WO2019148684A1 - 一种车内监控方法及设备 - Google Patents

一种车内监控方法及设备 Download PDF

Info

Publication number
WO2019148684A1
WO2019148684A1 PCT/CN2018/085879 CN2018085879W WO2019148684A1 WO 2019148684 A1 WO2019148684 A1 WO 2019148684A1 CN 2018085879 W CN2018085879 W CN 2018085879W WO 2019148684 A1 WO2019148684 A1 WO 2019148684A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicle
image data
abnormality
analysis result
real
Prior art date
Application number
PCT/CN2018/085879
Other languages
English (en)
French (fr)
Inventor
刘均
刘新
周军
Original Assignee
深圳市元征软件开发有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 深圳市元征软件开发有限公司 filed Critical 深圳市元征软件开发有限公司
Publication of WO2019148684A1 publication Critical patent/WO2019148684A1/zh

Links

Classifications

    • 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
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
    • G08B25/007—Details of data content structure of message packets; data protocols
    • 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
    • G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
    • 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
    • G08B21/02—Alarms for ensuring the safety of persons
    • 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
    • G08B21/22—Status alarms responsive to presence or absence 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
    • H04N7/188—Capturing isolated or intermittent images triggered by the occurrence of a predetermined event, e.g. an object reaching a predetermined position

