WO2021159682A1 - 一种异常对象管理方法、系统、机器可读介质及设备 - Google Patents

一种异常对象管理方法、系统、机器可读介质及设备 Download PDF

Info

Publication number
WO2021159682A1
WO2021159682A1 PCT/CN2020/110454 CN2020110454W WO2021159682A1 WO 2021159682 A1 WO2021159682 A1 WO 2021159682A1 CN 2020110454 W CN2020110454 W CN 2020110454W WO 2021159682 A1 WO2021159682 A1 WO 2021159682A1
Authority
WO
WIPO (PCT)
Prior art keywords
detection
area
temperature
target
abnormal
Prior art date
Application number
PCT/CN2020/110454
Other languages
English (en)
French (fr)
Inventor
周曦
姚志强
龚强
Original Assignee
上海云从汇临人工智能科技有限公司
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 上海云从汇临人工智能科技有限公司 filed Critical 上海云从汇临人工智能科技有限公司
Publication of WO2021159682A1 publication Critical patent/WO2021159682A1/zh

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/01—Measuring temperature of body parts ; Diagnostic temperature sensing, e.g. for malignant or inflamed tissue
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
    • A61B5/14546—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue for measuring analytes not otherwise provided for, e.g. ions, cytochromes
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
    • A61B5/1455—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters

Definitions

  • the invention relates to the field of abnormal situation detection, in particular to an abnormal object management method, system, machine-readable medium and equipment.
  • fever is a common manifestation of various infectious diseases. Many infectious diseases are even named after “heat”, such as hemorrhagic fever, dengue fever, and scarlet fever. It can be seen that fever is closely related to infectious diseases. Fever is usually a pathophysiological response of the human body to pathogenic factors. It is generally believed that when the oral temperature is higher than 37.3C or the daily body temperature change exceeds 1.2C, it is called "fever".
  • the purpose of the present invention is to provide an abnormal object management method, system, machine-readable medium and equipment to solve the problems existing in the prior art.
  • an abnormal object management method including:
  • the multiple types of images include: visible light images, infrared images, and laser images.
  • the detection indicators include temperature and blood nucleic acid characteristics.
  • the image of the detection object includes a visible light image and an infrared image
  • the image of the detection object includes a visible light image and a laser image
  • the target part includes a face, a back of the hand, a neck, and a shoulder
  • the target detection area includes a face area, a back of the hand area, a neck area, and a shoulder area.
  • the detection index is temperature
  • the temperature of the target detection area of the detection object exceeds a temperature threshold
  • the detection object is an abnormal object
  • the detection index is a blood nucleic acid feature
  • the detection object is an abnormal object.
  • the method further includes:
  • the method further includes:
  • the method further includes:
  • the method further includes:
  • the temperature of the target detection area is compensated based on the distance between the detection object and the image acquisition device.
  • the method further includes:
  • the temperature of the target detection area is compensated according to the ambient temperature.
  • the method further includes:
  • an abnormal object management system including:
  • the image acquisition module is used to acquire multiple types of images of the detected object
  • a detection area determination module which is used to determine the target detection area of the detection object
  • An index detection module which is used to obtain the detection index of the target detection area
  • the abnormality judgment module is used for judging whether the detection object is an abnormal object according to the detection index.
  • the multiple types of images include: visible light images, infrared images, and laser images.
  • the detection indicators include temperature and blood nucleic acid characteristics.
  • the image of the detection object includes a visible light image and an infrared image
  • the image of the detection object includes a visible light image and a laser image
  • the target part includes a face, a back of the hand, a neck, and a shoulder
  • the target detection area includes a face area, a back of the hand area, a neck area, and a shoulder area.
  • the detection index is temperature
  • the temperature of the target detection area of the detection object exceeds a temperature threshold
  • the detection object is an abnormal object
  • the detection index is a blood nucleic acid feature
  • the detection object is an abnormal object.
  • system further includes:
  • the tracking module is used to track the abnormal object using face recognition technology or human body recognition technology.
