CN111428696A - Intelligent abnormity detection emergency rescue method, device and system - Google Patents
Intelligent abnormity detection emergency rescue method, device and system Download PDFInfo
- Publication number
- CN111428696A CN111428696A CN202010442990.XA CN202010442990A CN111428696A CN 111428696 A CN111428696 A CN 111428696A CN 202010442990 A CN202010442990 A CN 202010442990A CN 111428696 A CN111428696 A CN 111428696A
- Authority
- CN
- China
- Prior art keywords
- human body
- emergency rescue
- image
- intelligent
- drowning
- 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.)
- Withdrawn
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 40
- 238000000034 method Methods 0.000 title claims abstract description 39
- 206010013647 Drowning Diseases 0.000 claims abstract description 34
- 238000012545 processing Methods 0.000 claims abstract description 17
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 13
- 230000006399 behavior Effects 0.000 claims description 36
- 230000009182 swimming Effects 0.000 claims description 33
- 238000012549 training Methods 0.000 claims description 28
- 230000008859 change Effects 0.000 claims description 19
- 238000013527 convolutional neural network Methods 0.000 claims description 19
- 230000036391 respiratory frequency Effects 0.000 claims description 18
- 206010000117 Abnormal behaviour Diseases 0.000 claims description 16
- 230000005856 abnormality Effects 0.000 claims description 10
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 230000009189 diving Effects 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 238000007654 immersion Methods 0.000 claims description 4
- 210000003928 nasal cavity Anatomy 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000036387 respiratory rate Effects 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 210000000115 thoracic cavity Anatomy 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000013475 authorization Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 206010003591 Ataxia Diseases 0.000 description 1
- 206010010947 Coordination abnormal Diseases 0.000 description 1
- 208000003464 asthenopia Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 208000016290 incoordination Diseases 0.000 description 1
- 230000006996 mental state Effects 0.000 description 1
- 230000037081 physical activity Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000029058 respiratory gaseous exchange Effects 0.000 description 1
- 230000001360 synchronised effect 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24133—Distances to prototypes
- G06F18/24137—Distances to cluster centroïds
- G06F18/2414—Smoothing the distance, e.g. radial basis function networks [RBFN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
- G06V40/23—Recognition of whole body movements, e.g. for sport training
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Probability & Statistics with Applications (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Alarm Systems (AREA)
Abstract
The invention relates to the technical field of intelligent self-rescue, and discloses an intelligent abnormity detection emergency rescue method, device and system, wherein the method comprises the following steps: establishing a library in advance, and collecting human body life parameter data and a field video image sequence in real time; processing vital parameter data and a live video image sequence in real time; judging whether the human body is in a drowning emergency; the processor sends out a control instruction according to the judgment result; receiving a control instruction sent by a processor or an instruction sent by a background authorized manager to open an emergency rescue device detachably connected to a human body, so as to ensure that the human body floats on the water surface and simultaneously send an alarm signal; the invention can automatically identify and carry out multiple control, plays an important role when the swimmer is drowned to carry out self rescue, ensures that the swimmer can swim at ease, and simultaneously has higher practical value and wide application prospect.
Description
Technical Field
The invention relates to the technical field of intelligent self-rescue, in particular to an intelligent abnormity detection emergency rescue method.
Background
With the development of economy and the progress of society, the living standard and quality of people are higher and higher, the demand for cultural and physical activities is gradually increased, many people gradually realize the importance of sports, and swimming is gradually linked with the life of people as a widely popularized project. Can build up the health, change the mental state and realize certain rehabilitation training through swimming.
Learning swimming in a swimming pool or swimming in a field river, a lake and the sea is a good choice. However, some drowning situations are easy to occur inevitably in the process of swimming under water, and drowning is possible if the drowning situation is found out untimely. The existing drowning prevention measures are taken as drowning emergency measures by carrying some swim rings or floating bags, but the swimmers cannot open hands and feet when wearing the facilities in the swimming process, and the effect is unsatisfactory.