Definitions

  • the present invention relates to the field of vehicle technology, and in particular, to an in-vehicle monitoring method and device.
  • the embodiment of the invention provides an in-vehicle monitoring method and device, which is beneficial to solving the problem of relying on manual judgment of the interior environment and information security leakage in the prior art, and improving the monitoring efficiency of the vehicle interior environment.
  • an embodiment of the present invention provides an in-vehicle monitoring method, the method comprising: acquiring real-time image data inside a vehicle; analyzing and processing the real-time image data according to a preset algorithm to obtain an image analysis result; Determining whether there is an abnormality in the image analysis result; if yes, sending an alarm to the server or the bound vehicle owner terminal; transmitting corresponding abnormal image data according to the data request of the server or the vehicle owner terminal, so that the server or the The owner terminal performs the corresponding measures after confirming the abnormality.
  • the preset algorithm includes a portrait recognition algorithm and a smoke detection algorithm
  • the The real-time image data is analyzed and processed, and specifically includes: identifying a number of portraits and a portrait state in the real-time image data by using a portrait recognition algorithm; and identifying a smoke occurrence state in the real-time image data by using a smoke detection algorithm.
  • the determining, by the image analysis result, whether an abnormality exists specifically includes : determining whether there is smoke in the vehicle according to the state of occurrence of smoke in the image analysis result, and if so, determining that there is an abnormality.
  • the The image analysis result determines whether there is an abnormality, and specifically includes: acquiring an operating state of the vehicle; determining whether the number of portraits and/or the portrait state in the image analysis result matches the running state of the vehicle; if not, determining There is an exception.
  • the corresponding abnormal image data includes image data of an abnormal start to an abnormal elimination time period.
  • a second aspect of the present invention provides an apparatus, the apparatus comprising: a memory storing executable program code; a processor coupled to the memory; the processor invoking the executable program stored in the memory
  • the code performs the following steps: acquiring real-time image data inside the vehicle; analyzing and processing the real-time image data according to a preset algorithm to obtain an image analysis result; determining whether there is an abnormality according to the image analysis result; if present, going to the server Or the bound vehicle owner terminal sends an alarm; and sends corresponding abnormal image data according to the data request of the server or the vehicle owner terminal, so that the server or the vehicle owner terminal performs corresponding measures after confirming the abnormality.
  • the preset algorithm includes a portrait recognition algorithm and a smoke detection algorithm, where the processor performs the pre-prevention
  • the algorithm is configured to analyze and process the real-time image data by using a portrait recognition algorithm to identify the number of portraits and a portrait state in the real-time image data; and using a smoke detection algorithm to identify a smoke occurrence state in the real-time image data.
  • the processor performs, according to the image analysis result, whether There is an abnormality.
  • the specific method is: determining whether there is smoke in the vehicle according to the state of occurrence of smoke in the image analysis result, and if so, determining that there is an abnormality.
  • the processing Performing the determining whether the abnormality exists according to the image analysis result includes: acquiring an operating state of the vehicle; determining whether the number of portraits and/or the portrait state in the image analysis result matches the running state of the vehicle; If there is no match, it is determined that there is an abnormality.
  • the processor performs the image data of the abnormal image data from the abnormal start to the abnormal elimination time period.
  • real-time image data of the interior of the vehicle is acquired; the real-time image data is analyzed and processed according to a preset algorithm to obtain an image analysis result; and whether an abnormality exists according to the image analysis result; If yes, send an alarm to the server or the bound vehicle owner terminal; send corresponding abnormal image data according to the data request of the server or the vehicle owner terminal, so that the server or the vehicle owner terminal performs corresponding after confirming the abnormality Measures.
  • FIG. 1 is a schematic diagram of an application scenario of an in-vehicle monitoring method according to an embodiment of the present invention
  • FIG. 2 is a schematic flowchart of a method for monitoring a vehicle in an embodiment of the present invention
  • FIG. 3 is a schematic structural diagram of an in-vehicle monitoring device according to an embodiment of the present invention.
  • FIG. 4 is a schematic structural diagram of another in-vehicle monitoring device according to an embodiment of the present invention.
  • references to "an embodiment” herein mean that a particular feature, structure, or characteristic described in connection with the embodiments can be included in at least one embodiment of the invention.
  • the appearances of the phrases in various places in the specification are not necessarily referring to the same embodiments, and are not exclusive or alternative embodiments that are mutually exclusive. Those skilled in the art will understand and implicitly understand that the embodiments described herein can be combined with other embodiments.
  • Multiple means two or more. "and/or”, describing the association relationship of the associated objects, indicating that there may be three relationships, for example, A and/or B, which may indicate that there are three cases where A exists separately, A and B exist at the same time, and B exists separately.
  • the character "/" generally indicates that the contextual object is an "or" relationship.
  • FIG. 1 is a schematic diagram of an application scenario of an in-vehicle monitoring method according to an embodiment of the present invention.
  • the application scenario includes: a vehicle 10, an in-vehicle monitoring device 20 installed on the vehicle 10, a server 30 and a vehicle owner terminal 40.
  • the in-vehicle monitoring device 20 has a built-in controller with analysis and calculation functions, and can The acquired data is analyzed and processed.
  • the in-vehicle monitoring device 20 may be an in-vehicle device with an image acquisition module (such as a camera, an image scanner, or an infrared detection sensor), or may have an in-vehicle image acquisition hardware (such as an in-vehicle camera, an image scanner, or an infrared detector). Instrument, etc.)
  • An in-vehicle device such as an in-vehicle terminal, an OBD, or a digital instrument that performs communication connection and controls image acquisition hardware to acquire image data.
  • the in-vehicle monitoring device 20 can establish a communication connection with the server 30 and the vehicle owner terminal 40 via a communication network or short-range wireless communication.
  • the in-vehicle monitoring method of the embodiment of the present invention is applied to the in-vehicle monitoring device 20.
  • the in-vehicle monitoring device acquires real-time image data of the interior of the vehicle, analyzes and processes the image data, and performs the analysis result obtained. If it is determined that there is an abnormality, the abnormal result is transmitted to the server 30 or the vehicle owner terminal 40, and the abnormal image data is transmitted to the server 30 or the vehicle owner terminal 40.
  • FIG. 2 is a schematic flowchart diagram of an in-vehicle monitoring method according to an embodiment of the present invention. As shown in FIG. 2, the method is applied to an in-vehicle monitoring device, and the method includes the following steps.
  • the in-vehicle monitoring device can obtain real-time image data inside the vehicle through a built-in image acquisition module (such as an in-vehicle camera, an image scanner or an infrared detector), and can also control the in-vehicle image acquisition hardware after establishing a communication connection (such as An in-vehicle camera, an image scanner, or an infrared detector, etc.) acquires real-time image data inside the vehicle.
  • a built-in image acquisition module such as an in-vehicle camera, an image scanner or an infrared detector
  • the in-vehicle monitoring device can analyze and process the real-time image data according to a preset algorithm by using its own controller.
  • the preset algorithm includes a portrait recognition algorithm and a smoke detection algorithm.
  • the analyzing and processing the real-time image data according to the preset algorithm comprises: identifying a number of portraits and a portrait state in the real-time image data by using a portrait recognition algorithm, and identifying a smoke occurrence state in the real-time image data by using a smoke detection algorithm.
  • the portrait recognition algorithm can be used to analyze the number of portraits in the real-time image data, the number of portraits is determined according to the number of portraits, the facial feature recognition technology is combined with the facial feature recognition technology in the portrait recognition algorithm, and the portrait state is analyzed according to the facial features such as normal and sleepy. , coma or intense exercise.
  • the smoke detection algorithm can be used to analyze whether the smoke occurs, the type of smoke generated, and the type of smoke that occurs and occurs as the result of the smoke generation state by analyzing the brightness contrast and brightness color in the image.
  • the analysis of the portrait data in the image by using the portrait recognition algorithm can be performed simultaneously with the smoke detection state by using the smoke detection algorithm, or can be performed sequentially. This is not specifically limited.
  • the in-vehicle monitoring device After analyzing the real-time image data and obtaining the analysis result, the in-vehicle monitoring device further determines whether there is an abnormality.
  • determining whether there is an abnormality according to the image analysis result comprises: determining whether there is smoke in the vehicle according to the state of occurrence of smoke in the image analysis result, and if yes, determining that there is an abnormality.
  • the smoke detection algorithm by analyzing the brightness contrast and brightness color in the image, the brightness is obviously contrasted. When the brightness contrast is obvious, and the brightness color is white and accompanied by the intermittent time of the flame, it is considered that there is an occupant in the vehicle.
  • smoking or taking drugs the smoke in the car is in a state of extreme smoking/drug smoking.
  • the brightness contrast is obvious and the brightness color is obvious flame color accompanied by black, it is considered that there is a occupant in the car.
  • Fire or fire At this time, the state of smoke generation in the car is recorded as a fire/fire. When the smoke occurrence state is occurring, it is judged that there is an abnormality in the vehicle.
  • determining whether there is an abnormality according to the image analysis result includes: acquiring an operating state of the vehicle, determining whether the number of portraits and/or the portrait state in the image analysis result is related to the vehicle The running status matches. If there is no match, it is judged that there is an abnormality.
  • the running state of the vehicle can be obtained by acquiring the running speed of the vehicle and the holding time of the running speed of the vehicle. For example, when the vehicle has been running for 30 minutes at the current speed of 60 km/h, it is considered that the running state of the vehicle is the running state at this time; when the current speed of the vehicle is 0 and the speed is maintained for more than 5 minutes, the operating state of the vehicle is considered to be Parking status.
  • the running state of the vehicle After the running state of the vehicle is acquired, it is determined whether the number of portraits and/or the portrait state in the image analysis result match, and if there is no match, it is determined that there is an abnormality. For example, when the running state of the vehicle is the running state, if the number of portraits in the image analysis result does not exceed the upper limit value of the vehicle occupant, and the portrait state is a normal state, the number of portraits and the portrait state in the image analysis result are considered as described above.
  • the running state of the vehicle is matched; if the number of portraits in the image analysis result exceeds the upper limit of the vehicle occupant, or the state of the driver in the portrait state is drowsy or a coma or intense movement occurs in the occupant, the portrait in the image analysis result is considered The number and/or portrait state does not match the running status of the vehicle.
  • the running state of the vehicle is in the parking state, if there is no portrait data in the image analysis result, it is considered that the number of portraits and the portrait state in the image analysis result match the running state of the vehicle at this time; as long as the portrait appears in the image analysis result, regardless of the Whether the number of portraits exceeds the upper limit of the vehicle members, and whether the portrait state is normal, drowsiness, coma or intense exercise, the number of portraits and/or the state of the portrait in the image analysis result does not match the running state of the vehicle. .
  • determining whether there is an abnormality according to the image analysis result comprises: determining whether there is smoke in the vehicle according to the smoke occurrence state in the image analysis result, acquiring an operating state of the vehicle, and determining the location Whether the number of portraits and/or the portrait state in the image analysis result matches the running state of the vehicle, and if there is smoke, and the number of portraits and/or the portrait state in the image analysis result does not match the running state of the vehicle, then the judgment is made. There is an exception.
  • whether or not there is an abnormality can be determined by simultaneously determining whether there is smoke and determining whether the number of portraits and/or the state of the image in the image analysis result matches the running state of the vehicle.
  • the specific judgment process can be referred to the above description. Both can be analyzed at the same time, or they can be analyzed successively, and finally a summary result of whether or not an abnormality is obtained. There is no limit here.
  • the abnormal analysis result may be sent to the server or the bound vehicle owner terminal at this time.
  • an alarm is sent to the server or the bound vehicle owner terminal to prompt the server corresponding to the service platform or the vehicle owner vehicle to have an abnormal situation.
  • S205 Send corresponding abnormal image data according to the data request of the server or the vehicle owner terminal, so that the server or the vehicle owner terminal performs a corresponding measure after confirming an abnormality.
  • the corresponding abnormal image data may be continuously sent to the server or the vehicle owner terminal for the service platform or the owner. After confirming the abnormality, take corresponding measures and send corresponding control commands through the server or the vehicle owner terminal to reduce the loss caused by the abnormality.
  • the corresponding abnormal image data includes image data from the abnormal start to the abnormal elimination time period, so that the service platform or the owner of the server knows the entire abnormal data and the processing process in detail, and may only include data of a certain period of time after the abnormal start. As long as the data can help the service platform or the owner understand the abnormal content and develop corresponding measures.
  • the in-vehicle monitoring device obtains real-time image data of the interior of the vehicle, and then analyzes and processes the real-time image data according to a preset algorithm to obtain an image analysis result, and determines whether an abnormality exists according to the image analysis result. Sending an alarm to the server or the bound vehicle owner terminal, and transmitting corresponding abnormal image data according to the data request of the server or the vehicle owner terminal, so that the server or the vehicle owner terminal confirms an abnormality. Then perform the corresponding measures. The analysis of the in-vehicle image data is performed on the in-vehicle monitoring device.
