CN112489372A - Swimming pool monitoring and alarming system - Google Patents
Swimming pool monitoring and alarming system Download PDFInfo
- Publication number
- CN112489372A CN112489372A CN202011576423.XA CN202011576423A CN112489372A CN 112489372 A CN112489372 A CN 112489372A CN 202011576423 A CN202011576423 A CN 202011576423A CN 112489372 A CN112489372 A CN 112489372A
- Authority
- CN
- China
- Prior art keywords
- swimmer
- swimming
- water surface
- time
- coordinate
- 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
- 230000009182 swimming Effects 0.000 title claims abstract description 95
- 238000012544 monitoring process Methods 0.000 title claims abstract description 27
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 67
- 238000001514 detection method Methods 0.000 claims abstract description 8
- 206010013647 Drowning Diseases 0.000 claims description 25
- 238000013527 convolutional neural network Methods 0.000 claims description 19
- 239000013598 vector Substances 0.000 claims description 12
- 238000000034 method Methods 0.000 claims description 6
- 238000011176 pooling Methods 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 2
- 238000012545 processing Methods 0.000 claims description 2
- 230000011218 segmentation Effects 0.000 claims description 2
- 238000012549 training Methods 0.000 claims description 2
- 238000013519 translation Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 claims 1
- 238000005070 sampling Methods 0.000 claims 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000002612 cardiopulmonary effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000029087 digestion Effects 0.000 description 1
- 238000005538 encapsulation Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000000465 moulding Methods 0.000 description 1
- 239000005022 packaging material Substances 0.000 description 1
- 239000004033 plastic Substances 0.000 description 1
- 229920003023 plastic Polymers 0.000 description 1
- 230000002265 prevention Effects 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
- G08B21/08—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
- 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
- G08B21/088—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 by monitoring a device worn by the person, e.g. a bracelet attached to the swimmer
-
- 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
- G08B21/182—Level alarms, e.g. alarms responsive to variables exceeding a threshold
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
- G08B25/01—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium
- G08B25/10—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium using wireless transmission systems
Landscapes
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Alarm Systems (AREA)
Abstract
A swimming pool monitoring and alarming system comprises a swimming cap with a water pressure detection and positioning module, a high-definition panoramic camera, a PC (personal computer) end or a server end, a display and a mobile phone app of a lifesaving person; swimming cap with water pressure detection and location: the swimming cap is provided with a water pressure sensor, a positioning module, a Wifi module and an embedded microcontroller, and the water pressure sensor, the positioning module and the Wifi module are all connected to the embedded microcontroller; the swimmer needs to wear the swimming cap, the water pressure sensor is used for detecting whether the head of the swimmer is under the water surface or giving the position under the water surface, and if the head of the swimmer is under the water surface, the judgment information is transmitted into the embedded microcontroller; the positioning module realizes real-time positioning and transmits coordinate information of a swimmer in the swimming pool into the embedded microcontroller; the embedded microcontroller transmits the received information to a PC end or a server end through a Wifi module.
Description
Technical Field
The invention relates to an application of an artificial intelligence method in the field of safety prevention and control, in particular to a (child) swimming pool monitoring and alarming system and method based on a convolutional neural network.
Background
With the continuous economic rapid growth of the 21 st century, people pay more and more attention to the comprehensive development of the mind and body of children, and more parents choose to carry the children to do swimming exercises because the swimming benefits are more, such as making the children more clever, improving the sleeping quality, enhancing the cardio-pulmonary function, helping the children grow tall and tall, helping the digestion and the like. However, the risk of swimming cannot be completely avoided, as the swimming pool has too many children, the life preservers cannot pay attention to the swimming state of each child, and if the children are in danger of drowning, even if a plurality of life preservers cannot find the accident and prevent the accident situation at the first time. Even if a plurality of life-saving personnel still have the time of being careless to observe.