How to guarantee the safety of swimming of children and how to strengthen the guarantee mechanism of a natatorium is a popular social hot topic. The existing overall solution and technology have the following core problems: the water-saving agent is not suitable for the dense water areas of people: for example, the design of detecting and judging the stationary time of the shelter by adopting the underwater infrared is not suitable for a water area with more people and is not suitable for synchronous integrated intelligent supervision of a large number of people; the false alarm rate is high: due to the problem of an alarm algorithm, the false alarm rate of the SOS alarm signal is high, so that scene panic and incoordination are caused, and the stress and fatigue of the lifeguard are invisibly increased. Moreover, the physical reaction mechanism when the SOS event occurs is too primitive and monotonous to be discovered and disposed in time effectively.
Aiming at the problems, the novel self-rescue device is provided, and normal swimming of people is not influenced while the self-rescue device is realized in case of drowning.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides an intelligent abnormity detection emergency rescue method, which is used for solving the problems in the background technology.
The technical scheme adopted by the invention for solving the technical problems is as follows:
the invention provides an intelligent abnormity detection emergency rescue method, which comprises the following steps:
pre-building a library, comprising:
collecting the respiratory frequency of human bodies in different sections and the normal ranges of the conversion rate, the heart rate, the change rate, the humidity and the change rate of swimming behaviors including diving, free swimming, backstroke and breaststroke in advance according to age sections, and establishing a life database;
the method comprises the steps of pre-collecting video sequences of various swimming posture behaviors of a human body under a fixed single background, collecting video sequences of drowning behaviors of the human body under the fixed single background, extracting a moving human body target by using a Kalman filtering algorithm, extracting a moving human body moving target image, storing the detected moving human body target image, and constructing a training database;
respectively training a Bayes classifier and a convolutional neural network by using images in a training database to obtain the trained Bayes classifier and convolutional neural network, wherein the Bayes classifier is established in the following process: firstly, respectively extracting three characteristics of the length-width ratio, the image entropy and the Hu invariant moment of an image according to various swimming posture behaviors and drowning behavior categories of the image in a training database, establishing a Bayes classifier according to the conditional probability distribution of behavior image characteristic values, and realizing the classification and identification of abnormal behaviors by using a Bayes formula;
collecting human body life parameter data and a field video image sequence in real time;
processing vital parameter data and a live video image sequence in real time;
judging whether the human body is in a drowning emergency;
the processor sends out a control instruction according to the judgment result;
receiving a control instruction sent by a processor or an instruction sent by a background authorized manager to open an emergency rescue device detachably connected to the human body, wherein the emergency rescue device is used for ensuring that the human body floats on the water surface;
and simultaneously sending out an alarm signal: and sending the personnel information to the rescue working platform, and turning on a light alarm arranged on the emergency rescue device and a voice alarm arranged on the rescue working platform.
Preferably, the real-time processing of live video images comprises the steps of:
firstly, rapidly detecting a moving target by adopting improved frame difference, then carrying out human body analysis in a moving target area, specifically, rapidly screening out a suspected human body target based on the shape characteristics of the target, then extracting HOG characteristics only aiming at the suspected human body target area, classifying by adopting an Adaboost method, determining whether the suspected human body target area contains a human body, then respectively inputting the extracted moving human body image into a trained Bayes classifier and a trained convolutional neural network, and respectively carrying out Bayes classifier abnormal behavior classification recognition and convolutional neural network abnormal behavior classification recognition on each extracted picture to respectively obtain test results; when abnormal behaviors are detected, comprehensively judging the two test results, and directly outputting the identification result when the two classification identification results are consistent; when one classification identification detects that there is abnormality and the other classification identification detects that there is no abnormality, giving an early warning of possible abnormality and continuously detecting the next frame of image; and when the two kinds of classification and identification are detected to have abnormity but the detection types are different, giving an early warning of abnormity existence and uncertain type, and continuously detecting the next frame of image until an identification result is output.