  • the abnormal result is sent to the server or the bound vehicle owner terminal, thereby reducing the workload of manual participation and improving the workload.
  • Monitoring efficiency reduces the possibility of manual miss or misjudgment.
  • it greatly reduces the amount of data transmitted to the network, greatly reduces the risk of information security incidents, and effectively protects user privacy.
  • FIG. 3 is a schematic structural diagram of an in-vehicle monitoring device according to an embodiment of the present invention. As shown in Figure 3, the device includes:
  • the obtaining unit 301 is configured to acquire real-time image data inside the vehicle.
  • the in-vehicle monitoring device can acquire real-time image data of the interior of the vehicle through the built-in acquisition unit 301 (such as an in-vehicle camera, an image scanner or an infrared detector, etc.), or can control the in-vehicle acquisition unit 301 after establishing a communication connection (eg, An in-vehicle camera, an image scanner, or an infrared detector, etc.) acquires real-time image data inside the vehicle.
  • the built-in acquisition unit 301 such as an in-vehicle camera, an image scanner or an infrared detector, etc.
  • the analyzing unit 302 is configured to perform analysis processing on the real-time image data according to a preset algorithm to obtain an image analysis result.
  • the analyzing unit 302 may analyze and process the real-time image data according to a preset algorithm.
  • the preset algorithm includes a portrait recognition algorithm and a smoke detection algorithm.
  • the analyzing and processing the real-time image data according to the preset algorithm comprises: identifying a number of portraits and a portrait state in the real-time image data by using a portrait recognition algorithm, and identifying a smoke occurrence state in the real-time image data by using a smoke detection algorithm.
  • the portrait recognition algorithm can be used to analyze the number of portraits in the real-time image data, the number of portraits is determined according to the number of portraits, the facial feature recognition technology is combined with the facial feature recognition technology in the portrait recognition algorithm, and the portrait state is analyzed according to the facial features such as normal and sleepy. , coma or intense exercise.
  • the smoke detection algorithm can be used to analyze whether the smoke occurs, the type of smoke generated, and the type of smoke that occurs and occurs as the result of the smoke generation state by analyzing the brightness contrast and brightness color in the image.
  • the analysis of the portrait data in the image by using the portrait recognition algorithm can be performed simultaneously with the smoke detection state by using the smoke detection algorithm, or can be performed sequentially. This is not specifically limited.
  • the determining unit 303 is configured to determine, according to the image analysis result, whether there is an abnormality.
  • the analyzing unit 302 After analyzing the real-time image data and obtaining the analysis result, the analyzing unit 302 further determines whether there is an abnormality.
  • the determining unit 303 determines whether there is an abnormality according to the image analysis result, and specifically includes: the determining unit 303 determines, according to the smoke occurrence state in the image analysis result, whether there is smoke in the vehicle, if any, The judging unit 303 judges that there is an abnormality. For example, in the smoke detection algorithm, by analyzing the brightness contrast and brightness color in the image, the brightness is obviously contrasted. When the brightness contrast is obvious, and the brightness color is white and accompanied by the intermittent time of the flame, it is considered that there is an occupant in the vehicle. When smoking or taking drugs, the smoke in the car is in a state of extreme smoking/drug smoking.
  • the determination unit 303 determines that there is an abnormality in the vehicle.
  • the determining unit 303 determines whether there is an abnormality according to the image analysis result, and specifically includes: after acquiring the running state of the vehicle by the acquiring unit 301, the determining unit 303 determines the image analysis result. Whether the portrait number and/or the portrait state match the running state of the vehicle, if not, the judging unit 303 judges that there is an abnormality.
  • the operation state of the vehicle may be acquired by the acquisition unit 301 acquiring the running speed of the vehicle and the holding time of the running speed of the vehicle.
  • the running state of the vehicle is the running state at this time; when the current speed of the vehicle is 0 and the speed is maintained for more than 5 minutes, the operating state of the vehicle is considered to be Parking status.
  • the acquisition unit 301 acquires the operating state of the vehicle, it is determined whether the number of portraits and/or the portrait state in the image analysis result are matched. If not, the determining unit 303 determines that there is an abnormality.
  • the determining unit 303 regards the number of portraits and the portrait state in the image analysis result. Matching with the running state of the vehicle; if the number of portraits in the image analysis result exceeds the upper limit value of the vehicle occupant, or the state of the driver in the portrait state is drowsy or a coma or intense exercise state occurs in the occupant, the judging unit 303 considers The number of portraits and/or portrait states in the image analysis results do not match the running status of the vehicle.
  • the determining unit 303 When the running state of the vehicle is the parking state, if there is no portrait data in the image analysis result, the determining unit 303 considers that the number of portraits and the portrait state in the image analysis result match the running state of the vehicle at this time; as long as the portrait appears in the image analysis result Regardless of whether the number of portraits exceeds the upper limit value of the vehicle member at this time, and regardless of whether the portrait state is normal, drowsiness, coma or intense exercise at this time, the judging unit 303 regards the number of portraits and/or the portrait state in the image analysis result at this time. The running status of the vehicle does not match.
  • the determining unit 303 determines whether there is an abnormality according to the image analysis result, and specifically includes: the determining unit 303 determines, according to the smoke occurrence state in the image analysis result, whether there is smoke in the vehicle, and the acquiring unit 301: Obtain an operating state of the vehicle, and the determining unit 303 determines whether the number of portraits and/or the portrait state in the image analysis result matches the running state of the vehicle, if there is smoke, and the number of portraits in the image analysis result and/or The portrait state does not match the running state of the vehicle, and the judging unit 303 judges that there is an abnormality.
  • the determining unit 303 can determine whether there is an abnormality by simultaneously determining whether there is smoke and determining whether the number of portraits and/or the portrait state in the image analysis result match the running state of the vehicle.
  • the specific judgment process can be referred to the above description. Both can be analyzed at the same time, or they can be analyzed successively, and finally a summary result of whether or not an abnormality is obtained. There is no limit here.
  • the sending unit 304 is configured to send an alarm to the server or the bound vehicle owner terminal if the determining unit 303 determines that the abnormality exists.
  • the transmitting unit 304 may transmit the abnormality analysis result to the server or the bound vehicle owner terminal. At the same time, an alarm is sent to the server or the bound vehicle owner terminal to prompt the server corresponding to the service platform or the vehicle owner vehicle to have an abnormal situation.
  • the sending unit 304 is further configured to send corresponding abnormal image data according to the data request of the server or the vehicle owner terminal, so that the server or the vehicle owner terminal performs a corresponding measure after confirming an abnormality.
  • the sending unit 304 sends an alarm prompt to the server or the vehicle owner terminal, in order to make the service platform or the vehicle owner corresponding to the server know the abnormal situation in the vehicle in detail, the corresponding abnormal image data may be continuously sent to the server or the vehicle owner terminal for confirmation by the service platform or the vehicle owner.
  • the corresponding measures are taken and the corresponding control commands are sent through the server or the vehicle owner terminal to reduce the loss caused by the abnormality.
  • the corresponding abnormal image data includes image data from the abnormal start to the abnormal elimination time period, so that the service platform or the owner of the server knows the entire abnormal data and the processing process in detail, and may only include data of a certain period of time after the abnormal start. As long as the data can help the service platform or the owner understand the abnormal content and develop corresponding measures.
  • the in-vehicle monitoring device obtains real-time image data of the interior of the vehicle, and then analyzes and processes the real-time image data according to a preset algorithm to obtain an image analysis result, and determines whether an abnormality exists according to the image analysis result. Sending an alarm to the server or the bound vehicle owner terminal, and transmitting corresponding abnormal image data according to the data request of the server or the vehicle owner terminal, so that the server or the vehicle owner terminal confirms an abnormality. Then perform the corresponding measures. The analysis of the in-vehicle image data is performed on the in-vehicle monitoring device.
  • the abnormal result is sent to the server or the bound vehicle owner terminal, thereby reducing the workload of manual participation and improving the workload.
  • Monitoring efficiency reduces the possibility of manual miss or misjudgment.
  • it greatly reduces the amount of data transmitted to the network, greatly reduces the risk of information security incidents, and effectively protects user privacy.
  • FIG. 4 is a schematic structural diagram of another in-vehicle monitoring device according to an embodiment of the present invention.
  • the device includes a processor 401, a memory 402, and a bus 403.
  • the processor 401 and the memory 402 can be coupled by a bus or other means.
  • FIG. 4 is exemplified by a bus 403 connection.
  • the processor 401 can be digital signal processing (English: Digital Signal Processing, DSP) chip.
  • the processor 401 may include: a management/communication module (administration) Module/communication module, AM/CM) (center for voice exchange and information exchange), module for completing call processing, signaling processing, radio resource management, radio link management, and circuit maintenance functions, code rate Transform and sub-multiplex module (transcoder Submultiplexer, TCSM) (for completing the multiplexing demultiplexing and code conversion functions) and other modules.
  • a management/communication module administration
  • AM/CM center for voice exchange and information exchange
  • module for completing call processing
  • signaling processing radio resource management
  • radio link management radio link management
  • circuit maintenance functions code rate Transform and sub-multiplex module (transcoder Submultiplexer, TCSM) (for completing the multiplexing demultiplexing and code conversion functions) and other modules.
  • code rate Transform and sub-multiplex module for completing the multiplexing demultiplexing and code conversion functions
  • the memory 402 is used to store program codes shared by the vehicle.
  • the memory 402 can be a read-only memory (English: Read-Only Memory, ROM) or a random access memory (RAM). Program code shared by the storage vehicle.
  • Bus 403 can be an industry standard architecture (English: Industry Standard Architecture, ISA) bus, external device interconnection (English: Peripheral Component Interconnect, PCI) bus, extended standard architecture (English: Extended Industry Standard Architecture (EISA) bus, integrated circuit bus (English: Inter Integrated Circuit, IIC).
  • ISA Industry Standard Architecture
  • PCI Peripheral Component Interconnect
  • EISA Extended Industry Standard Architecture
  • IIC Inter Integrated Circuit
  • the processor calls the executable program code stored in the memory, and performs the following operations:
  • Corresponding abnormal image data is sent according to the data request of the server or the vehicle owner terminal, so that the server or the vehicle owner terminal performs corresponding measures after confirming an abnormality.
  • the preset algorithm includes a portrait recognition algorithm and a smoke detection algorithm
  • the processor performs the analysis and processing on the real-time image data according to a preset algorithm, where the specific manner is:
  • a smoke detection algorithm is used to identify the state of occurrence of smoke in the real-time image data.
  • the performing, by the processor, determining, according to the image analysis result, whether an abnormality exists, the specific manner is:
  • the presence or absence of smoke in the vehicle is determined based on the state of occurrence of smoke in the image analysis result, and if it exists, it is determined that there is an abnormality.
  • the performing, by the processor, determining, according to the image analysis result, whether an abnormality exists specifically:
  • the processor executes the corresponding abnormal image data, including image data of an abnormal start to an abnormal elimination period.
  • the in-vehicle monitoring device obtains real-time image data of the interior of the vehicle, and then analyzes and processes the real-time image data according to a preset algorithm to obtain an image analysis result, and determines whether an abnormality exists according to the image analysis result. Sending an alarm to the server or the bound vehicle owner terminal, and transmitting corresponding abnormal image data according to the data request of the server or the vehicle owner terminal, so that the server or the vehicle owner terminal confirms an abnormality. Then perform the corresponding measures. The analysis of the in-vehicle image data is performed on the in-vehicle monitoring device.
  • the abnormal result is sent to the server or the bound vehicle owner terminal, thereby reducing the workload of manual participation and improving the workload.
  • Monitoring efficiency reduces the possibility of manual miss or misjudgment.
  • it greatly reduces the amount of data transmitted to the network, greatly reduces the risk of information security incidents, and effectively protects user privacy.
  • the embodiment of the present invention further provides a computer storage medium, wherein the computer storage medium can store a program, and the program includes some or all of the steps of any of the in-vehicle monitoring methods described in the foregoing method embodiments.
  • the disclosed apparatus may be implemented in other ways.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division.
  • there may be another division manner for example, multiple units or components may be combined or may be Integrate into another system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be electrical or otherwise.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the 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 standalone product, may be stored in a computer readable memory. Based on such understanding, the technical solution of the present invention may contribute to the prior art or all or part of the technical solution may be embodied in the form of a software product stored in a memory.
  • a number of instructions are included to cause a computer device (which may be a personal computer, server or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention.
  • the foregoing memory includes: a U disk, a read-only memory (ROM), a random access memory (RAM, Random Access). Memory, removable hard disk, disk or optical disk, etc., which can store program code.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Emergency Management (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Alarm Systems (AREA)
  • Emergency Alarm Devices (AREA)