The invention designs a child swimming pool monitoring and alarming system based on a convolutional neural network, the swimming of the children is monitored in real time, the position of the children in the swimming pool is positioned, whether the head of the children is underwater or not is judged, and tracking and judging the dangerous image, judging the swimming posture by using a model trained by a convolutional neural network, and when a child is judged to be drowned, when the head is below the water surface for a certain time (such as 8-20 seconds, different criteria can be designed at different age stages) and the posture is judged to be drowned, the system quickly responds to send an alarm to the life-saving personnel, and the coordinate information of the children with drowning risks is marked under a swimming pool coordinate system, so that the lifesaving personnel can find the drowned children more quickly to carry out key observation and rescue.
Disclosure of Invention
The invention aims to provide a (child) swimming pool monitoring and alarming system and method based on a convolutional neural network. Adopt high definition panorama camera to carry out real time monitoring to the swimming pool to handle the picture of gathering according to the chronogenesis at PC end with convolution neural network, judge whether the swimmer has drowned risk, when the swimmer has drowned risk, the system will send the cell-phone app that the alarm was given to the lifesaving personnel, and send drowned children's coordinate information, so that the lifesaving personnel carry out key observation and in time find drowned children and rescue. The present invention can also be used in all pool monitoring and warning systems and methods. And the safety personnel is assisted to guarantee the safety of the swimmer.
The technical scheme of the invention is that a (child) swimming pool monitoring and alarming system based on a convolutional neural network is based on the following devices: the system comprises a swimming cap with water pressure detection and (GPS, Beidou and the like) positioning, a high-definition panoramic camera, a PC end or server end, a display and a mobile phone app of a lifesaving person; swimming cap with water pressure detection and (GPS) positioning: the swimming cap is provided with a water pressure sensor, a GPS positioning module, a Wifi module and an embedded microcontroller, and the water pressure sensor, the GPS positioning module and the Wifi module are connected to the embedded microcontroller; the water pressure sensor is used for detecting whether the head of the swimmer is under the water surface or giving the position under the water surface, and if the head of the swimmer is under the water surface, judging information is transmitted into the embedded microcontroller; the positioning module (such as a GPS module) realizes real-time positioning and transmits the coordinate information of the swimmer in the swimming pool into the embedded microcontroller; the embedded microcontroller transmits the received information to a PC (personal computer) end (or a server end) through a Wifi module; the swimmer must wear the swimming cap to swim.
High-definition panoramic camera: panoramic monitoring in the swimming pool is realized, and shot pictures are transmitted into a PC (personal computer) end;
PC (analysis of the captured images by software at regular intervals): establishing a two-dimensional coordinate system for the swimming pool, and counting the number of swimmers in the swimming pool in real time according to the swimming cap signal or the image signal; counting and judging the number and time of each swimmer head under the water surface through a water pressure sensor, and when the number and time of a certain swimmer head under the water surface exceed a threshold time, the PC end gives an alarm to the mobile phone app of the lifesaving personnel through a Wifi module;
determining the position coordinate of each swimmer from the coordinate information transmitted from the swimming cap, marking the coordinate of each swimmer as green, displaying the green coordinate on a coordinate system and updating the green coordinate in real time; the judgment information of the swimmer above and below the water surface is transmitted by the swimming cap, if the swimmer is below the water surface, the coordinate mark of the swimmer is yellow (representing that the swimmer has a drowning risk and needs to judge the swimming posture), and if the swimmer is above the water surface, the swimmer is judged to be safe.
Further, gesture recognition and judgment are carried out on a swimmer with a possible drowning risk through a convolutional neural network (LeNet-5), if the swimmer is detected to be under the water surface within a certain time (8-20 seconds and different criteria are set at different age stages), and the swimming gesture is judged to be the drowning risk, the coordinate of the swimmer is marked to be red, and the position coordinate of the swimmer in the swimming pool and the result of judging whether the drowning risk exists are transmitted to a mobile phone app of a rescuer.
Mobile phone app of the rescuer: and receiving the swimming pool coordinate system, the real-time coordinate of each swimmer and the real-time number of swimmers in the swimming pool obtained by processing from the PC end, and displaying the coordinates and the real-time number of swimmers in the swimming pool on a mobile phone screen. The coordinate of the swimmer in normal swimming is green, and the coordinate of the swimmer with drowning risk is marked as red. And when the red coordinate appears, the mobile phone sends out vibration and gives an alarm. The swimming cap is a swimming pool standard, so the swimming cap has great practical value.
