing device is generally disposed at a fixed position, and the water area is also fixed, in general, both will not change greatly, so after the water area frame is generated, the water area frame before the water area frame can be directly used in the subsequent anti-drowning detection, the time of data processing is reduced, and the anti-drowning alarm is more timely.
However, since the situation may occur in which the image capturing apparatus is replaced or the water area is newly planned, in order to avoid detection errors, it is necessary to re-recognize the water area in the video screen and generate a corresponding water area frame in these cases. In these cases, there is a large change between the current video frame and the previous video frame, so the currently monitored video frame and the historical video frame can be compared to detect the change degree of the video frame, the preset change degree is preset as a reference, the current change degree is compared with the preset change degree, if the current change degree exceeds the preset change degree, the water area is identified again from the video frame and a corresponding water area frame is generated for subsequent anti-drowning detection, if the current change degree does not exceed the preset change degree, the re-identification is not needed, and the water area frame corresponding to the historical video frame is directly used for subsequent anti-drowning detection. Therefore, the scheme can perform water area identification and image segmentation on the video picture when large picture change occurs each time so as to generate a water area frame corresponding to the water area.
It should be noted that the degree of change may be quantified by a percentage method, or may be quantified by another method, which is not limited in this embodiment.
And step S30, when a human body appears in the video picture, generating a human body detection frame according to the human body position corresponding to the human body.
It should be understood that the function of human body detection may be continuously performed based on the video picture, and when a human body is detected to occur in the video picture, the human body position corresponding to the human body is recognized, and then the human body detection frame is generated according to the human body position corresponding to the human body.
It can be appreciated that after determining the position of the human body, the human body contour corresponding to the human body can be identified, and then the human body detection frame is generated according to the human body contour; the corresponding skeleton points of the human body can be identified, and then a human body detection frame is generated according to the connection line of the skeleton points of the human body; human body characteristics corresponding to the human body can be extracted based on the characteristic extractor, and then boundary box prediction is carried out according to the human body characteristics so as to generate a human body detection box. In addition to the above, the human body detection frame may be generated according to other ways that can achieve similar or identical functions, which is not limited in this embodiment.
And step S40, triggering an alarm prompt when an intersection exists between the human body detection frame and the water area frame.
It should be appreciated that after the body of water region frame and the body of water detection frame are determined, it may be determined whether an intersection exists between the body of water detection frame and the body of water region frame, if an intersection exists between the body of water detection frame and the body of water region frame, it is determined that a person is approaching a hazardous water region, thereby triggering an alarm function, alerting the person, and alerting the monitoring room that a person is approaching the hazardous water region, and not stopping the alarm until all persons leave the hazardous water region.
In this embodiment, a preset area is monitored to obtain a video picture; identifying a water area from the video picture, and generating a corresponding water area frame according to the outline of the water area; when a human body appears in the video picture, a human body detection frame is generated according to the human body position corresponding to the human body; when an intersection exists between the human body detection frame and the water area frame, an alarm prompt is triggered. According to the scheme, the water area frame and the human body detection frame are determined according to the video pictures monitored in real time, a person is judged to be close to a dangerous water area under the condition that the two have an intersection, and an alarm prompt is triggered, so that drowning alarm is timely prevented when drowning danger possibly exists, the probability that the person enters the dangerous water area can be reduced, and a drowning event is avoided.
In an embodiment, as shown in fig. 7, a second embodiment of the anti-drowning alarm method according to the present invention is proposed based on the first embodiment, and the step S40 includes:
step S401, when there is an intersection between the human body detection frame and the water area frame exceeding a preset number of pixels, determining that a person approaches the water area.
Note that the preset number of pixels may be a certain number of pixels preset according to actual situations, for example, may be 1 pixel or 2 pixels, or may be other numbers of pixels, which is not limited in this embodiment, and in this embodiment, 1 pixel is taken as an example for the preset number of pixels.
It will be appreciated that when there is more than 1 pixel intersection between the body detection frame and the body of water region frame, it is determined that a person is approaching the hazardous body of water region, whereas if there is no more than 1 pixel intersection between the body detection frame and the body of water region frame, it is determined that no person is approaching the hazardous body of water region.
Step S402, when a person approaches a water area, warning prompt information and alarm information are acquired.