  • system further includes:
  • the alarm module is used to send out an alarm when an abnormal object is detected.
  • the system further includes:
  • the age attribute acquisition module is used to acquire the age attribute of the detected object
  • the temperature threshold setting module is used to set temperature thresholds corresponding to different age groups according to different age attributes.
  • system further includes:
  • the first temperature compensation module compensates the temperature of the target detection area based on the distance between the detection object and the image acquisition device.
  • system further includes:
  • the temperature acquisition module is used to acquire the ambient temperature
  • the second temperature compensation module is used to compensate the temperature of the target detection area according to the ambient temperature.
  • the system further includes:
  • a smoking judging module for judging whether the detected object has smoking behavior
  • the shielding module is used to shield the smoking area in the presence of smoking behavior.
  • the present invention provides a device, including:
  • One or more processors are One or more processors.
  • the present invention provides one or more machine-readable media on which instructions are stored.
  • the device executes one or more of the aforementioned method.
  • the abnormal object management method, system, machine-readable medium, and equipment provided by the present invention have the following beneficial effects:
  • the present invention obtains multiple types of images of the detection object; determines the target detection area of the detection object; obtains the detection index of the target detection area; and judges whether the detection object is an abnormal object according to the detection index.
  • the invention adopts non-contact type to detect the detection index, and the detected person can complete the detection without stopping, standing or making any actions. At the same time, the staff stay away from the tested population, effectively avoiding cross-infection.
  • FIG. 1 is a flowchart of an abnormal object management method provided by an embodiment of the present invention
  • FIG. 2 is a flowchart of an abnormal object management method provided by another embodiment of the present invention.
  • FIG. 3 is a flowchart of an abnormal object management method provided by another embodiment of the present invention.
  • FIG. 4 is a schematic diagram of the hardware structure of an abnormal object management system provided by an embodiment of the present invention.
  • FIG. 5 is a schematic diagram of the hardware structure of a terminal device provided by an embodiment of the present invention.
  • FIG. 6 is a schematic diagram of the hardware structure of a terminal device provided by another embodiment of the present invention.
  • an abnormal object management method includes:
  • S11 obtains multiple types of images of the detected object
  • S14 Determine whether the detection object is an abnormal object according to the detection index.
  • the present invention obtains multiple types of images of the detection object; determines the target detection area of the detection object; obtains the detection index of the target detection area; and judges whether the detection object is an abnormal object according to the detection index.
  • the invention adopts non-contact type to detect the detection index, and the detected person can complete the detection without stopping, standing or making any actions. At the same time, the staff stay away from the tested population, effectively avoiding cross-infection.
  • the multiple types of images may include: visible light images, infrared images, and laser images.
  • the visible light image can be collected by the visible light image acquisition sensor
  • the infrared image can be collected by the infrared image acquisition sensor.
  • the image can also be collected by the RGB-IR image sensor (which can receive both the RGB component and the IR component).
  • the IR processing unit separates the received RGB-IR image data to obtain synchronized RGB images (visible light images) and IR images (infrared images);
  • the laser image can be acquired by the laser image acquisition sensor acquisition module.
  • At least two of the images can be collected by one device, for example, an infrared temperature measuring probe that can collect visible light images and infrared images at the same time, or can collect laser images and infrared images at the same time.
  • an infrared temperature measuring probe that can collect visible light images and infrared images at the same time, or can collect laser images and infrared images at the same time.
  • a laser temperature measuring probe that collects images or other image collection devices with the same function; or an image collection device that can collect visible light images, infrared images, and laser images at the same time.
  • the detection indicators of the target detection area include: temperature and blood nucleic acid characteristics.
  • the detection index is temperature
  • the detection object is an abnormal object.
  • an alarm is issued.
  • the user can set alarm parameters, such as preset temperature thresholds, alarm sensitivity, and so on. For example, when the temperature of the target detection area exceeds 37.3 degrees, an alarm is issued.