Has the advantages that: the invention provides a drowning risk monitoring and alarming system mainly applied to a child swimming pool (or other swimming pools) and used for realizing drowning risk judgment and position coordinate monitoring functions based on a convolutional neural network. When a child or other swimmers are judged to be in drowning danger, the main criterion is that the head of the person is under water or the face of the person is under the water for more than ten seconds (for example, 8-20 seconds, different criteria can be designed at different age stages), the drowning risk is judged to exist in the posture, the system quickly responds to send out an alarm to the lifesaving personnel, and the coordinate information of the child with the drowning risk is marked under a coordinate system of the swimming pool, so that the lifesaving personnel can find the drowned child more quickly to perform key observation and rescue. Especially, the judgment of the human head under water can be more accurate.
Drawings
FIG. 1 is a schematic structural view of the present invention;
fig. 2 is a swimming cap structure:
fig. 3 is a flowchart of swimmer swim gesture recognition determination by the convolutional neural network.
Detailed Description
The working process of the monitoring alarm system comprises the following steps:
the GPS and the pressure sensor on the swimming cap transmit coordinate information and judgment information of the head above and below the water surface into the PC end, the PC end marks the swimmer with the head above the water surface as green, and the swimmer with the head below the water surface as yellow. Then, the image collected by the high-definition panoramic camera is matched with the swimmer marked with yellow, the swimmer is tracked, shot (one image is collected every second in a specific time) and divided, the images are transmitted to a convolutional neural network (LeNet-5) for posture judgment, if the head is under the water surface and the posture is judged to have drowning risk, the coordinate of the swimmer is marked with red, the PC end sends alarm information to the application program end, and if the head is not under the water surface and the posture is judged to have drowning risk, the PC end marks the swimmer with green. GPS and pressure sensor WIFI on the swimming cap are mark 4 and microprocessor 2 and battery all seal with sealed packaging material (if the encapsulation of moulding plastics, can be water-fast, also can become the different swimming cap of a single individual configuration), can be similar to electric toothbrush's charge structure.
(children) swimming pool monitoring alarm system device model based on convolutional neural network: the system comprises a swimming cap with water pressure detection and (GPS) positioning, a high-definition panoramic camera, a PC (personal computer) end or server end, a display and a mobile phone app of a lifesaving person; swimming cap with water pressure detection and (GPS) positioning: the swimming cap is provided with a water pressure sensor 5 (arranged at the edge of the swimming cap), a (GPS or Beidou or UWB positioning module) positioning module 3, a Wifi module and an embedded microcontroller, wherein the water pressure sensor, the (GPS) positioning module and the Wifi module are all connected to the embedded microcontroller; the types of pressure sensors are: CM5541, waterproof digital pressure sensor, has the characteristics of low-power consumption. The WIFI module uses AP6212A, has the characteristics of low-power consumption. The embedded microcontroller uses the stm32f103 chip and has the characteristics of low power consumption and high performance.
The swimmer must wear the swimming cap 1 to swim; positioning modules such as a GPS module and a Beidou module are suitable for being used outdoors; when the UWB positioning tag is used for an indoor swimming pool, the UWB positioning tag can be arranged on a swimming cap (the molded package can resist water and can also be a single body) to continuously send UWB positioning pulses; the three UWB base stations respectively measure UWB positioning pulses and feed back measurement results to a PC (personal computer) end (or server end); the PC end estimates the position of the UWB positioning tag by adopting a TOF algorithm according to the received measurement result, so that the downstream swimmer of the swimming cap is positioned; the criterion of the upper and lower water surfaces of the head is still provided by a pressure sensor of the swimmer swimming cap, and the types of the pressure sensor are as follows: and the CM5541 and the like can be transmitted to the PC side (server side) through the AD conversion post-transmission WIFI module.