Abstract

本方案公开了一种车内监控方法及设备，所述车内监控方法包括：获取车辆内部的实时影像数据；按照预设算法对所述实时影像数据进行分析处理，得到影像分析结果；根据所述影像分析结果判断是否存在异常；若存在，则向服务器或者绑定的车主终端发送警报；根据所述服务器或者所述车主终端的数据请求发送对应的异常影像数据，以使所述服务器或者所述车主终端在确认异常后执行相应的措施。采用本方案实施例降低了人工参与的工作量，提升了监控效率，降低了人工漏判或者误判的可能性，另一方面大大减少了传输到网络的数据量，极大的降低了信息安全事件的风险，有效的保护了用户隐私。

Description

一种车内监控方法及设备 技术领域
本发明涉及车辆技术领域，尤其涉及一种车内监控方法及设备。
 背景技术
随着汽车技术的发展，车辆的大规模使用成为现实，给人们的生活带来了极大的便利性。然而在使用过程中也伴生了很多问题。比如有时候车主停车后将小孩遗忘在车内发生一些悲剧，或者当其他人使用车主的车辆，在车内的一些不规范行为会导致车辆的使用效能降低。为了避免上述问题，现在普遍采用了车内监控的方法对车辆内部进行监控，一方面规范其他使用者的用车行为，另一方面也避免因遗忘产生的悲剧。但现有的车内监控方法，都是由车载设备采集车内数据后，上传到服务器或者直接传输到人工终端，由人来进行判别车内是否有异常。现有技术虽然可以做到车内的实时监控，但由于数据量大，一方面存在人工判断容易出现误判、漏判的现象，同时巨大的工作量也会导致效率低下；另一方面由于数据通过网络传输到服务器或者监控终端，容易发生信息安全事件，带来隐私泄露的风险。
 技术问题
本发明实施例提供一种车内监控方法及设备，有利于解决现有技术中依靠人工判断车内环境和信息安全泄露的问题，同时提高了车内环境的监控效率。
 技术解决方案
第一方面，本发明实施例提供一种车内监控方法，所述方法包括：获取车辆内部的实时影像数据；按照预设算法对所述实时影像数据进行分析处理，得到影像分析结果；根据所述影像分析结果判断是否存在异常；若存在，则向服务器或者绑定的车主终端发送警报；根据所述服务器或者所述车主终端的数据请求发送对应的异常影像数据，以使所述服务器或者所述车主终端在确认异常后执行相应的措施。
结合本发明实施例第一方面，在本发明实施例第一方面的第一种可能的实现方式中，所述预设算法包括人像识别算法、烟雾检测算法，所述按照预设算法对所述实时影像数据进行分析处理，具体包括：利用人像识别算法识别所述实时影像数据中的人像数量和人像状态；利用烟雾检测算法识别所述实时影像数据中的烟雾发生状态。
结合本发明实施例第一方面的第一种可能的实现方式，在本发明实施例第一方面的第二种可能的实现方式中，所述根据所述影像分析结果判断是否存在异常，具体包括：根据所述影像分析结果中的烟雾发生状态判断车内是否存在烟雾，若存在，则判断存在异常。
结合本发明实施例第一方面的第一种可能的实现方式、第一方面的第二种可能的实现方式、在本发明实施例第一方面的第三种可能的实现方式中，所述根据所述影像分析结果判断是否存在异常，具体包括：获取车辆的运行状态；判断所述影像分析结果中的人像数量和/或人像状态是否与所述车辆的运行状态匹配；若不匹配，则判断存在异常。
结合本发明实施例第一方面，在本发明实施例第一方面的第四种可能的实现方式中，所述对应的异常影像数据包括异常开始至异常消除时间段的影像数据。
本发明第二方面提供了一种设备，所述设备包括：存储有可执行程序代码的存储器；与所述存储器耦合的处理器；所述处理器调用所述存储器中存储的所述可执行程序代码，执行如下步骤：获取车辆内部的实时影像数据；按照预设算法对所述实时影像数据进行分析处理，得到影像分析结果；根据所述影像分析结果判断是否存在异常；若存在，则向服务器或者绑定的车主终端发送警报；根据所述服务器或者所述车主终端的数据请求发送对应的异常影像数据，以使所述服务器或者所述车主终端在确认异常后执行相应的措施。
结合本发明实施例第二方面，在本发明实施例第二方面的第一种可能的实现方式中，所述预设算法包括人像识别算法、烟雾检测算法，所述处理器执行所述按照预设算法对所述实时影像数据进行分析处理，具体方式为：利用人像识别算法识别所述实时影像数据中的人像数量和人像状态；利用烟雾检测算法识别所述实时影像数据中的烟雾发生状态。
结合本发明实施例第二方面的第一种可能的实现方式，在本发明实施例第二方面的第二种可能的实现方式中，所述处理器执行所述根据所述影像分析结果判断是否存在异常，具体方式为：根据所述影像分析结果中的烟雾发生状态判断车内是否存在烟雾，若存在，则判断存在异常。
结合本发明实施例第二方面的第一种可能的实现方式、第二方面的第二种可能的实现方式、在本发明实施例第二方面的第三种可能的实现方式中，所述处理器执行所述根据所述影像分析结果判断是否存在异常，具体包括：获取车辆的运行状态；判断所述影像分析结果中的人像数量和/或人像状态是否与所述车辆的运行状态匹配；若不匹配，则判断存在异常。
结合本发明实施例第二方面，在本发明实施例第二方面的第四种可能的实现方式中，所述处理器执行所述对应的异常影像数据包括异常开始至异常消除时间段的影像数据。
 有益效果
可以看出，在本发明的实施例中，获取车辆内部的实时影像数据；按照预设算法对所述实时影像数据进行分析处理，得到影像分析结果；根据所述影像分析结果判断是否存在异常；若存在，则向服务器或者绑定的车主终端发送警报；根据所述服务器或者所述车主终端的数据请求发送对应的异常影像数据，以使所述服务器或者所述车主终端在确认异常后执行相应的措施。通过采取上述车内监控方法，能实时监控车内环境，也提高了信息安全及车内环境的监控效率。
本发明的这些方面或其他方面在以下实施例的描述中会更加简明易懂。
 附图说明
为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1为本发明实施例提供的一种车内监控方法的应用场景示意图；
图2为本发明实施例提供的一种车内监控方法的流程示意图；
图3为本发明实施例提供的一种车内监控设备的结构示意图；
图4为本发明实施例提供的另一种车内监控设备的结构示意图。
 本发明的实施方式
为了使本技术领域的人员更好地理解本发明方案，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分的实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都应当属于本发明保护的范围。
以下分别进行详细说明。
本发明的说明书和权利要求书及所述附图中的术语“第一”、“第二”、“第三”和“第四”等是用于区别不同对象，而不是用于描述特定顺序。此外，术语“包括”和“具有”以及它们任何变形，意图在于覆盖不排他的包含。例如包含了一系列步骤或单元的过程、方法、系统、产品或设备没有限定于已列出的步骤或单元，而是可选地还包括没有列出的步骤或单元，或可选地还包括对于这些过程、方法、产品或设备固有的其它步骤或单元。
在本文中提及“实施例”意味着，结合实施例描述的特定特征、结构或特性可以包含在本发明的至少一个实施例中。在说明书中的各个位置出现该短语并不一定均是指相同的实施例，也不是与其它实施例互斥的独立的或备选的实施例。本领域技术人员显式地和隐式地理解的是，本文所描述的实施例可以与其它实施例相结合。
“多个”是指两个或两个以上。“和/或”，描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。字符“/”一般表示前后关联对象是一种“或”的关系。
下面结合附图对本申请的实施例进行描述。
请参见图1，图1为本发明实施例提供的一种车内监控方法的应用场景示意图。如图1所示，该应用场景包括：车辆10，安装在车辆10上的车内监控设备20，服务器30和车主终端40. 车内监控设备20内置控制器，具有分析和计算功能，能对获取到的数据进行分析处理。车内监控设备20可以是具有图像获取模块(如摄像头、图像扫描仪或者红外探测传感器等)的车载设备，也可以是具有与车内图像获取硬件（如车内摄像头、图像扫描仪或者红外探测仪等）进行通讯连接并控制图像获取硬件获取图像数据的车载终端、OBD、数字仪表等车载设备。车内监控设备20可以与服务器30和车主终端40通过通信网络或者近距离无线通信方式建立通信连接。
本发明实施例的车内监控方法应用于车内监控设备20.在本发明实施例中，车内监控设备获取车辆内部的实时影像数据，并对影像数据进行分析处理，将得到的分析结果进行判断，若判断存在异常，则将异常结果发送至服务器30或者车主终端40，同时将异常影像数据发送给服务器30或者车主终端40.通过仅向服务器或者车主终端发送异常结果及异常图像数据，从而一方面降低了人工参与的工作量，提升了监控效率，降低了人工漏判或者误判的可能性；另一方面降低了传输到网络的数据量，大大减少了信息安全事件的风险，有效的保护用户隐私。
请参见图2，图2是本发明实施例提供的一种车内监控方法的流程示意图。如图2所示，该方法应用于车内监控设备，该方法包括如下步骤。
S201. 获取车辆内部的实时影像数据。
车内监控设备可以通过内置的图像获取模块（如车内摄像头、图像扫描仪或者红外探测仪等）获取车辆内部的实时影像数据，也可以在建立通信连接后，控制车内图像获取硬件（如车内摄像头、图像扫描仪或者红外探测仪等）获取车辆内部的实时影像数据。