Preferably, the human vital parameter data comprises heart rate, respiratory rate;
the respiratory frequency comprises a respiratory frequency sensor arranged on the surface of the thoracic cavity and a water immersion sensor arranged in the nasal cavity of the human body.
Preferably, the real-time processing vital parameter data includes:
calculating the size of the respiratory frequency and the transformation rate;
calculating the heart rate and the change rate;
and calculating the humidity change rate and the humidity.
Preferably, the judging whether the human body is in a drowning emergency includes:
comparing the acquired respiratory frequency, the acquired heart rate, the acquired humidity and the acquired humidity with a life database, and judging that the drowning emergency situation exists if at least 4 of the six data exceed a normal range;
if the detection result of the live video image is abnormal, at least two of the six data exceed the normal range, and then the drowning emergency is judged.
Preferably, the emergency rescue apparatus includes a detachable connection to the person's body and a controlled inflation component.
The invention also provides an intelligent abnormity detection emergency rescue device, which comprises:
the preprocessing module is used for building a library in advance and comprises:
collecting the respiratory frequency of human bodies in different sections and the normal ranges of the conversion rate, the heart rate, the change rate, the humidity and the change rate of swimming behaviors including diving, free swimming, backstroke and breaststroke in advance according to age sections, and establishing a life database;
the method comprises the steps of pre-collecting video sequences of various swimming posture behaviors of a human body under a fixed single background, collecting video sequences of drowning behaviors of the human body under the fixed single background, extracting a moving human body target by using a Kalman filtering algorithm, extracting a moving human body moving target image, storing the detected moving human body target image, and constructing a training database;
respectively training the Bayes classifier and the convolutional neural network by using the images in the training database to obtain training
The method comprises the following steps of establishing a good Bayes classifier and a convolutional neural network, wherein the Bayes classifier comprises the following steps: firstly, respectively extracting three characteristics of the length-width ratio, the image entropy and the Hu invariant moment of an image according to various swimming posture behaviors and drowning behavior categories of the image in a training database, establishing a Bayes classifier according to the conditional probability distribution of behavior image characteristic values, and realizing the classification and identification of abnormal behaviors by using a Bayes formula;
the data acquisition module is used for acquiring human body life parameter data and a field video image sequence in real time;
the data processing module is used for processing the vital parameter data and the field video image sequence in real time;
the controller module is used for judging whether the human body is in a drowning emergency condition or not and sending a control instruction according to a judgment result;
and the execution module is used for receiving a control instruction sent by the processor or an instruction sent by a background authorization manager, opening the emergency rescue device detachably connected to the human body, ensuring that the human body floats on the water surface, sending an alarm signal, sending personnel information to the rescue working platform, and opening a light alarm arranged on the emergency rescue device and a voice alarm arranged on the rescue working platform.
Preferably, the controller module further comprises an electronic ring worn on the arm, the electronic ring is wirelessly connected with the control module, and the electronic ring is provided with a manual instruction control button.
The invention also provides an intelligent abnormity detection emergency rescue system, which comprises:
one or more processors;
storage means for storing one or more programs;
an intelligent anomaly detection emergency rescue device;
when the one or more programs are executed by the one or more processors, the intelligent anomaly detection emergency rescue apparatus is caused to implement the intelligent anomaly detection emergency rescue method as described above in cooperation with the one or more processors.
The present invention also provides a storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the intelligent anomaly detection emergency rescue method as described above.
Compared with the prior art, the invention has the following beneficial effects:
the invention adopts multiple judgment standards to share, integrates human life information and video identification technology, effectively reduces false alarm rate, avoids visual fatigue and negligence caused by manual supervision, particularly various control ports, can effectively resist various factors causing drowning danger, can directly generate rescue effect by combining supervision and self-rescue, and wins time for the final rescue of a rescuer, so that accurate and effective intelligent abnormal detection emergency rescue information can be obtained by further processing for drivers to refer.