The swimmer swimming posture identification and judgment based on the convolutional neural network, a convolutional neural network algorithm (LeNet-5 model): monitoring the posture of a swimmer (monitoring a swimmer near the threshold, with the swimmer's head below the water surface for 3 seconds):
step 1: the picture (48 × 48 pixels) in which the target segmentation has been completed is used as an input layer, and is convolved with 6 different 5 × 5 convolution kernels, so that a 44 × 44 × 6 feature map is obtained.
Step 2: the obtained feature map is maximally pooled in 2 steps using a 2 × 2 window, and is also referred to as downsampling. The purpose of this step is to keep the image rotation, translation, etc. invariant and reduce the feature dimension. After pooling a 22X 6 profile will be obtained.
Step 3: the feature map obtained in the previous step was convolved with 16 different 5 × 5 convolution kernels, resulting in an 18 × 18 × 16 feature map.
Step 4: the obtained feature maps were subjected to maximum pooling in 2 × 2 windows with 2 as a step size, to obtain 9 × 9 × 16 feature maps.
Step 5: and expanding 1298 features obtained in the last step into one-dimensional feature vectors, and reducing the dimension to 400 features through a first full-connection layer, reducing the dimension to 120 features through a second full-connection layer, and reducing the dimension to 84 features through a third full-connection layer. The conversion formula of the feature vector of the upper layer to the feature vector of the lower layer during full connection is
a[i]＝g(W[i]a[i-1])
W is a weight vector; a is[i-1]The input feature vector of the previous layer; a is[i]The layer feature vector is used; g is the activation function, here the ReLU function is used.
Step 6: the last layer of the convolutional network adopts a Softmax classifier, the output result of the last layer is combined, and Softmax divides the result into 2 types which respectively correspond to a normal swimming posture and a swimming posture with drowning risk.
The training set of the convolutional neural network is derived from a monitoring database of a natatorium, and all swimming images are divided into two types, namely a normal swimming posture and a swimming posture with drowning risk.
(II) the operation mode of the system, namely the scheme flow of the invention:
1. coordinate information of the swimmers and judgment information of the swimmers above and below the water surface are acquired through the swimming cap and transmitted into the PC end, the swimmers on the water surface are marked as green by the PC end, and the swimmers below the water surface are marked as yellow.
2. The image collected by the high-definition panoramic camera is matched with a swimmer with yellow coordinates in the PC end, the specific position of the swimmer in the image is found, the image is collected within a certain time (8-20 seconds, different criteria are set at different age stages) and the swimmer is segmented.
3. And transmitting the segmented image into a trained convolutional neural network model (LeNet-5), identifying and judging the swimming posture of the image, and storing a judgment result in the period of time.
4. If the posture judgment result is that drowning is in place and the head of the person is below the water surface in the period of time, marking the person as red and sending alarm information to the mobile phone app of the rescue worker; otherwise its coordinates are relabeled to green.
5. The above judgment is carried out 1-4 times every 5-10 seconds.
Claims (8)
1. A swimming pool monitoring and alarming system is characterized by comprising a swimming cap with a water pressure detection and positioning module, a high-definition panoramic camera, a PC (personal computer) end or a server end, a display and a mobile phone app of a lifesaving person; swimming cap with water pressure detection and location: the swimming cap is provided with a water pressure sensor, a positioning module, a Wifi module and an embedded microcontroller, and the water pressure sensor, the positioning module and the Wifi module are all connected to the embedded microcontroller; the swimmer needs to wear the swimming cap, the water pressure sensor is used for detecting whether the head of the swimmer is under the water surface or giving the position under the water surface, and if the head of the swimmer is under the water surface, the judgment information is transmitted into the embedded microcontroller; the positioning module realizes real-time positioning and transmits coordinate information of a swimmer in the swimming pool into the embedded microcontroller; the embedded microcontroller transmits the received information to a PC (personal computer) end or a server end through a Wifi (wireless fidelity) module; high-definition panoramic camera: the realization is to the panorama control in the swimming pool, and the picture of will shooing is spread into PC end.