S202. 按照预设算法对所述实时影像数据进行分析处理，得到影像分析结果。
车内监控设备获取到车辆内部的实时影像数据后，可以利用自身的控制器对实时影像数据按照预设算法进行分析处理。其中，预设算法包括人像识别算法、烟雾检测算法。具体的，按照预设算法对实时影像数据进行分析处理包括：利用人像识别算法识别所述实时影像数据中的人像数量和人像状态，利用烟雾检测算法识别所述实时影像数据中的烟雾发生状态。例如，可以利用人像识别算法分析实时影像数据中的人像个数，根据人像个数确定人像数量，结合人像识别算法中的面部特征识别技术提取人像面部特征，根据面部特征分析人像状态如正常、瞌睡、昏迷或者激烈运动等。可以利用烟雾检测算法通过分析图像中亮度对比和亮度颜色识别烟雾是否发生、发生的烟雾类别，并将烟雾是否发生和发生的烟雾类别作为烟雾的发生状态分析结果。利用人像识别算法对图像中的人像数据进行分析可以和利用烟雾检测算法对图像中的烟雾发生状态进行分析同时进行，也可以先后进行。在此不做具体限定。
S203. 根据所述影像分析结果判断是否存在异常。
车内监控设备在对实时影像数据进行分析并得到分析结果后，进一步判断是否存在异常。
在一种可能的实施方式中，根据所述影像分析结果判断是否存在异常，具体包括：根据所述影像分析结果中的烟雾发生状态判断车内是否存在烟雾，若存在，则判断存在异常。例如，在利用烟雾检测算法通过分析图像中亮度对比和亮度颜色识别烟雾发现亮度对比明显，当亮度对比明显，且亮度颜色为白色并伴随有火焰的时断时续时，则认为车内有乘员在吸烟或者吸食毒品，此时将车内的烟雾发生状态极为香烟/毒品吸食正在发生；当亮度对比明显，且亮度颜色为明显的火焰颜色并伴随有黑色时，则认为车内有乘员在玩火或者发生火灾。此时将车内的烟雾发生状态记为玩火/火灾发生。当烟雾发生状态为发生时，则判断车内存在异常。
在另一种可能的实施方式中，根据所述影像分析结果判断是否存在异常，具体包括：获取车辆的运行状态，判断所述影像分析结果中的人像数量和/或人像状态是否与所述车辆的运行状态匹配，若不匹配，则判断存在异常。在具体的实施过程中，可以通过获取车辆的运行速度和车辆运行速度的保持时间来获取车辆的运行状态。例如，当车辆保持当前速度60km/h已经行驶了30min，则认为此时车辆的运行状态为行驶状态；当车辆当前速度为0且该速度保持了5min以上，则认为此时车辆的运行状态为停车状态。在获取到车辆的运行状态后，结合影像分析结果中的人像数量和/或人像状态判断是否匹配，若不匹配，则判断存在异常。例如，当车辆的运行状态为行驶状态，若影像分析结果中的人像数量未超出车辆乘员上限值，且人像状态为正常状态时，则认为影像分析结果中的人像数量和人像状态与所述车辆的运行状态匹配；若影像分析结果中的人像数量超出车辆乘员上限值，或者人像状态中驾驶员的状态呈现瞌睡或者乘员中出现昏迷、激烈运动状态时，则认为影像分析结果中的人像数量和/或人像状态与车辆的运行状态不匹配。当车辆的运行状态为停车状态时，若影像分析结果中没有人像数据，则认为此时影像分析结果中的人像数量和人像状态与车辆的运行状态匹配；只要影像分析结果中出现人像，不论此时人像数量是否超出车辆成员上限值，也不论此时人像状态是正常、瞌睡、昏迷或者激烈运动，就认为此时影像分析结果中的人像数量和/或人像状态与车辆的运行状态不匹配。
在另一种可能的实施方式中，根据所述影像分析结果判断是否存在异常，具体包括：根据所述影像分析结果中的烟雾发生状态判断车内是否存在烟雾，获取车辆的运行状态，判断所述影像分析结果中的人像数量和/或人像状态是否与所述车辆的运行状态匹配，若存在烟雾，且影像分析结果中的人像数量和/或人像状态与车辆的运行状态不匹配，则判断存在异常。在具体的实施过程中，可以通过同时判断是否存在烟雾及判断影像分析结果中的人像数量和/或人像状态与车辆的运行状态是否匹配来判断是否存在异常。具体的判断过程可以参照上文描述。两者可以同时分析，也可以先后分析，最后得到一个是否异常的汇总结果。在此不做限定。
S204. 若存在，则向服务器或者绑定的车主终端发送警报。
当车内监控设备判断车内存在异常时，此时可以将异常分析结果发送给服务器或者绑定的车主终端。同时向服务器或者绑定的车主终端发送警报，以提示服务器对应的服务平台或者车主车辆发生异常状况。
S205. 根据所述服务器或者所述车主终端的数据请求发送对应的异常影像数据，以使所述服务器或者所述车主终端在确认异常后执行相应的措施。
车内监控设备向服务器或者车主终端发送警报提示后，为了使服务器对应的服务平台或者车主详细了解车内的异常情况，可以继续向服务器或者车主终端发送对应的异常影像数据，以便服务平台或者车主确认异常后采取对应的措施并通过服务器或者车主终端发送相应的控制指令，以减少异常造成的损失。该对应的异常影像数据包括异常开始至异常消除时间段的影像数据，以便服务器对应的服务平台或者车主详细了解整个异常数据及其处理过程，也可以仅包括异常开始之后某一时间段的数据，只要该数据能帮助服务平台或者车主了解异常的内容并制定对应的措施即可。
在本实施例中，车内监控设备通过获取车辆内部的实时影像数据，之后按照预设算法对所述实时影像数据进行分析处理，得到影像分析结果，并根据所述影像分析结果判断是否存在异常，当存在时，则向服务器或者绑定的车主终端发送警报，并根据所述服务器或者所述车主终端的数据请求发送对应的异常影像数据，以使所述服务器或者所述车主终端在确认异常后执行相应的措施。车内影像数据的分析在车内监控设备端进行，只有在根据分析结果判断发生异常时才将异常结果发送给服务器或者绑定的车主终端，从而一方面降低了人工参与的工作量，提升了监控效率，降低了人工漏判或者误判的可能性，另一方面大大减少了传输到网络的数据量，极大的降低了信息安全事件的风险，有效的保护了用户隐私。
请参见图3，图3为本发明实施例提供的一种车内监控设备的结构示意图。如图3所示，该设备包括：
获取单元301，用于获取车辆内部的实时影像数据。
车内监控设备可以通过内置的获取单元301（如车内摄像头、图像扫描仪或者红外探测仪等）获取车辆内部的实时影像数据，也可以在建立通信连接后，控制车内获取单元301（如车内摄像头、图像扫描仪或者红外探测仪等）获取车辆内部的实时影像数据。
分析单元302，用于按照预设算法对所述实时影像数据进行分析处理，得到影像分析结果。
获取单元301获取到车辆内部的实时影像数据后，可以利用分析单元302对实时影像数据按照预设算法进行分析处理。其中，预设算法包括人像识别算法、烟雾检测算法。具体的，按照预设算法对实时影像数据进行分析处理包括：利用人像识别算法识别所述实时影像数据中的人像数量和人像状态，利用烟雾检测算法识别所述实时影像数据中的烟雾发生状态。例如，可以利用人像识别算法分析实时影像数据中的人像个数，根据人像个数确定人像数量，结合人像识别算法中的面部特征识别技术提取人像面部特征，根据面部特征分析人像状态如正常、瞌睡、昏迷或者激烈运动等。可以利用烟雾检测算法通过分析图像中亮度对比和亮度颜色识别烟雾是否发生、发生的烟雾类别，并将烟雾是否发生和发生的烟雾类别作为烟雾的发生状态分析结果。利用人像识别算法对图像中的人像数据进行分析可以和利用烟雾检测算法对图像中的烟雾发生状态进行分析同时进行，也可以先后进行。在此不做具体限定。
判断单元303，用于根据所述影像分析结果判断是否存在异常。
分析单元302在对实时影像数据进行分析并得到分析结果后，判断单元303进一步判断是否存在异常。
在一种可能的实施方式中，判断单元303根据所述影像分析结果判断是否存在异常，具体包括：判断单元303根据所述影像分析结果中的烟雾发生状态判断车内是否存在烟雾，若存在，判断单元303则判断存在异常。例如，在利用烟雾检测算法通过分析图像中亮度对比和亮度颜色识别烟雾发现亮度对比明显，当亮度对比明显，且亮度颜色为白色并伴随有火焰的时断时续时，则认为车内有乘员在吸烟或者吸食毒品，此时将车内的烟雾发生状态极为香烟/毒品吸食正在发生；当亮度对比明显，且亮度颜色为明显的火焰颜色并伴随有黑色时，则认为车内有乘员在玩火或者发生火灾。此时将车内的烟雾发生状态记为玩火/火灾发生。当烟雾发生状态为发生时，判断单元303则判断车内存在异常。
在另一种可能的实施方式中，判断单元303根据所述影像分析结果判断是否存在异常，具体包括：在通过获取单元301获取车辆的运行状态后，判断单元303判断所述影像分析结果中的人像数量和/或人像状态是否与所述车辆的运行状态匹配，若不匹配，判断单元303则判断存在异常。在具体的实施过程中，可以通过获取单元301获取车辆的运行速度和车辆运行速度的保持时间来获取车辆的运行状态。例如，当车辆保持当前速度60km/h已经行驶了30min，则认为此时车辆的运行状态为行驶状态；当车辆当前速度为0且该速度保持了5min以上，则认为此时车辆的运行状态为停车状态。在获取单元301获取到车辆的运行状态后，结合影像分析结果中的人像数量和/或人像状态判断是否匹配，若不匹配，判断单元303则判断存在异常。例如，当车辆的运行状态为行驶状态，若影像分析结果中的人像数量未超出车辆乘员上限值，且人像状态为正常状态时，则判断单元303认为影像分析结果中的人像数量和人像状态与所述车辆的运行状态匹配；若影像分析结果中的人像数量超出车辆乘员上限值，或者人像状态中驾驶员的状态呈现瞌睡或者乘员中出现昏迷、激烈运动状态时，判断单元303则认为影像分析结果中的人像数量和/或人像状态与车辆的运行状态不匹配。当车辆的运行状态为停车状态时，若影像分析结果中没有人像数据，判断单元303则认为此时影像分析结果中的人像数量和人像状态与车辆的运行状态匹配；只要影像分析结果中出现人像，不论此时人像数量是否超出车辆成员上限值，也不论此时人像状态是正常、瞌睡、昏迷或者激烈运动，判断单元303就认为此时影像分析结果中的人像数量和/或人像状态与车辆的运行状态不匹配。
