CN115019462A - Video processing method, device, storage medium and equipment - Google Patents
Video processing method, device, storage medium and equipment Download PDFInfo
- Publication number
- CN115019462A CN115019462A CN202210594790.5A CN202210594790A CN115019462A CN 115019462 A CN115019462 A CN 115019462A CN 202210594790 A CN202210594790 A CN 202210594790A CN 115019462 A CN115019462 A CN 115019462A
- Authority
- CN
- China
- Prior art keywords
- target
- area
- living body
- image
- shooting
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 29
- 238000004458 analytical method Methods 0.000 claims abstract description 53
- 238000000034 method Methods 0.000 claims abstract description 34
- 238000012545 processing Methods 0.000 claims abstract description 29
- 238000001514 detection method Methods 0.000 claims description 31
- 230000004044 response Effects 0.000 claims description 31
- 238000012549 training Methods 0.000 claims description 16
- 210000000988 bone and bone Anatomy 0.000 claims description 12
- 230000007613 environmental effect Effects 0.000 claims description 12
- 230000015654 memory Effects 0.000 claims description 9
- 230000009471 action Effects 0.000 claims description 7
- 230000033001 locomotion Effects 0.000 claims description 7
- 239000013056 hazardous product Substances 0.000 claims description 6
- 238000004806 packaging method and process Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 5
- 238000004590 computer program Methods 0.000 description 16
- 238000012544 monitoring process Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 230000006399 behavior Effects 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 238000005538 encapsulation Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000013527 convolutional neural network Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 238000001931 thermography Methods 0.000 description 3
- 210000003423 ankle Anatomy 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 239000007789 gas Substances 0.000 description 2
- 210000003127 knee Anatomy 0.000 description 2
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 210000000707 wrist Anatomy 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 239000000383 hazardous chemical Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000009545 invasion Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 239000003345 natural gas Substances 0.000 description 1
- 238000012858 packaging process Methods 0.000 description 1
- 239000003209 petroleum derivative Substances 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000000391 smoking effect Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- 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
- G06V40/40—Spoof detection, e.g. liveness detection
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/12—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions
- G08B17/125—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions by using a video camera to detect fire or smoke
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/182—Level alarms, e.g. alarms responsive to variables exceeding a threshold
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
Abstract
The application discloses a video processing method, a video processing device, a storage medium and video processing equipment, and belongs to the field of security and protection. The method comprises the following steps: acquiring a video stream acquired by shooting equipment, and decoding the video stream to obtain a multi-frame image; determining an area type of a shooting area of a shooting device; performing content analysis on the multi-frame image according to a content analysis mode matched with the region type; responding to the obtained analysis result to indicate that the safety abnormity occurs in the shooting area, and determining an alarm level corresponding to the safety abnormity; and sending an alarm prompt matched with the alarm level to the target equipment according to the sending mode matched with the alarm level. The method is completely and automatically completed without manual participation, and is time-saving, labor-saving, high in efficiency and timely. In addition, the method can adaptively analyze the contents of different types of shooting areas, and has good identification effect; and different alarm levels correspond to different sending modes and alarm prompts, so that the alarm modes are enriched.
Description
Technical Field
The present application relates to the field of security, and in particular, to a video processing method, apparatus, storage medium, and device.
Background
With the continuous progress of science and technology, security protection based on videos is widely applied to various industries.
The security measures adopted in the related art are generally that videos collected by shooting equipment are displayed through a display screen, and whether security abnormity occurs in a shooting area is judged by means of manually staring at the screen.
However, not only is manually viewing video a heavy and inefficient task, but there is also a risk that security anomalies cannot be identified timely and accurately.
Disclosure of Invention
The embodiment of the application provides a video processing method, a video processing device, a storage medium and video processing equipment. The technical scheme is as follows:
in one aspect, a video processing method is provided, and the method includes:
acquiring a video stream acquired by shooting equipment, and decoding the video stream to obtain a plurality of frames of images;
determining the area type of a shooting area of the shooting equipment, wherein the area type comprises an entrance area and a dangerous goods storage area;
performing content analysis on the multi-frame image according to a content analysis mode matched with the region type;
responding to the obtained analysis result to indicate that safety abnormity occurs in the shooting area, and determining an alarm level corresponding to the safety abnormity;
and sending an alarm prompt matched with the alarm level to the target equipment according to the sending mode matched with the alarm level.
In a possible implementation manner, the sending, to the target device, the alert prompt matching the alert level according to the sending manner matching the alert level includes:
responding to the alarm level larger than the target level, and sending a first type of alarm prompt to the target equipment according to a first sending mode;
the first type of alarm prompt carries a target image, wherein the target image is an image associated with the security anomaly and the image content in the multi-frame image;
the first sending mode comprises sending in the form of an in-application message and sending in the form of an out-of-application message; the in-application message is displayed through a target application installed on the target device, and the out-application message is not displayed through the target application.
In one possible implementation, the method further includes:
obtaining a plurality of transcoding parameters; transcoding the video stream according to the plurality of transcoding parameters respectively to obtain a plurality of transcoded video streams;
and determining a target transcoded video stream in the plurality of transcoded video streams based on the current network bandwidth and the device parameters of the target device, and sending the target transcoded video stream to the target device.
In one possible implementation, the method further includes:
converting and packaging the video stream from an original video format into a plurality of target video formats to obtain a plurality of converted and packaged video streams;
and determining a target to package video stream in the multiple to package video streams based on the video format supported by the target device to play, and sending the target to package video stream to the target device.
In a possible implementation manner, the performing content analysis on the multiple frames of images according to the content analysis manner matched with the region type includes:
selecting a vehicle image from the multi-frame images in response to the shooting area being an entrance area;
detecting a license plate region of the vehicle image; cutting out a license plate area from the vehicle image based on the obtained license plate area detection result;
recognizing license plate characters of the license plate area based on a first recognition model; the first recognition model is obtained by training based on a sample vehicle image marked with license plate characters.
In a possible implementation manner, the performing content analysis on the multiple frames of images according to the content analysis manner matched with the region type includes:
responding to the fact that the shooting area is a dangerous goods storage area, selecting a living body image from the multi-frame image, wherein the living body image comprises a target living body;
detecting a bone key point of a target living body included in the living body image;
identifying the action type of the target living body through a second identification model based on the obtained bone key point detection result; and the second recognition model is obtained by training based on the sample living body image marked with the dangerous motion type.
In one possible implementation manner, the multi-frame image is an infrared image; the content analysis of the multi-frame image according to the content analysis mode matched with the region type comprises the following steps:
determining the current temperature of the shooting area based on the infrared image in response to the shooting area being a dangerous goods storage area;
identifying a fire position of the shooting area through a third identification model based on the infrared image in response to the current temperature of the shooting area being higher than a target temperature; and the third recognition model is obtained by training based on the sample infrared image marked with the fire position.