  • alarm parameters such as preset temperature thresholds, alarm sensitivity, and so on.
  • the temperature of the target detection area exceeds 37.3 degrees
  • an alarm is issued.
  • ways to alarm such as sound and light indication alarm, or voice alarm.
  • the alarm level can be set. Different colors can be used to display different alarm levels, and different alarm levels send different alarm signals. For example, if the alarm level is low, only audible and visual alarms can be issued. If the alarm level is very high, verbal alarms can be issued. If the alarm level is high, audible and visual alarms and voice alarms can be issued at the same time.
  • the detection index is a blood nucleic acid feature
  • the detection object is an abnormal object.
  • an abnormal nucleic acid feature library needs to be set up in advance, in which there are several nucleic acid features, which can reflect the abnormal state of the human body, and the corresponding abnormal symptoms can be determined through these nucleic acid features.
  • the preset conditions are met, it can be considered that the blood nucleic acid feature of the test object is one of the abnormal nucleic acid feature libraries.
  • an alarm is issued. For the reminder of issuing an alarm, refer to the foregoing embodiment, which will not be repeated here.
  • the target detection area of the detection object can be determined based on multiple types of images, and then it is determined whether the detection object is an abnormal object according to the detection index of the target detection area. Take visible light images and infrared images as examples. As shown in Figure 2, the specific process includes:
  • S21 Perform target part detection on the visible light image to obtain the target part position; determine the target detection area of the target part position in the infrared image of the detection object;
  • S23 judges whether the detection object is an abnormal object according to the detection index of the target detection area.
  • the target part includes the face, the back of the hand, the neck, and the shoulder
  • the target detection area includes the face area, the back of the hand area, the neck area, and the shoulder area.
  • the target part is the face
  • the target detection area is the face area
  • the detection index is the temperature
  • infrared detection is a continuous process, multiple infrared images will be obtained continuously for a period of time. Therefore, when detecting the temperature of the face area, it is necessary to obtain the image at the same time, that is, the infrared image at the current time and the visible light image at the current time.
  • the process of determining the face area first perform face detection on the visible light image at the current moment to obtain the position of the face, and then map the face position in the visible light image at the current moment to the infrared image of the detection object at the current moment , Get the face area of the detected object in the infrared image at the current moment.
  • the temperature of the face area in the infrared image at the current moment can be measured to obtain the temperature of the face area.
  • the image of the face area is an infrared image, and the corresponding relationship between color and temperature can be obtained in advance. According to the corresponding relationship between color and temperature, the temperature corresponding to the color in the face area can be determined. The temperature of the face area.
  • This embodiment adopts a face detection technology, which can detect multiple faces in a video frame at the same time to obtain face data of a detection object. Furthermore, the best face can be obtained through the face data, and the face area at the best face temperature can be used as the temperature measurement object when the face temperature is measured.
  • the best face can be comprehensively selected through multiple dimensions such as face quality score, face size, face angle, and face occlusion rate.
  • the target detection area of the detection object can be determined based on multiple types of images, and then it is determined whether the detection object is an abnormal object according to the detection index of the target detection area. Take the visible light image and the laser image as examples. As shown in Figure 3, the specific process includes:
  • S31 Perform target part detection on the visible light image to obtain the target part position; determine the target detection area of the target part position in the laser image of the detection object;
  • S33 judges whether the detection object is an abnormal object according to the detection index of the target detection area.
  • the target part includes the face, the back of the hand, the neck, and the shoulder
  • the target detection area includes the face area, the back of the hand area, the neck area, and the shoulder area.
  • the target part is the face
  • the target detection area is the face area
  • the detection index is the temperature
  • the temperature of the face area in the laser image at the current moment can be measured to obtain the temperature of the face area.
  • This embodiment adopts a face detection technology, which can detect multiple faces in a video frame at the same time to obtain face data of a detection object. Furthermore, the best face can be obtained through the face data, and the face area at the best face temperature can be used as the temperature measurement object when the face temperature is measured.
