WO2021164644A1 - 违规事件检测方法及装置、电子设备和存储介质 - Google Patents

违规事件检测方法及装置、电子设备和存储介质 Download PDF

Info

Publication number
WO2021164644A1
WO2021164644A1 PCT/CN2021/076201 CN2021076201W WO2021164644A1 WO 2021164644 A1 WO2021164644 A1 WO 2021164644A1 CN 2021076201 W CN2021076201 W CN 2021076201W WO 2021164644 A1 WO2021164644 A1 WO 2021164644A1
Authority
WO
WIPO (PCT)
Prior art keywords
detection
processed video
violation event
detection result
processed
Prior art date
Application number
PCT/CN2021/076201
Other languages
English (en)
French (fr)
Inventor
罗予晨
吴军
焦义奎
田纪彭
袁诵弦
Original Assignee
深圳市商汤科技有限公司
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 深圳市商汤科技有限公司 filed Critical 深圳市商汤科技有限公司
Priority to JP2021562343A priority Critical patent/JP2022529300A/ja
Priority to KR1020217036108A priority patent/KR20210148313A/ko
Publication of WO2021164644A1 publication Critical patent/WO2021164644A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/20—Movements or behaviour, e.g. gesture recognition
    • 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
    • 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
    • G08B13/19613—Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion
    • G08B13/19615—Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion wherein said pattern is defined by the user
    • 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
    • G08B21/24—Reminder alarms, e.g. anti-loss alarms