In one possible implementation, the method further includes:
acquiring a current position of a target living body in response to the presence of the target living body within the photographing region;
and determining a moving route for the target living body according to a fire passing range of the shooting area after a target time length by taking the current position of the target living body as a starting point and the exit position of the shooting area as an end point, wherein the moving route is used for indicating the target living body to leave the shooting area.
In one possible implementation, the method further includes:
acquiring current environmental information of the shooting area;
acquiring the types of dangerous goods stored in the shooting area and the total amount of the dangerous goods;
determining the progress speed of the fire according to the environmental information, the type of the dangerous goods and the total amount of the dangerous goods;
and determining the fire passing range of the shooting area after the target duration according to the fire progress speed and the fire position.
In a possible implementation manner, the performing content analysis on the multiple frames of images according to the content analysis manner matched with the region type includes:
in response to the fact that the shooting area is a dangerous goods storage area, selecting a living body image from the multi-frame image, wherein the living body image comprises a target living body;
carrying out face recognition on the target living body; and in response to the fact that the recognized face does not match the target face template, recognizing the moving direction of the target living body in the shooting area based on the position information of the target living body in the living body image.
In another aspect, a video processing apparatus is provided, the apparatus comprising:
the first processing module is configured to acquire a video stream acquired by shooting equipment, decode the video stream and obtain a multi-frame image;
a first determination module configured to determine an area type of a photographing area of the photographing apparatus, the area type including an entrance area and a hazardous material storage area;
the second processing module is configured to perform content analysis on the multi-frame images according to a content analysis mode matched with the region type;
the second determination module is configured to respond to the obtained analysis result indicating that safety abnormity occurs in the shooting area, and determine an alarm level corresponding to the safety abnormity;
and the sending module is configured to send the alarm prompt matched with the alarm level to the target equipment according to the sending mode matched with the alarm level.
In one possible implementation, the sending module is configured to:
responding to the alarm level larger than the target level, and sending a first type of alarm prompt to the target equipment according to a first sending mode;
the first type of alarm prompt carries a target image, wherein the target image is an image associated with the security anomaly and the image content in the multi-frame image;
the first sending mode comprises sending in the form of an in-application message and sending in the form of an out-of-application message; the in-application message is displayed through a target application installed on the target device, and the out-application message is not displayed through the target application.
In one possible implementation, the apparatus further includes:
a transcoding module configured to obtain a plurality of transcoding parameters; transcoding the video stream according to the plurality of transcoding parameters respectively to obtain a plurality of transcoded video streams; and determining a target transcoded video stream in the plurality of transcoded video streams based on the current network bandwidth and the device parameters of the target device, and sending the target transcoded video stream to the target device.
In one possible implementation, the apparatus further includes:
the trans-encapsulation module is configured to trans-encapsulate the video stream from an original video format into a plurality of target video formats to obtain a plurality of trans-encapsulated video streams; and determining a target to encapsulated video stream in the multiple types of to encapsulated video streams based on the video format supported by the target device to be played, and sending the target to encapsulated video stream to the target device.
In one possible implementation, the second processing module is configured to:
selecting a vehicle image from the multi-frame images in response to the shooting area being an entrance area;
detecting a license plate region of the vehicle image; cutting out a license plate area from the vehicle image based on the obtained license plate area detection result;
recognizing license plate characters of the license plate area based on a first recognition model; the first recognition model is obtained by training based on a sample vehicle image marked with license plate characters.
In one possible implementation, the second processing module is configured to:
responding to the fact that the shooting area is a dangerous goods storage area, selecting a living body image from the multi-frame image, wherein the living body image comprises a target living body;
detecting a bone key point of a target living body included in the living body image;
identifying the action type of the target living body through a second identification model based on the obtained bone key point detection result; and the second recognition model is obtained by training based on the sample living body image marked with the dangerous motion type.
In one possible implementation manner, the multi-frame image is an infrared image; the second processing module configured to:
determining the current temperature of the shooting area based on the infrared image in response to the shooting area being a dangerous goods storage area;
identifying a fire position of the shooting area through a third identification model based on the infrared image in response to the current temperature of the shooting area being higher than a target temperature; and the third recognition model is obtained by training based on the sample infrared image marked with the fire position.
In one possible implementation, the apparatus further includes:
a route planning module configured to acquire a current position of a target living body in response to the presence of the target living body within the photographing region; and determining a moving route for the target living body according to a fire passing range of the shooting area after a target time length by taking the current position of the target living body as a starting point and the exit position of the shooting area as an end point, wherein the moving route is used for indicating the target living body to leave the shooting area.
In one possible implementation, the route planning module is further configured to:
acquiring current environmental information of the shooting area;
acquiring the types of dangerous goods stored in the shooting area and the total amount of the dangerous goods;
determining the progress speed of the fire according to the environmental information, the type of the dangerous goods and the total amount of the dangerous goods;
and determining the fire passing range of the shooting area after the target duration according to the fire progress speed and the fire position.
In one possible implementation, the second processing module is configured to:
responding to the fact that the shooting area is a dangerous goods storage area, selecting a living body image from the multi-frame image, wherein the living body image comprises a target living body;
carrying out face recognition on the target living body; and in response to the fact that the recognized face does not match the target face template, recognizing the moving direction of the target living body in the shooting area based on the position information of the target living body in the living body image.
In another aspect, a computer device is provided, the device comprising a processor and a memory, the memory having stored therein at least one program code, the at least one program code being loaded and executed by the processor to implement the video processing method described above.
In another aspect, a computer-readable storage medium is provided, in which at least one program code is stored, the at least one program code being loaded and executed by a processor to implement the video processing method described above.
In another aspect, a computer program product or a computer program is provided, the computer program product or the computer program comprising computer program code, the computer program code being stored in a computer-readable storage medium, the computer program code being read by a processor of a computer device from the computer-readable storage medium, the computer program code being executable by the processor to cause the computer device to perform the video processing method described above.
The video processing method provided by the embodiment of the application can automatically analyze the video stream acquired by the shooting equipment, automatically determine whether the shooting area has safety abnormity according to the analysis result, and automatically alarm and prompt under the condition of determining the safety abnormity, and the whole process is not required to be manually participated in and is completely and automatically completed, so that the time and labor are saved, the efficiency is higher and the time is more timely. In addition, the video processing method can adaptively analyze the contents of different types of shooting areas, has good identification effect and can accurately determine safety abnormity; in addition, different alarm levels correspond to different sending modes and alarm prompts, and the alarm modes are enriched.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic diagram of an implementation environment for a video processing method according to an example embodiment;
FIG. 2 is a flow diagram illustrating a video processing method according to an exemplary embodiment;
FIG. 3 is a flow diagram illustrating another video processing method in accordance with an exemplary embodiment;
FIG. 4 is a block diagram of a video processing device according to an exemplary embodiment;
FIG. 5 is a schematic diagram illustrating a configuration of a computer device, according to an example embodiment.