在另一种可能的实施方式中，判断单元303根据所述影像分析结果判断是否存在异常，具体包括：判断单元303根据所述影像分析结果中的烟雾发生状态判断车内是否存在烟雾，获取单元301获取车辆的运行状态，判断单元303判断所述影像分析结果中的人像数量和/或人像状态是否与所述车辆的运行状态匹配，若存在烟雾，且影像分析结果中的人像数量和/或人像状态与车辆的运行状态不匹配，判断单元303则判断存在异常。在具体的实施过程中，判断单元303可以通过同时判断是否存在烟雾及判断影像分析结果中的人像数量和/或人像状态与车辆的运行状态是否匹配来判断是否存在异常。具体的判断过程可以参照上文描述。两者可以同时分析，也可以先后分析，最后得到一个是否异常的汇总结果。在此不做限定。
发送单元304，用于若判断单元303判断异常存在，则向服务器或者绑定的车主终端发送警报。
当判断单元303判断车内存在异常时，此时发送单元304可以将异常分析结果发送给服务器或者绑定的车主终端。同时向服务器或者绑定的车主终端发送警报，以提示服务器对应的服务平台或者车主车辆发生异常状况。
发送单元304还用于根据所述服务器或者所述车主终端的数据请求发送对应的异常影像数据，以使所述服务器或者所述车主终端在确认异常后执行相应的措施。
发送单元304向服务器或者车主终端发送警报提示后，为了使服务器对应的服务平台或者车主详细了解车内的异常情况，可以继续向服务器或者车主终端发送对应的异常影像数据，以便服务平台或者车主确认异常后采取对应的措施并通过服务器或者车主终端发送相应的控制指令，以减少异常造成的损失。该对应的异常影像数据包括异常开始至异常消除时间段的影像数据，以便服务器对应的服务平台或者车主详细了解整个异常数据及其处理过程，也可以仅包括异常开始之后某一时间段的数据，只要该数据能帮助服务平台或者车主了解异常的内容并制定对应的措施即可。
在本实施例中，车内监控设备通过获取车辆内部的实时影像数据，之后按照预设算法对所述实时影像数据进行分析处理，得到影像分析结果，并根据所述影像分析结果判断是否存在异常，当存在时，则向服务器或者绑定的车主终端发送警报，并根据所述服务器或者所述车主终端的数据请求发送对应的异常影像数据，以使所述服务器或者所述车主终端在确认异常后执行相应的措施。车内影像数据的分析在车内监控设备端进行，只有在根据分析结果判断发生异常时才将异常结果发送给服务器或者绑定的车主终端，从而一方面降低了人工参与的工作量，提升了监控效率，降低了人工漏判或者误判的可能性，另一方面大大减少了传输到网络的数据量，极大的降低了信息安全事件的风险，有效的保护了用户隐私。
请参见图4，图4为本发明实施例提供的另一种车内监控设备的结构示意图。如图4所示，该设备包括：处理器401、存储器402和总线403，其中处理器401和存储器402可以通过总线或其他方式耦合连接，图4以通过总线403连接为例。
其中，处理器401可以是数字信号处理（英文：Digital Signal Processing，DSP）芯片。具体实现中，处理器401可包括：管理/通信模块（administration module/communication module，AM/CM）（用于话路交换和信息交换的中心）、用于完成呼叫处理、信令处理、无线资源管理、无线链路的管理和电路维护功能的模块、码速率变换与子复用模块（transcoder submultiplexer，TCSM）（用于完成复用解复用及码变换功能）等模块。具体信息可参考移动通讯相关知识。
存储器402用于存储车辆共享的程序代码，具体实现中，存储器402可以采用只读存储器（英文：Read-Only Memory，ROM）或随机存取存贮器（英文：Random Access Memory，RAM），可用于存储车辆共享的程序代码。
总线403可以是工业标准体系结构（英文：Industry Standard Architecture，ISA）总线、外部设备互连（英文：Peripheral Component Interconnect，PCI）总线、扩展标准体系结构（英文：Extended Industry Standard Architecture，EISA）总线、集成电路总线（英文：Inter Integrated Circuit，IIC）等。
本发明实施例中，所述处理器调用所述存储器中存储的所述可执行程序代码，执行如下操作：
获取车辆内部的实时影像数据；
按照预设算法对所述实时影像数据进行分析处理，得到影像分析结果；
根据所述影像分析结果判断是否存在异常；
若存在，则向服务器或者绑定的车主终端发送警报；
根据所述服务器或者所述车主终端的数据请求发送对应的异常影像数据，以使所述服务器或者所述车主终端在确认异常后执行相应的措施。
可选的，所述预设算法包括人像识别算法、烟雾检测算法，所述处理器执行所述按照预设算法对所述实时影像数据进行分析处理，具体方式为：
利用人像识别算法识别所述实时影像数据中的人像数量和人像状态；
利用烟雾检测算法识别所述实时影像数据中的烟雾发生状态。
可选的，所述处理器执行所述根据所述影像分析结果判断是否存在异常，具体方式为：
根据所述影像分析结果中的烟雾发生状态判断车内是否存在烟雾，若存在，则判断存在异常。
可选的，所述处理器执行所述根据所述影像分析结果判断是否存在异常，具体包括：
获取车辆的运行状态；
判断所述影像分析结果中的人像数量和/或人像状态是否与所述车辆的运行状态匹配；
若不匹配，则判断存在异常。
可选的，所述处理器执行所述对应的异常影像数据包括异常开始至异常消除时间段的影像数据。
在本实施例中，车内监控设备通过获取车辆内部的实时影像数据，之后按照预设算法对所述实时影像数据进行分析处理，得到影像分析结果，并根据所述影像分析结果判断是否存在异常，当存在时，则向服务器或者绑定的车主终端发送警报，并根据所述服务器或者所述车主终端的数据请求发送对应的异常影像数据，以使所述服务器或者所述车主终端在确认异常后执行相应的措施。车内影像数据的分析在车内监控设备端进行，只有在根据分析结果判断发生异常时才将异常结果发送给服务器或者绑定的车主终端，从而一方面降低了人工参与的工作量，提升了监控效率，降低了人工漏判或者误判的可能性，另一方面大大减少了传输到网络的数据量，极大的降低了信息安全事件的风险，有效的保护了用户隐私。
本发明实施例还提供一种计算机存储介质，其中，该计算机存储介质可存储有程序，该程序执行时包括上述方法实施例中记载的任何一种车内监控方法的部分或全部步骤。
需要说明的是，对于前述的各方法实施例，为了简单描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本发明并不受所描述的动作顺序的限制，因为依据本发明，某些步骤可以采用其他顺序或者同时进行。其次，本领域技术人员也应该知悉，说明书中所描述的实施例均属于优选实施例，所涉及的动作和模块并不一定是本发明所必须的。
在上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述的部分，可以参见其他实施例的相关描述。
在本申请所提供的几个实施例中，应该理解到，所揭露的装置，可通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本发明各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储器中。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储器中，包括若干指令用以使得一台计算机设备（可为个人计算机、服务器或者网络设备等）执行本发明各个实施例所述方法的全部或部分步骤。而前述的存储器包括：U盘、只读存储器（ROM，Read-Only Memory）、随机存取存储器（RAM，Random Access Memory）、移动硬盘、磁碟或者光盘等各种可以存储程序代码的介质。
本领域普通技术人员可以理解上述实施例的各种方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成，该程序可以存储于一计算机可读存储器中，存储器可以包括：闪存盘、只读存储器（英文：Read-Only Memory ，简称：ROM）、随机存取器（英文：Random Access Memory，简称：RAM）、磁盘或光盘等。
以上对本发明实施例进行了详细介绍，本文中应用了具体个例对本发明的原理及实施方式进行了阐述，以上实施例的说明只是用于帮助理解本发明的方法及其核心思想；同时，对于本领域的一般技术人员，依据本发明的思想，在具体实施方式及应用范围上均会有改变之处，综上上述，本说明书内容不应理解为对本发明的限制。