Definitions

  • the present disclosure relates to the field of computer technology, and in particular to a method and device for detecting a violation event, electronic equipment, and a storage medium.
  • the embodiments of the present disclosure provide a method and device for detecting a violation event, an electronic device, and a storage medium.
  • a violation event method including: performing detection processing on a to-be-processed video frame of a to-be-processed video stream according to a preset detection mode, to obtain a detection result of the to-be-processed video stream; In a case where the detection result of the to-be-processed video stream is a violation event, a warning message is generated according to a preset warning mode and the detection result.
  • the to-be-processed video frame can be detected according to the preset detection mode, the detection result of the to-be-processed video stream can be obtained, and the warning information can be generated according to the preset warning mode, thereby achieving Automatically detect and alert violations in real time, reduce labor costs, and improve the efficiency of detection and warning of violations.
  • performing detection processing on the to-be-processed video frames of the to-be-processed video stream to obtain the detection result of the to-be-processed video stream includes: setting the detection mode to the first In the case of a detection mode, the detection processing is performed on the to-be-processed video frame extracted at the current moment to obtain the first detection result at the current moment; in the case that the first detection result is the first violation event, the first preset The multiple to-be-processed video frames extracted in the time period are subjected to detection processing, and the second detection results of the multiple to-be-processed video frames are respectively obtained, wherein the first preset time period starts from the current moment Time period, the first violation event is any type of violation event; when the second detection result is that the number of to-be-processed video frames for the first violation event is greater than or equal to the preset number threshold, all The detection result of the to-be-processed video stream is determined to be the first violation
  • the subsequent to-be-processed video frames can be confirmed multiple times, so as to reduce the probability of false detection.
  • performing detection processing on the to-be-processed video frames of the to-be-processed video stream to obtain the detection result of the to-be-processed video stream includes: setting the detection mode to the first In the case of the second detection mode, the detection processing is performed on the to-be-processed video frame extracted at the current moment to obtain the detection result of the to-be-processed video stream.
  • performing detection processing on the to-be-processed video frame of the to-be-processed video stream to obtain the detection result of the to-be-processed video stream includes: determining the face area of the target object in the to-be-processed video frame And/or the human body region; performing behavior detection processing on the human face region and/or human body region to obtain the detection result.
  • performing detection processing on the to-be-processed video frames of the to-be-processed video stream to obtain the detection result of the to-be-processed video stream includes: performing motion detection processing on the to-be-processed video frames extracted at multiple times; Obtain the area where the moving target object is located; perform detection processing on the area where the moving target object is located to obtain the detection result.
  • performing detection processing on the to-be-processed video frame of the to-be-processed video stream to obtain the detection result of the to-be-processed video stream includes: performing detection processing on the definition of the to-be-processed video frame to obtain the detection result.
  • generating a warning message according to a preset warning mode and the detection result includes: setting in the warning mode In the case of the first warning mode, the warning information corresponding to the second violation event is generated according to the first detection result corresponding to the second violation event, and the warning information corresponding to the second violation event is blocked within the second preset time period. 2. Warning information corresponding to the violation event, where the second violation event is any type of violation event.
  • generating a warning message according to a preset warning mode and the detection result includes: setting in the warning mode In the case of the second warning mode, the warning information corresponding to the second violation event is generated according to the detection result corresponding to the second violation event, where the second violation event is any type of violation event.
  • the strength of the warning can be increased, and the offenders can be urged to correct the violation as soon as possible.
  • the method further includes: performing frame extraction processing on the to-be-processed video stream according to a preset frequency to obtain the to-be-processed video frame.
  • a device for detecting a violation event including: a first obtaining module configured to perform detection processing on a to-be-processed video frame of a to-be-processed video stream according to a preset detection mode to obtain the The detection result of the to-be-processed video stream; a generating module configured to generate warning information according to a preset warning mode and the detection result when the detection result of the to-be-processed video stream is a violation event.
  • the first obtaining module is configured to perform detection processing on the to-be-processed video frame extracted at the current time when the detection mode is set to the first detection mode to obtain the current time A first detection result; in the case that the first detection result is a first violation event, perform detection processing on a plurality of to-be-processed video frames extracted within a first preset time period, and obtain the plurality of to-be-processed videos respectively
  • the second detection result of the frame wherein the first preset time period is a time period starting from the current moment, the first violation event is any kind of violation event; in the second detection If the result is that the number of to-be-processed video frames of the first violation event is greater than or equal to the preset number threshold, the detection result of the to-be-processed video stream is determined as the first violation event.
  • the first obtaining module is configured to perform detection processing on the to-be-processed video frame extracted at the current moment when the detection mode is set to the second detection mode to obtain the to-be-processed video frame. Process the detection results of the video stream.
  • the first obtaining module is configured to determine the face area and/or the human body area of the target object in the to-be-processed video frame; Perform behavior detection processing to obtain the detection result.
  • the first obtaining module is configured to perform motion detection processing on the to-be-processed video frames extracted at multiple times to obtain the area where the moving target object is located; and to determine the area where the moving target object is located. Perform detection processing to obtain the detection result.
  • the first obtaining module is configured to perform detection processing on the definition of the to-be-processed video frame to obtain the detection result.
  • the generating module is configured to generate the first warning mode according to the first detection result corresponding to the second violation event when the warning mode is set to the first warning mode. 2. Warning information corresponding to the violation event, and shielding the warning information corresponding to the second violation event within a second preset time period, where the second violation event is any type of violation event.
  • the generating module is configured to generate the second violation event according to the detection result corresponding to the second violation event when the warning mode is set to the second warning mode.
  • the device further includes: a second obtaining module configured to perform frame extraction processing on the video stream to be processed according to a preset frequency to obtain the video frame to be processed.
  • an electronic device including: a processor; a memory for storing executable instructions of the processor; wherein the processor is configured to execute the above-mentioned violation event detection method.
  • a computer-readable storage medium having computer program instructions stored thereon, and when the computer program instructions are executed by a processor, the above-mentioned violation event detection method is implemented.
  • the computer program product includes program instructions that, when executed by a processor, implement the above-mentioned violation event detection method.
  • a computer program including computer-readable code, and when the computer-readable code is executed in an electronic device, a processor in the electronic device executes for realizing the present disclosure.
  • the above-mentioned violation event detection method is implemented.
  • Fig. 1 shows a flowchart of a method for detecting a violation event according to an embodiment of the present disclosure
  • Fig. 2 shows a schematic diagram 1 of the application of the method for detecting a violation event according to an embodiment of the present disclosure
  • FIG. 3 shows a second schematic diagram of the application of the method for detecting a violation event according to an embodiment of the present disclosure
  • FIG. 4 shows a third schematic diagram of application of the method for detecting a violation event according to an embodiment of the present disclosure
  • FIG. 5 shows a fourth schematic diagram of application of the method for detecting a violation event according to an embodiment of the present disclosure
  • Fig. 6 shows a block diagram of a device for detecting a violation event according to an embodiment of the present disclosure
  • Fig. 7 shows a block diagram of an electronic device according to an embodiment of the present disclosure
  • Fig. 8 shows another block diagram of an electronic device according to an embodiment of the present disclosure.
  • Fig. 1 shows a flow chart of a method for detecting a violation event according to an embodiment of the present disclosure. As shown in Fig. 1, the method includes:
  • step S11 perform behavior detection processing on the to-be-processed video frames of the to-be-processed video stream according to a preset detection mode, to obtain a behavior detection result of the to-be-processed video stream;
  • step S12 when the behavior detection result of the to-be-processed video stream is a violation behavior, a warning message is generated according to a preset warning mode and the behavior detection result.
  • the video frame to be processed can be detected according to the preset detection mode, the detection result of the video stream to be processed can be obtained, and the warning information can be generated according to the preset warning mode, thereby realizing automatic Real-time detection and warning of violations, reducing labor costs, and improving the efficiency of detection and warning of violations.
  • the violation event detection method may be executed by a terminal device or other processing equipment, where the terminal device may be a user equipment (UE), a mobile device, a user terminal, a terminal, a cellular phone , Cordless phones, Personal Digital Assistant (PDA), handheld devices, computing devices, in-vehicle devices, wearable devices, etc.
  • UE user equipment
  • PDA Personal Digital Assistant
  • Other processing equipment can be servers or cloud servers.
  • the violation event detection method may be implemented by a processor invoking a computer-readable instruction stored in a memory.
  • the violation event detection method can be used to monitor the behavior of the target object in the surveillance video (the video stream to be processed) (for example, the violation operation behavior, the violation wearing behavior, etc.) or the violation target object ( For example, people who enter illegally, rats entering the kitchen, etc.) are detected, and violations are warned, so as to reduce the occurrence of violations and improve the efficiency of supervision.
  • the violation event detection method can be used to perform behavior detection processing on target objects in surveillance videos of kitchens, canteens, food processing plants, catering companies and other places, so as to warn employees of violations, thereby providing employment The consciousness of personnel improves food safety and food quality.
  • the violation event detection method can be executed by a front-end detection device, and the detection mode and warning mode of the front-end detection device can be set by the back-end service device.
  • the detection mode and warning mode of the front-end detection device can be set through instructions sent by the back-end service device. Or, you can directly set the detection mode and warning mode of the front-end detection device.
  • an instruction receiving device for example, buttons, touch screen, remote control, etc.
  • the preset mode may be solidified in the front-end detection equipment.
  • the present disclosure does not limit the setting methods of the detection mode and the warning mode.
  • the preset detection mode may include a first detection mode and/or a second detection mode
  • the first detection mode may include, for example, the following detection strategy: for the first time after a violation event is detected in a video frame to be processed , The violation event may not be determined immediately, but continue to detect multiple subsequent video frames to be processed. After multiple violation events are determined in the multiple pending video frames, the detection result of the video stream to be detected can be determined as Violation incidents can reduce false alarms of violation incidents.
  • the second detection mode may include, for example, the following detection strategy: immediately after the violation event is detected, the behavior detection result of the to-be-processed video stream is generated, without the need for multiple confirmations of subsequent to-be-processed video frames.
  • the preset warning mode may include a first warning mode and/or a second warning mode
  • the first warning mode may include, for example, the following warning strategy: after a violation event is detected for the first time, a warning message is generated , And no longer generate warning messages for the same violation event within a preset time period, avoiding repeated warnings for the same violation event.
  • the second warning mode may include, for example, the following warning strategy: every time a violation event is detected, a warning message is generated.
  • the front-end detection device can detect the to-be-processed video frame of the video stream to be processed according to the preset detection mode. If the detection result is a violation event, the front-end detection The device can generate warning messages according to the preset warning mode.
  • the front-end detection device may detect the to-be-processed video frame of the to-be-processed video stream according to a preset detection mode.
  • the front-end detection device may perform frame-by-frame detection on each video frame of the to-be-processed video stream, or may first perform frame extraction processing on the to-be-processed video stream and detect the extracted video frames.
  • the method further includes: performing frame extraction processing on the to-be-processed video stream according to a preset frequency to obtain the to-be-processed video frame.
  • the front-end detection device may perform frame extraction processing on the video stream to be processed.
  • a video frame may be extracted every 3 seconds, that is, a video frame to be processed may be acquired every 3 seconds.
  • the preset frequency can be adaptively adjusted according to the detection mode, and can also be adaptively adjusted according to the type of the detected violation event.
  • the preset frequency in the first detection mode may be lower than the preset frequency in the second detection mode.
  • the preset frequency for detecting video clarity may be lower than the preset frequency for detecting violations.
  • the embodiment of the present disclosure does not limit the preset frequency.
  • the front-end detection device may perform detection processing on the to-be-processed video frame according to a preset detection mode. For example, in the first detection mode, after the front-end detection device detects a violation event in a video frame to be processed for the first time, it may not immediately determine the violation event, but continue to detect multiple subsequent video frames to be processed, that is, in multiple video frames. After multiple violation events are determined in a video frame to be processed, the detection result of the video stream to be detected can be determined as a violation event, which can reduce false alarms of violation events. For example, in scenes such as canteens, kitchens, etc., violations may include staff not wearing hats, masks, shirtless, smoking, etc. The detection mode (ie, the first detection mode) of violations can be reduced after multiple confirmations. False alarms caused by workers accidentally taking off their masks or hats (for example, wiping sweat).
  • step S11 may include: when the detection mode is set to the first detection mode, performing detection processing on the to-be-processed video frame extracted at the current moment to obtain the first detection result at the current moment
  • the multiple to-be-processed video frames extracted within the first preset time period are detected and processed, and the second of the multiple to-be-processed video frames are obtained respectively
  • the detection result wherein the first preset time period is a time period starting from the current moment, the first violation event is any kind of violation event; and the second detection result is the first
  • the detection result of the to-be-processed video stream is determined as the first violation event.
  • the detection mode of the front-end application device can be set to the first detection mode through the back-end service device, or the detection mode can be directly set to the first detection mode at the front-end application device.
  • the front-end application device can perform detection processing on the to-be-processed video frame in the first detection mode.
  • the front-end application device may detect the to-be-processed video frames extracted from the to-be-processed video stream at a preset frequency (for example, 3 seconds/time) one by one, and obtain the detection result of each to-be-processed video frame, For example, the front-end application device may perform detection processing on the to-be-processed video frame extracted at the current time t to obtain the first detection result at the current time t.
  • a preset frequency for example, 3 seconds/time
  • the front-end detection device detects that the first detection result at the current time t is the first violation event (that is, the target object in the to-be-processed video frame extracted at the current time t may be performing a violation), but because There may be misdetection (for example, the worker accidentally removes a mask or hat and other actions (for example, wiping sweat) and is detected, which is not a real violation).
  • the front-end detection device can detect multiple actions after the current time t. The video frame is detected and processed to determine the violation event multiple times.
  • detection processing may be performed on multiple to-be-processed video frames extracted within the first preset time period, and the second detection results of the multiple to-be-processed video frames may be obtained respectively.
  • the first preset time period is a time period starting from the current time t, for example, from the current time t to the time period t+A (the duration is A), at the first preset time Within a segment, multiple frame extractions can be performed on the video stream to be processed to obtain multiple video frames to be processed. For example, if the duration A is 5 minutes and the preset frequency of frame drawing is 3 seconds/time, then 100 video frames can be extracted in the first preset time period.
  • the front-end detection device may perform detection processing on the 100 to-be-processed video frames one by one, and obtain the second detection result of the 100 to-be-processed video frames.
  • the second detection result of the to-be-processed video frames extracted within the first preset time period may be counted to determine the number of to-be-processed video frames whose second detection result is the first violation event ; If the number is greater than the preset number threshold, the violation event can be confirmed, and the probability of false detection of the first violation event can be reduced by confirming multiple video frames to be processed. In some optional examples, if the detection result is that the number of first violation events is greater than or equal to 50 (the preset number threshold) in the above-mentioned 100 video frames to be processed, the violation events can be confirmed.
  • the preset number threshold is not limited.
  • the time threshold may not be set, and a preset number of to-be-processed video frames may be continuously extracted from the next frame drawing. For example, 100 video frames to be processed may be extracted, and the second detection result in these video frames to be processed may be determined to be the number of the first violation event. If the number is greater than or equal to the preset number threshold, the first violation event may be determined.
  • the embodiments of the present disclosure do not limit the number of extracted video frames to be processed.
  • the subsequent to-be-processed video frames can be confirmed multiple times, so as to reduce the probability of false detection.
  • step S11 may include: in the case that the detection mode is set to the second detection mode, performing detection processing on the to-be-processed video frame extracted at the current moment to obtain the image of the to-be-processed video stream Test results.
  • the detection mode of the front-end application device can be set to the second detection mode through the back-end service device, or the detection mode can be directly set to the second detection mode at the front-end application device.
  • the front-end application device can perform detection processing on the video frame to be processed in the second detection mode.
  • the front-end detection device may immediately generate the behavior detection result of the video stream to be processed after detecting the violation event. For example, when detecting a video frame to be processed, if it is detected that a target object in a to-be-processed video frame is performing a violation, it can be immediately confirmed that the target object in the to-be-processed video stream is performing a violation, that is, the target object in the to-be-processed video stream is The detection result of processing the video stream is confirmed as a violation event, and there is no need to confirm multiple subsequent video frames to be processed, which can improve the sensitivity of detection.
  • the front-end detection device may detect one or more preset violation events.
  • the violation event can be set. For example, if the front-end detection device is used to detect the pending video frames of surveillance videos in public places (for example, shopping malls, schools, offices, office buildings, etc.), the violation events can be set as smoking, playing with mobile phones, etc.
  • Violations can be set as non-wearing behaviors such as no hats, masks, gloves, shirts, etc., as well as sanitation violations such as pests and rats.
  • the embodiments of the present disclosure do not limit the types of violations.
  • the front-end detection device may use different behavior detection methods to detect various violation events.
  • performing detection processing on the to-be-processed video frame of the to-be-processed video stream to obtain the detection result of the to-be-processed video stream includes: determining the face area and/or human body of the target object in the to-be-processed video frame Region; performing behavior detection processing on the face region and/or human body region to obtain the behavior detection result.
  • the front-end detection device can use methods such as convolutional neural networks to detect the face area and/or human body area of the target object in the to-be-processed video frame, so that the face area and/or human body area can be detected. Perform behavior detection processing.
  • the face area of the target object may be detected, so as to detect whether the target object wears a hat or a mask.
  • the face area and/or the human body area of the target object can be detected, so that it can be detected whether the target object is compliant. For example, whether the staff is shirtless, whether they wear work clothes, etc.
  • the human body area of the target object can be detected, and whether the target object smokes can be determined according to the action of the target object in the human body area and whether there is smoke in the human body area, and further, the target can be detected The face area of the object to determine the identity information of the target object.
  • the embodiment of the present disclosure does not limit the behavior detection method.
  • the front-end detection device may use the to-be-processed video frames extracted at multiple times to detect the presence of rats or pests and other violations that affect sanitary conditions.
  • performing behavior detection processing on the to-be-processed video frames of the to-be-processed video stream to obtain the behavior detection result of the to-be-processed video stream includes: performing motion detection processing on the to-be-processed video frames extracted at multiple times to obtain the motion The area where the target object is located; the detection processing is performed on the area where the moving target object is located to obtain the detection result.
  • the front-end detection device can determine whether the to-be-processed video frame includes mice, mice, and other objects by comparing target objects in multiple to-be-processed video frames under poor light conditions (for example, at night).
  • Target objects such as pests. For example, at night, there is no staff in the kitchen and other objects are still. If a certain target object is detected in a certain video frame, but there is no such target object in another video frame, the target object may be a mouse, Moving target objects such as pests can improve the accuracy of detecting moving target objects under poor light conditions or under the hardware conditions of visible light cameras or infrared light cameras. Further, further detection processing can be performed on the area where the target object is located to determine whether the target object is a violation target object.
  • a mouse can be set as a target object that violates regulations, and a bird that flies over a window captured by a camera can be set as a target object that does not violate regulations.
  • the detection result can be determined as a violation event.
  • the front-end detection device can use multiple time-extracted video frames to be processed to detect the clarity of the video to be processed, for example, the camera is blurred by pollution caused by oil, dust, etc., or due to focus adjustment. The image is blurred and so on.
  • performing detection processing on the to-be-processed video frames of the to-be-processed video stream to obtain the detection result of the to-be-processed video stream includes: performing detection processing on the definition of the to-be-processed video frame to obtain the detection result.
  • the clarity of the extracted video frame to be processed may be detected. For example, indicators such as texture clarity can be detected. If the indicator of the to-be-processed video frame is lower than the indicator threshold, or the indicator of multiple to-be-processed video frames is lower than the indicator threshold in the first preset time period, the detection can be determined The result is a violation event, that is, the camera is contaminated or the focus is adjusted incorrectly.
  • the violation event may also include multiple events.
  • students whispering in class, cheating in the examination room and other violations the embodiment of the present disclosure does not limit the types of violations.
  • the foregoing behavior detection processing may be executed in parallel, and one or more of the detection processing may be selectively executed.