2. The pool monitoring and warning system as claimed in claim 1, wherein the PC establishes a two-dimensional coordinate system for the swimming pool, and counts the number of swimmers in the swimming pool in real time according to the swimming cap signal or the image signal; the number and time of each swimmer head under the water surface are counted and judged through the water pressure sensor, and when the number and time of a certain swimmer head under the water surface exceed a threshold time, the PC end gives an alarm to the mobile phone app of the lifesaving personnel through the Wifi module.
3. The pool monitoring alarm system of claim 1 wherein the coordinates of each swimmer's location are determined from the coordinate information transmitted from the cap, and the coordinates of each swimmer are marked green to be displayed on the coordinate system and updated in real time; the swimming cap transmits judgment information of the swimmer above and below the water surface, if the swimmer is below the water surface, the coordinate mark of the swimmer is yellow, the swimmer possibly has a drowning risk, the swimming posture of the swimmer needs to be judged, and if the swimmer is above the water surface, the swimmer is judged to be safe.
4. The swimming pool monitoring and alarming system as claimed in claim 1 or 2, wherein the gesture recognition judgment is performed on the swimmer with the possible risk of drowning through the convolutional neural network (LeNet-5), if the swimmer is detected under the water surface within a certain time (8-20 seconds, different criteria are set at different age stages) and the swimming gesture is judged to be the risk of drowning, the coordinate is marked as red, and the position coordinate of the swimmer in the swimming pool and the result of judging whether the drowning risk exists are transmitted to the mobile phone app of the rescuer;
mobile phone app of the rescuer: receiving a swimming pool coordinate system, real-time coordinates of each swimmer and the number of the real-time swimmers in the swimming pool obtained by processing from a PC (personal computer) end, and displaying the coordinates and the real-time coordinates on a mobile phone screen; the coordinate mark of the swimmer with drowning risk is red; and when the red coordinate appears, the mobile phone sends out vibration and gives an alarm.
5. The pool monitoring and alarm system of claim 1 or 2, wherein when used in an indoor pool, UWB positioning tags are also used on the swimming cap to send UWB positioning pulses continuously; the three UWB base stations respectively measure UWB positioning pulses and feed back measurement results to a PC (personal computer) end (or server end); the PC end estimates the position of the UWB positioning tag by adopting a TOF algorithm according to the received measurement result, so that the downstream swimmer of the swimming cap is positioned; the criterion of the upper and lower water surfaces of the head is still provided by a pressure sensor of the swimmer swimming cap, and the types of the pressure sensor are as follows: and sending the data to a PC (personal computer) end or a server end through the AD conversion post-sending WIFI module.
6. The method as claimed in any one of claims 1 to 4, wherein the PC terminal alarms the lifesaving device through the Wifi module when the number of persons under the water and the time are counted and judged by the water pressure sensor and the number of persons under the water and the time exceed a threshold value.
7. The pool monitoring and alarm system of claim 6, wherein said convolutional neural network based swimmer gesture recognition and determination, convolutional neural network algorithm and LeNet-5 model: monitoring the posture of a swimmer, monitoring the swimmer approaching a threshold, and when the head of the swimmer is positioned below the water surface for 3 seconds:
step 1: taking the picture which is subjected to target segmentation as an input layer, and performing convolution with 6 different 5 × 5 convolution kernels to obtain a 44 × 44 × 6 feature map;
step 2: performing maximum pooling on the obtained feature map by using a 2 × 2 window and taking 2 as a step length, and performing down-sampling; the purpose of this step is to keep the image rotation, translation, etc. invariant and reduce the feature dimension; obtaining a 22 multiplied by 6 characteristic diagram after pooling;
step 3: convolving the feature map obtained in the last step by 16 different 5 × 5 convolution kernels to obtain an 18 × 18 × 16 feature map;
step 4: performing maximum pooling on the obtained feature map by using a 2 × 2 window and taking 2 as a step length to obtain a 9 × 9 × 16 feature map;
step 5: expanding 1298 features obtained in the last step into one-dimensional feature vectors, and reducing the dimension to 400 features through a first full-connection layer, reducing the dimension to 120 features through a second full-connection layer, and reducing the dimension to 84 features through a third full-connection layer; the conversion formula of the feature vector of the upper layer to the feature vector of the lower layer during full connection is
a[i]＝g(W[i]a[i-1])
W is a weight vector; a is[i-1]The input feature vector of the previous layer; a is[i]The layer feature vector is used; g is an activation function, here a ReLU function;
step 6: the last layer of the convolutional network adopts a Softmax classifier, the output result of the last layer is combined, and Softmax divides the result into 2 types which respectively correspond to a normal swimming posture and a swimming posture with drowning risk;
the training set of the convolutional neural network is derived from a monitoring database of a natatorium, and all swimming images are divided into two types, namely a normal swimming posture and a swimming posture with drowning risk.