Claims (10)

  1. 一种车内监控方法，其特征在于，所述方法包括：
    获取车辆内部的实时影像数据；
    按照预设算法对所述实时影像数据进行分析处理，得到影像分析结果；
    根据所述影像分析结果判断是否存在异常；
    若存在，则向服务器或者绑定的车主终端发送警报；
    根据所述服务器或者所述车主终端的数据请求发送对应的异常影像数据，以使所述服务器或者所述车主终端在确认异常后执行相应的措施。
  2. 根据权利要求1所述的车内监控方法，其特征在于，所述预设算法包括人像识别算法、烟雾检测算法，所述按照预设算法对所述实时影像数据进行分析处理，具体包括：
    利用人像识别算法识别所述实时影像数据中的人像数量和人像状态；
    利用烟雾检测算法识别所述实时影像数据中的烟雾发生状态。
  3. 根据权利要求2所述的车内监控方法，其特征在于，所述根据所述影像分析结果判断是否存在异常，具体包括：
    根据所述影像分析结果中的烟雾发生状态判断车内是否存在烟雾，若存在，则判断存在异常。
  4. 根据权利要求2或3所述的车内监控方法，其特征在于，所述根据所述影像分析结果判断是否存在异常，具体包括：
    获取车辆的运行状态；
    判断所述影像分析结果中的人像数量和/或人像状态是否与所述车辆的运行状态匹配；
    若不匹配，则判断存在异常。
  5. 根据权利要求1所述的方法，其特征在于，所述对应的异常影像数据包括异常开始至异常消除时间段的影像数据。
  6. 一种设备，所述设备包括：
    存储有可执行程序代码的存储器；
    与所述存储器耦合的处理器；
    所述处理器调用所述存储器中存储的所述可执行程序代码，执行如下步骤：
    获取车辆内部的实时影像数据；
    按照预设算法对所述实时影像数据进行分析处理，得到影像分析结果；
    根据所述影像分析结果判断是否存在异常；
    若存在，则向服务器或者绑定的车主终端发送警报；
    根据所述服务器或者所述车主终端的数据请求发送对应的异常影像数据，以使所述服务器或者所述车主终端在确认异常后执行相应的措施。
  7. 根据权利要求6所述的设备，其特征在于，所述预设算法包括人像识别算法、烟雾检测算法，所述处理器执行所述按照预设算法对所述实时影像数据进行分析处理，具体方式为：
    利用人像识别算法识别所述实时影像数据中的人像数量和人像状态；
    利用烟雾检测算法识别所述实时影像数据中的烟雾发生状态。
  8. 根据权利要求7所述的设备，其特征在于，所述处理器执行所述根据所述影像分析结果判断是否存在异常，具体方式为：
    根据所述影像分析结果中的烟雾发生状态判断车内是否存在烟雾，若存在，则判断存在异常。
  9. 根据权利要求7或8所述的设备，其特征在于，所述处理器执行所述根据所述影像分析结果判断是否存在异常，具体方式为：
    获取车辆的运行状态；
    判断所述影像分析结果中的人像数量和/或人像状态是否与所述车辆的运行状态匹配；
    若不匹配，则判断存在异常。
  10. 根据权利要求6所述的设备，其特征在于，所述处理器执行所述对应的异常影像数据包括异常开始至异常消除时间段的影像数据。
PCT/CN2018/085879 2018-01-30 2018-05-07 一种车内监控方法及设备 WO2019148684A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810090072.8 2018-01-30
CN201810090072.8A CN108449571A (zh) 2018-01-30 2018-01-30 一种车内监控方法及设备