  • the behavior detection processing can be performed in parallel to detect whether the target object does not wear a hat, a mask, a glove, a shirtless, and other illegal wear behaviors, as well as detection of pests, mice, etc.
  • the detection and processing of sanitary violations, and the various detection and processing do not interfere with each other.
  • the detection processing can also be set as required. For example, during the daytime, there is no need to perform event detection processing for detecting sanitary violations such as pests and rats, and the detection processing can be temporarily closed.
  • the embodiment of the present disclosure does not limit the type of detection processing.
  • warning information corresponding to the violation event may be generated according to a preset warning mode.
  • the warning mode can be set through the back-end service device, or it can be directly set at the front-end detection device. The embodiment of the present disclosure does not limit the setting method of the warning mode.
  • the front-end detection device may be set to the first detection mode, and step S12 may include: when the warning mode is set to the first warning mode Next, generate warning information corresponding to the second violation event according to the first detection result corresponding to the second violation event, and block the warning information corresponding to the second violation event within a second preset time period , Wherein the second violation event is any type of violation event.
  • the second preset time period may be a time period starting at the time t1 when the second violation event is first detected (for example, taking t1 as the starting time and a time period of 30 minutes). Section, the embodiment of the present disclosure does not limit the duration of the second preset time period).
  • the warning mode can be set to the first warning mode. If a second violation event is detected in this warning mode, only one warning message will be generated for the second violation event within the second preset time period. During the time period, if multiple second violation events are repeatedly detected, the repeated warning information can be shielded, and the second violation event will be warned only once. After the second preset time period ends, if the second violation event is detected again, the warning message can be generated again, and the second preset time period starts again, and so on.
  • Step S12 may include: when the warning mode is set to the second warning mode, generating warning information corresponding to the second violation event according to the detection result corresponding to the second violation event, wherein the second violation event A violation event is any kind of violation event.
  • warning information in the second warning mode, as long as a violation event is detected, warning information can be generated for the violation event, regardless of whether the warning information is duplicated with the previous warning information.
  • the strength of the warning can be increased, and the offenders can be urged to correct the violations as soon as possible.
  • the front-end detection device can also customize which warning messages are generated.
  • the front-end detection equipment has carried out behavior detection processing to detect violations of wearing behaviors such as no hats, masks, gloves, shirts, etc., but the front-end detection equipment can selectively generate one or more violation events. Warning message.
  • the front-end detection device detects that the target object is not wearing a hat, a mask, or gloves, but when generating warning information, it may only generate warning information that the target object is not wearing a mask.
  • the embodiments of the present disclosure do not impose restrictions on violation events.
  • the front-end detection device may also display the warning information or send it to the back-end service module to display the warning information through the back-end service module.
  • front-end detection equipment can be connected with display equipment or audio equipment, etc., and warning information can be sent to the display device, displayed through the user interface (UI) display interface, or sent to the audio device to play and correspond to the warning information Voice information.
  • the front-end detection device may send the warning information to the back-end service module, and the back-end service module may display the warning information.
  • the back-end service module may display the warning information through a UI display interface or audio equipment.
  • the embodiment of the present disclosure does not limit the display mode of the warning information.
  • the to-be-processed video frame can be detected according to a preset detection mode, and after the first-infringement event’s to-be-processed video frame is detected for the first time, subsequent to-be-processed video frames are performed multiple times Confirmation can improve the accuracy of detection, reduce the probability of false detection, and can generate warning messages according to the preset warning mode, shield repeated warning messages in the second time period, reduce warning message redundancy, and improve alarm efficiency.
  • Fig. 2 shows a schematic diagram 1 of the application of the method for detecting violation events according to an embodiment of the present disclosure.
  • a surveillance camera can capture dining places (for example, restaurants, kitchens, canteens, food processing plants, etc.) or medical and health places (For example, hospitals, pharmacies, laboratories, operating rooms, etc.) surveillance video.
  • the front-end detection equipment can detect whether there are violations of the staff in the video between 7:00-23:00.
  • Frame extraction can be performed on the video.
  • the frame extraction frequency can be 3 seconds/time, and the extracted video frames to be processed can be detected.
  • the front-end detection equipment can be used to detect and process violations of wearing hats, masks, shirts, etc., and turn off the event detection process for nocturnal objects such as rats. If a violation event is detected, a warning message can also be selectively generated. For example, warning information is only generated for violations of not wearing a mask, and warning information may not be generated for violations of not wearing a hat and shirtless.
  • Fig. 3 shows a schematic diagram of the second application of the method for detecting a violation event according to an embodiment of the present disclosure.
  • the detection mode of the front-end detection device can be set to the first detection mode, and the warning mode of the front-end detection device can be set This is the first warning mode.
  • the front-end detection equipment can detect the extracted video frames to be processed between 7:00-23:00, and detect whether the staff is wearing hats, masks, shirts, etc. Violation, if the violation is detected in the to-be-processed video frame for the first time at time t, in order to reduce the probability of false alarms, the extraction can be performed within the first preset time period (for example, within 5 minutes from time t) The 100 video frames of the same violation are detected separately. If the number of video frames to be processed with the same violation is less than the preset number threshold (for example, 60), it can be considered that the staff did not conduct the violation.
  • the preset number threshold for example, 60
  • the violation is detected When the number of to-be-processed video frames with the same violation is greater than or equal to the preset number threshold (for example, 60), it can be considered that the staff has committed the violation, and at the end of the first preset time period, the The warning message corresponding to the violation. For example, a warning message related to not wearing a mask can be generated.
  • the preset number threshold for example, 60
  • the second preset time period for example, 30 minutes
  • the second preset time period for example, 30 minutes
  • the second preset time period for example, 30 minutes
  • Fig. 4 shows the third application schematic diagram of the method for detecting violation events according to an embodiment of the present disclosure.
  • the back-end service device can set the detection mode and warning mode of multiple front-end detection devices, and the front-end detection devices can be multiple The video streams collected by two cameras are processed for violation event detection.
  • the back-end service equipment may include a public cloud platform, and the public cloud service may be invoked through a router/gateway to set up the front-end detection equipment.
  • Fig. 5 shows the fourth application schematic diagram of the method for detecting violation events according to an embodiment of the present disclosure.
  • the back-end service device may include a client application management platform, and the client application management platform may use the , API) Set the detection mode and warning mode of the front-end detection equipment, and can also set parameters such as frame rate.
  • the present disclosure does not limit the setting method of the front-end detection device.
  • the violation event detection method can be used in the violation detection of school canteens, and the behavior detection method can be used to achieve continuous monitoring of the sanitary conditions of canteens, kitchens, etc., to ensure the diet of teachers and students Safety.
  • the detection method for violations can be used in the detection of violations in catering companies.
  • the kitchen sewers of catering companies are the worst-hit areas of rodents, and companies often reduce the source of customers due to rodent problems.
  • the detection methods for violations can be greatly improved. The accuracy of rat detection and recognition under visible light or infrared light, and can detect irregularities in the kitchen area where the staff is located, and improve the sanitary condition.
  • the detection method for violations can be used in the detection of violations in food processing plants.
  • the labor intensity of the food processing plants is high, and the staff will take off their hats or masks because of sweating, etc., which may cause false alarms.
  • Event detection methods can effectively reduce false alarms and improve warning efficiency.
  • the violation detection method can also be used in hospitals, pharmacies, pharmaceutical factories and other places with high hygiene requirements, or used in office buildings, factories, schools and other places to detect whether staff or students have violations such as playing mobile phones. Or detect whether students cheat on exams and other violations.
  • the embodiment of the present disclosure does not limit the application field of the violation event detection method.
  • the embodiment of the present disclosure also provides a violation event detection device, electronic equipment, computer-readable storage medium, and a program. All of the above can be used to implement any violation event detection method provided by the embodiments of the present disclosure, and the corresponding technical solutions and descriptions are as follows: Refer to the corresponding records in the method section, and details are not described in this embodiment.
  • the writing order of the steps does not mean a strict execution order but constitutes any limitation on the implementation process.
  • the specific execution order of each step should be based on its function and possibility.
  • the inner logic is determined.
  • the device includes: a first obtaining module 11 configured to perform detection processing on the to-be-processed video frames of the to-be-processed video stream according to a preset detection mode , Obtain the detection result of the to-be-processed video stream; the generating module 12 is configured to generate warning information according to the preset warning mode and the detection result when the detection result of the to-be-processed video stream is a violation event .
  • the first obtaining module 11 is configured to perform detection processing on the to-be-processed video frame extracted at the current time when the detection mode is set to the first detection mode to obtain the current time
  • the first detection result is the first violation event
  • the second detection result of the video frame wherein the first preset time period is a time period starting from the current moment, the first violation event is any kind of violation event; in the second If the detection result is that the number of to-be-processed video frames of the first violation event is greater than or equal to the preset number threshold, the detection result of the to-be-processed video stream is determined as the first violation event.
  • the first obtaining module 11 is configured to perform detection processing on the to-be-processed video frame extracted at the current moment when the detection mode is set to the second detection mode to obtain the The detection result of the video stream to be processed.
  • the first obtaining module 11 is configured to determine the face area and/or the human body area of the target object in the to-be-processed video frame; The area performs behavior detection processing to obtain the detection result.
  • the first obtaining module 11 is configured to perform motion detection processing on the to-be-processed video frames extracted at multiple times to obtain the area where the moving target object is located; The detection process is performed on the area to obtain the detection result.
  • the first obtaining module 11 is configured to perform detection processing on the definition of the video frame to be processed to obtain the detection result.
  • the generating module 12 is configured to generate a data corresponding to the first warning mode according to the first detection result corresponding to the second violation event when the warning mode is set to the first warning mode. Warning information corresponding to the second violation event, and shielding the warning information corresponding to the second violation event within a second preset time period, where the second violation event is any type of violation event.
  • the generating module 12 is configured to generate the second warning mode according to the detection result corresponding to the second violation event when the warning mode is set to the second warning mode.
  • the device further includes: a second obtaining module configured to perform frame extraction processing on the video stream to be processed according to a preset frequency to obtain the video frame to be processed.
  • the functions or modules contained in the device provided in the embodiments of the present disclosure can be used to execute the methods described in the above method embodiments.
  • the functions or modules contained in the device provided in the embodiments of the present disclosure can be used to execute the methods described in the above method embodiments.
  • brevity, here No longer refer to the description of the above method embodiments.
  • the embodiment of the present disclosure also proposes a computer-readable storage medium on which computer program instructions are stored, and the computer program instructions implement the above-mentioned method when executed by a processor.
  • the computer-readable storage medium may be a non-volatile or volatile computer-readable storage medium.
  • An embodiment of the present disclosure also provides an electronic device, including: a processor; a memory for storing executable instructions of the processor; wherein the processor is configured as the above-mentioned method.
  • the electronic device can be provided as a terminal, server or other form of device.
  • Fig. 7 is a block diagram showing an electronic device 800 according to an exemplary embodiment.
  • the electronic device 800 may be a terminal such as a mobile phone, a computer, a digital broadcasting terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, and a personal digital assistant.
  • the electronic device 800 may include one or more of the following components: a processing component 802, a memory 804, a power supply component 806, a multimedia component 808, an audio component 810, an input/output (I/O) interface 812, and a sensor component 814 And the communication component 816.
  • the processing component 802 generally controls the overall operations of the electronic device 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations.
  • the processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the foregoing method.
  • the processing component 802 may include one or more modules to facilitate the interaction between the processing component 802 and other components.
  • the processing component 802 may include a multimedia module to facilitate the interaction between the multimedia component 808 and the processing component 802.
  • the memory 804 is configured to store various types of data to support operations in the electronic device 800. Examples of these data include instructions for any application or method operating on the electronic device 800, contact data, phone book data, messages, pictures, videos, and the like.
  • the memory 804 can be implemented by any type of volatile or non-volatile storage device or their combination, such as static random access memory (Static Random Access Memory, SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory). Programmable Read-Only Memory, EEPROM, Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (Read Only Memory) , ROM), magnetic memory, flash memory, magnetic disk or optical disk.
  • SRAM static random access memory
  • EPROM Erasable Programmable Read-Only Memory
  • PROM Programmable Read-Only Memory
  • Read Only Memory Read Only Memory
  • the power supply component 806 provides power for various components of the electronic device 800.
  • the power supply component 806 may include a power management system, one or more power supplies, and other components associated with the generation, management, and distribution of power for the electronic device 800.
  • the multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and the user.
  • the screen may include a liquid crystal display (Liquid Crystal Display, LCD) and a touch panel (Touch Panel, TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user.
  • the touch panel includes one or more touch sensors to sense touch, sliding, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure related to the touch or slide operation.
  • the multimedia component 808 includes a front camera and/or a rear camera. When the electronic device 800 is in an operation mode, such as a shooting mode or a video mode, the front camera and/or the rear camera can receive external multimedia data. Each front camera and rear camera can be a fixed optical lens system or have focal length and optical zoom capabilities.
  • the audio component 810 is configured to output and/or input audio signals.
  • the audio component 810 includes a microphone (Microphone, MIC).
  • the microphone is configured to receive an external audio signal.
  • the received audio signal may be further stored in the memory 804 or transmitted via the communication component 816.
  • the audio component 810 further includes a speaker for outputting audio signals.
  • the I/O interface 812 provides an interface between the processing component 802 and a peripheral interface module.
  • the above-mentioned peripheral interface module may be a keyboard, a click wheel, a button, and the like. These buttons may include, but are not limited to: home button, volume button, start button, and lock button.
  • the sensor component 814 includes one or more sensors for providing the electronic device 800 with various aspects of state evaluation.
  • the sensor component 814 can detect the on/off status of the electronic device 800 and the relative positioning of the components.
  • the component is the display and the keypad of the electronic device 800.
  • the sensor component 814 can also detect the electronic device 800 or the electronic device 800.
  • the position of the component changes, the presence or absence of contact between the user and the electronic device 800, the orientation or acceleration/deceleration of the electronic device 800, and the temperature change of the electronic device 800.
  • the sensor component 814 may include a proximity sensor configured to detect the presence of nearby objects when there is no physical contact.
  • the sensor component 814 may also include a light sensor, such as a Complementary Metal-Oxide Semiconductor (CMOS) or Charge Coupled Device (CCD) image sensor for use in imaging applications.
  • CMOS Complementary Metal-Oxide Semiconductor
  • CCD Charge Coupled Device
  • the sensor component 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
  • the communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices.
  • the electronic device 800 can access a wireless network based on a communication standard, such as WiFi, 2G, or 3G, or a combination thereof.
  • the communication component 816 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel.
  • the communication component 816 further includes a Near Field Communication (NFC) module to facilitate short-range communication.
  • NFC Near Field Communication
  • the NFC module can be based on radio frequency identification (RFID) technology, infrared data association (Infrared Data Association, IrDA) technology, ultra wideband (Ultra WideBand, UWB) technology, Bluetooth (BlueTooth, BT) technology and other technologies to fulfill.
  • RFID radio frequency identification
  • IrDA infrared Data Association
  • UWB ultra wideband
  • Bluetooth Bluetooth, BT
  • the electronic device 800 may be used by one or more application specific integrated circuits (Application Specific Integrated Circuit, ASIC), digital signal processor (Digital Signal Processor, DSP), digital signal processing device (DSPD), Programmable logic device (Programmable Logic Device, PLD), Field-Programmable Gate Array (Field-Programmable Gate Array, FPGA), controller, microcontroller, microprocessor or other electronic components are implemented to implement the above methods.
  • ASIC Application Specific Integrated Circuit
  • DSP Digital Signal Processor
  • DSPD digital signal processing device
  • PLD Programmable logic device
  • Field-Programmable Gate Array Field-Programmable Gate Array
  • controller microcontroller, microprocessor or other electronic components
  • a non-volatile computer-readable storage medium such as the memory 804 including computer program instructions, which can be executed by the processor 820 of the electronic device 800 to complete the foregoing method.
  • Fig. 8 is a block diagram showing an electronic device 1900 according to an exemplary embodiment.
  • the electronic device 1900 may be provided as a server.
  • the electronic device 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource represented by a memory 1932, for storing instructions executable by the processing component 1922, such as application programs.
  • the application program stored in the memory 1932 may include one or more modules each corresponding to a set of instructions.
  • the processing component 1922 is configured to execute instructions to perform the above-described methods.
  • the electronic device 1900 may also include a power supply component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to the network, and an input output (I/O) interface 1958 .
  • the electronic device 1900 can operate based on an operating system stored in the memory 1932, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM or the like.
  • a non-volatile computer-readable storage medium is also provided, such as the memory 1932 including computer program instructions, which can be executed by the processing component 1922 of the electronic device 1900 to complete the foregoing method.
  • a computer program including computer-readable code, and when the computer-readable code runs in an electronic device, the processor in the electronic device executes the implementation of the present disclosure.
  • the present disclosure may be a system, method and/or computer program product.
  • the computer program product may include a computer-readable storage medium loaded with computer-readable program instructions for enabling a processor to implement various aspects of the present disclosure.
  • the computer-readable storage medium may be a tangible device that can hold and store instructions used by the instruction execution device.
  • the computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing.
  • Computer-readable storage media include: portable computer disks, hard disks, random access memory (Random Access Memory, RAM), read-only memory (Read Only Memory, ROM), erasable Type programmable read-only memory (EPROM or flash memory), static random access memory (Static Random Access Memory, SRAM), portable compact disc read-only memory (CD-ROM), digital multi-function disk ( DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards on which instructions are stored or raised structures in the grooves, and any suitable combination of the above.
  • RAM Random Access Memory
  • ROM read-only memory
  • EPROM or flash memory erasable Type programmable read-only memory
  • SRAM static random access memory
  • CD-ROM compact disc read-only memory
  • DVD digital multi-function disk
  • memory sticks floppy disks
  • mechanical encoding devices such as punch cards on which instructions are stored or raised structures in the grooves, and any suitable combination of the above.
  • the computer-readable storage medium used here is not interpreted as the instantaneous signal itself, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (for example, light pulses through fiber optic cables), or through wires Transmission of electrical signals.
  • the computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to various computing/processing devices, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and/or a wireless network.
  • the network may include copper transmission cables, optical fiber transmission, wireless transmission, routers, firewalls, switches, gateway computers, and/or edge servers.
  • the network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network, and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing/processing device .
  • the computer program instructions used to perform the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or in one or more programming languages.
  • Source code or object code written in any combination, the programming language includes object-oriented programming languages such as Smalltalk, C++, etc., and conventional procedural programming languages such as "C" language or similar programming languages.
  • Computer-readable program instructions can be executed entirely on the user's computer, partly on the user's computer, executed as a stand-alone software package, partly on the user's computer and partly executed on a remote computer, or entirely on the remote computer or server implement.
  • the remote computer can be connected to the user's computer through any kind of network-including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to connect to the user's computer) connect).
  • LAN local area network
  • WAN wide area network
  • an electronic circuit such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), can be customized by using the status information of the computer-readable program instructions.
  • the computer-readable program instructions are executed to realize various aspects of the present disclosure.
  • These computer-readable program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine that makes these instructions when executed by the processor of the computer or other programmable data processing device , A device that implements the functions/actions specified in one or more blocks in the flowcharts and/or block diagrams is produced. It is also possible to store these computer-readable program instructions in a computer-readable storage medium. These instructions make computers, programmable data processing apparatuses, and/or other devices work in a specific manner, so that the computer-readable medium storing the instructions includes An article of manufacture, which includes instructions for implementing various aspects of the functions/actions specified in one or more blocks in the flowcharts and/or block diagrams.
  • each block in the flowchart or block diagram may represent a module, program segment, or part of an instruction, and the module, program segment, or part of an instruction contains one or more components for realizing the specified logical function.
  • Executable instructions may also occur in a different order from the order marked in the drawings. For example, two consecutive blocks can actually be executed substantially in parallel, or they can sometimes be executed in the reverse order, depending on the functions involved.
  • each block in the block diagram and/or flowchart, and the combination of the blocks in the block diagram and/or flowchart can be implemented by a dedicated hardware-based system that performs the specified functions or actions Or it can be realized by a combination of dedicated hardware and computer instructions.