  • the best face can be comprehensively selected through multiple dimensions such as face quality score, face size, face angle, and face occlusion rate.
  • this method also includes:
  • the corresponding temperature threshold for children can be set a little higher; for the elderly, the metabolic rate is lower, and the temperature can be slightly lower than that of young adults. Therefore, the corresponding threshold for the elderly can be set a little lower .
  • face recognition technology or human body recognition technology may also be used to track the abnormal object.
  • the detection index is used to detect the abnormal object, and after the abnormal object is judged, the abnormal object is tracked through the recognized face or human body characteristics.
  • the detection object After capturing the face or human body of the detection object, it is compared with the face or human body in the abnormal object library, and if the comparison is successful, the detection object is tracked.
  • the method further includes:
  • the burning cigarette butts belong to an external heat source, which will interfere with the detection of the temperature of the face area. Therefore, if the detected object has smoking behavior, the smoking area will be shielded.
  • the behavior identifier is a preset smoking behavior identifier, it is determined that the behavior of the detection object belongs to a smoking behavior.
  • the temperature of the target detection area is related to the distance between the image acquisition device that acquires the image and the target detection area. Therefore, in one embodiment, the method further includes: The distance compensates for the temperature of the target detection area. The accuracy of the measurement is improved by compensating the temperature of the target detection area.
  • the ambient temperature is acquired, and the temperature of the target detection area is compensated according to the ambient temperature. More specifically, in the case of low ambient temperature, the detected temperature value will be lower than the real body temperature. At this time, the infrared sensor measurement value should be appropriately increased according to the ambient temperature; in the case of high ambient temperature, the detected temperature value may be If the temperature is higher than the real body temperature, the infrared sensor measurement value should be appropriately lowered according to the ambient temperature.
  • the invention uses infrared images, visible light images, and laser images, combined with artificial intelligence algorithms, to automatically track, measure, and warn heat-producing persons, achieving quick customs clearance for normal persons without feeling, and timely warning of heat-generating persons, reducing the risk of infection by inspectors.
  • an abnormal object management system includes:
  • the image acquisition module 41 is used to acquire multiple types of images of the detection object
  • the detection area determining module 42 is configured to determine the target detection area of the detection object
  • the index detection module 43 is configured to obtain the detection index of the target detection area
  • the abnormality judgment module 44 is used for judging whether the detection object is an abnormal object according to the detection index.
  • the present invention obtains multiple types of images of the detection object; determines the target detection area of the detection object; obtains the detection index of the target detection area; and judges whether the detection object is an abnormal object according to the detection index.
  • the invention adopts non-contact type to detect the detection index, and the detected person can complete the detection without stopping, standing or making any actions. At the same time, the staff stay away from the tested population, effectively avoiding cross-infection.
  • the multiple types of images may include: visible light images, infrared images, and laser images.
  • the visible light image can be acquired by a visible light camera
  • the infrared image can be acquired by an infrared image acquisition sensor
  • the laser image can be acquired by a laser image acquisition module.
  • at least two of the images can be collected by one device, for example, an infrared temperature measuring probe that can collect visible light images and infrared images at the same time, or can collect laser images and infrared images at the same time.
  • Laser temperature measurement probe for image acquisition or other image acquisition equipment with the same function can also be collected by RGB-IR image sensor (which can receive both RGB component and IR component at the same time), and then the image will be received by the RGB-IR processing unit
  • the received RGB-IR image data is separated to obtain synchronized RGB images (visible light images) and IR images (infrared images); image acquisition equipment that can also collect visible light images, infrared images, and laser images at the same time.
  • the detection indicators of the target detection area include: temperature and blood nucleic acid characteristics.
  • the detection index is temperature
  • the temperature of the target detection area of the detection object exceeds the temperature threshold
  • the detection object is an abnormal object.
  • the user can set alarm parameters, such as preset temperature thresholds, alarm sensitivity, and so on. For example, when the temperature of the target detection area exceeds 37.3 degrees, an alarm is issued.