Publications (1)

Publication Number Publication Date
WO2019148684A1 true WO2019148684A1 (zh) 2019-08-08

Family

ID=63191180

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/085879 WO2019148684A1 (zh) 2018-01-30 2018-05-07 一种车内监控方法及设备

Country Status (2)

Country Link
CN (1) CN108449571A (zh)
WO (1) WO2019148684A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113542047A (zh) * 2020-04-21 2021-10-22 北京沃东天骏信息技术有限公司 异常请求的检测方法、装置、电子设备及计算机可读介质
CN115205952A (zh) * 2022-09-16 2022-10-18 深圳市企鹅网络科技有限公司 一种基于深度学习的线上学习图像采集方法及系统

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109515315A (zh) * 2018-09-14 2019-03-26 纵目科技（上海）股份有限公司 一种无人驾驶车辆内物体识别方法、系统、终端和存储介质
CN110001566B (zh) * 2019-03-25 2022-02-01 奇瑞汽车股份有限公司 车内生命体保护方法、装置及计算机可读存储介质
CN113129475A (zh) * 2021-03-30 2021-07-16 广州小鹏汽车科技有限公司 一种监控方法、装置和车辆

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101192314A (zh) * 2006-11-24 2008-06-04 苏立军 具有异地控制功能的无线汽车防盗方法和装置
CN102658804A (zh) * 2012-04-09 2012-09-12 上海齐汇通讯技术有限公司 一种车载智能终端系统及其实现方法
CN203410366U (zh) * 2013-08-16 2014-01-29 长安大学 一种客车安全监控装置
CN106228750A (zh) * 2016-09-20 2016-12-14 李国远 锁车后异常情况报警方法、装置及系统
CN107341438A (zh) * 2017-01-24 2017-11-10 问众智能信息科技（北京）有限公司 基于计算机视觉的车内安全监测的方法和装置

Family Cites Families (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101800772A (zh) * 2010-02-02 2010-08-11 大连海创高科信息技术有限公司 3g车载智能监控管理系统
CN202650211U (zh) * 2012-03-20 2013-01-02 山东北斗空间定位设备销售服务有限公司 基于北斗卫星定位、3g与4g通信技术的车辆安全监控系统
CN103379310A (zh) * 2012-04-26 2013-10-30 哈尔滨工业大学深圳研究生院 一种交通意外医疗辅助系统及方法
CN202624069U (zh) * 2012-06-29 2012-12-26 北京兴科迪科技有限公司 带疲劳驾驶报警系统的汽车内后视镜
CN102930700A (zh) * 2012-10-25 2013-02-13 上海市城市建设设计研究总院 校车车内安全监控系统
CN104299355A (zh) * 2014-09-28 2015-01-21 厦门蓝斯通信股份有限公司 一种基于视频智能识别的车辆监控方法及系统
US10061486B2 (en) * 2014-11-05 2018-08-28 Northrop Grumman Systems Corporation Area monitoring system implementing a virtual environment
CN105657335A (zh) * 2014-11-14 2016-06-08 江苏省兴泽实业发展有限公司 一种校车安全监管系统及应用方法
CN105427529B (zh) * 2015-12-04 2018-06-29 北京奇虎科技有限公司 一种车内环境监控的方法及终端
CN105933427A (zh) * 2016-05-24 2016-09-07 张力 基于汽车智能交互系统的汽车安全预警方法
CN106059868A (zh) * 2016-07-24 2016-10-26 哈尔滨理工大学 家居智能视频监控防护系统
CN106274799A (zh) * 2016-08-25 2017-01-04 乐视控股（北京）有限公司 一种汽车报警系统和汽车
CN106335432B (zh) * 2016-08-29 2018-11-06 赵谕 具有行车辅助系统的智能后视镜、控制系统及处理方法
CN106364442A (zh) * 2016-11-29 2017-02-01 李森 一种车内遗留人员检测报警装置和方法
CN107472124A (zh) * 2017-07-01 2017-12-15 湖南海翼电子商务股份有限公司 车内生存环境的预警方法及其车载系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101192314A (zh) * 2006-11-24 2008-06-04 苏立军 具有异地控制功能的无线汽车防盗方法和装置
CN102658804A (zh) * 2012-04-09 2012-09-12 上海齐汇通讯技术有限公司 一种车载智能终端系统及其实现方法
CN203410366U (zh) * 2013-08-16 2014-01-29 长安大学 一种客车安全监控装置
CN106228750A (zh) * 2016-09-20 2016-12-14 李国远 锁车后异常情况报警方法、装置及系统
CN107341438A (zh) * 2017-01-24 2017-11-10 问众智能信息科技（北京）有限公司 基于计算机视觉的车内安全监测的方法和装置

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113542047A (zh) * 2020-04-21 2021-10-22 北京沃东天骏信息技术有限公司 异常请求的检测方法、装置、电子设备及计算机可读介质
CN115205952A (zh) * 2022-09-16 2022-10-18 深圳市企鹅网络科技有限公司 一种基于深度学习的线上学习图像采集方法及系统

Also Published As

Publication number Publication date
CN108449571A (zh) 2018-08-24

Similar Documents

Publication Publication Date Title
WO2019148684A1 (zh) 一种车内监控方法及设备
WO2022062775A1 (zh) 一种基于车辆终端系统的监控处理方法、系统及相关设备
US20230036290A1 (en) Apparatus and method for emergency dispatch
US10176654B2 (en) Suspicious person detection system, suspicious person detection method
KR20170018140A (ko) 비언어적 음성 인식을 포함하는 응급 상황 진단 방법 및 장치
CN113377088A (zh) 即时通讯的汽车远程诊断检测方法、电子设备及存储介质
KR20210042860A (ko) 정보 출력 방법, 장치 및 시스템
CN108898807A (zh) 隐蔽报警方法、装置、终端及存储介质
CN108806151A (zh) 监控报警方法、装置、服务器和存储介质
CN110087205B (zh) 一种用于获取被救援者的基础参数的方法与设备
CN110650243A (zh) 一种报警方法、装置、存储介质以及终端
CN112149589B (zh) 车内驾驶员行为识别方法及装置
CN111583732B (zh) 基于头戴式显示设备的测评状态监测方法、装置和设备
CN112565062A (zh) 即时通信订单的处理方法、相关装置、设备及介质
CN111908288A (zh) 一种基于TensorFlow的电梯安全系统及方法
CN109147238A (zh) 报警方法、装置、终端及存储介质
US11830343B2 (en) Information processing apparatus, information processing method, and non-transitory storage medium
WO2022039373A1 (ko) 개인 위험 상태 감지 기반 상황 정보 획득 장치
JP2019086895A (ja) ドライブレコーダシステムおよびそれに用いられる車両、情報収集装置、ならびに方法
CN214965464U (zh) 人脸识别智能测温系统和设备
CN111882815A (zh) 一种智能的安防消防一体化方法及系统
CN113489939A (zh) 一种输电线路施工现场智能监控方法和系统
JP2021149246A (ja) 安全運転支援装置、システム、方法、及びプログラム
CN111857000A (zh) 基于电视的物联网数据监测处理方法、系统、电视
CN111178562A (zh) 信息处理方法、装置、设备及计算机可读存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18903592

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18903592

Country of ref document: EP

Kind code of ref document: A1