It should be appreciated that no alarm is required in the case where no person is approaching the hazardous area, and that an alarm is required in the case where a person is approaching the hazardous area.
It should be noted that, in order to achieve a better anti-drowning effect, the alarm prompt in the embodiment may include, but is not limited to, a human body warning and a monitoring room warning, and both methods may be adopted to perform the alarm prompt at the same time. The monitoring room can warn the person not to enter the dangerous water area through the human body warning, and can leave as soon as possible, so that the drowning danger is avoided, the staff in the monitoring room can quickly know the current situation through the monitoring room warning, corresponding measures are timely taken, and the drowning danger of the person is further prevented.
It should be understood that, in order to perform the human body warning and the monitoring room warning, warning prompt information corresponding to the human body warning and warning information corresponding to the monitoring room warning may be acquired, respectively, so that the human body warning is performed according to the warning prompt information and the monitoring room warning is performed according to the warning information.
It can be understood that the warning prompt information can be preset, and the set warning prompt information can be directly obtained to warn the human body. The current position of the shooting equipment can be obtained, and the alarm information is generated by combining the current position, so that the staff in the monitoring room can timely know the current position of the person with drowning risk, and the staff can timely and pointedly take measures.
Step S403, sending out an alarm to the human body according to the alarm prompt information, and giving an alarm to a monitoring room according to the alarm information.
It should be understood that the sound playing device may be installed on the image capturing device, or the sound playing device may be installed around the water area, or may be disposed at other suitable positions, which is not limited in this embodiment. The warning prompt information can be sent to the sound playing equipment, and the sound playing equipment plays the warning prompt information so as to give a warning to a human body, so that the person is warned not to enter a dangerous water area, and the drowning danger is avoided.
It should be understood that a terminal device may be provided in the monitoring room, and the alarm information may be sent to the terminal device in the monitoring room, through which the alarm is given according to the alarm information, so that the staff knows the current dangerous situation according to the alarm information.
It can be understood that in the process of continuously carrying out the alarm prompt, the monitoring can be further carried out, when no intersection exists between the human body detection frame and the water area frame, the personnel is indicated to leave the dangerous water area, the drowning danger does not exist, and the alarm prompt can be stopped.
In this embodiment, when there is an intersection between the human body detection frame and the water area frame that exceeds a preset number of pixels, it is determined that a person approaches the water area; when a person approaches a water area, acquiring warning prompt information and alarm information; and sending out an alarm to the human body according to the alarm prompt information, and giving an alarm to a monitoring room according to the alarm information. Therefore, when a person is detected to approach the water area, the person is simultaneously warned by adopting a human body warning and a monitoring room warning to carry out warning prompt, so that the person is prevented from entering a dangerous water area to have a drowning danger.
In an embodiment, as shown in fig. 8, a third embodiment of the anti-drowning alarm method according to the present invention is provided based on the first embodiment or the second embodiment, and in this embodiment, the method further includes, after step S40:
step S501, detecting an intersection area between the human body detection frame and the water area frame when the time of the intersection between the human body detection frame and the water area frame exceeds a preset time.
It should be noted that, because there may be a scene in which although the alarm prompt is performed, the person still enters the dangerous water area, and the situation that the person drowns after the warning is not taken into consideration may occur, the life-saving device can be thrown to the person with drowning according to the situation, so as to timely rescue the person with drowning.
It can be understood that, referring to fig. 9, fig. 9 is an overall flow chart of the intelligent water area monitoring anti-drowning alarm system, and the scheme can be divided into two parts: (1) Alarming and giving an alarm to personnel approaching the dangerous water area; (2) And helping people who have drowned after the water is discharged.
Therefore, besides the alarm prompt, whether the person who has a drowning event after the water is in need of rescue can be judged through detection. The preset time can be preset, and when the duration of the intersection between the human body detection frame and the water area frame exceeds the preset time, the person is not separated from the dangerous water area all the time. Therefore, in order to determine whether the person is drowned, the intersection area between the human body detection frame and the water area frame can be detected.
And step S502, judging whether a person enters the water area according to the intersection area.
It can be understood that the detection frame area of the human body detection frame can be obtained, and whether a person enters the water area can be judged by combining the detection frame area and the intersection area.