  • alarm parameters such as preset temperature thresholds, alarm sensitivity, and so on.
  • the temperature of the target detection area exceeds 37.3 degrees
  • an alarm is issued.
  • ways to alarm such as sound and light indication alarm, or voice alarm.
  • display in eye-catching colors on the screen showing the infrared image and set the alarm level. Different colors can be used to display different alarm levels, and different alarm levels send different alarm signals. For example, if the alarm level is low, only audible and visual alarms can be issued. If the alarm level is very high, verbal alarms can be issued. If the alarm level is high, audible and visual alarms and voice alarms can be issued at the same time.
  • the detection index is a blood nucleic acid feature
  • the detection object is an abnormal object.
  • a library of abnormal nucleic acid signatures needs to be set up in advance, in which there are several nucleic acid signatures, these nucleic acid signatures can reflect the abnormal state of the human body, and the corresponding abnormal symptoms can be determined by these nucleic acid signatures.
  • the preset conditions are met, it can be considered that the blood nucleic acid feature of the test object is one of the abnormal nucleic acid feature libraries.
  • an alarm is issued. For the reminder of issuing an alarm, refer to the foregoing embodiment, which will not be repeated here.
  • the target detection area of the detection object can be determined based on multiple types of images, and then it is determined whether the detection object is an abnormal object according to the detection index of the target detection area. Take visible light images and infrared images as examples.
  • the specific process includes:
  • the target part includes the face, the back of the hand, the neck, and the shoulder
  • the target detection area includes the face area, the back of the hand area, the neck area, and the shoulder area.
  • the target part is the face and the target detection area is the face area.
  • infrared detection is a continuous process, multiple infrared images will be obtained continuously for a period of time. Therefore, when detecting the temperature of the face area, it is necessary to obtain the image at the same time, that is, the infrared image at the current time and the visible light image at the current time.
  • the process of determining the face area first perform face detection on the visible light image at the current moment to obtain the position of the face, and then map the face position in the visible light image at the current moment to the infrared image of the detection object at the current moment , Get the face area of the detected object in the infrared image at the current moment.
  • the temperature of the face area in the infrared image at the current moment can be measured to obtain the temperature of the face area.
  • the image of the face area is an infrared image, and the corresponding relationship between color and temperature can be obtained in advance. According to the corresponding relationship between color and temperature, the temperature corresponding to the color in the face area can be determined. The temperature of the face area.
  • This embodiment adopts a face detection technology, which can detect multiple faces in a video frame at the same time to obtain face data of a detection object. Furthermore, the best face can be obtained through the face data, and the face area at the best face temperature can be used as the temperature measurement object when the face temperature is measured.
  • the best face can be comprehensively selected through multiple dimensions such as face quality score, face size, face angle, and face occlusion rate.
  • the target detection area of the detection object can be determined based on multiple types of images, and then it is determined whether the detection object is an abnormal object according to the detection index of the target detection area. Take the visible light image and the laser image as examples.
  • the specific process includes:
  • the target part includes the face, the back of the hand, the neck, and the shoulder
  • the target detection area includes the face area, the back of the hand area, the neck area, and the shoulder area.
  • the target part is the face and the target detection area is the face area.
  • the temperature of the face area in the laser image at the current moment can be measured to obtain the temperature of the face area.
  • the image of the face area is a laser image.
  • the corresponding relationship between color and temperature can be obtained in advance, and the temperature corresponding to the color in the face area can be determined according to the corresponding relationship between color and temperature.
  • the temperature of the face area is a laser image.
  • This embodiment adopts a face detection technology, which can detect multiple faces in a video frame at the same time to obtain face data of a detection object. Furthermore, the best face can be obtained through the face data, and the face area at the best face temperature can be used as the temperature measurement object when the face temperature is measured.
  • the best face can be comprehensively selected through multiple dimensions such as face quality score, face size, face angle, and face occlusion rate.