Landscapes

  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Emergency Management (AREA)
  • Business, Economics & Management (AREA)
  • General Health & Medical Sciences (AREA)
  • Psychiatry (AREA)
  • Social Psychology (AREA)
  • Human Computer Interaction (AREA)
  • Health & Medical Sciences (AREA)
  • Image Analysis (AREA)
  • Closed-Circuit Television Systems (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
  • Burglar Alarm Systems (AREA)
  • Emergency Alarm Devices (AREA)
  • Alarm Systems (AREA)

Abstract

本公开实施例公开了一种违规事件检测方法及装置、电子设备和存储介质，所述方法包括：根据预设的检测模式，对待处理视频流的待处理视频帧进行检测处理，获得待处理视频流的检测结果；在待处理视频流的检测结果为违规事件的情况下，根据预设的警告模式以及检测结果，生成警告信息。

Description

违规事件检测方法及装置、电子设备和存储介质
相关申请的交叉引用
本公开基于申请号为202010098904.8、申请日为2020年02月18日的中国专利申请提出，并要求该中国专利申请的优先权，该中国专利申请的全部内容在此以引入方式并入本公开。
技术领域
本公开涉及计算机技术领域，尤其涉及一种违规事件检测方法及装置、电子设备和存储介质。
背景技术
目前对监控视频流中违规事件进行检测，例如厨房监控视频，主要还是依靠相关部门对监控视频数据进行人工排查来实现，人力上消耗巨大，同时效率低下且实时性很差。
发明内容
本公开实施例提出了一种违规事件检测方法及装置、电子设备和存储介质。
根据本公开实施例的一方面，提供了一种违规事件方法，包括：根据预设的检测模式，对待处理视频流的待处理视频帧进行检测处理，获得所述待处理视频流的检测结果；在所述待处理视频流的检测结果为违规事件的情况下，根据预设的警告模式以及所述检测结果，生成警告信息。
根据本公开的实施例的违规事件检测方法，可根据预设的检测模式对待处理视频帧进行检测，获得待处理视频流的检测结果，并可根据预设的警告模式生成警告信息，从而可以实现自动实时检测并告警违规事件，减少人力成本，提高违规事件的检测和警告效率。
在一种可能的实现方式中，根据预设的检测模式，对待处理视频流的待处理视频帧进行检测处理，获得所述待处理视频流的检测结果，包括：在所述检测模式设置为第一检测模式的情况下，对当前时刻抽取的待处理视频帧进行检测处理，获得当前时刻的第一检测结果；在所述第一检测结果为第一违规事件的情况下，对第一预设时间段内抽取的多个待处理视频帧进行检测处理，分别获得所述多个待处理视频帧的第二检测结果，其中，所述第一预设时间段为以所述当前时刻为起始时刻的时间段，所述第一违规事件 为任意一种违规事件；在所述第二检测结果为第一违规事件的待处理视频帧的数量大于或等于预设数量阈值的情况下，将所述待处理视频流的检测结果确定为第一违规事件。
通过这种方式，可在首次检测到第一违规事件的待处理视频帧后，对后续的待处理视频帧进行多次确认，以降低误检测的概率。
在一种可能的实现方式中，根据预设的检测模式，对待处理视频流的待处理视频帧进行检测处理，获得所述待处理视频流的检测结果，包括：在所述检测模式设置为第二检测模式的情况下，对当前时刻抽取的待处理视频帧进行检测处理，获得所述待处理视频流的检测结果。
通过这种方式，可根据当前时刻抽取的待处理视频帧立即确认待处理视频流中是否存在违规事件，可提高检测的灵敏度。
在一种可能的实现方式中，对待处理视频流的待处理视频帧进行检测处理，获得所述待处理视频流的检测结果，包括：在所述待处理视频帧中确定目标对象的人脸区域和/或人体区域；对所述人脸区域和/或人体区域进行行为检测处理，获得所述检测结果。
在一种可能的实现方式中，对待处理视频流的待处理视频帧进行检测处理，获得所述待处理视频流的检测结果，包括：对多个时刻抽取的待处理视频帧进行运动检测处理，获得运动的目标对象所在区域；对所述运动的目标对象所在区域进行检测处理，获得所述检测结果。
在一种可能的实现方式中，对待处理视频流的待处理视频帧进行检测处理，获得所述待处理视频流的检测结果，包括：对待处理视频帧的清晰度进行检测处理，获得所述检测结果。
在一种可能的实现方式中，在所述待处理视频流的检测结果为违规事件的情况下，根据预设的警告模式以及所述检测结果，生成警告信息，包括：在所述警告模式设置为第一警告模式的情况下，根据与第二违规事件对应的第一个检测结果，生成与所述第二违规事件对应的警告信息，并在第二预设时间段内屏蔽与所述第二违规事件对应的警告信息，其中，所述第二违规事件为任意一种违规事件。
通过这种方式，可在第二时间段内屏蔽重复的警告信息，减少警告信息冗余，提高报警效率。
在一种可能的实现方式中，在所述待处理视频流的检测结果为违规事件的情况下，根据预设的警告模式以及所述检测结果，生成警告信息，包括：在所述警告模式设置为第二警告模式的情况下，根据与第二违规事件的对应的检测结果，生成与所述第二违规事件对应的警告信息，其中，所述第二违规事件为任意一种违规事件。
通过这种方式，可提升警告的力度，督促违规人员尽快纠正违规事件。
在一种可能的实现方式中，所述方法还包括：根据预设频率对待处理视频流进行抽帧处理，获得待处理视频帧。
通过这种方式，可减少视频帧处理量，提高视频处理速度。
根据本公开实施例的一方面，提供了一种违规事件检测装置，包括：第一获得模块，配置为根据预设的检测模式，对待处理视频流的待处理视频帧进行检测处理，获得所述待处理视频流的检测结果；生成模块，配置为在所述待处理视频流的检测结果为违规事件的情况下，根据预设的警告模式以及所述检测结果，生成警告信息。
在一种可能的实现方式中，所述第一获得模块，配置为在所述检测模式设置为第一检测模式的情况下，对当前时刻抽取的待处理视频帧进行检测处理，获得当前时刻的第一检测结果；在所述第一检测结果为第一违规事件的情况下，对第一预设时间段内抽取的多个待处理视频帧进行检测处理，分别获得所述多个待处理视频帧的第二检测结果，其中，所述第一预设时间段为以所述当前时刻为起始时刻的时间段，所述第一违规事件为任意一种违规事件；在所述第二检测结果为第一违规事件的待处理视频帧的数量大于或等于预设数量阈值的情况下，将所述待处理视频流的检测结果确定为第一违规事件。
在一种可能的实现方式中，所述第一获得模块，配置为在所述检测模式设置为第二检测模式的情况下，对当前时刻抽取的待处理视频帧进行检测处理，获得所述待处理视频流的检测结果。
在一种可能的实现方式中，所述第一获得模块，配置为在所述待处理视频帧中确定目标对象的人脸区域和/或人体区域；对所述人脸区域和/或人体区域进行行为检测处理，获得所述检测结果。
在一种可能的实现方式中，所述第一获得模块，配置为对多个时刻抽取的待处理视频帧进行运动检测处理，获得运动的目标对象所在区域；对所述运动的目标对象所在区域进行检测处理，获得所述检测结果。
在一种可能的实现方式中，所述第一获得模块，配置为对待处理视频帧的清晰度进行检测处理，获得所述检测结果。
在一种可能的实现方式中，所述生成模块，配置为在所述警告模式设置为第一警告模式的情况下，根据与第二违规事件对应的第一个检测结果，生成与所述第二违规事件对应的警告信息，并在第二预设时间段内屏蔽与所述第二违规事件对应的警告信息，其中，所述第二违规事件为任意一种违规事件。
在一种可能的实现方式中，所述生成模块，配置为在所述警告模式设置为第二警告模式的情况下，根据与第二违规事件的对应的检测结果，生成与所述第二违规事件对应的警告信息，其中，所述第二违规事件为任意一种违规事件。
在一种可能的实现方式中，所述装置还包括：第二获得模块，配置为根据预设频率对待处理视频流进行抽帧处理，获得待处理视频帧。
根据本公开实施例的一方面，提供了一种电子设备，包括：处理器；用于存储处理器可执行指令的存储器；其中，所述处理器被配置为：执行上述违规事件检测方法。
根据本公开实施例的一方面，提供了一种计算机可读存储介质，其上存储有计算机程序指令，所述计算机程序指令被处理器执行时实现上述违规事件检测方法。
根据本公开实施例的一方面，提供了一种计算机程序产品，所述计算机程序产品包括程序指令，所述程序指令当被处理器执行时实现上述违规事件检测方法。
根据本公开实施例的一方面，提供了一种计算机程序，包括计算机可读代码，当所述计算机可读代码在电子设备中运行时，所述电子设备中的处理器执行用于实现本公开实施例上述的违规事件检测方法。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，而非限制本公开。
根据下面参考附图对示例性实施例的详细说明，本公开的其它特征及方面将变得清楚。
附图说明
此处的附图被并入说明书中并构成本说明书的一部分，这些附图示出了符合本公开的实施例，并与说明书一起用于说明本公开的技术方案。
图1示出根据本公开实施例的违规事件检测方法的流程图；
图2示出根据本公开的实施例的违规事件检测方法的应用示意图一；
图3示出根据本公开的实施例的违规事件检测方法的应用示意图二；
图4示出根据本公开的实施例的违规事件检测方法的应用示意图三；
图5示出根据本公开的实施例的违规事件检测方法的应用示意图四；
图6示出根据本公开的实施例的违规事件检测装置的框图；
图7示出根据本公开的实施例的电子设备的一种框图；
图8示出根据本公开的实施例的电子设备的另一种框图。
具体实施方式
以下将参考附图详细说明本公开的各种示例性实施例、特征和方面。附图中相同的附图标记表示功能相同或相似的元件。尽管在附图中示出了实施例的各种方面，但是除非特别指出，不必按比例绘制附图。
在这里专用的词“示例性”意为“用作例子、实施例或说明性”。这里作为“示例性”所说明的任何实施例不必解释为优于或好于其它实施例。
本文中术语“和/或”，仅仅是一种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。另外，本文中术语“至少一种”表示多种中的任意一种或多种中的至少两种的任意组合，例如，包括A、B、C中的至少一种，可以表示包括从A、B和C构成的集合中选择的任意一个或多个元素。
另外，为了更好的说明本公开实施例，在下文的具体实施方式中给出了众多的具体 细节。本领域技术人员应当理解，没有某些具体细节，本公开同样可以实施。在一些实例中，对于本领域技术人员熟知的方法、手段、元件和电路未作详细描述，以便于凸显本公开实施例的主旨。
图1示出根据本公开实施例的违规事件检测方法的流程图，如图1所示，所述方法包括：
在步骤S11中，根据预设的检测模式，对待处理视频流的待处理视频帧进行行为检测处理，获得所述待处理视频流的行为检测结果；
在步骤S12中，在所述待处理视频流的行为检测结果为违规行为的情况下，根据预设的警告模式以及所述行为检测结果，生成警告信息。
根据本公开实施例的违规事件检测方法，可根据预设的检测模式对待处理视频帧进行检测，获得待处理视频流的检测结果，并可根据预设的警告模式生成警告信息，从而可以实现自动实时检测并告警违规事件，减少人力成本，提高违规事件的检测和警告效率。
在一种可能的实现方式中，所述违规事件检测方法可以由终端设备或其它处理设备执行，其中，终端设备可以为用户设备(User Equipment，UE)、移动设备、用户终端、终端、蜂窝电话、无绳电话、个人数字处理(Personal Digital Assistant，PDA)、手持设备、计算设备、车载设备、可穿戴设备等。其它处理设备可为服务器或云端服务器等。在一些可能的实现方式中，该违规事件检测方法可以通过处理器调用存储器中存储的计算机可读指令的方式来实现。
在一种可能的实现方式中，所述违规事件检测方法可用于对监控视频(待处理视频流)中的目标对象的行为(例如，违规操作行为、违规穿戴行为等)或违规的目标对象(例如，非法进入的人员、进入厨房的老鼠等)进行检测，并对违规事件进行警告，以减少违规事件的发生，提高监管效率。在示例中，所述违规事件检测方法可用于对厨房、食堂、食品加工厂、餐饮企业等场所的监控视频中的目标对象进行行为检测处理，以对工作人员的违规行为进行警告，从而提供从业人员的自觉性，提升食品安全和食品质量。
在一种可能的实现方式中，所述违规事件检测方法可通过前端检测设备来执行，可通过后端服务设备对前端检测设备的检测模式和警告模式进行设置。例如，可通过后端服务设备发送的指令来设置前端检测设备的检测模式和警告模式。或者，也可直接对前端检测设备的检测模式和警告模式进行设置。例如，可提供用于设置前端检测设备的检测模式和警告模式的指令接收装置(例如，按钮、触摸屏、遥控器等)，或者将预设的模式固化在前端检测设备中。本公开对检测模式和警告模式的设置方式不做限制。
在一些可选示例中，所述预设的检测模式可包括第一检测模式和/或第二检测模式，第一检测模式例如可包括如下检测策略：首次在待处理视频帧检测到违规事件后，可不立即确定违规事件，而是继续对后续的多个待处理视频帧进行检测处理，在上述多个待处理视频帧中多次确定违规事件后，可将待检测视频流的检测结果确定为违规事件，可 减少违规事件的误报。第二检测模式例如可可包括如下检测策略：在检测到违规事件后立即生成待处理视频流的行为检测结果，无需对后续的待处理视频帧进行多次确认。
在一些可选示例中，所述预设的警告模式可包括第一警告模式和/或第二警告模式，第一警告模式例如可包括如下警告策略：在首次检测到违规事件后，生成警告信息，并在预设时间段内不再生成相同违规事件的警告信息，避免对相同违规事件的重复警告。第二警告模式例如可包括如下警告策略：每次检测到违规事件均生成警告信息。
在一种可能的实现方式中，在检测模式和警告模式设置完成后，前端检测设备可按照预设的检测模式对待处理视频流的待处理视频帧进行检测，如果检测结果为违规事件，前端检测设备可按照预设的警告模式生成警告信息。
在一种可能的实现方式中，在步骤S11中，前端检测设备可按照预设的检测模式对待处理视频流的待处理视频帧进行检测。在一些可选示例中，前端检测设备可对待处理视频流的各视频帧进行逐帧检测，或者也可首先对待处理视频流进行抽帧处理，并对抽取的视频帧进行检测。
在一种可能的实现方式中，所述方法还包括：根据预设频率对待处理视频流进行抽帧处理，获得待处理视频帧。在一些可选示例中，前端检测设备可对待处理视频流进行抽帧处理，例如，可每隔3秒钟抽取一个视频帧，即，每隔3秒获取一个待处理视频帧。在一些可选示例中，预设频率可根据检测模式适应性调整，也可根据检测的违规事件的类型进行适应性调整。例如，在第一检测模式下的预设频率可低于第二检测模式下的预设频率。检测视频清晰度的预设频率可低于检测违规行为的预设频率。本公开实施例对预设频率不做限制。
在一种可能的实现方式中，前端检测设备可根据预设的检测模式对待处理视频帧进行检测处理。例如，在第一检测模式下，前端检测设备首次在待处理视频帧检测到违规事件后，可不立即确定违规事件，而是继续对后续的多个待处理视频帧进行检测处理，即，在多个待处理视频帧中多次确定违规事件后，可将待检测视频流的检测结果确定为违规事件，可减少违规事件的误报。例如，在食堂、厨房等场景中，违规事件可包括工作人员未戴帽子、未戴口罩、赤膊、吸烟等，多次确认后再确认违规事件的检测模式(即，第一检测模式)可减少工作人员偶然摘下口罩或帽子等动作(例如，擦汗)而发生的误报。