It should be noted that, the preset percentage value may be set to 80% in advance, and other values may be set in addition, which is not limited in this embodiment. The area to be compared can be calculated according to the area of the detection frame and a preset percentage value, then the intersection area is compared with the area to be compared, whether a person enters the water area or not is judged according to the comparison result, when the comparison result is that the intersection area exceeds the area to be compared, the person is judged to enter the water area, and when the comparison result is that the intersection area does not exceed the area to be compared, the person is judged to not enter the water area.
It should be understood that in this embodiment, the above manner is adopted to determine whether a person enters the water area, and the cross-over ratio between the human body detection frame and the water area frame is not used, because the area of the water is generally larger and the area of the human body is smaller, so that the difference between the area of the human body detection frame and the area of the water area frame is larger, and if the cross-over ratio is used, a larger error may exist, which affects the detection accuracy.
Step S503, throwing life-saving equipment to a person when the person enters a water area.
It should be understood that when a person enters a water area, the action information of the person can be further detected, whether the person has drowning behavior is judged according to the action information, and if the drowning behavior is detected, the life-saving equipment is thrown to the person according to the position of the person. Meanwhile, the monitoring room can be further alerted, and the monitoring room can be dialed 120 to be alerted, so that rescue can be timely carried out.
In a specific implementation, the change of the area of the intersection between the human body detection frame and the water area region frame can be judged, when the intersection area exceeds 80% of the area of the human body detection frame, the person is indicated to have entered a dangerous water area, then the action judgment is continuously carried out on the person, when the drowning behavior of the person is judged, the position and the distance of the drowning person can be calculated according to the detected position of the human body, the life-saving equipment is thrown to the position of the drowning person according to a certain force, and the person is dialed 120 to give an alarm.
Because of the wide range of the dangerous waters, a plurality of throwing devices may be disposed along the dangerous waters, and each of the throwing devices has the ability to throw the lifesaving device. In order to enable the life-saving equipment to be thrown to the vicinity of drowning personnel, the situation of throwing errors is avoided, equipment positions of a plurality of throwing equipment can be obtained, position distances between the positions of a human body and the positions of the equipment are calculated respectively, then target throwing equipment closest to the human body is selected from the plurality of throwing equipment according to the position distances, and then the life-saving equipment is thrown to the human body through the target throwing equipment according to the positions of the human body. The life-saving equipment can include but is not limited to life-saving equipment such as life rings, life jackets, life-saving balls and the like, the embodiment is not limited to the life-saving equipment, the life-saving equipment can be thrown directly when not needing to be inflated, and the life-saving equipment needing to be inflated can be thrown after being inflated.
It will be appreciated that both the throwing direction and the throwing power may be considered for better throwing results. The position and distance of the person relative to the target throwing device can be determined according to the position of the person and the position of the target device of the target throwing device, and the target throwing device can be controlled to throw the life saving device to the person according to the position and distance of the person relative to the target throwing device.
It can be appreciated that the throwing direction can be determined according to the direction of the human body relative to the target throwing device, the throwing force can be determined according to the distance between the human body and the target throwing device, and then a throwing instruction is generated according to the throwing direction and the throwing force, and the throwing instruction is sent to the target throwing device so as to control the target throwing device to throw the life-saving device to the human body.
It should be noted that, this scheme utilizes image segmentation technique and human detection technique, then according to the intersection between human detection frame and the waters area frame of calculation, judge whether the human body is close or gets into the waters. And a controllable life-saving equipment throwing device is arranged, so that the direction and the position of a drowner can be judged, and the drowner can be inflated in a certain direction with a certain force in a short time and thrown to the side of the drowner. Through this scheme, on the one hand can reduce the number of times that personnel got into dangerous waters, on the other hand even personnel have got into dangerous waters, still can judge in real time whether someone is drowned, if take place drowned, then can carry out timely rescue, reduce drowned mortality, further ensured personnel's safety.
In this embodiment, when the time when there is an intersection between the human body detection frame and the water area frame exceeds a preset time, detecting an intersection area between the human body detection frame and the water area frame; judging whether a person enters a water area according to the intersection area; when a person enters a water area, throwing the life-saving equipment to the person. Therefore, under the condition that people do not hear the warning and enter the dangerous water area to drown, the life-saving equipment can be thrown to the person to timely rescue the drowned person.
In addition, the embodiment of the invention also provides a storage medium, wherein the storage medium is stored with a drowning prevention alarm program, and the drowning prevention alarm program realizes the steps of the drowning prevention alarm method when being executed by a processor.