Further salient features and significant advances with respect to the present invention over the prior art are described in further detail in the examples section.
Drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments with reference to the following drawings:
FIG. 1 is a schematic flow chart of an emergency rescue method with intelligent anomaly detection according to the present invention;
fig. 2 is a schematic structural diagram of an intelligent abnormality detection emergency rescue device according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that certain names are used throughout the specification and claims to refer to particular components. It will be understood that one of ordinary skill in the art may refer to the same component by different names. The present specification and claims do not intend to distinguish between components that differ in name but not function. As used in the specification and claims of this application, the terms "comprises" and "comprising" are intended to be open-ended terms that should be interpreted as "including, but not limited to," or "including, but not limited to. The embodiments described in the detailed description are preferred embodiments of the present invention and are not intended to limit the scope of the present invention.
Moreover, those skilled in the art will appreciate that aspects of the present invention may be embodied as a system, method or computer program product. Accordingly, various aspects of the present invention may be embodied in a combination of hardware and software, which may be referred to herein generally as a "circuit," module "or" system. Furthermore, in some embodiments, various aspects of the invention may also be embodied in the form of a computer program product in one or more microcontroller-readable media having microcontroller-readable program code embodied therein.
The emergency rescue method for intelligent anomaly detection in the embodiment comprises the following steps of:
pre-building a library, comprising:
collecting the respiratory frequency of human bodies in different sections and the normal ranges of the conversion rate, the heart rate, the change rate, the humidity and the change rate of swimming behaviors including diving, free swimming, backstroke and breaststroke in advance according to age sections, and establishing a life database;
the method comprises the steps of pre-collecting video sequences of various swimming posture behaviors of a human body under a fixed single background, collecting video sequences of drowning behaviors of the human body under the fixed single background, extracting a moving human body target by using a Kalman filtering algorithm, extracting a moving human body moving target image, storing the detected moving human body target image, and constructing a training database;
respectively training the Bayes classifier and the convolutional neural network by using the images in the training database to obtain training
The method comprises the following steps of establishing a good Bayes classifier and a convolutional neural network, wherein the Bayes classifier comprises the following steps: firstly, respectively extracting three characteristics of the length-width ratio, the image entropy and the Hu invariant moment of an image according to various swimming posture behaviors and drowning behavior categories of the image in a training database, establishing a Bayes classifier according to the conditional probability distribution of behavior image characteristic values, and realizing the classification and identification of abnormal behaviors by using a Bayes formula;
collecting human body life parameter data and a field video image sequence in real time;
the human body life parameter data comprises heart rate and respiratory rate;
the respiratory frequency comprises a respiratory frequency sensor arranged on the surface of the thoracic cavity and a water immersion sensor arranged in the nasal cavity of the human body;
in the embodiment, the accuracy of drowning judgment can be comprehensively ensured by adopting the heart rate and the respiration as well as the immersion sensor arranged in the nasal cavity of the human body;
processing vital parameter data and a live video image sequence in real time;
the real-time processing vital parameter data comprises:
calculating the size of the respiratory frequency and the transformation rate;
calculating the heart rate and the change rate;
calculating the humidity change rate and the humidity;
the real-time processing of live video images comprises the steps of:
firstly, rapidly detecting a moving target by adopting improved frame difference, then carrying out human body analysis in a moving target area, specifically, rapidly screening out a suspected human body target based on the shape characteristics of the target, then extracting HOG characteristics only aiming at the suspected human body target area, classifying by adopting an Adaboost method, determining whether the suspected human body target area contains a human body, then respectively inputting the extracted moving human body image into a trained Bayes classifier and a trained convolutional neural network, and respectively carrying out Bayes classifier abnormal behavior classification recognition and convolutional neural network abnormal behavior classification recognition on each extracted picture to respectively obtain test results; when abnormal behaviors are detected, comprehensively judging the two test results, and directly outputting the identification result when the two classification identification results are consistent; when one classification identification detects that there is abnormality and the other classification identification detects that there is no abnormality, giving an early warning of possible abnormality and continuously detecting the next frame of image; when the two kinds of classification and identification are detected to have abnormity but the detection types are different, giving an early warning of abnormity existence and uncertain type, and continuously detecting the next frame of image until an identification result is output;