Detailed Description
To make the objects, technical solutions and advantages of the present application more clear, the following detailed description of the embodiments of the present application will be made with reference to the accompanying drawings.
The terms "first," "second," and the like, in this application, are used for distinguishing between similar items and items that have substantially the same function or similar functionality, and it should be understood that "first," "second," and "nth" do not have any logical or temporal dependency, nor do they define a quantity or order of execution. It will be further understood that, although the following description uses the terms first, second, etc. to describe various elements, these elements should not be limited by these terms.
These terms are only used to distinguish one element from another. For example, a first element can be termed a second element, and, similarly, a second element can also be termed a first element, without departing from the scope of various examples. The first element and the second element may both be elements, and in some cases, may be separate and distinct elements.
At least one means one or more, and for example, at least one element may be an integer of one or more, such as one element, two elements, or three elements. And at least two means two or more, for example, at least two elements may be any integer number of two or more, such as two elements, three elements, and the like.
It should be noted that information (including but not limited to user equipment information, user personal information, etc.), data (including but not limited to data for analysis, stored data, presented data, etc.), and signals referred to in this application are authorized by the user or sufficiently authorized by various parties, and the collection, use, and processing of the relevant data is required to comply with relevant laws and regulations and standards in relevant countries and regions.
An implementation environment related to the video processing method provided by the embodiment of the present invention is described below.
Fig. 1 is a schematic diagram illustrating an environment for implementing a video processing method according to an exemplary embodiment.
Referring to fig. 1, the implementation environment includes: a photographing device 101, a streaming server 102, and a target device 103. The shooting device 101 has a video shooting function, and the shooting device 101 is a camera, for example. The streaming media server 102 is deployed privately, and is connected with the shooting device 101 through a network; the network connection may be a wired network connection or a wireless network connection, and the present application is not limited thereto.
The shooting device 101 is responsible for shooting a shooting area and pushing a collected video stream to the streaming media server 102 based on a streaming protocol; furthermore, the streaming media server 102 may push the video stream collected by the shooting device 101 to the target device 103 based on the streaming protocol, so as to be viewed online by the relevant people. The target device 103 is installed with a target application, which is also referred to as a video monitoring client or a video monitoring service or video monitoring software, and accordingly, the target device 103 is also referred to as a monitoring platform, and related people can view video pictures of a shooting area through the target application.
The first point to be noted is that the target device 103 may be a fixed device, such as a desktop computer or other computer device connected with a large screen; the target device 103 may also be a mobile device, such as a smartphone or tablet. In addition, the video stream forwarded to the target device 103 may not be the original video stream captured by the shooting device 101, but may be a video stream transcoded or transcoded and encapsulated by the streaming media server 102, which will be described in detail later.
In one possible implementation, the streaming protocol includes, but is not limited to: RTSP (Real Time Streaming Protocol) or RTMP (Real Time Messaging Protocol), which is not limited herein.
In another possible implementation manner, the shooting device 101 has a video acquisition function and also has a calculation processing capability, for example, after the shooting device 101 acquires a video stream, content analysis (also called video analysis) may be directly performed on the video stream based on an artificial intelligence technology, and then whether a security anomaly occurs in the shooting area is determined based on an analysis result, and an alarm prompt is generated under the condition that the security anomaly occurs, and then the generated alarm prompt is pushed to the target device 103 through the streaming media server 102.
To sum up, based on the streaming media server 102, the shooting device 101 can report the video stream and the corresponding alarm prompt to the monitoring platform in real time. The shooting device 101 may perform content analysis on the video stream, for example, behavior recognition, regional intrusion detection, fire recognition, and the like. For example, the camera 101 is of the infrared camera type for fire detection, i.e. fire detection is performed by infrared thermal imaging.
In another possible implementation manner, the streaming media server 102 may further perform content analysis on the video stream acquired by the shooting device 101 based on an artificial intelligence technology, which is not limited herein.
The second point of the description is that the number of the above-mentioned photographing apparatuses 101 is at least one, and the specific number can be set according to the area size of the target location. In a possible implementation manner, the shooting devices are respectively installed in different areas of a target place, and then different types of content analysis manners are set for different types of shooting areas, so that the safety abnormity of the target place is dynamically detected in real time, and an alarm prompt is given for the condition of the safety abnormity. For example, the target location to be photographed may be a hazardous material storage location, such as a liquefied gas station, and the present application is not limited thereto.
Fig. 2 is a flow diagram illustrating a video processing method according to an example embodiment. In a possible implementation manner, the method is applied to the streaming media server shown in fig. 1, that is, the shooting device is responsible for acquiring a video stream and pushing the video stream to the streaming media server, and then the streaming media server performs video analysis based on the video stream and generates an alarm prompt when it is determined that a security anomaly occurs. The method comprises the following steps.
201. The streaming media server acquires a video stream acquired by the shooting equipment, and decodes the video stream to obtain a multi-frame image.
The shooting equipment can be a fixed camera or a movable camera, and the application is not limited herein. After the streaming media server acquires the video stream, the streaming media server decodes the video stream, and changes an expression mode, the streaming media server divides the video stream frame by frame, namely, the video stream is divided into frames, and then a single image of one frame is obtained.
202. The streaming media server determines the area type of a shooting area of the shooting device, wherein the area type comprises an entrance area and a dangerous goods storage area.
In one possible implementation manner, a correspondence table between the device identifier of the shooting device and the area type of the shooting area may be established in advance, and the correspondence table may be stored in the streaming server. Therefore, after receiving the video stream pushed by the shooting device, the streaming media server can determine the area type of the corresponding shooting area according to the device identification of the shooting device.
The division of the area type is related to the target location to be photographed.
For example, assuming that the target site is used for storing dangerous goods, the types of shooting areas include, but are not limited to: an access area and a hazardous materials storage area. The hazardous material may be flammable material, such as liquefied gas, petroleum or natural gas, and the like, which is not limited herein. And if the target place is a shopping mall, the types of the shooting areas include, but are not limited to, an entrance area, a dining area, an entertainment area, and the like.
203. And the streaming media server performs content analysis on the multi-frame image according to a content analysis mode matched with the determined region type.
Taking the target site including the entrance area and the hazardous material storage area as an example, the content analysis method includes, but is not limited to: the method and the device are used for recognizing license plates of entrance areas and exit areas, and recognizing behaviors, regional invasion detection or fire conditions of dangerous goods storage areas, and the like.