  • the system also includes:
  • the age attribute acquisition module is used to acquire the age attribute of the detected object
  • the temperature threshold setting module is used to set temperature thresholds corresponding to different age groups according to different age attributes.
  • the corresponding temperature threshold for children can be set a little higher; for the elderly, the metabolic rate is lower, and the temperature can be slightly lower than that of young adults. Therefore, the corresponding threshold for the elderly can be set a little lower .
  • system further includes:
  • the tracking module is used to track the abnormal object using face recognition technology or human body recognition technology.
  • the detection index is used to detect the abnormal object, and after the abnormal object is judged, the abnormal object is tracked through the recognized face or human body characteristics.
  • the detected object is tracked.
  • the system further includes:
  • a smoking judging module for judging whether the detected object has smoking behavior
  • the shielding module is used to shield the smoking area in the presence of smoking behavior.
  • the burning cigarette butts belong to an external heat source, which will interfere with the detection of the temperature of the face area. Therefore, if the detected object has smoking behavior, the smoking area will be shielded.
  • the behavior identifier is a preset smoking behavior identifier, it is determined that the behavior of the detection object belongs to a smoking behavior.
  • the system further includes:
  • the first temperature compensation module compensates the temperature of the target detection area based on the distance between the detection object and the image acquisition device. The accuracy of the measurement is improved by compensating the temperature of the target detection area.
  • the system also includes:
  • the temperature acquisition module is used to acquire the ambient temperature
  • the second temperature compensation module is used to compensate the temperature of the target detection area according to the ambient temperature.
  • the detected temperature value when the ambient temperature is low, the detected temperature value will be lower than the real body temperature. At this time, the infrared sensor measurement value should be appropriately increased according to the ambient temperature; when the ambient temperature is high, the detected temperature The value may be higher than the real body temperature. At this time, the infrared sensor measurement value should be appropriately reduced according to the ambient temperature.
  • the invention uses infrared images, visible light images, and laser images, combined with artificial intelligence algorithms, to automatically track, measure, and warn heat-producing persons, achieving quick customs clearance for normal persons without feeling, and timely warning of heat-generating persons, reducing the risk of infection by inspectors.
  • the invention adopts non-contact temperature measurement, and the detected person can complete body temperature detection without stopping, standing or making any actions. At the same time, the staff stay away from the tested population, effectively avoiding cross-infection.
  • the image response speed is 0.04ms, and the temperature measurement response speed is fast. It can complete 16 target detections within 30 milliseconds, and can measure the temperature of 16 targets at the same time.
  • thermometers it has the characteristics of non-contact fast, convenient, intuitive, and safe, which overcomes the traditional
  • the clinical thermometers, forehead thermometers, spot thermometers and ear thermometers are only for individual measurement, (such as the use of traditional thermometers to test generally takes 3 minutes/person, ordinary spot thermometers, forehead thermometers, and ear thermometers are for individual human testing , The general detection time takes 4 to 5 seconds/person).
  • the temperature measurement range of the invention is: 0°C ⁇ 60°C, the temperature measurement accuracy: 28°C ⁇ 45°C ⁇ 0.3°C, built-in automatic temperature measurement correction.
  • Face quarantine and body temperature screening early warning avoids the deficiencies of time-consuming and easy cross-infection, and can effectively control the spread of the epidemic and reduce casualties. It is very suitable for heavy traffic in airports, docks, stations, banks, hospitals and shopping malls. Perform a quick temperature check on large occasions.
  • the invention can carry out long-distance, large-area detection
  • Visible light resolution 1920*1080, focal length 5mm;
  • the embodiment of the present application also provides a device, which may include: one or more processors; and one or more machine-readable media on which instructions are stored, when executed by the one or more processors At this time, the device is caused to execute the method described in FIG. 1.
  • the device can be used as a terminal device or a server.
  • terminal devices include: smart phones, tablets, e-book readers, MP3 (Moving Picture Experts Group Audio) Layer III) Players, MP4 (Moving Picture Experts Group Audio Layer IV) players, laptops, car computers, desktop computers, set-top boxes, smart TVs, wearable devices, etc.