8. The pool monitoring and warning system as claimed in claim 6, wherein the step 1. obtaining the coordinate information of the swimmer and the judgment information of the head above and below the water surface through the swimming cap is transmitted to the PC terminal, the PC terminal marks the swimmer above the water surface as green, and the swimmer below the water surface as yellow;
step2, matching the image acquired by the high-definition panoramic camera with a swimmer with yellow coordinates in a PC (personal computer) end, finding out the specific position of the swimmer in the image, selecting the image for 8-20 seconds within a certain time, setting image acquisition with different criteria at different age stages, and segmenting the image;
step3, transmitting the segmented image into a trained convolutional neural network model LeNet-5, identifying and judging the swimming posture of the image, and storing a judgment result in the period of time;
step4, if the posture judgment result is that drowning is caused and the head of the person is under the water surface in the period of time, marking the person as red and sending alarm information to the mobile phone app of the rescue worker; otherwise, the coordinates are marked as green again;
and 5, judging the steps 1-4 once every 5-10 seconds.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011576423.XA CN112489372A (en) | 2020-12-28 | 2020-12-28 | Swimming pool monitoring and alarming system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011576423.XA CN112489372A (en) | 2020-12-28 | 2020-12-28 | Swimming pool monitoring and alarming system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112489372A true CN112489372A (en) | 2021-03-12 |
Family
ID=74915820
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011576423.XA Pending CN112489372A (en) | 2020-12-28 | 2020-12-28 | Swimming pool monitoring and alarming system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112489372A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114613097A (en) * | 2022-03-10 | 2022-06-10 | 孔丽 | Automatic planning system based on function integration association |
| CN114783147A (en) * | 2022-04-19 | 2022-07-22 | 珠海市杰理科技股份有限公司 | Intelligent monitoring method and device, wearable device and readable storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105069413A (en) * | 2015-07-27 | 2015-11-18 | 电子科技大学 | Human body gesture identification method based on depth convolution neural network |
| US9640058B1 (en) * | 2016-05-10 | 2017-05-02 | Jimmy Bollman | Swimming pool monitor |
| CN106912006A (en) * | 2017-04-01 | 2017-06-30 | 成都精位科技有限公司 | A kind of wisdom swimming exercise system and the method for realizing Sport Administration |
| CN207946102U (en) * | 2018-02-01 | 2018-10-09 | 杭州水豚科技有限公司 | Swimming pool is drowned positioning system |
| CN109102678A (en) * | 2018-08-30 | 2018-12-28 | 青岛联合创智科技有限公司 | A kind of drowned behavioral value method of fusion UWB indoor positioning and video object detection and tracking technique |
| CN109635636A (en) * | 2018-10-30 | 2019-04-16 | 国家新闻出版广电总局广播科学研究院 | The pedestrian that blocking characteristic based on attributive character and weighting blends recognition methods again |
| CN109753948A (en) * | 2019-01-28 | 2019-05-14 | 珠海格力电器股份有限公司 | Air conditioning control method and device, storage medium and processor based on microwave radar |
| CN111833567A (en) * | 2020-05-30 | 2020-10-27 | 北京方德泳安体育文化有限公司 | Motion detection system based on UWB and nine-axis gyroscope |
-
2020
- 2020-12-28 CN CN202011576423.XA patent/CN112489372A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105069413A (en) * | 2015-07-27 | 2015-11-18 | 电子科技大学 | Human body gesture identification method based on depth convolution neural network |
| US9640058B1 (en) * | 2016-05-10 | 2017-05-02 | Jimmy Bollman | Swimming pool monitor |
| CN106912006A (en) * | 2017-04-01 | 2017-06-30 | 成都精位科技有限公司 | A kind of wisdom swimming exercise system and the method for realizing Sport Administration |
| CN207946102U (en) * | 2018-02-01 | 2018-10-09 | 杭州水豚科技有限公司 | Swimming pool is drowned positioning system |
| CN109102678A (en) * | 2018-08-30 | 2018-12-28 | 青岛联合创智科技有限公司 | A kind of drowned behavioral value method of fusion UWB indoor positioning and video object detection and tracking technique |
| CN109635636A (en) * | 2018-10-30 | 2019-04-16 | 国家新闻出版广电总局广播科学研究院 | The pedestrian that blocking characteristic based on attributive character and weighting blends recognition methods again |
| CN109753948A (en) * | 2019-01-28 | 2019-05-14 | 珠海格力电器股份有限公司 | Air conditioning control method and device, storage medium and processor based on microwave radar |
| CN111833567A (en) * | 2020-05-30 | 2020-10-27 | 北京方德泳安体育文化有限公司 | Motion detection system based on UWB and nine-axis gyroscope |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114613097A (en) * | 2022-03-10 | 2022-06-10 | 孔丽 | Automatic planning system based on function integration association |
| CN114783147A (en) * | 2022-04-19 | 2022-07-22 | 珠海市杰理科技股份有限公司 | Intelligent monitoring method and device, wearable device and readable storage medium |
| CN114783147B (en) * | 2022-04-19 | 2023-10-27 | 珠海市杰理科技股份有限公司 | Intelligent monitoring method and device, wearable device and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110569772B (en) | Method for detecting state of personnel in swimming pool | |
| CN102693606B (en) | A kind of swimming pool anti-drowning method for early warning based on shooting network and system | |
| CN109522793A (en) | More people's unusual checkings and recognition methods based on machine vision | |
| US20200388135A1 (en) | Automated water body area monitoring | |
| CN103021136B (en) | System and method for monitoring swimming pool drowning based on internet of things | |
| CN113516076B (en) | Attention mechanism improvement-based lightweight YOLO v4 safety protection detection method | |
| CN110155274B (en) | Underwater intelligent lifesaving system for swimming pool | |
| CN112489372A (en) | Swimming pool monitoring and alarming system | |
| CN106022230A (en) | Video-based detection method for drowning event in swimming pool | |
| CN110246306A (en) | Underwater exercise safety monitoring system design method based on wireless signal transmission | |
| CN104318716A (en) | Drowning detection pre-warning system using attitude calculation | |
| CN101650870B (en) | Safety monitoring method and device for swimming pool | |
| CN111341068A (en) | Drilling site dangerous area early warning system and method based on deep learning | |
| CN112489371A (en) | Swimming pool drowning prevention early warning system based on computer vision | |
| CN111028480A (en) | Drowning detection and alarm system | |
| CN111833567B (en) | Motion detection system based on UWB and nine-axis gyroscope | |
| CN104484654A (en) | Drowning prevention identification method based on mode identification and fingerprint matching and positioning algorithm | |
| CN215310088U (en) | Swimming cap for safety monitoring of swimming pool | |
| CN202033875U (en) | Swimming pool anti-drowning early warning system based on shooting network | |
| Niranjan et al. | IoT-based safety system for swimming pools to avoid sinking of individuals | |
| CN210377785U (en) | Swimming pool drowning prevention intelligent identification and positioning device | |
| Handalage et al. | Computer vision enabled drowning detection system | |
| CN114612933A (en) | Monocular social distance detection tracking method | |
| CN211015841U (en) | Drowning event detection system | |
| CN117011946B (en) | Unmanned rescue method based on human behavior recognition |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210312 |