204. The streaming media server responds to the obtained analysis result to indicate that the safety abnormity occurs in the shooting area, and determines an alarm level corresponding to the safety abnormity; and sending an alarm prompt matched with the determined alarm level to the target equipment according to the sending mode matched with the determined alarm level.
In a possible implementation manner, a correspondence table between the security anomaly and the alarm level may be established in advance, and the correspondence table is stored in the streaming media server. Therefore, after the stream media server determines that the safety abnormity occurs in the shooting area, the corresponding alarm level can be determined according to the corresponding relation table.
In another possible implementation manner, three alarm levels may be set, which are a first level, a second level and a third level, respectively, where the alarm level of the third level is the highest, and the alarm level of the second level is the next highest and the alarm level of the third level is the highest. Illustratively, the alarm level corresponding to the fire is set to a third level, the alarm level corresponding to the dangerous behavior is set to a second level, and the alarm levels corresponding to the intrusion of the foreign vehicle and the intrusion of the stranger are set to a third level.
The video processing method provided by the embodiment of the application can automatically analyze the video stream acquired by the shooting equipment, automatically determine whether the shooting area has safety abnormity according to the analysis result, and automatically alarm and prompt under the condition of determining the safety abnormity, and the whole process is not required to be manually participated in and is completely and automatically completed, so that the time and labor are saved, the efficiency is higher, and the time is more timely. In addition, the video processing method can adaptively analyze the contents of different types of shooting areas, has good identification effect and can accurately determine safety abnormity; in addition, different alarm levels correspond to different sending modes and alarm prompts, so that the alarm modes are enriched.
Fig. 2 is a basic flow chart of the present application, and the scheme provided in the present application is further described below based on a specific implementation manner, and fig. 3 is a flow chart of another video processing method according to an exemplary embodiment. Taking the example of interaction between the shooting device, the streaming media server and the target device, see fig. 3, the method includes the following steps.
301. And the shooting equipment pushes the collected video stream to a streaming media server.
The shooting device and the streaming media server are used for transmitting video data based on a streaming protocol, and the video data collected by the shooting device is transmitted in a streaming form, so the shooting device is called a video stream. Accordingly, the photographing apparatus may also be referred to as a push streaming side, and the streaming server may also be referred to as a streaming side.
302. The streaming media server decodes the video stream to obtain a plurality of frames of images.
The step of decoding the video stream may refer to the step 201, and is not described herein again.
In a possible implementation manner, after receiving a video stream (also referred to as an original video stream), the streaming media server may also transcode the original video stream to obtain video streams with different bit rates, frame rates, or resolutions; it is also possible to trans-encapsulate the original video stream to obtain video streams with different video formats. Namely, the embodiment of the application further comprises the steps of transcoding and trans-encapsulation.
Aiming at a transcoding process, a streaming media server acquires a plurality of transcoding parameters; the transcoding parameter may be a code rate, a frame rate, or a resolution, which is not limited herein. Taking the transcoding parameter as the resolution, each of the transcoding parameters is used to indicate a different resolution, for example, the number of the transcoding parameters is 3, which indicates three different resolutions, 720 × 480, 1280 × 720 and 1920 × 1080. And then, the streaming media server transcodes the original video stream respectively according to the plurality of transcoding parameters to obtain a plurality of transcoded video streams.
In consideration of network bandwidth and device performance, the streaming media server may determine a target transcoded video stream suitable for playing by the target device from among the plurality of transcoded video streams based on the current network bandwidth and device parameters of the target device, and then transmit the target transcoded video stream to the target device. The device parameter is used for indicating device performance, such as indicating display performance of the target device.
It should be noted that, in the embodiment of the present application, the transcoded video stream may also be sent to the target device based on the user requirement. Illustratively, after sending the target transcoded video stream to the target device, if the relevant person switches to a lower resolution transcoded video stream by operating on the target device, the streaming media server pushes the selected transcoded video stream to the target device.
The second point to be noted is that the transcoding operation may be performed by a dedicated transcoding server in addition to the streaming server, that is, the transcoding server is also included in the implementation environment shown in fig. 1, where the transcoding server is connected to the streaming server. The streaming media server can send the original video stream to the transcoding server for transcoding, and after transcoding is completed, the transcoding server sends the transcoded video stream to the streaming media server, so that the streaming media server sends the transcoded video stream to the target device.
And aiming at the conversion packaging process, the streaming media server converts and packages the original video stream from the original video format into a plurality of target video formats to obtain a plurality of conversion packaged video streams. For example, assuming that the original Video format is FLV (Flash Video, streaming media), the target Video format may be MP4(Moving Picture Experts Group Audio Layer IV, motion Picture Experts compression standard Audio Layer 4) or AVI (Audio Video Interleaved), etc., and the present application is not limited herein. Then, the streaming media server may determine a target trans-encapsulation video stream among the multiple trans-encapsulation video streams based on the video format that the target device supports playing, and then send the target trans-encapsulation video stream to the target device.
A third point to be noted is that the target device supports a played video format, including: a video monitoring client installed on the target equipment supports the played video format; or, the browser installed in the target device supports the played video format, which is not limited herein. For the latter, the target device may also play the video pictures collected by the shooting device through the browser.
303. The method comprises the steps that a streaming media server determines the area type of a shooting area of shooting equipment; and performing content analysis on the multi-frame image according to a content analysis mode matched with the region type.
In a possible implementation manner, taking a photographed target place including an entrance area and a dangerous goods storage area as an example, license plate recognition may be performed on the entrance area, and behavior recognition, fire recognition, area intrusion detection and the like may be performed on the dangerous goods area, which is not limited herein.
3031. Selecting a vehicle image from the multi-frame images in response to the shooting area being an entrance area; detecting a license plate area of the vehicle image; cutting out a license plate area in the vehicle image based on the obtained license plate area detection result; recognizing license plate characters of a license plate area based on a first recognition model; the first recognition model is obtained by training based on a sample vehicle image marked with license plate characters.
In the embodiment of the present application, the selection of the vehicle image among the plurality of frame images belongs to an Object Detection (Object Detection) task. The target detection task is used for detecting and identifying the positions and the types of the targets such as people, vehicles, animals, plants and the like in the image. In this step, the target is a vehicle.
Generally, the object detection includes two tasks of detection and identification, wherein the detection task is used for determining the specific position of an object in an image, and the identification task is used for carrying out category judgment on the detected object. Put another way, object detection typically involves two processes, one to predict the class of the object and the other to draw a bounding box around the object.