the human body abnormal behavior detection method combining the Bayesian classifier and the convolutional neural network is adopted, so that the recognition precision can be effectively improved;
judge whether the human body is in drowned emergency, specifically include:
comparing the acquired respiratory frequency, the acquired heart rate, the acquired humidity and the acquired humidity with a life database, and judging that the drowning emergency situation exists if at least 4 of the six data exceed a normal range;
if the detection result of the live video image is abnormal, judging that the drowning emergency situation exists when at least two of the six data exceed the normal range;
the embodiment effectively combines the human body data and the video monitoring data together, and carries out different judgment standards according to different conditions, so that the accuracy rate of the monitoring result is greatly increased, and the zero false alarm rate is basically achieved in practical application;
the processor sends out a control instruction according to the judgment result;
receiving a control instruction sent by a processor or an instruction sent by a background authorized manager to open an emergency rescue device detachably connected to a human body, wherein the emergency rescue device is used for ensuring that the human body floats on the water surface and comprises a detachable connection part and a controlled inflation part which are connected with the human body;
and simultaneously sending out an alarm signal: and sending the personnel information to the rescue working platform, and turning on a light alarm arranged on the emergency rescue device and a voice alarm arranged on the rescue working platform.
An intelligent anomaly detection emergency rescue device, comprising:
the preprocessing module is used for building a library in advance and comprises:
collecting the respiratory frequency of human bodies in different sections and the normal ranges of the conversion rate, the heart rate, the change rate, the humidity and the change rate of swimming behaviors including diving, free swimming, backstroke and breaststroke in advance according to age sections, and establishing a life database;
the method comprises the steps of pre-collecting video sequences of various swimming posture behaviors of a human body under a fixed single background, collecting video sequences of drowning behaviors of the human body under the fixed single background, extracting a moving human body target by using a Kalman filtering algorithm, extracting a moving human body moving target image, storing the detected moving human body target image, and constructing a training database;
respectively training the Bayes classifier and the convolutional neural network by using the images in the training database to obtain training
The method comprises the following steps of establishing a good Bayes classifier and a convolutional neural network, wherein the Bayes classifier comprises the following steps: firstly, respectively extracting three characteristics of the length-width ratio, the image entropy and the Hu invariant moment of an image according to various swimming posture behaviors and drowning behavior categories of the image in a training database, establishing a Bayes classifier according to the conditional probability distribution of behavior image characteristic values, and realizing the classification and identification of abnormal behaviors by using a Bayes formula;
the data acquisition module is used for acquiring human body life parameter data and a field video image sequence in real time;
the data processing module is used for processing the vital parameter data and the field video image sequence in real time;
the controller module is used for judging whether the human body is in a drowning emergency condition or not and sending a control instruction according to a judgment result;
the execution module is used for receiving a control instruction sent by the processor or an instruction sent by a background authorized manager to open the emergency rescue device detachably connected to the human body and ensure that the human body floats on the water surface;
the control module also comprises an electronic ring worn on the arm, the electronic ring is wirelessly connected with the control module, and the electronic ring is provided with a manual instruction control button.
This embodiment still provides an intelligence anomaly detection emergency rescue system, includes:
one or more processors;
storage means for storing one or more programs;
an intelligent anomaly detection emergency rescue device;
when the one or more programs are executed by the one or more processors, the intelligent anomaly detection emergency rescue apparatus is caused to implement the intelligent anomaly detection emergency rescue method as described above in cooperation with the one or more processors.