Because the storage medium adopts all the technical schemes of all the embodiments, the storage medium has at least all the beneficial effects brought by the technical schemes of the embodiments, and the description is omitted here.
In addition, referring to fig. 10, an embodiment of the present invention further provides a drowning prevention alarm device, where the drowning prevention alarm device includes:
the area detection module 10 is configured to monitor a preset area to obtain a video picture.
And the water area identification module 20 is used for identifying a water area from the video picture and generating a corresponding water area frame according to the outline of the water area.
The human body recognition module 30 is configured to generate a human body detection frame according to a human body position corresponding to a human body when the human body appears in the video frame.
And the alarm prompt module 40 is used for triggering an alarm prompt when an intersection exists between the human body detection frame and the water area frame.
In this embodiment, a preset area is monitored to obtain a video picture; identifying a water area from the video picture, and generating a corresponding water area frame according to the outline of the water area; when a human body appears in the video picture, a human body detection frame is generated according to the human body position corresponding to the human body; when an intersection exists between the human body detection frame and the water area frame, an alarm prompt is triggered. According to the scheme, the water area frame and the human body detection frame are determined according to the video pictures monitored in real time, a person is judged to be close to a dangerous water area under the condition that the two have an intersection, and an alarm prompt is triggered, so that drowning alarm is timely prevented when drowning danger possibly exists, the probability that the person enters the dangerous water area can be reduced, and a drowning event is avoided.
In an embodiment, the alarm prompting module 40 is further configured to determine that a person approaches the water area when there is an intersection between the human body detection frame and the water area frame that exceeds a preset number of pixels; when a person approaches a water area, acquiring warning prompt information and alarm information; and sending out an alarm to the human body according to the alarm prompt information, and giving an alarm to a monitoring room according to the alarm information.
In an embodiment, the alarm prompting module 40 is further configured to stop the alarm prompting when there is no intersection between the human body detection frame and the water area frame.
In an embodiment, the drowning prevention alarm device further includes an equipment control module, configured to detect an intersection area between the human body detection frame and the water area frame when an intersection time between the human body detection frame and the water area frame exceeds a preset time; judging whether a person enters a water area according to the intersection area; when a person enters a water area, throwing the life-saving equipment to the person.
In an embodiment, the device control module is further configured to obtain a detection frame area of the human body detection frame; and judging whether a person enters the water area according to the intersection area and the detection frame area.
In an embodiment, the device control module is further configured to calculate an area to be compared according to the detection frame area and a preset percentage value; comparing the intersection area with the area to be compared; and judging whether a person enters the water area according to the comparison result.
In an embodiment, the device control module is further configured to determine that a person enters the water area when the intersection area exceeds the area to be compared as a result of the comparison.
In an embodiment, the device control module is further configured to detect motion information of a person when the person enters the water area; judging whether the human body has drowning behavior according to the action information; when the human body has drowning behavior, throwing the life-saving equipment to the human body according to the position of the human body.
In an embodiment, the device control module is further configured to obtain device positions of a plurality of throwing devices; calculating the position distance between the human body position and each equipment position; selecting a target throwing device from a plurality of throwing devices according to the position distance; and throwing the life saving equipment to the human body through the target throwing equipment according to the human body position.
In an embodiment, the device control module is further configured to determine an orientation and a distance of the person relative to the target throwing device based on the person position and a target device position of the target throwing device; and controlling the target throwing device to throw the life-saving device to the human body according to the azimuth and the distance.
In an embodiment, the device control module is further configured to determine a throwing direction according to the azimuth, and determine a throwing force according to the distance; generating a throwing instruction according to the throwing direction and the throwing force; and controlling the target throwing device to throw the life-saving device to the human body according to the throwing instruction.
In an embodiment, the area detection module 10 is further configured to identify a water area from the video frame; when the water area is a dangerous water area, image segmentation is carried out according to the outline of the water area; and generating a water area frame corresponding to the water area according to the image segmentation result.
In an embodiment, the area detection module 10 is further configured to detect a degree of change of the video frame; and when the change degree exceeds the preset change degree, identifying a water area from the video picture.
In an embodiment, the area detection module 10 is further configured to perform scene recognition on the video frame, and allocate corresponding class labels to each element in the video frame respectively; performing scene annotation on the video picture according to the category label; determining the outline of the water area in the video picture according to the scene annotation result; and image segmentation is carried out according to the outline of the water area.