In a possible implementation manner, taking the detected target as a pedestrian as an example, the target detection result gives the position information (xb, yb, width, height) of the pedestrian. Where, (xb, yb) is the coordinates of the starting point of the detected bounding box, and width and height refer to the width and height of the bounding box, respectively.
In another possible implementation manner, target detection is performed on multiple frames of images based on a target detection algorithm. The target detection algorithm used includes, but is not limited to: fast R-CNN (Convolutional Neural Networks), Mask R-CNN, YOLO (young Only Look one), YOLOv2, YOLOv3, etc., which are not limited herein.
After the vehicle image is identified, vehicle region detection can be carried out on the vehicle image based on the trained machine learning model; the machine learning model is obtained by training based on a sample vehicle image marked with a vehicle region.
In a possible implementation manner, aiming at license plate recognition, in response to the fact that recognized license plate characters are inconsistent with pre-stored license plate characters, safety abnormity is determined to occur.
3032. Responding to the fact that the shooting area is a dangerous goods storage area, selecting a living body image from the multi-frame image, wherein the living body image comprises a target living body; detecting a bone key point of a target living body included in the living body image; identifying the action type of the target living body through a second identification model based on the obtained bone key point detection result; and the second recognition model is obtained by training based on the sample living body image marked with the dangerous motion type.
Selecting a living body image from the plurality of frame images also belongs to the target detection task, and may be performed with reference to step 3031, which is not described herein again.
In one possible implementation, the target living body is a pedestrian, and accordingly, the living body image is a pedestrian image, and the above-mentioned bone key point detection is human bone key point detection. The human skeleton key point detection takes the pedestrian image as input to detect the position of a human key part. Exemplary human skeletal key points include, but are not limited to: left eye, right eye, left ear, right ear, nose, left shoulder, right shoulder, left elbow, right elbow, left wrist, right wrist, left hip, right hip, left knee, right knee, left ankle, right ankle, and the like.
Wherein the types of dangerous actions include, but are not limited to, smoking, falling, picking up dangerous goods, etc., and the application is not limited thereto. In one possible implementation, for behavior recognition, in response to the recognized action type being consistent with a pre-stored dangerous behavior type, it is determined that a safety exception has occurred.
In the embodiment of the application, the multi-frame image is an infrared image in response to the fact that the shooting device is an infrared camera; the infrared image is an image formed by the infrared camera collecting radiation of a target in an infrared band, and the image can be a gray image or a color image. The fire may also be identified using infrared thermal imaging principles, as detailed in step 3033 below.
3033. Responding to the fact that the shooting area is a dangerous goods storage area, and determining the current temperature of the shooting area based on the infrared image; recognizing the fire position of the shooting area through a third recognition model based on the infrared image in response to the current temperature of the shooting area being higher than the target temperature; and the third recognition model is obtained by training based on the sample infrared image marked with the fire position.
In one possible implementation, the infrared image is detected by using the infrared thermal imaging principle, so as to determine the current temperature of the shooting area. In order to more accurately identify the fire situation, the fire position can be further identified under the condition that the current temperature of the shooting area is determined to be higher than the target temperature; if a location of a fire is identified, a safety exception is determined to have occurred. That is, for fire recognition, it is determined that a safety abnormality occurs in response to the current temperature of the photographing region being higher than the target temperature and the location of fire being recognized.
It should be noted that the first recognition model, the second recognition model, and the third recognition model are all machine learning models, such as convolutional neural networks, and the application is not limited herein.
In another possible implementation, if a fire is identified and a living body exists in the shooting area, an escape route can be planned according to the progress of the fire. Namely, the embodiment of the application further comprises the following steps: responding to the existence of the target living body in the shooting area, and acquiring the current position of the target living body; and determining a moving route for the target living body according to the fire passing range of the shooting area after the target time length by taking the current position of the target living body as a starting point and the exit position of the shooting area as an end point, wherein the moving route is used for indicating that the target living body leaves the shooting area.
In another possible implementation manner, since the current environmental information, the type of the dangerous goods and the total amount of the dangerous goods in the shooting area all affect the progress of the fire, the fire passing range of the shooting area after the target duration is obtained as follows: acquiring current environmental information of a shooting area; acquiring the types of dangerous goods and the total amount of the dangerous goods stored in a shooting area; determining the progress speed of the fire according to the current environmental information, the types of dangerous goods and the total amount of the dangerous goods in the shooting area; and determining the fire passing range of the shooting area after the target duration according to the fire progress speed and the fire position. For example, the environmental information includes, but is not limited to, wind power, humidity, and the like, and the embodiments of the present application are not limited thereto.
3034. Responding to the fact that the shooting area is a dangerous goods storage area, selecting a living body image from the multi-frame image, wherein the living body image comprises a target living body; carrying out face recognition on a target living body; and in response to the fact that the recognized face does not match the target face template, recognizing the moving direction of the target living body in the shooting area based on the position information of the target living body in the living body image.
Based on the above step 3031, the position information of the target living body in the living body image can be obtained at the stage of selecting the living body image. In the embodiment of the application, if the living body images are multiple frames, the position information of the target living body in each frame of living body image is connected, so that the motion trail of the target living body can be formed, the target living body is tracked, and the moving direction of the target living body can be identified by tracking the target living body. Wherein, the identified human face is not matched with the target human face template, which indicates that the target living body is a stranger appearing in the shooting area.
In one possible implementation, for the area intrusion recognition, the occurrence of the security anomaly is determined in response to the presence of a stranger within the shooting area and the stranger not moving away from the shooting area.
304. The streaming media server responds to the obtained analysis result to indicate that the safety abnormity occurs in the shooting area, and determines an alarm level corresponding to the safety abnormity; and sending an alarm prompt matched with the alarm level to the target equipment according to the sending mode matched with the alarm level.
In one possible implementation manner, the sending of the alarm prompt matching the alarm level to the target device is performed according to a sending manner matching the alarm level, which includes the following manners.
3041. And responding to the alarm level larger than the target level, and sending a first type of alarm prompt to the target equipment according to a first sending mode.
The first type of alarm prompt may carry a target image, where the target image is an image in which image content is associated with a security anomaly. For example, if a dangerous behavior is recognized, the target image includes a living body that is performing the dangerous behavior. In addition, the number of frames of the target image may be one or more frames. Besides the target image, the first type of alarm prompt may also carry a text prompt or a voice prompt, which is not limited herein.
For example, as described above, the alarm level is divided into three levels as an example, the target level may be the first level, and the application is not limited herein.
In another possible implementation, the first sending mode comprises sending in the form of an in-application message and sending in the form of an out-of-application message; the information in the application is displayed through a video monitoring client installed on the target equipment, and the information out of the application is not displayed through the video monitoring client.