The present embodiment also provides a storage medium having a computer program stored thereon, where the computer program is executed by a processor to perform the steps of the intelligent anomaly detection emergency rescue method as described above.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.
Claims (10)
1. An intelligent abnormity detection emergency rescue method is characterized by comprising the following steps:
pre-building a library, comprising:
collecting the respiratory frequency of human bodies in different sections and the normal ranges of the conversion rate, the heart rate, the change rate, the humidity and the change rate of swimming behaviors including diving, free swimming, backstroke and breaststroke in advance according to age sections, and establishing a life database;
the method comprises the steps of pre-collecting video sequences of various swimming posture behaviors of a human body under a fixed single background, collecting video sequences of drowning behaviors of the human body under the fixed single background, extracting a moving human body target by using a Kalman filtering algorithm, extracting a moving human body moving target image, storing the detected moving human body target image, and constructing a training database;
respectively training a Bayes classifier and a convolutional neural network by using images in a training database to obtain the trained Bayes classifier and convolutional neural network, wherein the Bayes classifier is established in the following process: firstly, respectively extracting three characteristics of the length-width ratio, the image entropy and the Hu invariant moment of an image according to various swimming posture behaviors and drowning behavior categories of the image in a training database, establishing a Bayes classifier according to the conditional probability distribution of behavior image characteristic values, and realizing the classification and identification of abnormal behaviors by using a Bayes formula;
collecting human body life parameter data and a field video image sequence in real time;
processing vital parameter data and a live video image sequence in real time;
judging whether the human body is in a drowning emergency;
the processor sends out a control instruction according to the judgment result;
receiving a control instruction sent by a processor or an instruction sent by a background authorized manager to open an emergency rescue device detachably connected to the human body, wherein the emergency rescue device is used for ensuring that the human body floats on the water surface;
and simultaneously sending out an alarm signal: and sending the personnel information to the rescue working platform, and turning on a light alarm arranged on the emergency rescue device and a voice alarm arranged on the rescue working platform.
2. The intelligent anomaly detection emergency rescue method according to claim 1, wherein the real-time processing of live video images comprises the following steps:
firstly, rapidly detecting a moving target by adopting improved frame difference, then carrying out human body analysis in a moving target area, specifically, rapidly screening out a suspected human body target based on the shape characteristics of the target, then extracting HOG characteristics only aiming at the suspected human body target area, classifying by adopting an Adaboost method, determining whether the suspected human body target area contains a human body, then respectively inputting the extracted moving human body image into a trained Bayes classifier and a trained convolutional neural network, and respectively carrying out Bayes classifier abnormal behavior classification recognition and convolutional neural network abnormal behavior classification recognition on each extracted picture to respectively obtain test results; when abnormal behaviors are detected, comprehensively judging the two test results, and directly outputting the identification result when the two classification identification results are consistent; when one classification identification detects that there is abnormality and the other classification identification detects that there is no abnormality, giving an early warning of possible abnormality and continuously detecting the next frame of image; and when the two kinds of classification and identification are detected to have abnormity but the detection types are different, giving an early warning of abnormity existence and uncertain type, and continuously detecting the next frame of image until an identification result is output.
3. The intelligent abnormity detection emergency rescue method according to claim 1, wherein the human body life parameter data comprises heart rate, respiratory rate;
the respiratory frequency comprises a respiratory frequency sensor arranged on the surface of the thoracic cavity and a water immersion sensor arranged in the nasal cavity of the human body.
4. The intelligent abnormity detection emergency rescue method according to claim 1, wherein the real-time processing of the vital parameter data comprises:
calculating the size of the respiratory frequency and the transformation rate;
calculating the heart rate and the change rate;
and calculating the humidity change rate and the humidity.