Other embodiments or specific implementation methods of the drowning prevention alarm device according to the present invention may refer to the above method embodiments, and will not be described herein.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in an estimator readable storage medium (e.g. ROM/RAM, magnetic disk, optical disk) as described above, comprising instructions for causing a smart device (which may be a mobile phone, estimator, anti-drowning alarm device, or network anti-drowning alarm device, etc.) to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
The invention discloses an anti-drowning alarm method which comprises the following steps:
monitoring a preset area to obtain a video picture;
identifying a water area from the video picture, and generating a corresponding water area frame according to the outline of the water area;
when a human body appears in the video picture, a human body detection frame is generated according to the human body position corresponding to the human body;
when an intersection exists between the human body detection frame and the water area frame, an alarm prompt is triggered.
A2, the drowning prevention alarm method as set forth in A1, wherein when an intersection exists between the human body detection frame and the water area frame, an alarm prompt is triggered, comprising:
when an intersection exceeding a preset number of pixels exists between the human body detection frame and the water area frame, judging that a person approaches the water area;
when a person approaches a water area, acquiring warning prompt information and alarm information;
and sending out an alarm to the human body according to the alarm prompt information, and giving an alarm to a monitoring room according to the alarm information.
A3, the drowning prevention alarm method as set forth in A1, wherein when an intersection exists between the human body detection frame and the water area frame, after triggering an alarm prompt, the method further includes:
And stopping alarming prompt when no intersection exists between the human body detection frame and the water area frame.
A4, the anti-drowning alarm method according to any one of A1 to A3, when the intersection exists between the human body detection frame and the water area frame, after triggering an alarm prompt, further comprising:
detecting the intersection area between the human body detection frame and the water area frame when the intersection time between the human body detection frame and the water area frame exceeds the preset time;
judging whether a person enters a water area according to the intersection area;
when a person enters a water area, throwing the life-saving equipment to the person.
A5, the drowning prevention alarm method according to A4, wherein the judging whether a person enters a water area according to the intersection area comprises the following steps:
acquiring the detection frame area of the human body detection frame;
and judging whether a person enters the water area according to the intersection area and the detection frame area.
A6, the drowning prevention alarm method according to A5, wherein the judging whether a person enters a water area according to the intersection area and the detection frame area comprises the following steps:
calculating the area to be compared according to the area of the detection frame and a preset percentage value;
Comparing the intersection area with the area to be compared;
and judging whether a person enters the water area according to the comparison result.
A7, the drowning prevention alarm method according to A6, after judging whether a person enters a water area according to the comparison result, further comprising:
and when the comparison result shows that the intersection area exceeds the area to be compared, judging that a person enters the water area.
A8, the anti-drowning alarm method of A4, when a person enters a water area, throwing life-saving equipment to the person, comprising:
detecting action information of a human body when the human body enters a water area;
judging whether the human body has drowning behavior according to the action information;
when the human body has drowning behavior, throwing the life-saving equipment to the human body according to the position of the human body.
A9, the drowning prevention alarming method of A8, according to the human body position, throwing life saving equipment to the human body, comprising:
acquiring device positions of a plurality of throwing devices;
calculating the position distance between the human body position and each equipment position;
selecting a target throwing device from a plurality of throwing devices according to the position distance;
and throwing the life saving equipment to the human body through the target throwing equipment according to the human body position.
A10, the anti-drowning alarm method of A9, according to the human body position, throwing life-saving equipment to the human body through the target throwing equipment, comprising:
determining the position and distance of the human body relative to the target throwing device according to the human body position and the target device position of the target throwing device;
and controlling the target throwing device to throw the life-saving device to the human body according to the azimuth and the distance.
A11, the anti-drowning alarm method of A10, according to the azimuth and the distance, the target throwing device is controlled to throw life-saving equipment to the human body, comprising:
determining a throwing direction according to the azimuth, and determining throwing force according to the distance;
generating a throwing instruction according to the throwing direction and the throwing force;
and controlling the target throwing device to throw the life-saving device to the human body according to the throwing instruction.