在一种可能的实现方式中，步骤S11可包括：在所述检测模式设置为第一检测模式的情况下，对当前时刻抽取的待处理视频帧进行检测处理，获得当前时刻的第一检测结果；在所述第一检测结果为第一违规事件的情况下，对第一预设时间段内抽取的多个待处理视频帧进行检测处理，分别获得所述多个待处理视频帧的第二检测结果，其中，所述第一预设时间段为以所述当前时刻为起始时刻的时间段，所述第一违规事件为任意一种违规事件；在所述第二检测结果为第一违规事件的待处理视频帧的数量大于或等于预设数量阈值的情况下，将所述待处理视频流的检测结果确定为第一违规事件。
在一种可能的实现方式中，可通过后端服务设备将前端应用设备的检测模式设置为第一检测模式，或者可直接在前端应用设备处将检测模式设置为第一检测模式。前端应用设备可在第一检测模式下对待处理视频帧进行检测处理。在一些可选示例中，前端应用设备可逐一检测按照预设频率(例如，3秒/次)从待处理视频流中抽取的待处理视频帧，并获得每个待处理视频帧的检测结果，例如，前端应用设备可对当前时刻t抽取的待处理视频帧进行检测处理，获得当前时刻t的第一检测结果。
在一些可选示例中，前端检测设备检测到当前时刻t的第一检测结果为第一违规事件(即，当前时刻t抽取的待处理视频帧中的目标对象可能正在进行违规行为)，但由于可能存在误检测的情况(例如，工作人员偶然摘下口罩或帽子等动作(例如，擦汗)而被检测到，不属于真正的违规行为)，前端检测设备可对当前时刻t之后的多个视频帧进行检测处理，以对违规事件进行多次确定。
在一种可能的实现方式中，可对第一预设时间段内抽取的多个待处理视频帧进行检测处理，分别获得所述多个待处理视频帧的第二检测结果。在一些可选示例中，第一预设时间段为以当前时刻t为起始时刻的时间段，例如，从当前时刻t至t+A时间段(时长为A)，在第一预设时间段内，可对待处理视频流进行多次抽帧，获得多个待处理视频帧。例如，时长A为5分钟，抽帧的预设频率为3秒/次，则在第一预设时间段内可抽取100个视频帧。前端检测设备可对该100个待处理视频帧逐一进行检测处理，并获得该100个待处理视频帧的第二检测结果。
在一种可能的实现方式中，可对第一预设时间段内抽取的待处理视频帧的第二检测结果进行统计，以确定第二检测结果为第一违规事件的待处理视频帧的数量；如果该数量大于预设数量阈值，则可确认违规事件，通过对多个待处理视频帧的确认工作，可降低对第一违规事件误检测的概率。在一些可选示例中，如果在上述100个待处理视频帧中，检测结果为第一违规事件的数量大于或等于50个(预设数量阈值)，则可确认违规事件，本公开实施例对预设数量阈值不做限制。
在一些可选示例中，也可不设置时间阈值，可从下一次抽帧开始，连续抽取预设数量的待处理视频帧。例如，可抽取100个待处理视频帧，并确定这些待处理视频帧中第二检测结果为第一违规事件的数量，如果该数量大于或等于预设数量阈值，则可确定第一违规事件。本公开实施例对抽取待处理视频帧的数量不做限制。
通过这种方式，可在首次检测到第一违规事件的待处理视频帧后，对后续的待处理视频帧进行多次确认，以降低误检测的概率。
在一种可能的实现方式中，步骤S11可包括：在所述检测模式设置为第二检测模式的情况下，对当前时刻抽取的待处理视频帧进行检测处理，获得所述待处理视频流的检测结果。
在一种可能的实现方式中，可通过后端服务设备将前端应用设备的检测模式设置为第二检测模式，或者可直接在前端应用设备处将检测模式设置为第二检测模式。前端应 用设备可在第二检测模式下对待处理视频帧进行检测处理。
在一些可选示例中，前端检测设备可在检测到违规事件后立即生成待处理视频流的行为检测结果。例如，在对待处理视频帧进行检测时，如果检测到某个待处理视频帧中的目标对象正在进行违规行为，则可立即确认待处理视频流中的目标对象正在进行违规行为，即，将待处理视频流的检测结果确认为违规事件，无需对后续的待处理视频帧进行多次确认，可提高检测的灵敏度。
在一种可能的实现方式中，在对待处理视频帧进行行为检测时，前端检测设备可检测预设的一种或多种违规事件。在一些可选示例中，可对违规事件进行设置。例如，如果前端检测设备用于检测公共场所(例如，商场、学校、办公厅、写字楼等)的监控视频的待处理视频帧，则可将违规事件设置为吸烟、玩手机等。如果前端检测设备用于检测餐饮场所(例如，餐厅、厨房、食堂、食品加工厂等)或医疗卫生场所(例如，医院、药房、化验室、手术室等)的监控视频的待处理视频帧，则可将违规事件设置为未戴帽子、未戴口罩、未戴手套、赤膊、等违规穿戴行为，以及害虫、老鼠等卫生违规事件等。本公开实施例对违规行为的类型不做限制。
在一种可能的实现方式中，前端检测设备可对针对各种违规事件使用不同的行为检测方法进行检测。本公开实施例上述对待处理视频流的待处理视频帧进行检测处理，获得所述待处理视频流的检测结果，包括：在所述待处理视频帧中确定目标对象的人脸区域和/或人体区域；对所述人脸区域和/或人体区域进行行为检测处理，获得所述行为检测结果。
在一种可能的实现方式中，前端检测设备可使用卷积神经网络等方法检测待处理视频帧中的目标对象的人脸区域和/或人体区域，从而可对人脸区域和/或人体区域进行行为检测处理。在一些可选示例中，可检测目标对象的人脸区域，从而检测目标对象是否戴帽子或戴口罩。
在一些可选示例中，可在检测到目标对象的人脸区域和/或人体区域，从而可检测目标对象穿着是否合规。例如，工作人员是否赤膊、是否穿工作服等。在一些可选示例中，可检测到目标对象的人体区域，并根据人体区域中目标对象的动作以及人体区域中有无烟雾等判断条件来判断目标对象是否吸烟，进一步地，可检测到该目标对象的人脸区域，以确定该目标对象的身份信息。本公开实施例对行为检测的方法不做限制。
在一种可能的实现方式中，前端检测设备可使用多个时刻抽取的待处理视频帧来检测有无老鼠或害虫等影响卫生条件的违规事件。本公开实施例上述对待处理视频流的待处理视频帧进行行为检测处理，获得所述待处理视频流的行为检测结果，包括：对多个时刻抽取的待处理视频帧进行运动检测处理，获得运动的目标对象所在区域；对所述运动的目标对象所在区域进行检测处理，获得所述检测结果。
在一些可选示例中，前端检测设备可在光线条件较差(例如，夜间)的情况下，通过比对多个待处理视频帧中的目标对象，来判断待处理视频帧中是否包括老鼠、害虫等 目标对象。例如，在夜间，厨房中无工作人员，其他物品静止不动，如果在某个视频帧中检测到某一目标对象，而另一个视频帧中没有该目标对象，则该目标对象可能是老鼠、害虫等正在运动的目标对象，可在光线条件较差的情况下，或者在可见光摄像头或红外光摄像头的硬件条件下，提高检测运动的目标对象的精度。进一步地，可对目标对象所在区域进行进一步地检测处理，以确定目标对象是否为违规的目标对象。例如，可将老鼠设置为违规的目标对象，而对摄像头拍摄到的窗外飞过的鸟类等设置为不违规的目标对象。在检测到违规的目标对象时，可将检测结果确定为违规事件。
在一种可能的实现方式中，前端检测设备可使用多个时刻抽取的待处理视频帧来检测待处理视频的清晰度，例如，摄像头被油污、灰尘等污染造成的模糊，或者由于焦距调整造成的成像模糊等。本公开实施例上述对待处理视频流的待处理视频帧进行检测处理，获得所述待处理视频流的检测结果，包括：对待处理视频帧的清晰度进行检测处理，获得所述检测结果。
在一些可选示例中，可检测抽取的待处理视频帧的清晰度。例如，可检测纹理清晰度等指标，如果待处理视频帧的该指标低于指标阈值，或者在第一预设时间段内多个待处理视频帧的该指标低于指标阈值，则可确定检测结果为违规事件，即，摄像头被污染或焦距调整失误等。
在一种可能的实现方式中，违规事件还可包括多种事件。例如，学生在课堂上交头接耳，在考场中作弊等违规事件，本公开实施例对违规事件的类型不作限制。
在一种可能的实现方式中，上述行为检测处理可并行执行，并且可有选择地执行其中的一种或多种检测处理。例如，在对厨房的监控视频进行行为检测处理时，可并行执行检测目标对象是否未戴帽子、未戴口罩、未戴手套、赤膊、等违规穿戴行为的行为检测处理，以及检测害虫、老鼠等卫生违规事件的检测处理，各种检测处理之间互不干扰。也可按照需要设置执行的检测处理，例如，在白天可不需要执行检测害虫、老鼠等卫生违规行为的事件检测处理，则可暂时关闭该种检测处理。本公开实施例对检测处理的类型不做限制。
在一种可能的实现方式中，在检测到待处理视频流中的违规事件时，可根据预设的警告模式，生成与违规事件对应的警告信息。在一些示例中，可通过后端服务设备设置警告模式，也可在前端检测设备处直接设置，本公开实施例对警告模式的设置方式不做限制。
在一种可能的实现方式中，为了避免针对同一种违规事件进行重复警告，可将前端检测设备设置为第一检测模式，步骤S12可包括：在所述警告模式设置为第一警告模式的情况下，根据与第二违规事件对应的第一个检测结果，生成与所述第二违规事件对应的警告信息，并在第二预设时间段内屏蔽与所述第二违规事件对应的警告信息，其中，所述第二违规事件为任意一种违规事件。
在一些可选示例中，第二预设时间段可以是以首次检测到针对第二违规事件的时刻 t1为起始时刻的时间段(例如，以t1为起始时刻，时长为30分钟的时间段，本公开实施例对第二预设时间段的时长不做限制)。警告模式可设置为第一警告模式，如果在该警告模式下检测到第二违规事件，则在第二预设时间段内仅会针对第二违规事件生成一次警告信息，如果在第二预设时间段内，重复检测到多次第二违规事件，则可屏蔽重复的警告信息，仅针对第二违规事件警告一次。在第二预设时间段结束后，如果再次检测到第二违规事件，则可再次生成警告信息，并再次开始第二预设时间段，以此类推。
通过这种方式，可在第二时间段内屏蔽重复的警告信息，减少警告信息冗余，提高报警效率。
在一种可能的实现方式中，也可不屏蔽针对相同违规事件的警告信息。步骤S12可包括：在所述警告模式设置为第二警告模式的情况下，根据与第二违规事件对应的检测结果，生成与所述第二违规事件对应的警告信息，其中，所述第二违规事件为任意一种违规事件。
在一些可选示例中，在第二警告模式下，只要检测到违规事件，即可针对该违规事件生成警告信息，不论该警告信息是否与之前的警告信息重复。可提升警告的力度，督促违规人员尽快纠正违规事件。
在一种可能的实现方式中，前端检测设备还可自定义生成哪些警告信息。例如，前端检测设备进行了检测未戴帽子、未戴口罩、未戴手套、赤膊、等违规穿戴行为的行为检测处理，但前端检测设备可选择性地生成其中的一种或多种违规事件的警告信息。例如，前端检测设备检测到目标对象未戴帽子、未戴口罩、未戴手套，但在生成警告信息时，可仅生成未戴口罩的警告信息。本公开实施例对违规事件不做限制。
在一种可能的实现方式中，所述前端检测设备还可将警告信息进行展示，或发送至后端服务模块，以通过后端服务模块展示警告信息。例如，前端检测设备可与显示设备或音响设备等进行连接，警告信息可发送至显示设备，通过用户接口(User Interface，UI)展示界面进行展示，或者发送至音响设备，以播放与警告信息对应的声音信息。或者，前端检测设备可将警告信息发送至后端服务模块，并由后端服务模块来展示警告信息，例如，后端服务模块可通过UI展示界面或音响设备展示警告信息。本公开实施例对警告信息的展示方式不做限制。
根据本公开实施例的违规事件检测方法，可根据预设的检测模式对待处理视频帧进行检测，在首次检测到第一违规事件的待处理视频帧后，对后续的待处理视频帧进行多次确认，可提高检测的准确率，降低误检的概率，并可根据预设的警告模式生成警告信息，在第二时间段内屏蔽重复的警告信息，减少警告信息冗余，提高报警效率。
图2示出根据本公开的实施例的违规事件检测方法的应用示意图一，如图2所示，监控摄像头可采集餐饮场所(例如，餐厅、厨房、食堂、食品加工厂等)或医疗卫生场所(例如，医院、药房、化验室、手术室等)的监控视频。前端检测设备可在7:00-23:00之间检测视频中的工作人员是否存在违规行为。可对该视频进行抽帧，例如，抽帧频率 可以是3秒/次，并对抽取的待处理视频帧进行检测处理。
在一种可能的实现方式中，可通过前端检测设备对未戴帽子、未戴口罩、赤膊等穿戴违规行为进行检测处理，并关闭对老鼠等夜间活动物的事件检测处理。如果检测到违规事件，还可选择性地生成警告信息。例如，仅对未戴口罩的违规行为生成警告信息，对未戴帽子和赤膊的违规行为可不生成警告信息。
图3示出根据本公开的实施例的违规事件检测方法的应用示意图二，如图3所示，可将前端检测设备的检测模式设置为第一检测模式，并将前端检测设备的警告模式设置为第一警告模式。
在一种可能的实现方式中，前端检测设备可在7:00-23:00之间，对抽取的待处理视频帧进行检测，检测工作人员是否存在未戴帽子、未戴口罩、赤膊等穿戴违规行为，如果在时刻t首次在待处理视频帧中检测到上述违规行为，为了减低误报的概率，可在第一预设时间段内(例如，从时刻t开始的5分钟内)对抽取的100个视频帧分别进行检测处理，如果检测到相同违规行为的待处理视频帧的数量小于预设数量阈值(例如，60个)，则可认为工作人员未进行该违规行为，反之，如果检测到相同违规行为的待处理视频帧的数量大于或等于预设数量阈值(例如，60个)，则可认为工作人员进行了该违规行为，并在第一预设时间段结束时，生成与该违规行为对应的警告信息。例如，可生成与未戴口罩相关的警告信息。
在一种可能的实现方式中，为减少针对相同的违规事件进行重复警告，在生成与未戴口罩对应的警告信息时，可开始第二预设时间段(例如，30分钟)，可在第二预设时间段内，屏蔽相同的警告信息，例如，如果再次检测到同一个工作人员未戴口罩，则可屏蔽警告信息，在30分钟之内不再重复警告。如果该工作人员进行其他违规行为，或者其他工作人员未戴口罩或进行其他违规行为，仍可生成警告信息。在30分钟的第二预设时间段结束后，如果该工作人员仍未戴口罩，则可再次生成警告信息。
图4示出根据本公开的实施例的违规事件检测方法的应用示意图三，如图4所示，后端服务设备可设置多个前端检测设备的检测模式和警告模式，前端检测设备可对多个摄像头采集的视频流进行违规事件检测处理。例如，后端服务设备可包括公有云平台，可通过路由器/网关调用公有云服务对前端检测设备进行设置。
图5示出根据本公开的实施例的违规事件检测方法的应用示意图四，如图5所示，后端服务设备可包括客户应用管理平台，客户应用管理平台可通过应用程序接口(Application Program Interface，API)设置前端检测设备的检测模式和警告模式，还可设置抽帧频率等参数。本公开对前端检测设备的设置方式不做限制。
在一种可能的实现方式中，所述违规事件检测方法可用于学校食堂的违规行为检测中，可通过所述行为检测方法实现对食堂、厨房等地的卫生状况不间断监测，保障师生饮食安全。或者，所述违规事件检测方法可用于餐饮企业的违规事件检测中，餐饮企业的厨房下水道是鼠害的重灾区，企业常常因为老鼠问题导致客源下降，所述违规事件检 测方法可极大提升在可见光或红外光线下老鼠的检测与识别的精度，并可对工作人员所在的厨房区域违规事件检测，提高卫生状况。或者，所述违规事件检测方法可用于食品加工厂的违规行为检测中，食品加工厂劳动强度大，工作人员会出现因为擦汗而摘掉帽子或者口罩等短暂行为而导致错误警报，所述违规事件检测方法可有效减少误报，提高警告效率。此外，所述违规事件检测方法还可用于医院、药房、制药厂等卫生要求较高的场所，或者用于写字楼、工厂、学校等场所，以检测工作人员或学生是否存在玩手机等违规行为，或检测学生是否进行考试作弊等违规行为。本公开实施例对所述违规事件检测方法的应用领域不做限制。
可以理解，本公开提及的上述各个方法实施例，在不违背原理逻辑的情况下，均可以彼此相互结合形成结合后的实施例，限于篇幅，本公开实施例不再赘述。