According to the method for pushing the alarm prompt in a combined manner, even if the video monitoring client is in a problem or the video monitoring client is not started, related personnel can still receive the alarm prompt through the external message, and therefore the safety abnormity can be timely processed. The out-of-application message includes, but is not limited to, a short message or an instant messaging message, and the like, and the application is not limited herein.
3042. And responding to the alarm level smaller than the target level, and sending a second type of alarm prompt to the target equipment according to a second sending mode. The second sending mode may be sending in the form of an in-application message, and the second type of alert prompt may carry a text prompt or a voice prompt, which is not limited herein.
305. And the target equipment displays the alarm prompt pushed by the streaming media server.
In the embodiment of the application, the alarm prompt can be displayed in a form of a popup window in the video monitoring client; or, the short message is displayed in the form of short message in the short message client; or, the instant messaging information is displayed in the instant messaging client; or, the display is performed in the form of a web page in the browser client, and the embodiment of the application is not limited herein. Illustratively, what display mode is specifically adopted to display the alarm prompt is related to the sending mode of the alarm prompt.
The video processing method provided by the embodiment of the application can automatically analyze the video stream acquired by the shooting equipment, automatically determine whether the shooting area has safety abnormity according to the analysis result, and automatically alarm and prompt under the condition of determining the safety abnormity, and the whole process is not required to be manually participated in and is completely and automatically completed, so that the time and labor are saved, the efficiency is higher, and the time is more timely. In addition, the video processing method can adaptively analyze the contents of different types of shooting areas, has good identification effect and can accurately determine safety abnormity; in addition, different alarm levels correspond to different sending modes and alarm prompts, so that the alarm modes are enriched.
Fig. 4 is a schematic diagram illustrating a structure of a video processing apparatus according to an exemplary embodiment. Referring to fig. 4, the apparatus includes:
the first processing module 401 is configured to acquire a video stream acquired by a shooting device, decode the video stream, and obtain a multi-frame image;
a first determining module 402 configured to determine an area type of a photographing area of the photographing apparatus, the area type including an entrance area and a hazardous material storage area;
a second processing module 403, configured to perform content analysis on the multiple frames of images according to a content analysis manner matched with the region type;
a second determining module 404, configured to determine, in response to the obtained analysis result indicating that a security anomaly occurs in the shooting area, an alarm level corresponding to the security anomaly;
and a sending module 405 configured to send an alarm prompt matching the alarm level to the target device according to the sending mode matching the alarm level.
The video processing device provided by the embodiment of the application can automatically analyze the video stream collected by the shooting equipment, automatically determine whether the shooting area has safety abnormity according to the analysis result, and automatically alarm and prompt under the condition of determining the safety abnormity, and because the whole process does not need to be manually participated in all automatic completion, the time and the labor are saved, the efficiency is higher, and the time is more timely. In addition, the video processing method can adaptively analyze the contents of different types of shooting areas, has good identification effect and can accurately determine safety abnormity; in addition, different alarm levels correspond to different sending modes and alarm prompts, so that the alarm modes are enriched.
In one possible implementation, the sending module is configured to:
responding to the alarm level larger than the target level, and sending a first type of alarm prompt to the target equipment according to a first sending mode;
the first type of alarm prompt carries a target image, wherein the target image is an image associated with the security anomaly and the image content in the multi-frame image;
the first sending mode comprises sending in the form of an in-application message and sending in the form of an out-of-application message; the in-application message is displayed through a target application installed on the target device, and the out-application message is not displayed through the target application.
In one possible implementation, the apparatus further includes:
a transcoding module configured to obtain a plurality of transcoding parameters; transcoding the video stream according to the plurality of transcoding parameters respectively to obtain a plurality of transcoded video streams; and determining a target transcoded video stream in the plurality of transcoded video streams based on the current network bandwidth and the device parameters of the target device, and sending the target transcoded video stream to the target device.
In one possible implementation, the apparatus further includes:
the trans-encapsulation module is configured to trans-encapsulate the video stream from an original video format into a plurality of target video formats to obtain a plurality of trans-encapsulated video streams; and determining a target to package video stream in the multiple to package video streams based on the video format supported by the target device to play, and sending the target to package video stream to the target device.
In one possible implementation, the second processing module is configured to:
selecting a vehicle image from the multi-frame images in response to the shooting area being an entrance area;
detecting a license plate region of the vehicle image; cutting out a license plate area from the vehicle image based on the obtained license plate area detection result;
recognizing license plate characters of the license plate area based on a first recognition model; the first recognition model is obtained by training based on a sample vehicle image marked with license plate characters.
In one possible implementation, the second processing module is configured to:
responding to the fact that the shooting area is a dangerous goods storage area, selecting a living body image from the multi-frame image, wherein the living body image comprises a target living body;
detecting a bone key point of a target living body included in the living body image;
identifying the action type of the target living body through a second identification model based on the obtained bone key point detection result; and the second recognition model is obtained by training based on the sample living body image marked with the dangerous motion type.
In one possible implementation manner, the multi-frame image is an infrared image; the second processing module configured to:
determining the current temperature of the shooting area based on the infrared image in response to the shooting area being a dangerous goods storage area;
identifying a fire position of the shooting area through a third identification model based on the infrared image in response to the current temperature of the shooting area being higher than a target temperature; and the third recognition model is obtained by training based on the sample infrared image marked with the fire position.
In one possible implementation, the apparatus further includes:
a route planning module configured to acquire a current position of a target living body in response to the presence of the target living body within the photographing region; and determining a moving route for the target living body according to a fire passing range of the shooting area after a target time length by taking the current position of the target living body as a starting point and the exit position of the shooting area as an end point, wherein the moving route is used for indicating the target living body to leave the shooting area.
In one possible implementation, the route planning module is further configured to:
acquiring current environmental information of the shooting area;
acquiring the types of dangerous goods stored in the shooting area and the total amount of the dangerous goods;
determining the progress speed of the fire according to the environmental information, the type of the dangerous goods and the total amount of the dangerous goods;
and determining the fire passing range of the shooting area after the target duration according to the fire progress speed and the fire position.
In one possible implementation, the second processing module is configured to:
in response to the fact that the shooting area is a dangerous goods storage area, selecting a living body image from the multi-frame image, wherein the living body image comprises a target living body;
carrying out face recognition on the target living body; and in response to the fact that the recognized face does not match the target face template, recognizing the moving direction of the target living body in the shooting area based on the position information of the target living body in the living body image.
All the above optional technical solutions may be combined arbitrarily to form the optional embodiments of the present disclosure, and are not described herein again.