A12, the drowning prevention alarm method according to any one of A1 to A3, wherein the steps of identifying a water area from the video picture and generating a corresponding water area frame according to the outline of the water area include:
identifying a water area from the video picture;
When the water area is a dangerous water area, image segmentation is carried out according to the outline of the water area;
and generating a water area frame corresponding to the water area according to the image segmentation result.
A13, the drowning prevention alarm method as set forth in A12, wherein the identifying the water area from the video picture includes:
detecting the change degree of the video picture;
and when the change degree exceeds the preset change degree, identifying a water area from the video picture.
A14, the drowning prevention alarm method as set forth in A12, wherein the image segmentation is performed according to the contour of the water area, and the method comprises the steps of:
performing scene recognition on the video picture, and respectively distributing corresponding category labels for each element in the video picture;
performing scene annotation on the video picture according to the category label;
determining the outline of the water area in the video picture according to the scene annotation result;
and image segmentation is carried out according to the outline of the water area.
The invention also discloses a B15 and a drowning prevention alarm device, which comprises:
the area detection module is used for monitoring a preset area to obtain a video picture;
The water area identification module is used for identifying a water area from the video picture and generating a corresponding water area frame according to the outline of the water area;
the human body identification module is used for generating a human body detection frame according to the human body position corresponding to the human body when the human body appears in the video picture;
and the alarm prompt module is used for triggering alarm prompt when an intersection exists between the human body detection frame and the water area frame.
B16, the anti-drowning alarm device according to B15, wherein the alarm prompt module is further configured to determine that a person approaches a water area when an intersection of more than a preset number of pixels exists between the human body detection frame and the water area frame; when a person approaches a water area, acquiring warning prompt information and alarm information; and sending out an alarm to the human body according to the alarm prompt information, and giving an alarm to a monitoring room according to the alarm information.
B17, the anti-drowning alarm device of B15, the alarm prompt module is further used for stopping alarm prompt when no intersection exists between the human body detection frame and the water area frame.
B18, the anti-drowning alarm device according to any one of B15 to B17, the anti-drowning alarm device further comprising:
The equipment control module is used for detecting the intersection area between the human body detection frame and the water area frame when the intersection time between the human body detection frame and the water area frame exceeds the preset time; judging whether a person enters a water area according to the intersection area; when a person enters a water area, throwing the life-saving equipment to the person.
The invention also discloses C19, a drowning prevention alarm device, which comprises: the anti-drowning alarm system comprises a memory, a processor and an anti-drowning alarm program which is stored in the memory and can run on the processor, wherein the anti-drowning alarm method is realized when the anti-drowning alarm program is executed by the processor.
The invention also discloses D20 and a storage medium, wherein the storage medium is stored with the anti-drowning alarm program, and the anti-drowning alarm method is realized when the anti-drowning alarm program is executed by the processor.
Claims (10)
1. The drowning prevention alarm method is characterized by comprising the following steps of:
monitoring a preset area to obtain a video picture;
identifying a water area from the video picture, and generating a corresponding water area frame according to the outline of the water area;
When a human body appears in the video picture, a human body detection frame is generated according to the human body position corresponding to the human body;
when an intersection exists between the human body detection frame and the water area frame, an alarm prompt is triggered.
2. The anti-drowning alarm method of claim 1, wherein triggering an alarm prompt when there is an intersection between the human body detection frame and the water area frame includes:
when an intersection exceeding a preset number of pixels exists between the human body detection frame and the water area frame, judging that a person approaches the water area;
when a person approaches a water area, acquiring warning prompt information and alarm information;
and sending out an alarm to the human body according to the alarm prompt information, and giving an alarm to a monitoring room according to the alarm information.
3. The anti-drowning alarm method according to claim 1, wherein after triggering an alarm prompt when there is an intersection between the human body detection frame and the water area frame, further comprising:
and stopping alarming prompt when no intersection exists between the human body detection frame and the water area frame.
4. A method of anti-drowning alarm according to any one of claims 1 to 3, wherein upon an intersection between the body detection frame and the body area frame, triggering an alarm prompt further comprises:
Detecting the intersection area between the human body detection frame and the water area frame when the intersection time between the human body detection frame and the water area frame exceeds the preset time;
judging whether a person enters a water area according to the intersection area;
when a person enters a water area, throwing the life-saving equipment to the person.
5. The anti-drowning alarm method of claim 4, wherein the determining whether a person enters a water area based on the intersection area includes:
acquiring the detection frame area of the human body detection frame;
and judging whether a person enters the water area according to the intersection area and the detection frame area.