此外，本公开实施例还提供了违规事件检测装置、电子设备、计算机可读存储介质、程序，上述均可用来实现本公开实施例提供的任一种违规事件检测方法，相应技术方案和描述和参见方法部分的相应记载，本实施例不再赘述。
本领域技术人员可以理解，在具体实施方式的上述方法中，各步骤的撰写顺序并不意味着严格的执行顺序而对实施过程构成任何限定，各步骤的具体执行顺序应当以其功能和可能的内在逻辑确定。
图6示出根据本公开的实施例的违规事件检测装置的框图，所述装置包括：第一获得模块11，配置为根据预设的检测模式，对待处理视频流的待处理视频帧进行检测处理，获得所述待处理视频流的检测结果；生成模块12，配置为在所述待处理视频流的检测结果为违规事件的情况下，根据预设的警告模式以及所述检测结果，生成警告信息。
在一种可能的实施例中，所述第一获得模块11，配置为在所述检测模式设置为第一检测模式的情况下，对当前时刻抽取的待处理视频帧进行检测处理，获得当前时刻的第一检测结果；在所述第一检测结果为第一违规事件的情况下，对第一预设时间段内抽取的多个待处理视频帧进行检测处理，分别获得所述多个待处理视频帧的第二检测结果，其中，所述第一预设时间段为以所述当前时刻为起始时刻的时间段，所述第一违规事件为任意一种违规事件；在所述第二检测结果为第一违规事件的待处理视频帧的数量大于或等于预设数量阈值的情况下，将所述待处理视频流的检测结果确定为第一违规事件。
在一种可能的实施例中，所述第一获得模块11，配置为在所述检测模式设置为第二检测模式的情况下，对当前时刻抽取的待处理视频帧进行检测处理，获得所述待处理视频流的检测结果。
在一种可能的实施例中，所述第一获得模块11，配置为在所述待处理视频帧中确定目标对象的人脸区域和/或人体区域；对所述人脸区域和/或人体区域进行行为检测处理，获得所述检测结果。
在一种可能的实施例中，所述第一获得模块11，配置为对多个时刻抽取的待处理视频帧进行运动检测处理，获得运动的目标对象所在区域；对所述运动的目标对象所在区 域进行检测处理，获得所述检测结果。
在一种可能的实施例中，所述第一获得模块11，配置为对待处理视频帧的清晰度进行检测处理，获得所述检测结果。
在一种可能的实施例中，所述生成模块12，配置为在所述警告模式设置为第一警告模式的情况下，根据与第二违规事件对应的第一个检测结果，生成与所述第二违规事件对应的警告信息，并在第二预设时间段内屏蔽与所述第二违规事件对应的警告信息，其中，所述第二违规事件为任意一种违规事件。
在一种可能的实施例中，所述生成模块12，配置为在所述警告模式设置为第二警告模式的情况下，根据与第二违规事件的对应的检测结果，生成与所述第二违规事件对应的警告信息，其中，所述第二违规事件为任意一种违规事件。
在一种可能的实施例中，所述装置还包括：第二获得模块，配置为根据预设频率对待处理视频流进行抽帧处理，获得待处理视频帧。
在一些实施例中，本公开实施例提供的装置具有的功能或包含的模块可以用于执行上文方法实施例描述的方法，其具体实现可以参照上文方法实施例的描述，为了简洁，这里不再赘述
本公开实施例还提出一种计算机可读存储介质，其上存储有计算机程序指令，所述计算机程序指令被处理器执行时实现上述方法。计算机可读存储介质可以是非易失性或易失性计算机可读存储介质。
本公开实施例还提出一种电子设备，包括：处理器；用于存储处理器可执行指令的存储器；其中，所述处理器被配置为上述方法。
电子设备可以被提供为终端、服务器或其它形态的设备。
图7是根据一示例性实施例示出的一种电子设备800的框图。例如，电子设备800可以是移动电话、计算机、数字广播终端、消息收发设备、游戏控制台、平板设备、医疗设备、健身设备、个人数字助理等终端。
参照图7，电子设备800可以包括以下一个或多个组件：处理组件802、存储器804、电源组件806、多媒体组件808、音频组件810、输入/输出(I/O)的接口812、传感器组件814以及通信组件816。
处理组件802通常控制电子设备800的整体操作，诸如与显示、电话呼叫、数据通信、相机操作和记录操作相关联的操作。处理组件802可以包括一个或多个处理器820来执行指令，以完成上述的方法的全部或部分步骤。此外，处理组件802可以包括一个或多个模块，便于处理组件802和其他组件之间的交互。例如，处理组件802可以包括多媒体模块，以方便多媒体组件808和处理组件802之间的交互。
存储器804被配置为存储各种类型的数据以支持在电子设备800的操作。这些数据的示例包括用于在电子设备800上操作的任何应用程序或方法的指令、联系人数据、电话簿数据、消息、图片、视频等。存储器804可以由任何类型的易失性或非易失性存储 设备或者它们的组合实现，如静态随机存取存储器(Static Random Access Memory，SRAM)，电可擦除可编程只读存储器(Electrically Erasable Programmable Read-Only Memory，EEPROM)，可擦除可编程只读存储器(Erasable Programmable Read-Only Memory，EPROM)，可编程只读存储器(Programmable Read-Only Memory，PROM)，只读存储器(Read Only Memory，ROM)，磁存储器，快闪存储器，磁盘或光盘。
电源组件806为电子设备800的各种组件提供电力。电源组件806可以包括电源管理系统、一个或多个电源、及其他与为电子设备800生成、管理和分配电力相关联的组件。
多媒体组件808包括在所述电子设备800和用户之间的提供一个输出接口的屏幕。在一些实施例中，屏幕可以包括液晶显示器(Liquid Crystal Display，LCD)和触摸面板(Touch Panel，TP)。如果屏幕包括触摸面板，屏幕可以被实现为触摸屏，以接收来自用户的输入信号。触摸面板包括一个或多个触摸传感器以感测触摸、滑动和触摸面板上的手势。所述触摸传感器可以不仅感测触摸或滑动动作的边界，而且还检测与所述触摸或滑动操作相关的持续时间和压力。在一些实施例中，多媒体组件808包括一个前置摄像头和/或后置摄像头。当电子设备800处于操作模式，如拍摄模式或视频模式时，前置摄像头和/或后置摄像头可以接收外部的多媒体数据。每个前置摄像头和后置摄像头可以是一个固定的光学透镜系统或具有焦距和光学变焦能力。
音频组件810被配置为输出和/或输入音频信号。例如，音频组件810包括一个麦克风(Microphone，MIC)，当电子设备800处于操作模式，如呼叫模式、记录模式和语音识别模式时，麦克风被配置为接收外部音频信号。所接收的音频信号可以被进一步存储在存储器804或经由通信组件816发送。在一些实施例中，音频组件810还包括一个扬声器，用于输出音频信号。
I/O接口812为处理组件802和外围接口模块之间提供接口，上述外围接口模块可以是键盘、点击轮、按钮等。这些按钮可包括但不限于：主页按钮、音量按钮、启动按钮和锁定按钮。
传感器组件814包括一个或多个传感器，用于为电子设备800提供各个方面的状态评估。例如，传感器组件814可以检测到电子设备800的打开/关闭状态、组件的相对定位，例如所述组件为电子设备800的显示器和小键盘，传感器组件814还可以检测电子设备800或电子设备800一个组件的位置改变，用户与电子设备800接触的存在或不存在，电子设备800方位或加速/减速和电子设备800的温度变化。传感器组件814可以包括接近传感器，被配置用来在没有任何的物理接触时检测附近物体的存在。传感器组件814还可以包括光传感器，如金属氧化物半导体元件(Complementary Metal-Oxide Semiconductor，CMOS)或电荷耦合元件(Charge Coupled Device，CCD)图像传感器，用于在成像应用中使用。在一些实施例中，该传感器组件814还可以包括加速度传感器、陀螺仪传感器、磁传感器、压力传感器或温度传感器。
通信组件816被配置为便于电子设备800和其他设备之间有线或无线方式的通信。电子设备800可以接入基于通信标准的无线网络，如WiFi，2G或3G，或它们的组合。在一个示例性实施例中，通信组件816经由广播信道接收来自外部广播管理系统的广播信号或广播相关信息。在一个示例性实施例中，所述通信组件816还包括近场通信(Near Field Communication，NFC)模块，以促进短程通信。例如，在NFC模块可基于射频识别(Radio Frequency Identification，RFID)技术，红外数据协会(Infrared Data Association，IrDA)技术，超宽带(Ultra WideBand，UWB)技术，蓝牙(BlueTooth，BT)技术和其他技术来实现。
在示例性实施例中，电子设备800可以被一个或多个应用专用集成电路(Application Specific Integrated Circuit，ASIC)、数字信号处理器(Digital Signal Processor，DSP)、数字信号处理设备(DSPD)、可编程逻辑器件(Programmable Logic Device，PLD)、现场可编程门阵列(Field-Programmable Gate Array，FPGA)、控制器、微控制器、微处理器或其他电子元件实现，用于执行上述方法。
在示例性实施例中，还提供了一种非易失性计算机可读存储介质，例如包括计算机程序指令的存储器804，上述计算机程序指令可由电子设备800的处理器820执行以完成上述方法。
图8是根据一示例性实施例示出的一种电子设备1900的框图。例如，电子设备1900可以被提供为一服务器。参照图8，电子设备1900包括处理组件1922，其进一步包括一个或多个处理器，以及由存储器1932所代表的存储器资源，用于存储可由处理组件1922的执行的指令，例如应用程序。存储器1932中存储的应用程序可以包括一个或一个以上的每一个对应于一组指令的模块。此外，处理组件1922被配置为执行指令，以执行上述方法。
电子设备1900还可以包括一个电源组件1926被配置为执行电子设备1900的电源管理，一个有线或无线网络接口1950被配置为将电子设备1900连接到网络，和一个输入输出(I/O)接口1958。电子设备1900可以操作基于存储在存储器1932的操作系统，例如Windows ServerTM，Mac OS XTM，UnixTM,LinuxTM，FreeBSDTM或类似。
在示例性实施例中，还提供了一种非易失性计算机可读存储介质，例如包括计算机程序指令的存储器1932，上述计算机程序指令可由电子设备1900的处理组件1922执行以完成上述方法。
在示例性实施例中，还提供了一种计算机程序，包括计算机可读代码，当所述计算机可读代码在电子设备中运行时，所述电子设备中的处理器执行用于实现本公开实施例所述的违规事件检测方法。
本公开可以是系统、方法和/或计算机程序产品。计算机程序产品可以包括计算机可读存储介质，其上载有用于使处理器实现本公开的各个方面的计算机可读程序指令。
计算机可读存储介质可以是可以保持和存储由指令执行设备使用的指令的有形设 备。计算机可读存储介质例如可以是――但不限于――电存储设备、磁存储设备、光存储设备、电磁存储设备、半导体存储设备或者上述的任意合适的组合。计算机可读存储介质的更具体的例子(非穷举的列表)包括：便携式计算机盘、硬盘、随机存取存储器(Random Access Memory，RAM)、只读存储器(Read Only Memory，ROM)、可擦式可编程只读存储器(EPROM或闪存)、静态随机存取存储器(Static Random Access Memory，SRAM)、便携式压缩盘只读存储器(Compact Disc Read-Only Memory，CD-ROM)、数字多功能盘(DVD)、记忆棒、软盘、机械编码设备、例如其上存储有指令的打孔卡或凹槽内凸起结构、以及上述的任意合适的组合。这里所使用的计算机可读存储介质不被解释为瞬时信号本身，诸如无线电波或者其他自由传播的电磁波、通过波导或其他传输媒介传播的电磁波(例如，通过光纤电缆的光脉冲)、或者通过电线传输的电信号。
这里所描述的计算机可读程序指令可以从计算机可读存储介质下载到各个计算/处理设备，或者通过网络、例如因特网、局域网、广域网和/或无线网下载到外部计算机或外部存储设备。网络可以包括铜传输电缆、光纤传输、无线传输、路由器、防火墙、交换机、网关计算机和/或边缘服务器。每个计算/处理设备中的网络适配卡或者网络接口从网络接收计算机可读程序指令，并转发该计算机可读程序指令，以供存储在各个计算/处理设备中的计算机可读存储介质中。
用于执行本公开操作的计算机程序指令可以是汇编指令、指令集架构(ISA)指令、机器指令、机器相关指令、微代码、固件指令、状态设置数据、或者以一种或多种编程语言的任意组合编写的源代码或目标代码，所述编程语言包括面向对象的编程语言—诸如Smalltalk、C++等，以及常规的过程式编程语言—诸如“C”语言或类似的编程语言。计算机可读程序指令可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络—包括局域网(LAN)或广域网(WAN)—连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。在一些实施例中，通过利用计算机可读程序指令的状态信息来个性化定制电子电路，例如可编程逻辑电路、现场可编程门阵列(FPGA)或可编程逻辑阵列(PLA)，该电子电路可以执行计算机可读程序指令，从而实现本公开的各个方面。
这里参照根据本公开实施例的方法、装置(系统)和计算机程序产品的流程图和/或框图描述了本公开的各个方面。应当理解，流程图和/或框图的每个方框以及流程图和/或框图中各方框的组合，都可以由计算机可读程序指令实现。
这些计算机可读程序指令可以提供给通用计算机、专用计算机或其它可编程数据处理装置的处理器，从而生产出一种机器，使得这些指令在通过计算机或其它可编程数据处理装置的处理器执行时，产生了实现流程图和/或框图中的一个或多个方框中规定的功 能/动作的装置。也可以把这些计算机可读程序指令存储在计算机可读存储介质中，这些指令使得计算机、可编程数据处理装置和/或其他设备以特定方式工作，从而，存储有指令的计算机可读介质则包括一个制造品，其包括实现流程图和/或框图中的一个或多个方框中规定的功能/动作的各个方面的指令。
也可以把计算机可读程序指令加载到计算机、其它可编程数据处理装置、或其它设备上，使得在计算机、其它可编程数据处理装置或其它设备上执行一系列操作步骤，以产生计算机实现的过程，从而使得在计算机、其它可编程数据处理装置、或其它设备上执行的指令实现流程图和/或框图中的一个或多个方框中规定的功能/动作。
附图中的流程图和框图显示了根据本公开的多个实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段或指令的一部分，所述模块、程序段或指令的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个连续的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或动作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
以上已经描述了本公开的各实施例，上述说明是示例性的，并非穷尽性的，并且也不限于所披露的各实施例。在不偏离所说明的各实施例的范围和精神的情况下，对于本技术领域的普通技术人员来说许多修改和变更都是显而易见的。本文中所用术语的选择，旨在最好地解释各实施例的原理、实际应用或对市场中的技术的技术改进，或者使本技术领域的其它普通技术人员能理解本文披露的各实施例。