It should be noted that: in the video processing apparatus provided in the above embodiment, when performing video processing, only the division of the above functional modules is taken as an example, and in practical applications, the above functions may be distributed by different functional modules according to needs, that is, the internal structure of the apparatus is divided into different functional modules to complete all or part of the above described functions. In addition, the video processing apparatus and the video processing method provided by the above embodiments belong to the same concept, and specific implementation processes thereof are described in the method embodiments in detail and are not described herein again.
Fig. 5 is a block diagram of a computer device 500 shown in accordance with an example embodiment. Wherein the computer device 500 may be the aforementioned streaming media server.
The computer device 500 may have a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 501 and one or more memories 502, where the memory 502 stores at least one program code, and the at least one program code is loaded and executed by the processors 501 to implement the video Processing method provided by the above-mentioned method embodiments. Of course, the computer device 500 may further have components such as a wired or wireless network interface, a keyboard, and an input/output interface, so as to perform input and output, and the computer device 500 may further include other components for implementing device functions, which are not described herein again.
In an exemplary embodiment, there is also provided a computer readable storage medium, such as a memory, including program code executable by a processor in a computer device to perform the video processing method in the above embodiments. For example, the computer-readable storage medium may be a Read-Only Memory (ROM), a Random Access Memory (RAM), a Compact Disc Read-Only Memory (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, and the like.
In an exemplary embodiment, a computer program product or a computer program is also provided, the computer program product or the computer program comprising computer program code, the computer program code being stored in a computer-readable storage medium, the computer program code being read by a processor of a computer device from the computer-readable storage medium, the processor executing the computer program code, such that the computer device performs the above-mentioned video processing method.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The above description is only exemplary of the present application and should not be taken as limiting, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (13)
1. A method of video processing, the method comprising:
acquiring a video stream acquired by shooting equipment, and decoding the video stream to obtain a plurality of frames of images;
determining the area type of a shooting area of the shooting equipment, wherein the area type comprises an entrance area and an exit area and a dangerous goods storage area;
performing content analysis on the multi-frame image according to a content analysis mode matched with the region type;
responding to the obtained analysis result to indicate that safety abnormity occurs in the shooting area, and determining an alarm level corresponding to the safety abnormity;
and sending an alarm prompt matched with the alarm level to the target equipment according to the sending mode matched with the alarm level.
2. The method of claim 1, wherein sending an alert prompt matching the alert level to a target device in a sending manner matching the alert level comprises:
responding to the alarm level larger than the target level, and sending a first type of alarm prompt to the target equipment according to a first sending mode;
the first type of alarm prompt carries a target image, wherein the target image is an image associated with the security anomaly and the image content in the multi-frame image;
the first sending mode comprises sending in the form of an in-application message and sending in the form of an out-application message; the in-application message is displayed through a target application installed on the target device, and the out-application message is not displayed through the target application.
3. The method of claim 1, further comprising:
obtaining a plurality of transcoding parameters; transcoding the video stream according to the plurality of transcoding parameters respectively to obtain a plurality of transcoded video streams;
and determining a target transcoded video stream in the plurality of transcoded video streams based on the current network bandwidth and the device parameters of the target device, and sending the target transcoded video stream to the target device.
4. The method of claim 1, further comprising:
converting and packaging the video stream from an original video format into a plurality of target video formats to obtain a plurality of converted and packaged video streams;
and determining a target to package video stream in the multiple to package video streams based on the video format supported by the target device to play, and sending the target to package video stream to the target device.
5. The method according to claim 1, wherein the performing content analysis on the multi-frame image according to the content analysis mode matched with the region type comprises:
selecting a vehicle image from the multi-frame images in response to the shooting area being an entrance area;
detecting a license plate region of the vehicle image; cutting out a license plate area from the vehicle image based on the obtained license plate area detection result;
recognizing license plate characters of the license plate area based on a first recognition model; the first recognition model is obtained by training based on a sample vehicle image marked with license plate characters.
6. The method according to claim 1, wherein the performing content analysis on the multi-frame image according to the content analysis mode matched with the region type comprises:
responding to the fact that the shooting area is a dangerous goods storage area, selecting a living body image from the multi-frame image, wherein the living body image comprises a target living body;
detecting a bone key point of a target living body included in the living body image;
identifying the action type of the target living body through a second identification model based on the obtained bone key point detection result; and the second recognition model is obtained by training based on the sample living body image marked with the dangerous motion type.
7. The method according to claim 1, wherein the multi-frame image is an infrared image; the content analysis of the multi-frame image according to the content analysis mode matched with the region type comprises the following steps:
determining the current temperature of the shooting area based on the infrared image in response to the shooting area being a dangerous goods storage area;
identifying a fire position of the shooting area through a third identification model based on the infrared image in response to the current temperature of the shooting area being higher than a target temperature; and the third recognition model is obtained by training based on the sample infrared image marked with the fire position.
8. The method of claim 7, further comprising:
acquiring a current position of a target living body in response to the presence of the target living body within the photographing region;
and determining a moving route for the target living body according to a fire passing range of the shooting area after a target time length by taking the current position of the target living body as a starting point and the exit position of the shooting area as an end point, wherein the moving route is used for indicating the target living body to leave the shooting area.
9. The method of claim 8, further comprising:
acquiring current environmental information of the shooting area;
acquiring the types of dangerous goods stored in the shooting area and the total amount of the dangerous goods;
determining the progress speed of the fire according to the environmental information, the type of the dangerous goods and the total amount of the dangerous goods;
and determining the fire passing range of the shooting area after the target duration according to the fire progress speed and the fire position.
10. The method according to claim 1, wherein the performing content analysis on the multi-frame image according to the content analysis mode matched with the region type comprises:
responding to the fact that the shooting area is a dangerous goods storage area, selecting a living body image from the multi-frame image, wherein the living body image comprises a target living body;
carrying out face recognition on the target living body; and in response to the fact that the recognized face does not match the target face template, recognizing the moving direction of the target living body in the shooting area based on the position information of the target living body in the living body image.
11. A video processing apparatus, characterized in that the apparatus comprises:
the first processing module is configured to acquire a video stream acquired by shooting equipment, decode the video stream and obtain a multi-frame image;
a first determination module configured to determine an area type of a photographing area of the photographing apparatus, the area type including an entrance area and a hazardous material storage area;
the second processing module is configured to perform content analysis on the multi-frame images according to a content analysis mode matched with the region type;
the second determination module is configured to respond to the obtained analysis result indicating that safety abnormity occurs in the shooting area, and determine an alarm level corresponding to the safety abnormity;
and the sending module is configured to send the alarm prompt matched with the alarm level to the target equipment according to the sending mode matched with the alarm level.
12. A computer device, characterized in that it comprises a processor and a memory in which at least one program code is stored, which is loaded and executed by the processor to implement the video processing method according to any one of claims 1 to 10.