5. The intelligent abnormity detection emergency rescue method according to claim 1, wherein said judging whether the human body is in drowning emergency comprises:
comparing the acquired respiratory frequency, the acquired heart rate, the acquired humidity and the acquired humidity with a life database, and judging that the drowning emergency situation exists if at least 4 of the six data exceed a normal range;
if the detection result of the live video image is abnormal, at least two of the six data exceed the normal range, and then the drowning emergency is judged.
6. The emergency rescue method according to claim 1, wherein the emergency rescue apparatus comprises a detachable connection part with a human body and a controlled inflation part.
7. An intelligent anomaly detection emergency rescue device, comprising:
the preprocessing module is used for building a library in advance and comprises:
collecting the respiratory frequency of human bodies in different sections and the normal ranges of the conversion rate, the heart rate, the change rate, the humidity and the change rate of swimming behaviors including diving, free swimming, backstroke and breaststroke in advance according to age sections, and establishing a life database;
the method comprises the steps of pre-collecting video sequences of various swimming posture behaviors of a human body under a fixed single background, collecting video sequences of drowning behaviors of the human body under the fixed single background, extracting a moving human body target by using a Kalman filtering algorithm, extracting a moving human body moving target image, storing the detected moving human body target image, and constructing a training database;
respectively training a Bayes classifier and a convolutional neural network by using images in a training database to obtain the trained Bayes classifier and convolutional neural network, wherein the Bayes classifier is established in the following process: firstly, respectively extracting three characteristics of the length-width ratio, the image entropy and the Hu invariant moment of an image according to various swimming posture behaviors and drowning behavior categories of the image in a training database, establishing a Bayes classifier according to the conditional probability distribution of behavior image characteristic values, and realizing the classification and identification of abnormal behaviors by using a Bayes formula;
the data acquisition module is used for acquiring human body life parameter data and a field video image sequence in real time;
the data processing module is used for processing the vital parameter data and the field video image sequence in real time;
the controller module is used for judging whether the human body is in a drowning emergency condition or not and sending a control instruction according to a judgment result;
and the execution module is used for receiving a control instruction sent by the processor or an instruction sent by a background authorization manager, opening the emergency rescue device detachably connected to the human body, ensuring that the human body floats on the water surface, sending an alarm signal, sending personnel information to the rescue working platform, and opening a light alarm arranged on the emergency rescue device and a voice alarm arranged on the rescue working platform.
8. The emergency rescue apparatus with intelligent anomaly detection according to claim 7, wherein the controller module further comprises an electronic ring worn on the arm, the electronic ring is wirelessly connected with the control module, and the electronic ring is provided with a manual command control button.
9. An intelligent anomaly detection emergency rescue system, comprising:
one or more processors;
storage means for storing one or more programs;
an intelligent anomaly detection emergency rescue device;
the one or more programs, when executed by the one or more processors, cause an intelligent anomaly detection emergency rescue apparatus to implement, in cooperation with the one or more processors, the method of any one of claims 1-6.
10. A storage medium, characterized in that the storage medium has stored thereon a computer program which, when being executed by a processor, performs the steps of the intelligent anomaly detection emergency rescue method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010442990.XA CN111428696A (en) | 2020-05-22 | 2020-05-22 | Intelligent abnormity detection emergency rescue method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010442990.XA CN111428696A (en) | 2020-05-22 | 2020-05-22 | Intelligent abnormity detection emergency rescue method, device and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111428696A true CN111428696A (en) | 2020-07-17 |
Family
ID=71551199
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010442990.XA Withdrawn CN111428696A (en) | 2020-05-22 | 2020-05-22 | Intelligent abnormity detection emergency rescue method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111428696A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113807328A (en) * | 2021-11-18 | 2021-12-17 | 济南和普威视光电技术有限公司 | Target detection method, device and medium based on algorithm fusion |
| CN114294047A (en) * | 2021-12-07 | 2022-04-08 | 中国人民解放军陆军军医大学 | Intelligent search and rescue system in special environments such as disasters |
| CN116088436A (en) * | 2022-12-07 | 2023-05-09 | 中用科技(南通)有限公司 | Industrial production field data acquisition method based on LPWAN technology |
| CN116088436B (en) * | 2022-12-07 | 2024-11-05 | 中用科技(南通)有限公司 | Industrial production field data acquisition method based on LPWAN technology |
-
2020
- 2020-05-22 CN CN202010442990.XA patent/CN111428696A/en not_active Withdrawn
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113807328A (en) * | 2021-11-18 | 2021-12-17 | 济南和普威视光电技术有限公司 | Target detection method, device and medium based on algorithm fusion |
| CN113807328B (en) * | 2021-11-18 | 2022-03-18 | 济南和普威视光电技术有限公司 | Target detection method, device and medium based on algorithm fusion |
| CN114294047A (en) * | 2021-12-07 | 2022-04-08 | 中国人民解放军陆军军医大学 | Intelligent search and rescue system in special environments such as disasters |
| CN114294047B (en) * | 2021-12-07 | 2023-11-14 | 中国人民解放军陆军军医大学 | Intelligent search and rescue system under special environments such as disasters |
| CN116088436A (en) * | 2022-12-07 | 2023-05-09 | 中用科技(南通)有限公司 | Industrial production field data acquisition method based on LPWAN technology |
| CN116088436B (en) * | 2022-12-07 | 2024-11-05 | 中用科技(南通)有限公司 | Industrial production field data acquisition method based on LPWAN technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102693606B (en) | A kind of swimming pool anti-drowning method for early warning based on shooting network and system | |
| CN107622505B (en) | Drowning monitoring and detecting method for swimming pool | |
| Alshbatat et al. | Automated vision-based surveillance system to detect drowning incidents in swimming pools | |
| US20200388135A1 (en) | Automated water body area monitoring | |
| CN108647575B (en) | Drowning early warning method based on optical vision analysis | |
| CN107566797A (en) | A kind of drowned monitor and detection device of swimming pool | |
| CN111428696A (en) | Intelligent abnormity detection emergency rescue method, device and system | |
| CN114219833B (en) | Overwater and underwater computer vision comprehensive drowning judgment system | |
| CN114359373B (en) | Swimming pool drowning prevention target behavior identification method and device, computer equipment and storage medium | |
| CN202033875U (en) | Swimming pool anti-drowning early warning system based on shooting network | |
| CN111833567B (en) | Motion detection system based on UWB and nine-axis gyroscope | |
| WO2021146617A1 (en) | Image based aquatic alert system | |
| CN116152928A (en) | Drowning prevention early warning method and system based on lightweight human body posture estimation model | |
| CN104484654A (en) | Drowning prevention identification method based on mode identification and fingerprint matching and positioning algorithm | |
| Hayat et al. | Comprehensive and comparative study of drowning person detection and rescue systems | |
| Shehata et al. | A Survey of Drowning Detection Techniques | |
| CN114155470A (en) | River channel area intrusion detection method, system and storage medium | |
| CN110443979A (en) | A kind of drowned salvage system, self-help apparatus and monitoring system | |
| Jalalifar et al. | Enhancing water safety: exploring recent technological approaches for drowning detection | |
| CN111557654A (en) | Monitoring and automatic rescue integrated human body security method, device and system | |
| CN111557653A (en) | Portable self-rescue device, and swimmer protection method, equipment and system based on device | |
| CN113468945A (en) | Swimmer drowning detection method | |
| CN111557655A (en) | Automatic control method, device and system based on underwater emergency rescue device | |
| TWM650345U (en) | Swimming pool drowning detection and alarm system | |
| CN111547209A (en) | Drowning prevention safety guarantee method, device and 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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20200717 |