6. The anti-drowning alarm method of claim 5, wherein the determining whether a person enters a water area based on the intersection area and the detection frame area includes:
calculating the area to be compared according to the area of the detection frame and a preset percentage value;
comparing the intersection area with the area to be compared;
and judging whether a person enters the water area according to the comparison result.
7. The drowning prevention alarm method according to claim 6, wherein after judging whether a person enters the water area according to the comparison result, further comprising:
And when the comparison result shows that the intersection area exceeds the area to be compared, judging that a person enters the water area.
8. Prevent drowned alarm device, its characterized in that, prevent drowned alarm device includes:
the area detection module is used for monitoring a preset area to obtain a video picture;
the water area identification module is used for identifying a water area from the video picture and generating a corresponding water area frame according to the outline of the water area;
the human body identification module is used for generating a human body detection frame according to the human body position corresponding to the human body when the human body appears in the video picture;
and the alarm prompt module is used for triggering alarm prompt when an intersection exists between the human body detection frame and the water area frame.
9. Prevent drowned alarm device, its characterized in that, prevent drowned alarm device includes: memory, processor and store on the memory and can be on the processing unit running prevent drowning alarm procedure, prevent drowning alarm procedure when being carried out by the processor and realize the method of preventing drowning according to any one of claims 1 to 7.
10. A storage medium, wherein the storage medium stores a drowning prevention alarm program, and the drowning prevention alarm program when executed by a processor implements the drowning prevention alarm method according to any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111487892.9A CN116246417A (en) | 2021-12-07 | 2021-12-07 | Drowning prevention alarm method, device, equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111487892.9A CN116246417A (en) | 2021-12-07 | 2021-12-07 | Drowning prevention alarm method, device, equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116246417A true CN116246417A (en) | 2023-06-09 |
Family
ID=86622955
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111487892.9A Pending CN116246417A (en) | 2021-12-07 | 2021-12-07 | Drowning prevention alarm method, device, equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116246417A (en) |
-
2021
- 2021-12-07 CN CN202111487892.9A patent/CN116246417A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109257569B (en) | Security video monitoring and analyzing method | |
JP4569190B2 (en) | Suspicious person countermeasure system and suspicious person detection device | |
US20200388135A1 (en) | Automated water body area monitoring | |
KR101877294B1 (en) | Smart cctv system for crime prevention capable of setting multi situation and recognizing automatic situation by defining several basic behaviors based on organic relation between object, area and object's events | |
KR100956978B1 (en) | The system which integrated manages a traffic accident notice area | |
KR101036947B1 (en) | The automatic guard system to prevent the crime and accident using computer video image analysis technology | |
CN113223046B (en) | Method and system for identifying prisoner behaviors | |
CN109492548B (en) | Method for obtaining region mask picture based on video analysis | |
CN108319892A (en) | A kind of vehicle safety method for early warning and system based on genetic algorithm | |
CN110718041B (en) | Method, device and system for preventing children from getting lost and storage medium | |
CN116743970A (en) | Intelligent management platform with video AI early warning analysis | |
CN110852362B (en) | Drowning event detection method and device and computer readable storage medium | |
CN112309077A (en) | Drowning alarm method and drowning alarm device for swimming pool | |
CN115503906A (en) | Intelligent life-saving system for people falling into water | |
JP5370009B2 (en) | Monitoring system | |
CN110809137A (en) | Campus safety trampling prevention monitoring system and method | |
CN113055651A (en) | Artificial intelligence type vehicle security system and computer readable storage medium | |
CN116246417A (en) | Drowning prevention alarm method, device, equipment and storage medium | |
JP5481333B2 (en) | Crime prevention device, crime prevention method and program | |
JP7447626B2 (en) | Information processing method, information processing device, program and information processing system | |
WO2023095196A1 (en) | Passenger monitoring device, passenger monitoring method, and non-transitory computer-readable medium | |
CN102595106A (en) | Device and method for harbor frontier inspection intelligent monitoring inspection | |
CN211554957U (en) | Be used for swimming pool personnel that fall into water to discriminate positioner and system | |
CN113420626A (en) | Construction site safety behavior judging method and storage device | |
JP2022175631A (en) | Monitoring device and monitoring system |
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 |