13. A computer-readable storage medium, having stored therein at least one program code, which is loaded and executed by a processor, to implement the video processing method according to any one of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210594790.5A CN115019462A (en) | 2022-05-27 | 2022-05-27 | Video processing method, device, storage medium and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210594790.5A CN115019462A (en) | 2022-05-27 | 2022-05-27 | Video processing method, device, storage medium and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115019462A true CN115019462A (en) | 2022-09-06 |
Family
ID=83070049
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210594790.5A Pending CN115019462A (en) | 2022-05-27 | 2022-05-27 | Video processing method, device, storage medium and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115019462A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117176962A (en) * | 2023-11-02 | 2023-12-05 | 中国铁塔股份有限公司 | Video encoding and decoding method and device and related equipment |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105719421A (en) * | 2016-04-27 | 2016-06-29 | 丛静华 | Big data mining based integrated forest fire prevention informatization system |
| CN106533479A (en) * | 2016-10-20 | 2017-03-22 | 上海宜君科技有限公司 | Infrared imaging search method and interphone with infrared imaging search function |
| KR101793636B1 (en) * | 2017-05-31 | 2017-11-03 | 주식회사 투윈스컴 | Image processing system |
| CN107941218A (en) * | 2017-10-31 | 2018-04-20 | 天津大学 | Visitor based on architecture structure drawing and fire communication system uses escape indoor navigation system |
| CN111199625A (en) * | 2020-01-19 | 2020-05-26 | 中山市果度装饰工程有限公司 | Whole fire control safety intelligent system of building |
| CN111258251A (en) * | 2020-01-19 | 2020-06-09 | 中山市果度装饰工程有限公司 | Fire extinguishing system for intelligent building |
| CN111507308A (en) * | 2020-05-07 | 2020-08-07 | 广东电网有限责任公司 | Transformer substation safety monitoring system and method based on video identification technology |
| CN112788367A (en) * | 2020-12-30 | 2021-05-11 | 杭州海康威视系统技术有限公司 | Streaming media scheduling method, system and scheduling component |
| CN113903141A (en) * | 2021-11-18 | 2022-01-07 | 贵州电网有限责任公司 | Scene abnormal event identification, analysis and alarm system for transformer substation and distribution room and outdoor transformer |
| CN114419536A (en) * | 2021-12-17 | 2022-04-29 | 北京声智科技有限公司 | Alarm method, device, equipment and computer readable storage medium |
-
2022
- 2022-05-27 CN CN202210594790.5A patent/CN115019462A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105719421A (en) * | 2016-04-27 | 2016-06-29 | 丛静华 | Big data mining based integrated forest fire prevention informatization system |
| CN106533479A (en) * | 2016-10-20 | 2017-03-22 | 上海宜君科技有限公司 | Infrared imaging search method and interphone with infrared imaging search function |
| KR101793636B1 (en) * | 2017-05-31 | 2017-11-03 | 주식회사 투윈스컴 | Image processing system |
| CN107941218A (en) * | 2017-10-31 | 2018-04-20 | 天津大学 | Visitor based on architecture structure drawing and fire communication system uses escape indoor navigation system |
| CN111199625A (en) * | 2020-01-19 | 2020-05-26 | 中山市果度装饰工程有限公司 | Whole fire control safety intelligent system of building |
| CN111258251A (en) * | 2020-01-19 | 2020-06-09 | 中山市果度装饰工程有限公司 | Fire extinguishing system for intelligent building |
| CN111507308A (en) * | 2020-05-07 | 2020-08-07 | 广东电网有限责任公司 | Transformer substation safety monitoring system and method based on video identification technology |
| CN112788367A (en) * | 2020-12-30 | 2021-05-11 | 杭州海康威视系统技术有限公司 | Streaming media scheduling method, system and scheduling component |
| CN113903141A (en) * | 2021-11-18 | 2022-01-07 | 贵州电网有限责任公司 | Scene abnormal event identification, analysis and alarm system for transformer substation and distribution room and outdoor transformer |
| CN114419536A (en) * | 2021-12-17 | 2022-04-29 | 北京声智科技有限公司 | Alarm method, device, equipment and computer readable storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117176962A (en) * | 2023-11-02 | 2023-12-05 | 中国铁塔股份有限公司 | Video encoding and decoding method and device and related equipment |
| CN117176962B (en) * | 2023-11-02 | 2024-01-30 | 中国铁塔股份有限公司 | Video encoding and decoding method and device and related equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20110128150A1 (en) | System and method for electronic surveillance | |
| CN110516529A (en) | It is a kind of that detection method and system are fed based on deep learning image procossing | |
| CN111414873B (en) | Alarm prompting method, device and alarm system based on wearing state of safety helmet | |
| TW201104585A (en) | Identifying spatial locations of events within video image data | |
| KR20110130033A (en) | Active image monitoring system using motion pattern database, and method thereof | |
| KR102407327B1 (en) | Apparatus for Monitoring Fire And System having the same | |
| CN110147723B (en) | Method and system for processing abnormal behaviors of customers in unmanned store | |
| CN109544870B (en) | Alarm judgment method for intelligent monitoring system and intelligent monitoring system | |
| CN116165981A (en) | Intelligent monitoring system for industrial industry safety production | |
| CN112422909B (en) | Video behavior analysis management system based on artificial intelligence | |
| CN111178241A (en) | Intelligent monitoring system and method based on video analysis | |
| CN211184122U (en) | Intelligent video analysis system for linkage of railway operation safety prevention and control and large passenger flow early warning | |
| CN112188164A (en) | AI vision-based violation real-time monitoring system and method | |
| CN115019462A (en) | Video processing method, device, storage medium and equipment | |
| CN115103157A (en) | Video analysis method and device based on edge cloud cooperation, electronic equipment and medium | |
| KR20230086457A (en) | Electronic apparatus for building fire detecting system and method thereof | |
| JPWO2018037665A1 (en) | INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING SYSTEM, CONTROL METHOD, AND PROGRAM | |
| CN110928305B (en) | Patrol method and system for patrol robot of railway passenger station | |
| Bhandari et al. | Development of a real-time security management system for restricted access areas using computer vision and deep learning | |
| CN112419639A (en) | Video information acquisition method and device | |
| CN112988337A (en) | Task processing system, method, device, electronic equipment and storage medium | |
| CN116824480A (en) | Monitoring video analysis method and system based on deep stream | |
| CN108073854A (en) | A kind of detection method and device of scene inspection | |
| US20100134619A1 (en) | Evaluating an effectiveness of a monitoring system | |
| CN112733809B (en) | Intelligent image identification method and system for natural protection area monitoring system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |