CN115147755A - Personnel rescue evacuation method, system, device, electronic equipment and storage medium - Google Patents
Personnel rescue evacuation method, system, device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115147755A CN115147755A CN202210646230.XA CN202210646230A CN115147755A CN 115147755 A CN115147755 A CN 115147755A CN 202210646230 A CN202210646230 A CN 202210646230A CN 115147755 A CN115147755 A CN 115147755A
- Authority
- CN
- China
- Prior art keywords
- target space
- target
- video stream
- stream data
- real
- 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
Images
Classifications
-
- 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
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Signal Processing (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Alarm Systems (AREA)
Abstract
The application discloses a personnel rescue evacuation method, a system, a device, electronic equipment and a storage medium, wherein the personnel rescue evacuation method comprises the following steps: acquiring real-time video stream data of a target space; when a preset dangerous event occurs in the target space, analyzing real-time video stream data of the target space, determining whether abnormal personnel exist in the target space; responding to the abnormal personnel existing in the target space, and sending a first reminding message to rescue and evacuate the abnormal personnel. By means of the scheme, rescue evacuation efficiency can be improved.
Description
Technical Field
The present disclosure relates to the field of image recognition technologies, and in particular, to a method, a system, a device, an electronic device, and a storage medium for rescue and evacuation.
Background
In case of a dangerous event, for example, a fire disaster, in recent years, there are problems that a fire rapidly spreads after a fire disaster occurs in a high-rise building, water supply is difficult, people are difficult to evacuate and rescue, and the like. In addition, the number of people is large and the people are dense, so that the people are not familiar with the conditions of exits, fire-fighting measures and the like in the building, particularly, the positions and the identities of the trapped people cannot be checked and mastered quickly and effectively at night when a fire disaster occurs, and great difficulty is brought to evacuation, so that the important significance is provided for how to effectively monitor whether people are detained in an evacuation area or not when the fire disaster occurs.
Disclosure of Invention
The technical problem mainly solved by the application is to provide a personnel rescue evacuation method, a personnel rescue evacuation system, a personnel rescue evacuation device, electronic equipment and a storage medium.
The application provides a person rescue evacuation method in a first aspect, and the person rescue evacuation method comprises the following steps: acquiring real-time video stream data of a target space; when a preset dangerous event occurs in the target space, analyzing real-time video stream data of the target space, and determining whether abnormal personnel exist in the target space; responding to the abnormal personnel existing in the target space, and sending a first reminding message to rescue and evacuate the abnormal personnel.
Therefore, by acquiring the real-time video stream data of the target space, when a preset dangerous event occurs in the target space, analyzing the real-time video stream data of the target space, whether abnormal personnel exist in the target space can be determined, and if the abnormal personnel exist in the target space, a first reminding message can be sent out to assist the rescue personnel to rapidly and efficiently make the best emergency plan, so that efficient rescue evacuation of the abnormal personnel is realized.
Analyzing the real-time video stream data of the target space to determine whether abnormal people exist in the target space, wherein the analyzing comprises: carrying out face recognition and/or human body recognition on the real-time video stream data of the target space through a target detection model to obtain face information and/or human body information in the real-time video stream data; and determining whether abnormal personnel exist in the target space or not based on the face information and/or the human body information in the real-time video stream data.
Therefore, the real-time video stream data in the target space is subjected to face recognition and/or human body recognition through the target detection model, so that the face information and/or the human body information in the real-time video stream data can be obtained, and whether abnormal personnel exist in the target space can be determined according to the face information and/or the human body information in the real-time video stream data, wherein the target detection model is a trained network model, and the real-time video stream data in the target space is analyzed through the target detection model, so that the reliability of abnormal personnel recognition is improved.
Wherein, the determining whether abnormal persons exist in the target space based on the face information and/or the body information in the real-time video stream data comprises: judging the state of a target person according to the face information and/or the human body information in the real-time video stream data; the status comprises a duration of time the target person is within the target space; and determining the target person as the abnormal person in response to the fact that the duration of the target person in the target space is greater than or equal to a preset duration threshold.
Therefore, the state of the target person corresponding to the face information and/or the human body information can be judged according to the face information and/or the human body information in the real-time video stream data, and when the target person is in the target space and the duration is greater than or equal to the preset duration threshold, the target person can be determined to be an abnormal person, so that the reliability of identifying the abnormal person is ensured.
Wherein, the responding to the abnormal personnel existing in the target space, sending a first reminding message to carry out rescue and evacuation on the abnormal personnel, comprises: responding to the existence of the abnormal personnel in the target space, and determining the target information of the abnormal personnel; and sending a first reminding message containing the target information of the abnormal personnel based on the target information of the abnormal personnel so as to rescue and evacuate the abnormal personnel.
Therefore, after the abnormal people exist in the target space, the target information of the abnormal people needs to be further determined, and then the first reminding message containing the target information of the abnormal people can be sent to the linkage rescue group, so that the abnormal people can be efficiently rescued and evacuated.
Wherein, the personnel rescue and evacuation method further comprises the following steps: acquiring real-time video stream data of a safety area; determining whether persons not to be evacuated exist in the target space according to the identification results of the target detection model on the real-time video stream data of the safe area, the real-time video stream data of the target space and the historical video stream data; and responding to the existence of the persons not evacuated in the target space, and sending a second reminding message containing target information of the persons not evacuated to rescue and evacuate the persons not evacuated.
Therefore, when whether abnormal people exist in the target space is determined, real-time video stream data of the safe area can be obtained, then the real-time video stream data of the safe area, the real-time video stream data of the target space and historical video stream data are searched and analyzed through the target detection model to determine whether people which are not evacuated exist in the target space, and if people which are not evacuated exist in the target space, a second reminding message containing target information of the people which are not evacuated can be sent out to timely rescue and evacuate the people which are not evacuated.
The determining whether people not to be evacuated exist in the target space according to the recognition results of the target detection model on the real-time video stream data of the safe area, the real-time video stream data of the target space and the historical video stream data comprises the following steps: performing target identification on real-time video stream data of the safe area through the target detection model, and determining actual personnel information in the safe area; performing target identification on real-time video stream data and historical video stream data of the target space through the target detection model, and determining target personnel information in the target space; and determining whether persons which are not evacuated exist in the target space or not according to the actual person information in the safety area and the target person information in the target space.
Therefore, the real-time video stream data of the safe area are subjected to target identification through the target detection model, the actual personnel information in the safe area can be determined, the real-time video stream data and the historical video stream data of the target space are subjected to target identification through the target detection model, the target personnel information in the target space can be determined, whether persons which are not evacuated exist in the target space can be determined according to the actual personnel information in the safe area and the target personnel information in the target space, people counting and identity confirmation can be automatically carried out during evacuation rescue, and rescue evacuation efficiency is improved.
Wherein the target information comprises at least one of location information, identity information and status information of the person.
Therefore, in the process of rescue evacuation, the position information, the identity information and the state information of abnormal people or people not evacuated can be obtained to assist the coordinated rescue groups to rapidly and efficiently formulate the best rescue scheme, so that the abnormal people or people not evacuated can be timely and efficiently rescued and evacuated.
Wherein the abnormal person comprises one or more of a detained person, a faint person and a help seeking person.
Therefore, the target space can be safely managed, large safety accidents caused by the occurrence of preset dangerous events are avoided, and efficient rescue evacuation can be performed on abnormal personnel such as detained personnel, falling personnel and help seeking personnel when the preset dangerous events occur.
In order to solve the above problems, a second aspect of the present application provides a rescue evacuation system including: the data acquisition device is used for acquiring real-time video stream data of a target space; the data processing platform is in communication connection with the data acquisition device, and is used for acquiring real-time video stream data of the target space and realizing the personnel rescue evacuation method of the first aspect based on the real-time video stream data of the target space.
In order to solve the above problems, a third aspect of the present application provides a rescue and evacuation device including: the data acquisition module is used for acquiring real-time video stream data of a target space; the data analysis module is used for analyzing real-time video stream data of the target space when a preset dangerous event occurs in the target space, and determining whether abnormal personnel exist in the target space; and the warning module is used for responding to the abnormal personnel in the target space and sending a first reminding message to rescue and evacuate the abnormal personnel.
In order to solve the above problem, a fourth aspect of the present application provides an electronic device, which includes a memory and a processor coupled to each other, wherein the processor is configured to execute program instructions stored in the memory to implement the rescue and evacuation method in the first aspect.
In order to solve the above-mentioned problems, a fifth aspect of the present application provides a computer-readable storage medium having stored thereon program instructions that, when executed by a processor, implement the rescue evacuation method in the first aspect described above.
According to the scheme, the real-time video stream data of the target space are obtained, when the preset dangerous event occurs in the target space, the real-time video stream data of the target space are analyzed, whether abnormal personnel exist in the target space can be determined, if the abnormal personnel exist in the target space, a first reminding message can be sent out to assist rescue workers to rapidly and efficiently make the best emergency plan, and efficient rescue evacuation of the abnormal personnel is achieved.
Drawings
Fig. 1 is a schematic flow chart of an embodiment of a rescue evacuation method of the present application;
FIG. 2 is a schematic flowchart of an embodiment of step S13 in FIG. 1;
FIG. 3 is a schematic flow chart of a rescue evacuation method for people in an application scene;
FIG. 4 is a schematic flow chart of another embodiment of a rescue evacuation method of the present application;
FIG. 5 is a flowchart illustrating an embodiment of step S45 in FIG. 4;
FIG. 6 is a flowchart illustrating an embodiment of step S46 in FIG. 4;
fig. 7 is a schematic flow chart of a rescue evacuation method in another application scenario;
FIG. 8 is a schematic diagram of a person rescue dispersal method in yet another application scenario;
FIG. 9 is a block diagram of an embodiment of a rescue evacuation system of the present application;
fig. 10 is a schematic frame diagram of an embodiment of the present rescue evacuation device;
FIG. 11 is a block diagram of an embodiment of an electronic device of the present application;
FIG. 12 is a block diagram of an embodiment of a computer-readable storage medium of the present application.
Detailed Description
The following describes in detail the embodiments of the present application with reference to the drawings attached hereto.
In the following description, for purposes of explanation and not limitation, specific details are set forth such as particular system structures, interfaces, techniques, etc. in order to provide a thorough understanding of the present application.
The terms "system" and "network" are often used interchangeably herein. The term "and/or" herein is merely an association describing an associated object, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter associated objects are in an "or" relationship. Further, the term "plurality" herein means two or more than two.
The present application provides a method for people rescue and evacuation, referring to fig. 1 specifically, fig. 1 is a schematic flow chart of an embodiment of the method for people rescue and evacuation. Specifically, the method may include the steps of:
step S11: and acquiring real-time video stream data of the target space.
In this embodiment, the video data is transmitted to the video analysis terminal in real time for analysis.
In one embodiment, the real-time video stream data is acquired by means of camera monitoring. Specifically, cameras may be installed at positions to be monitored in the target space in advance to monitor activity of people in the target space, and to monitor whether a preset dangerous event occurs in the target space.
In one embodiment, the target space includes a building. In this embodiment, the intelligent platform is accessed to the camera in the target space in an rts or national standard protocol manner, and acquires the real-time video stream data in the target space through the camera, and in other embodiments, the intelligent platform may also be accessed through other protocols, such as a network protocol, other communication protocols, and the like, which is not limited herein. The intelligent platform may be an intelligent building management platform, which is not limited herein.
In an embodiment, the intelligent platform further includes decoding real-time video stream data to obtain video frame data, and specifically, the intelligent platform decodes the encoded compressed video stream, that is, the real-time video stream is transmitted to the intelligent platform after encoding a video monitored by a camera according to a standard encoding rule such as h.264 or HEVC, and the intelligent platform decodes the real-time video stream data according to the decoding rule of h.264 or HEVC to obtain the video frame data. In this embodiment, the video frame data is frame data of a video, and specifically includes data of each frame of image/picture in the video, for example, a certain image in the video. It should be noted that a video is formed by consecutive combination of multiple frames of images, the video needs to be encoded and compressed to obtain a video stream convenient for transmission, and the video stream can be decoded to obtain a video or multiple pictures.
In an embodiment, after the intelligent platform obtains the video stream data, the intelligent platform further sends the video stream data to the event detection model for analysis, so as to determine whether a preset dangerous event occurs in the target space. Specifically, the intelligent platform sends the decoded video stream data or video frame data to the event detection model for analysis to determine whether a preset dangerous event occurs in the target space.
In an embodiment, the event detection model is used for determining whether a preset dangerous event occurs in the target space, and generating information of the preset dangerous event when the preset dangerous event occurs in the target space, and sending the information of the preset dangerous event to each platform unit of the intelligent platform for emergency linkage, wherein the information of the preset dangerous event includes the type of the dangerous event, and the position information or the image of the preset dangerous event, so that a manager can acquire the position of the dangerous event according to the image of the preset dangerous event to process the dangerous event in time. Referring to fig. 8, in an application scenario, a dangerous event is preset as a fire, and when the fire occurs, an emergency response linkage mechanism is triggered, which may specifically include starting an emergency plan, responding a linkage fire sensor to alarm, reporting to a fire brigade, starting fire fighting equipment such as a fire curtain, and performing ordered evacuation of people; specifically, the existing emergency scheme can be input into the system in advance, the emergency scheme comprises a disposal method, fire-fighting emergency material classification, an escape route, an emergency gathering point of personnel and the like, and when an accident happens, the emergency system can help rescue personnel to quickly know the environment in a building, the distribution of fire-fighting devices, the positions and the identities of the personnel, and quickly and effectively perform quick rescue in time.
Step S12: when a preset dangerous event occurs in the target space, analyzing real-time video stream data of the target space, and determining whether abnormal personnel exist in the target space.
In an embodiment, the model for analyzing the real-time video stream in the target space is a target detection model, and the step S12 specifically includes: carrying out face recognition and/or human body recognition on real-time video stream data of the target space through a target detection model to obtain face information and/or human body information in the real-time video stream data; and determining whether abnormal personnel exist in the target space or not based on the face information and/or the human body information in the real-time video stream data. The target detection model may be a single network model in the intelligent platform, or may be a network model externally connected to the intelligent platform, which is not limited herein. In this embodiment, the intelligent platform performs target identification on the monitored real-time video stream data through a target detection model. In the embodiment of the application, the real-time video stream data in the target space is subjected to face recognition and/or human body recognition through the target detection model, and according to the face information and/or the human body information in the real-time video stream data, living body detection can be realized, the personnel state can be determined, and whether abnormal personnel exist in the target space can be determined, wherein the target detection model is a trained network model, and the real-time video stream data in the target space is analyzed through the target detection model, so that the reliability of abnormal personnel recognition is improved. In another embodiment, after the camera acquires the real-time video stream data of the target space, the real-time video stream data is directly sent to the target detection model, and the real-time video stream data is decoded and analyzed by the target detection model to determine whether abnormal people exist in the target space.
Further, the step of determining whether an abnormal person exists in the target space based on the face information and/or the body information in the real-time video stream data may specifically include: judging the state of a target person according to the face information and/or the human body information in the real-time video stream data; the status comprises a duration of time the target person is within the target space; and determining the target person as the abnormal person in response to the fact that the duration of the target person in the target space is greater than or equal to a preset duration threshold. It can be understood that, according to the face information and/or the human body information in the real-time video stream data, the state of the target person corresponding to the face information and/or the human body information can be determined, for example, according to the face information and/or the human body information of the target person, whether the target person is in the target space can be determined, and if the target person is present in different image frames, the time length of the target person in the target space can be determined according to the time corresponding to the different image frames, and when the target person is determined to be in the target space and the duration is greater than or equal to the preset duration threshold, the target person can be determined to be an abnormal person, thereby ensuring the reliability of identifying the abnormal person.
In an embodiment, the target information comprises at least one of location information, identity information and status information of the person. Referring to fig. 8, in an application scenario, the target detection model may acquire the position and identity of a person through computer vision, for example, by starting a camera to perform activity monitoring, including living body detection and human face/body monitoring, on the space inside and outside the building, so as to determine the position and identity of the person. Therefore, in the process of rescue evacuation, the position information, the identity information and the state information of abnormal people are obtained, so that the coordinated rescue group can be assisted to rapidly and efficiently make an optimal rescue scheme, and timely and efficient rescue evacuation of the abnormal people is realized.
In one embodiment, the predetermined dangerous events include fire, toxic gas leakage, criminal security case, etc. occurring in the target space; and the abnormal personnel comprise detained personnel, faint personnel, help seeking personnel and the like. For example, the object detection model may determine that the monitored person is not evacuated and is an abnormal person in the case that the position of the evacuation area is unchanged and the duration is greater than or equal to the duration threshold value in the at least two images based on the at least two images. It can be understood that when fire, toxic gas leakage, criminal security cases and other preset dangerous events occur in the target space, abnormal personnel such as detained personnel, faint personnel, help seeking personnel and the like on the site need to be found in time, and effective rescue can be timely carried out. This application embodiment can carry out safety control to the building, avoids causing big incident because take place the dangerous event of predetermineeing such as conflagration, toxic gas reveal, criminal public security case, can carry out efficient rescue evacuation to unusual personnel such as detaining personnel, the personnel of falling down, the personnel of asking for help when taking place to predetermine the dangerous event.
Step S13: and responding to the abnormal personnel in the target space, and sending a first reminding message to rescue and evacuate the abnormal personnel.
In one embodiment, if abnormal people exist in the target space, a first reminding message is sent to corresponding workers to rescue and evacuate the abnormal people. The working personnel comprise management personnel, rescue personnel and the like. In one embodiment, if there are abnormal persons in the target space, the intelligent management platform sends a first reminding message to corresponding staff in any mode of short messages, small programs or intelligent calling and the like. In other embodiments, the display can be displayed to the staff member by means of a screen display to remind the staff member.
In an embodiment, please refer to fig. 2, fig. 2 is a schematic flowchart illustrating an embodiment of step S13 in fig. 1, and specifically, step S13 may include:
step S131: and determining the target information of the abnormal personnel in response to the abnormal personnel existing in the target space.
Step S132: sending a first reminding message containing the target information of the abnormal personnel based on the target information of the abnormal personnel so as to rescue and evacuate the abnormal personnel.
It can be understood that after the abnormal people are determined to be present in the target space, the target information of the abnormal people needs to be further determined, and then the first reminding message containing the target information of the abnormal people can be sent out, for example, the first reminding message is sent to a linkage rescue group, so as to implement efficient rescue and evacuation on the abnormal people.
According to the scheme, the real-time video stream data of the target space are obtained, when the preset dangerous event occurs in the target space, the real-time video stream data of the target space are analyzed, whether abnormal personnel exist in the target space can be determined, if the abnormal personnel exist in the target space, a first reminding message can be sent out to assist rescue workers to rapidly and efficiently make the best emergency plan, and efficient rescue evacuation of the abnormal personnel is achieved.
Please refer to fig. 3, fig. 3 is a schematic flow diagram of a rescue evacuation method in an application scenario, in the application scenario, an execution subject of the rescue evacuation method is an AI platform, when a fire occurs in a target space, real-time video stream data of the target space is obtained through various cameras in the target space, and the real-time video stream data is transmitted to the AI platform based on data stream, local file, network transmission and other manners, so that the AI platform calls a human face analysis algorithm by using a target detection model to obtain a human face and human bodies in an evacuation area in real time for cluster analysis, specifically, an evacuation area needing people evacuation can be determined first, then whether situations of people retention, people falling, people distress and the like exist is detected by using the target detection model, if the situations exist, the AI platform sends an alarm to prompt the existence of abnormal people, determines position information, identity information, state information and the like of the abnormal people, and then sends a first prompting message containing the position information, the identity information, the state information and the like of the abnormal people to a linkage evacuation group to rescue the abnormal people.
Referring to fig. 4, fig. 4 is a schematic flow chart of another embodiment of a rescue evacuation method of the present application. Specifically, the following steps may be included:
step S41: and acquiring real-time video stream data of the target space.
Step S42: and when a preset dangerous event occurs in the target space, analyzing real-time video stream data of the target space, and determining whether abnormal personnel exist in the target space.
Step S43: and responding to the abnormal personnel in the target space, and sending a first reminding message to rescue and evacuate the abnormal personnel.
Steps S41 to S43 in this embodiment are substantially the same as steps S11 to S13 in the previous embodiment, and are not repeated here.
Step S44: and acquiring real-time video stream data of the safe area.
It can be understood that, after a preset dangerous event occurs in the target space, people need to be evacuated to the secure area, and therefore, the secure area also needs to be managed, specifically, a camera in the secure area is accessed through a real-time system protocol (rts) or a national standard protocol, so as to acquire a picture shot by the camera in real time, and form real-time video stream data of the secure area.
Step S45: and determining whether persons not to be evacuated exist in the target space according to the identification results of the target detection model on the real-time video stream data of the safe area, the real-time video stream data of the target space and the historical video stream data.
Specifically, in the evacuation process, by performing joint retrieval analysis on the real-time video stream data of the safe area, the real-time video stream data of the target space and the historical video stream data, whether all people in the target space are evacuated into the safe area can be determined, and therefore whether people which are not evacuated exist in the target space can be determined.
Referring to fig. 5, fig. 5 is a schematic flowchart illustrating an embodiment of step S45 in fig. 4, and in an embodiment, the step S45 may specifically include:
step S451: and carrying out target identification on the real-time video stream data of the safe area through the target detection model, and determining the actual personnel information in the safe area.
Step S452: and carrying out target identification on the real-time video stream data and the historical video stream data of the target space through the target detection model, and determining target personnel information in the target space.
Step S453: and determining whether persons which are not evacuated exist in the target space or not according to the actual person information in the safety area and the target person information in the target space.
Specifically, the target detection model may count the number of people in the security area in real time through computer vision, determine actual people information in the security area, perform target identification on real-time video stream data and historical video stream data of the target space, search out all people who come in and go out of the target space within a preset time period of the day, determine the total number of people in the target space after a preset dangerous event occurs, that is, determine target people information in the target space, and then determine whether people who are not evacuated exist in the target space according to the actual people information in the security area and the target people information in the target space. Therefore, the real-time video stream data of the safe area are subjected to target identification through the target detection model, the actual personnel information in the safe area can be determined, the real-time video stream data and the historical video stream data of the target space are subjected to target identification through the target detection model, the target personnel information in the target space can be determined, whether persons which are not evacuated exist in the target space can be determined according to the actual personnel information in the safe area and the target personnel information in the target space, people counting and identity confirmation can be automatically carried out during evacuation rescue, and rescue evacuation efficiency is improved.
Step S46: responding to the existence of the persons not evacuated in the target space, and sending a second reminding message containing target information of the persons not evacuated to rescue and evacuate the persons not evacuated.
In one embodiment, if the persons not to be evacuated exist in the target space, a second reminding message is sent to the corresponding staff to rescue and evacuate the persons not to be evacuated. The working personnel comprise management personnel, rescue personnel and the like. In a specific embodiment, if there are persons not evacuated in the target space, the intelligent management platform sends a second reminding message to the corresponding staff in any one of a short message, a small program or an intelligent call. In other embodiments, the display can be displayed to the staff member by means of a screen display to remind the staff member.
In an embodiment, please refer to fig. 6, fig. 6 is a flowchart illustrating an embodiment of step S46 in fig. 4, and specifically, step S46 may include:
step S461: and determining target information of the persons not evacuated in response to the persons not evacuated existing in the target space.
Step S462: and sending a second reminding message containing the target information of the persons not evacuated to the linkage rescue group to rescue and evacuate the persons not evacuated.
It can be understood that after it is determined that people who are not evacuated exist in the target space, the target information of the people who are not evacuated needs to be further determined, and then a second reminding message containing the target information of the people who are not evacuated is sent to the linkage rescue group, so that efficient rescue and evacuation of the people who are not evacuated are achieved. Therefore, referring to fig. 8, in an application scenario, the embodiment of the present application may perform people counting confirmation through computer vision, including confirming whether all people in the evacuation area evacuate and confirming whether all people in the security area arrive; for example, the target detection model may acquire a plurality of images captured by a plurality of cameras, when a structured algorithm of a human face or a human body is within a preset confidence interval, the monitored human body may be determined, and when a fire occurs, the number of people escaping may be counted by computer vision, the positions of people not evacuated may be located, the identities of people not evacuated may be determined, and the like.
In an embodiment, the target information includes at least one of location information, identity information, and status information of the person. Therefore, in the process of rescue evacuation, the position information, the identity information and the state information of people who are not evacuated can be obtained to assist the linkage rescue group to rapidly and efficiently formulate the best rescue scheme, so that the timely and efficient rescue evacuation of the people who are not evacuated can be realized.
According to the scheme, whether abnormal people exist in the target space or not can be determined, meanwhile, real-time video stream data of the safe area can be obtained, then, the real-time video stream data of the safe area, the real-time video stream data of the target space and historical video stream data are searched and analyzed through the target detection model, whether people which are not evacuated exist in the target space or not can be determined, and if people which are not evacuated exist in the target space, a second reminding message can be sent out, so that rescue and evacuation can be conducted on the people which are not evacuated in time. Therefore, the emergency plan can be quickly and efficiently made by the commander according to computer visual positioning and the current situation of accidents, the optimal emergency plan and the escape plan can be effectively planned, and the number of the escaping personnel is qualified and the subsequent search and rescue tasks of the personnel can be guaranteed according to the position result of the personnel.
Please refer to fig. 7, fig. 7 is a schematic flow diagram of a rescue evacuation method in another application scenario, in an application scenario, an executing subject of the rescue evacuation method is an AI platform, and after a fire occurs in a target space, in addition to timely finding abnormal people in an evacuation area and giving an alarm, the number of people to be evacuated can be counted according to recognition results of real-time video stream data of a safe area, real-time video stream data of the target space and historical video stream data of a target detection model, so as to determine whether people not to be evacuated exist in the target space. Specifically, the method includes the steps of firstly determining an ROI of a safety area where people arrive after evacuation, then performing space-time retrieval on real-time video stream data of the safety area, real-time video stream data of a target space and historical video stream data by using a target detection model, determining a list of people needing to be checked, detecting whether the number of people in the safety area is consistent with the number of people in the target space on the same day, if not, specifically determining people who are not evacuated successfully, then sending an alarm by an AI platform to prompt the existence of people who are not evacuated, determining the position information, the identity information, the state information and the like of the people who are not evacuated, and then sending a second reminding message containing the position information, the identity information, the state information and the like of the people who are not evacuated to a linkage rescue group to evacuate the people who are not evacuated.
Fig. 9 is a schematic diagram illustrating a framework of an embodiment of the rescue and evacuation system of the present application. The rescue and evacuation system 90 comprises a data acquisition device 901 and a data processing platform 902, wherein the data acquisition device 901 is used for acquiring real-time video stream data of a target space, the data processing platform 902 is in communication connection with the data acquisition device 901, and the data processing platform 902 is used for acquiring the real-time video stream data of the target space and implementing the rescue and evacuation method in any of the above embodiments based on the real-time video stream data of the target space. In an implementation scenario, the data acquisition device 901 and the data processing platform 902 may be integrated or non-integrated. In an implementation scenario, there are a plurality of data acquisition devices 901, a plurality of data acquisition devices 901 are distributed at various scene locations in a city, and each data acquisition device 901 is in communication connection with the data processing platform 902.
According to the scheme, real-time video stream data of the target space are acquired through the data acquisition device 901 and transmitted to the data processing platform 902, the data processing platform 902 analyzes the real-time video stream data of the target space to determine whether abnormal personnel exist in the target space, and if the abnormal personnel exist in the target space, a first reminding message can be sent to assist rescue workers to rapidly and efficiently make an optimal emergency plan, so that efficient rescue evacuation of the abnormal personnel is achieved.
Referring to fig. 10, fig. 10 is a schematic frame diagram of an embodiment of the rescue and evacuation device of the present application. The rescue and evacuation device 100 comprises a data acquisition module 1000, a data analysis module 1002 and a warning module 1004, wherein the data acquisition module 1000 is used for acquiring real-time video stream data of a target space, the data analysis module 1002 is used for analyzing the real-time video stream data of the target space when a preset dangerous event occurs in the target space to determine whether abnormal people exist in the target space, and the warning module 1004 is used for responding to the abnormal people existing in the target space and sending a first reminding message to evacuate the abnormal people.
According to the scheme, the data acquisition module 1000 is used for acquiring real-time video stream data of the target space, when a preset dangerous event occurs in the target space, the data analysis module 1002 is used for analyzing the real-time video stream data of the target space, whether abnormal personnel exist in the target space can be determined, and if the abnormal personnel exist in the target space, the warning module 1004 can send out a first reminding message to assist rescue workers to rapidly and efficiently formulate the best emergency plan and achieve efficient rescue evacuation of the abnormal personnel.
In some embodiments, the data analysis module 1002 performs the step of analyzing the real-time video stream data of the target space to determine whether abnormal persons exist in the target space, including: carrying out face recognition and/or human body recognition on real-time video stream data of the target space through a target detection model to obtain face information and/or human body information in the real-time video stream data; and determining whether abnormal personnel exist in the target space or not based on the face information and/or the human body information in the real-time video stream data.
In some embodiments, the data analysis module 1002 performs the step of determining whether an abnormal person exists in the target space based on the human face information and/or the human body information in the real-time video stream data, including: judging the state of a target person according to the face information and/or the human body information in the real-time video stream data; the status comprises a duration of time that the target person is within the target space; and determining the target person as the abnormal person in response to the fact that the duration of the target person in the target space is greater than or equal to a preset duration threshold.
In some embodiments, the warning module 1004 executes the step of issuing a first warning message to perform rescue and evacuation on the abnormal people in response to the abnormal people existing in the target space, including: responding to the existence of the abnormal personnel in the target space, and determining the target information of the abnormal personnel; sending a first reminding message containing the target information of the abnormal personnel based on the target information of the abnormal personnel so as to rescue and evacuate the abnormal personnel.
In some embodiments, the data acquisition module 1000 is further configured to acquire real-time video stream data of the secure area; the data analysis module 1002 is further configured to determine whether people not to be evacuated exist in the target space according to the identification result of the target detection model on the real-time video stream data of the safe area, the real-time video stream data of the target space, and the historical video stream data; the warning module 1004 is further configured to send a second reminding message containing target information of the people not evacuated in response to the presence of the people not evacuated in the target space, so as to rescue and evacuate the people not evacuated.
In some embodiments, the data analysis module 1002 performs the step of determining whether people are not evacuated in the target space according to the identification result of the target detection model on the real-time video stream data of the safe area, the real-time video stream data of the target space and the historical video stream data, and specifically includes: performing target identification on real-time video stream data of the safe area through the target detection model, and determining actual personnel information in the safe area; performing target identification on real-time video stream data and historical video stream data of the target space through the target detection model, and determining target personnel information in the target space; and determining whether persons which are not evacuated exist in the target space or not according to the actual person information in the safety area and the target person information in the target space.
In some embodiments, the warning module 1004 executes the step of issuing a second warning message to perform rescue evacuation on the non-evacuated persons in response to the presence of the non-evacuated persons in the target space, including: responding to the existence of the persons not evacuated in the target space, and determining target information of the persons not evacuated; and sending a second reminding message containing the target information of the persons not evacuated to the linkage rescue group to rescue and evacuate the persons not evacuated.
In some embodiments, the target information includes at least one of location information, identity information, and status information of the person.
In some embodiments, the target space comprises a building; and/or the preset dangerous event comprises one or more of fire, toxic gas leakage and criminal security case in the target space; and/or the abnormal person comprises one or more of a detained person, a faint person and a help seeking person.
Fig. 11 shows a frame schematic diagram of an embodiment of an electronic device according to the present application, where fig. 11 is a schematic diagram. The electronic device 110 comprises a memory 1101 and a processor 1102 coupled to each other, the processor 1102 being configured to execute program instructions stored in the memory 1101 to implement the steps of any of the person rescue evacuation method embodiments described above. In one particular implementation scenario, the electronic device 110 may include, but is not limited to: microcomputer, server.
In particular, the processor 1102 is configured to control itself and the memory 1101 to implement the steps in any of the person rescue evacuation method embodiments described above. Processor 1102 may also be referred to as a CPU (Central Processing Unit). The processor 1102 may be an integrated circuit chip having signal processing capabilities. The Processor 1102 may also be a general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. In addition, the processor 1102 may be commonly implemented by integrated circuit chips.
According to the scheme, the processor 1102 analyzes the real-time video stream data of the target space by acquiring the real-time video stream data of the target space when a preset dangerous event occurs in the target space, so as to determine whether abnormal personnel exist in the target space, and if the abnormal personnel exist in the target space, a first reminding message can be sent out to assist rescue workers to rapidly and efficiently formulate an optimal emergency plan, so that the abnormal personnel can be efficiently rescued and evacuated.
Referring to fig. 12, fig. 12 is a schematic diagram of a framework of an embodiment of a computer-readable storage medium according to the present application. The computer readable storage medium 120 stores program instructions 1200 capable of being executed by the processor, the program instructions 1200 being for implementing the steps in any of the person rescue evacuation method embodiments described above.
The disclosure relates to the field of augmented reality, and in particular relates to a method for detecting or identifying relevant features, states and attributes of a target object by acquiring image information of the target object in a real environment and by means of various visual correlation algorithms, so as to obtain an AR effect combining virtual and reality matched with specific applications. For example, the target object may relate to a face, a limb, a gesture, an action, etc. associated with a human body, or a marker, a marker associated with an object, or a sand table, a display area, a display item, etc. associated with a venue or a place. The vision-related algorithms may involve visual localization, SLAM, three-dimensional reconstruction, image registration, background segmentation, key point extraction and tracking of objects, pose or depth detection of objects, etc. The specific application can relate to interactive scenes such as navigation, explanation, reconstruction, virtual effect superposition display and the like related to a real scene or an article, and can also relate to special effect treatment related to people such as interactive scenes such as makeup beautification, limb beautification, special effect display, virtual model display and the like.
The detection or identification processing of the relevant characteristics, states and attributes of the target object can be realized through the convolutional neural network. The convolutional neural network is a network model obtained by performing model training based on a deep learning framework.
In the several embodiments provided in the present application, it should be understood that the disclosed method and apparatus may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of a module or a unit is merely one type of logical division, and an actual implementation may have another division, for example, a unit or a component may be combined or integrated with another system, or some features may be omitted, or not implemented. In addition, the shown or discussed coupling or direct coupling or communication connection between each other may be through some interfaces, indirect coupling or communication connection between devices or units, and may be in an electrical, mechanical or other form.
Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on network elements. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a separate product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, a network device, or the like) or a processor (processor) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
If the technical scheme of the application relates to personal information, a product applying the technical scheme of the application clearly informs personal information processing rules before processing the personal information, and obtains personal independent consent. If the technical scheme of the application relates to sensitive personal information, a product applying the technical scheme of the application obtains individual consent before processing the sensitive personal information, and simultaneously meets the requirement of 'express consent'. For example, at a personal information collection device such as a camera, a clear and significant identifier is set to inform that the personal information collection range is entered, the personal information is collected, and if the person voluntarily enters the collection range, the person is regarded as agreeing to collect the personal information; or on the device for processing the personal information, under the condition of informing the personal information processing rule by using obvious identification/information, obtaining personal authorization by modes of popping window information or asking a person to upload personal information of the person by himself, and the like; the personal information processing rule may include information such as a personal information processor, a personal information processing purpose, a processing method, and a type of personal information to be processed.
Claims (11)
1. A rescue evacuation method for people, which is characterized by comprising the following steps:
acquiring real-time video stream data of a target space;
when a preset dangerous event occurs in the target space, analyzing real-time video stream data of the target space, and determining whether abnormal personnel exist in the target space;
and responding to the abnormal personnel in the target space, and sending a first reminding message to rescue and evacuate the abnormal personnel.
2. People rescue and evacuation method according to claim 1, wherein the analyzing the real-time video stream data of the target space to determine whether abnormal people exist in the target space comprises:
carrying out face recognition and/or human body recognition on real-time video stream data of the target space through a target detection model to obtain face information and/or human body information in the real-time video stream data;
and determining whether abnormal personnel exist in the target space or not based on the face information and/or the human body information in the real-time video stream data.
3. People rescue and evacuation method according to claim 2, wherein the determining whether abnormal people exist in the target space based on the human face information and/or the human body information in the real-time video stream data comprises:
judging the state of a target person according to the face information and/or the human body information in the real-time video stream data; the status comprises a duration of time that the target person is within the target space;
and determining the target person as the abnormal person in response to the fact that the duration of the target person in the target space is greater than or equal to a preset duration threshold.
4. People rescue and evacuation method according to claim 1, wherein the sending a first reminding message to rescue and evacuate the abnormal people in response to the abnormal people existing in the target space comprises:
responding to the existence of the abnormal personnel in the target space, and determining the target information of the abnormal personnel;
sending a first reminding message containing the target information of the abnormal personnel based on the target information of the abnormal personnel so as to rescue and evacuate the abnormal personnel.
5. Rescue evacuation method according to claim 1, further comprising:
acquiring real-time video stream data of a safety area;
determining whether persons not to be evacuated exist in the target space according to the identification results of the target detection model on the real-time video stream data of the safe area, the real-time video stream data of the target space and the historical video stream data;
and responding to the existence of the persons not evacuated in the target space, and sending a second reminding message containing target information of the persons not evacuated to rescue and evacuate the persons not evacuated.
6. The rescue and evacuation method as claimed in claim 5, wherein the determining whether persons not to be evacuated are present in the target space according to the recognition results of the target detection model on the real-time video stream data of the safety area, the real-time video stream data of the target space and the historical video stream data comprises:
performing target identification on real-time video stream data of the safe area through the target detection model, and determining actual personnel information in the safe area;
performing target identification on real-time video stream data and historical video stream data of the target space through the target detection model, and determining target personnel information in the target space;
and determining whether persons which are not evacuated exist in the target space or not according to the actual person information in the safety area and the target person information in the target space.
7. Rescue and evacuation method for people according to claim 4 or 5,
the target information includes at least one of location information, identity information, and status information of the person.
8. A rescue evacuation system, comprising:
the data acquisition device is used for acquiring real-time video stream data of a target space;
a data processing platform, which is in communication connection with the data acquisition device, and is used for acquiring real-time video stream data of the target space and implementing the people rescue evacuation method according to any one of claims 1 to 7 based on the real-time video stream data of the target space.
9. A rescue and evacuation system, comprising:
the data acquisition module is used for acquiring real-time video stream data of a target space;
the data analysis module is used for analyzing real-time video stream data of the target space when a preset dangerous event occurs in the target space, and determining whether abnormal personnel exist in the target space;
and the warning module is used for responding to the abnormal personnel in the target space and sending a first reminding message to rescue and evacuate the abnormal personnel.
10. An electronic device comprising a memory and a processor coupled to each other, the processor being configured to execute program instructions stored in the memory to implement the rescue evacuation method of any of claims 1-7.
11. A computer readable storage medium having stored thereon program instructions, which when executed by a processor, implement a rescue evacuation method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210646230.XA CN115147755A (en) | 2022-06-08 | 2022-06-08 | Personnel rescue evacuation method, system, device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210646230.XA CN115147755A (en) | 2022-06-08 | 2022-06-08 | Personnel rescue evacuation method, system, device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115147755A true CN115147755A (en) | 2022-10-04 |
Family
ID=83407846
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210646230.XA Pending CN115147755A (en) | 2022-06-08 | 2022-06-08 | Personnel rescue evacuation method, system, device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115147755A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116167901A (en) * | 2022-11-26 | 2023-05-26 | 中国消防救援学院 | Fire emergency drilling method and system based on computer technology |
-
2022
- 2022-06-08 CN CN202210646230.XA patent/CN115147755A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116167901A (en) * | 2022-11-26 | 2023-05-26 | 中国消防救援学院 | Fire emergency drilling method and system based on computer technology |
| CN116167901B (en) * | 2022-11-26 | 2024-04-26 | 中国消防救援学院 | Fire emergency drilling method and system based on computer technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101610657B1 (en) | Three-dimensional virtual entrance control and communicable disease control system and method based on entrance control data | |
| CN110795963A (en) | Monitoring method, device and equipment based on face recognition | |
| US11270562B2 (en) | Video surveillance system and video surveillance method | |
| CN109819043A (en) | 3 D intelligent emergency fire control platform system and its operating method | |
| CN111899466A (en) | System and method for seeking help and rescuing nearby around help seeker | |
| CN110223474A (en) | A kind of intelligent monitoring and alarming method, system and storage medium | |
| CN108830143A (en) | A kind of video analytic system based on deep learning | |
| CN105516659A (en) | Intelligent safe-guard system and method based on face emotion recognition | |
| US20220004949A1 (en) | System and method for artificial intelligence (ai)-based activity tracking for protocol compliance | |
| CN111259682B (en) | Method and device for monitoring safety of construction site | |
| CN111508126A (en) | Intelligent security system based on 5G communication | |
| CN115147755A (en) | Personnel rescue evacuation method, system, device, electronic equipment and storage medium | |
| CN115567690A (en) | Intelligent monitoring system capable of automatically identifying dangerous points of field operation | |
| KR20190049187A (en) | Method and apparatus for sharing dangerous status of user by using timer | |
| CN110751125A (en) | Wearing detection method and device | |
| CN114281656A (en) | Intelligent central control system | |
| CN109815828A (en) | Realize the system and method for initiative alarming or help-seeking behavior detection control | |
| CN112104837A (en) | Intelligent behavior analysis system applied to school places | |
| CN106921846A (en) | Video mobile terminal legacy detection means | |
| JP7447626B2 (en) | Information processing method, information processing device, program and information processing system | |
| CN211554957U (en) | Be used for swimming pool personnel that fall into water to discriminate positioner and system | |
| CN113628413A (en) | Automatic alarm and help-seeking technology for accidents of wearing and taking off protective clothing | |
| CN110895686A (en) | On-duty identification method for special person of fire-fighting person | |
| JP7438594B1 (en) | Digital intrusion detection system | |
| US20240185608A1 (en) | Scaffolding safety compliance detection using computer vision |
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 |