Claims (21)

  1. 一种违规事件检测方法，所述方法包括：
    根据预设的检测模式，对待处理视频流的待处理视频帧进行检测处理，获得所述待处理视频流的检测结果；
    在所述待处理视频流的检测结果为违规事件的情况下，根据预设的警告模式以及所述检测结果，生成警告信息。
  2. 根据权利要求1所述的方法，其中，所述根据预设的检测模式，对待处理视频流的待处理视频帧进行检测处理，获得所述待处理视频流的检测结果，包括：
    在所述检测模式设置为第一检测模式的情况下，对当前时刻抽取的待处理视频帧进行检测处理，获得当前时刻的第一检测结果；
    在所述第一检测结果为第一违规事件的情况下，对第一预设时间段内抽取的多个待处理视频帧进行检测处理，分别获得所述多个待处理视频帧的第二检测结果，其中，所述第一预设时间段为以所述当前时刻为起始时刻的时间段，所述第一违规事件为任意一种违规事件；
    在所述第二检测结果为第一违规事件的待处理视频帧的数量大于或等于预设数量阈值的情况下，将所述待处理视频流的检测结果确定为第一违规事件。
  3. 根据权利要求1所述的方法，其中，所述根据预设的检测模式，对待处理视频流的待处理视频帧进行检测处理，获得所述待处理视频流的检测结果，包括：
    在所述检测模式设置为第二检测模式的情况下，对当前时刻抽取的待处理视频帧进行检测处理，获得所述待处理视频流的检测结果。
  4. 根据权利要求1-3中任一项所述的方法，其中，所述对待处理视频流的待处理视频帧进行检测处理，获得所述待处理视频流的检测结果，包括：
    在所述待处理视频帧中确定目标对象的人脸区域和/或人体区域；
    对所述人脸区域和/或人体区域进行行为检测处理，获得所述检测结果。
  5. 根据权利要求1-3中任一项所述的方法，其中，所述对待处理视频流的待处理视频帧进行检测处理，获得所述待处理视频流的检测结果，包括：
    对多个时刻抽取的待处理视频帧进行运动检测处理，获得运动的目标对象所在区域；
    对所述运动的目标对象所在区域进行检测处理，获得所述检测结果。
  6. 根据权利要求1-3任一项所述的方法，其中，所述对待处理视频流的待处理视频帧进行检测处理，获得所述待处理视频流的检测结果，包括：
    对待处理视频帧的清晰度进行检测处理，获得所述检测结果。
  7. 根据权利要求1-6任一项所述的方法，其中，在所述待处理视频流的检测结果 为违规事件的情况下，根据预设的警告模式以及所述检测结果，生成警告信息，包括：
    在所述警告模式设置为第一警告模式的情况下，根据与第二违规事件对应的第一个检测结果，生成与所述第二违规事件对应的警告信息，并在第二预设时间段内屏蔽与所述第二违规事件对应的警告信息，其中，所述第二违规事件为任意一种违规事件。
  8. 根据权利要求1-6任一项所述的方法，其中，在所述待处理视频流的检测结果为违规事件的情况下，根据预设的警告模式以及所述检测结果，生成警告信息，包括：
    在所述警告模式设置为第二警告模式的情况下，根据与第二违规事件的对应的检测结果，生成与所述第二违规事件对应的警告信息，其中，所述第二违规事件为任意一种违规事件。
  9. 根据权利要求1-8任一项所述的方法，其中，所述方法还包括：
    根据预设频率对待处理视频流进行抽帧处理，获得待处理视频帧。
  10. 一种违规事件检测装置，所述装置包括：
    第一获得模块，配置为根据预设的检测模式，对待处理视频流的待处理视频帧进行检测处理，获得所述待处理视频流的检测结果；
    生成模块，配置为在所述待处理视频流的检测结果为违规事件的情况下，根据预设的警告模式以及所述检测结果，生成警告信息。
  11. 根据权利要求10所述的装置，其中，所述第一获得模块，配置为在所述检测模式设置为第一检测模式的情况下，对当前时刻抽取的待处理视频帧进行检测处理，获得当前时刻的第一检测结果；在所述第一检测结果为第一违规事件的情况下，对第一预设时间段内抽取的多个待处理视频帧进行检测处理，分别获得所述多个待处理视频帧的第二检测结果，其中，所述第一预设时间段为以所述当前时刻为起始时刻的时间段，所述第一违规事件为任意一种违规事件；在所述第二检测结果为第一违规事件的待处理视频帧的数量大于或等于预设数量阈值的情况下，将所述待处理视频流的检测结果确定为第一违规事件。
  12. 根据权利要求10所述的装置，其中，所述第一获得模块，配置为在所述检测模式设置为第二检测模式的情况下，对当前时刻抽取的待处理视频帧进行检测处理，获得所述待处理视频流的检测结果。
  13. 根据权利要求10-12任一项所述的装置，其中，所述第一获得模块，配置为在所述待处理视频帧中确定目标对象的人脸区域和/或人体区域；对所述人脸区域和/或人体区域进行行为检测处理，获得所述检测结果。
  14. 根据权利要求10-12任一项所述的装置，其中，所述第一获得模块，配置为对多个时刻抽取的待处理视频帧进行运动检测处理，获得运动的目标对象所在区域；对所述运动的目标对象所在区域进行检测处理，获得所述检测结果。
  15. 根据权利要求10-12任一项所述的装置，其中，所述第一获得模块，配置为对待处理视频帧的清晰度进行检测处理，获得所述检测结果。
  16. 根据权利要求10-15任一项所述的装置，其中，所述生成模块，配置为在所述警告模式设置为第一警告模式的情况下，根据与第二违规事件对应的第一个检测结果，生成与所述第二违规事件对应的警告信息，并在第二预设时间段内屏蔽与所述第二违规事件对应的警告信息，其中，所述第二违规事件为任意一种违规事件。
  17. 根据权利要求10-15任一项所述的装置，其中，所述生成模块，配置为在所述警告模式设置为第二警告模式的情况下，根据与第二违规事件的对应的检测结果，生成与所述第二违规事件对应的警告信息，其中，所述第二违规事件为任意一种违规事件。
  18. 根据权利要求10-17任一项所述的装置，其中，所述装置还包括第二获得模块，配置为根据预设频率对待处理视频流进行抽帧处理，获得待处理视频帧。
  19. 一种电子设备，包括：
    处理器；
    用于存储处理器可执行指令的存储器；
    其中，所述处理器被配置为：执行权利要求1至9中任意一项所述的方法。
  20. 一种计算机可读存储介质，其上存储有计算机程序指令，所述计算机程序指令被处理器执行时实现权利要求1至9中任意一项所述的方法。
  21. 一种计算机程序，包括计算机可读代码，当所述计算机可读代码在电子设备中运行时，所述电子设备中的处理器执行用于实现权利要求1至9中任意一项所述的违规事件检测方法。
PCT/CN2021/076201 2020-02-18 2021-02-09 违规事件检测方法及装置、电子设备和存储介质 WO2021164644A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
JP2021562343A JP2022529300A (ja) 2020-02-18 2021-02-09 違反イベント検出方法及び装置、電子デバイス並びに記憶媒体
KR1020217036108A KR20210148313A (ko) 2020-02-18 2021-02-09 위반 이벤트 검출 방법 및 장치, 전자 기기 및 저장 매체

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010098904.8A CN111310665A (zh) 2020-02-18 2020-02-18 违规事件检测方法及装置、电子设备和存储介质
CN202010098904.8 2020-02-18

Publications (1)

Publication Number Publication Date
WO2021164644A1 true WO2021164644A1 (zh) 2021-08-26

Family

ID=71145068

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/076201 WO2021164644A1 (zh) 2020-02-18 2021-02-09 违规事件检测方法及装置、电子设备和存储介质

Country Status (5)

Country Link
JP (1) JP2022529300A (zh)
KR (1) KR20210148313A (zh)
CN (1) CN111310665A (zh)
TW (1) TW202133034A (zh)
WO (1) WO2021164644A1 (zh)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113762169A (zh) * 2021-09-09 2021-12-07 北京市商汤科技开发有限公司 人流量统计方法及装置、电子设备和存储介质
CN113780213A (zh) * 2021-09-16 2021-12-10 上海西井信息科技有限公司 基于监控进行行人识别的方法、系统、设备及存储介质
CN114155612A (zh) * 2022-02-10 2022-03-08 深圳爱莫科技有限公司 餐饮人员不规范行为模型训练方法、检测方法及处理设备
CN114554110A (zh) * 2022-01-25 2022-05-27 北京百度网讯科技有限公司 视频生成方法、装置、电子设备和存储介质
CN114999172A (zh) * 2022-05-24 2022-09-02 浙江大华技术股份有限公司 事件处理方法、装置、存储介质及电子装置

Families Citing this family (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111310665A (zh) * 2020-02-18 2020-06-19 深圳市商汤科技有限公司 违规事件检测方法及装置、电子设备和存储介质
CN112084882A (zh) * 2020-08-18 2020-12-15 深圳英飞拓科技股份有限公司 一种行为检测方法、装置及计算机可读存储介质
CN112216073B (zh) * 2020-10-12 2022-05-03 浙江大华技术股份有限公司 一种梯子违规操作告警方法及装置
CN112163123A (zh) * 2020-11-10 2021-01-01 中国科学院长春光学精密机械与物理研究所 一种事件提取方法、装置、电子设备及存储介质
CN114513625A (zh) * 2020-11-16 2022-05-17 中国石油化工股份有限公司 存储器、罐区泄漏的安全联锁方法、装置及设备
CN112434612A (zh) * 2020-11-25 2021-03-02 创新奇智(上海)科技有限公司 吸烟检测方法、装置、电子设备及计算机可读存储介质
CN112464898A (zh) * 2020-12-15 2021-03-09 北京市商汤科技开发有限公司 事件检测方法及装置、电子设备和存储介质
CN112866808B (zh) * 2020-12-31 2022-09-06 北京市商汤科技开发有限公司 一种视频处理方法、装置、电子设备及存储介质
CN112988337A (zh) * 2021-03-01 2021-06-18 创新奇智(上海)科技有限公司 任务处理系统、方法、装置、电子设备、存储介质
CN113011290A (zh) * 2021-03-03 2021-06-22 上海商汤智能科技有限公司 事件检测方法及装置、电子设备和存储介质
CN113095178A (zh) * 2021-03-30 2021-07-09 北京大米科技有限公司 不良信息检测方法、系统、电子设备和可读存储介质
CN113179423A (zh) * 2021-04-23 2021-07-27 深圳市商汤科技有限公司 事件的检测输出方法及装置、电子设备和存储介质
CN113076566B (zh) * 2021-04-26 2024-02-27 深圳市三旺通信股份有限公司 显示内容检测方法、设备、计算机程序产品及存储介质
CN113705370B (zh) * 2021-08-09 2023-06-30 百度在线网络技术（北京）有限公司 直播间违规行为的检测方法及装置、电子设备和存储介质
CN115914512A (zh) * 2022-09-30 2023-04-04 广州安思创信息技术有限公司 直播截图方法、装置、设备及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107920223A (zh) * 2016-10-08 2018-04-17 杭州海康威视数字技术股份有限公司 一种对象行为检测方法及装置
CN109063612A (zh) * 2018-07-19 2018-12-21 中智城信息技术有限公司 城市智能红线管理方法及机器可读存储介质
CN110647819A (zh) * 2019-08-28 2020-01-03 中国矿业大学 一种井下人员跨越皮带异常行为检测方法及装置
CN110728815A (zh) * 2019-10-25 2020-01-24 深圳市商汤科技有限公司 基于视频分析的预警方法及装置、电子设备和存储介质
CN111310665A (zh) * 2020-02-18 2020-06-19 深圳市商汤科技有限公司 违规事件检测方法及装置、电子设备和存储介质

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4087600B2 (ja) * 2001-12-13 2008-05-21 セコム株式会社 画像監視装置
JP2010067169A (ja) * 2008-09-12 2010-03-25 Ntt Comware Corp 通信システム及び方法とそのプログラム
CN102081844A (zh) * 2011-01-25 2011-06-01 华中科技大学 一种交通视频行为分析与报警服务器
US9179096B2 (en) * 2013-10-11 2015-11-03 Fuji Xerox Co., Ltd. Systems and methods for real-time efficient navigation of video streams
EP3340104B1 (en) * 2016-12-21 2023-11-29 Axis AB A method for generating alerts in a video surveillance system
CN108810616B (zh) * 2018-05-31 2019-06-14 广州虎牙信息科技有限公司 目标定位方法、视频显示方法、装置、设备和存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107920223A (zh) * 2016-10-08 2018-04-17 杭州海康威视数字技术股份有限公司 一种对象行为检测方法及装置
CN109063612A (zh) * 2018-07-19 2018-12-21 中智城信息技术有限公司 城市智能红线管理方法及机器可读存储介质
CN110647819A (zh) * 2019-08-28 2020-01-03 中国矿业大学 一种井下人员跨越皮带异常行为检测方法及装置
CN110728815A (zh) * 2019-10-25 2020-01-24 深圳市商汤科技有限公司 基于视频分析的预警方法及装置、电子设备和存储介质
CN111310665A (zh) * 2020-02-18 2020-06-19 深圳市商汤科技有限公司 违规事件检测方法及装置、电子设备和存储介质

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113762169A (zh) * 2021-09-09 2021-12-07 北京市商汤科技开发有限公司 人流量统计方法及装置、电子设备和存储介质
CN113780213A (zh) * 2021-09-16 2021-12-10 上海西井信息科技有限公司 基于监控进行行人识别的方法、系统、设备及存储介质
CN113780213B (zh) * 2021-09-16 2024-02-02 上海西井科技股份有限公司 基于监控进行行人识别的方法、系统、设备及存储介质
CN114554110A (zh) * 2022-01-25 2022-05-27 北京百度网讯科技有限公司 视频生成方法、装置、电子设备和存储介质
CN114554110B (zh) * 2022-01-25 2023-12-29 北京百度网讯科技有限公司 视频生成方法、装置、电子设备和存储介质
CN114155612A (zh) * 2022-02-10 2022-03-08 深圳爱莫科技有限公司 餐饮人员不规范行为模型训练方法、检测方法及处理设备
CN114999172A (zh) * 2022-05-24 2022-09-02 浙江大华技术股份有限公司 事件处理方法、装置、存储介质及电子装置

Also Published As

Publication number Publication date
JP2022529300A (ja) 2022-06-20
KR20210148313A (ko) 2021-12-07
TW202133034A (zh) 2021-09-01
CN111310665A (zh) 2020-06-19

Similar Documents

Publication Publication Date Title
WO2021164644A1 (zh) 违规事件检测方法及装置、电子设备和存储介质
US9691256B2 (en) Method and device for presenting prompt information that recommends removing contents from garbage container
JP6466958B2 (ja) 端末異常の処理方法、端末異常の処理装置、電子装置、プログラム、及び記録媒体
KR101852284B1 (ko) 경보 방법 및 장치
US9934673B2 (en) Method and device for processing abnormality notification from a smart device
CN109040824A (zh) 视频处理方法、装置、电子设备和可读存储介质
WO2022183661A1 (zh) 事件检测方法、装置、电子设备、存储介质及程序产品
TW202134940A (zh) 監測方法、電子設備和儲存介質
US20170178289A1 (en) Method, device and computer-readable storage medium for video display
US10509540B2 (en) Method and device for displaying a message
US20180025229A1 (en) Method, Apparatus, and Storage Medium for Detecting and Outputting Image
WO2020062969A1 (zh) 动作识别方法及装置、驾驶员状态分析方法及装置
US10309673B2 (en) Air anomaly alarming method, device and storage medium
WO2018228422A1 (zh) 一种发出预警信息的方法、装置及系统
CN109951476B (zh) 基于时序的攻击预测方法、装置及存储介质
US10354678B2 (en) Method and device for collecting sounds corresponding to surveillance images
TW202113670A (zh) 一種圖像處理方法、電子設備和儲存介質
CN106303961A (zh) 自动报警方法及设备
CN110728815A (zh) 基于视频分析的预警方法及装置、电子设备和存储介质
CN105847763A (zh) 监控方法及装置
CN110807393A (zh) 基于视频分析的预警方法及装置、电子设备和存储介质
CN112633184A (zh) 告警方法及装置、电子设备和存储介质
CN107734303B (zh) 视频标识方法及装置
CN111353454A (zh) 一种数据处理方法、装置和电子设备
CN113011291A (zh) 事件检测方法及装置、电子设备和存储介质

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: 21757178

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2021562343

Country of ref document: JP

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 20217036108

Country of ref document: KR

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 24.01.2023)

122 Ep: pct application non-entry in european phase

Ref document number: 21757178

Country of ref document: EP

Kind code of ref document: A1