  • the embodiments of the present application do not impose restrictions on specific devices.
  • the embodiment of the present application also provides a non-volatile readable storage medium.
  • the storage medium stores one or more modules (programs). When the one or more modules are applied to a device, the device can execute Instructions for the steps included in the method in FIG. 1 of the embodiment of the present application.
  • FIG. 5 is a schematic diagram of the hardware structure of a terminal device provided by an embodiment of the application.
  • the terminal device may include: an input device 1100, a first processor 1101, an output device 1102, a first memory 1103, and at least one communication bus 1104.
  • the communication bus 1104 is used to implement communication connections between components.
  • the first memory 1103 may include a high-speed RAM memory, or may also include a non-volatile storage NVM, such as at least one disk memory.
  • the first memory 1103 may store various programs for completing various processing functions and implementing this embodiment. Method steps.
  • the foregoing first processor 1101 may be, for example, a central processing unit (Central Processing Unit, CPU for short), an application specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), and A programmable logic device (PLD), a field programmable gate array (FPGA), a controller, a microcontroller, a microprocessor or other electronic components are implemented, and the first processor 1101 is coupled to the aforementioned input device 1100 and via a wired or wireless connection.
  • the aforementioned input device 1100 may include multiple input devices, for example, it may include at least one of a user-oriented user interface, a device-oriented device interface, a software programmable interface, a camera, and a sensor.
  • the device-oriented device interface may be a wired interface for data transmission between the device and the device, or a hardware plug-in interface for data transmission between the device and the device (such as a USB interface, a serial port, etc.) );
  • the user-oriented user interface may be, for example, user-oriented control buttons, a voice input device for receiving voice input, and a touch sensing device for receiving user touch input (such as a touch screen with touch sensing function, touch Control board, etc.);
  • the programmable interface of the above software may be, for example, an entry for the user to edit or modify the program, such as the input pin interface or input interface of the chip, etc.;
  • the output device 1102 may include output devices such as a display and audio .
  • the processor of the terminal device includes functions for executing each module in each device.
  • functions for executing each module in each device please refer to the above-mentioned embodiment, which will not be repeated here.
  • FIG. 6 is a schematic diagram of the hardware structure of a terminal device provided by an embodiment of the application.
  • Fig. 6 is a specific embodiment of Fig. 5 in the implementation process.
  • the terminal device of this embodiment may include a second processor 1201 and a second memory 1202.
  • the second processor 1201 executes the computer program code stored in the second memory 1202 to implement the method described in FIG. 1 in the foregoing embodiment.
  • the second memory 1202 is configured to store various types of data to support operations on the terminal device. Examples of these data include instructions for any application or method operating on the terminal device, such as messages, pictures, videos, and so on.
  • the second memory 1202 may include a random access memory (random access memory, RAM for short), and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.
  • the second processor 1201 is provided in the processing component 1200.
  • the terminal device may also include: a communication component 1203, a power supply component 1204, a multimedia component 1205, a voice component 1206, an input/output interface 1207 and/or a sensor component 1208.
  • the specific components included in the terminal device are set according to actual requirements, which is not limited in this embodiment.
  • the processing component 1200 generally controls the overall operation of the terminal device.
  • the processing component 1200 may include one or more second processors 1201 to execute instructions to complete all or part of the steps in the foregoing data processing method.
  • the processing component 1200 may include one or more modules to facilitate the interaction between the processing component 1200 and other components.
  • the processing component 1200 may include a multimedia module to facilitate the interaction between the multimedia component 1205 and the processing component 1200.
  • the power supply component 1204 provides power for various components of the terminal device.
  • the power supply component 1204 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for terminal devices.
  • the multimedia component 1205 includes a display screen that provides an output interface between the terminal device and the user.
  • the display screen may include a liquid crystal display (LCD) and a touch panel (TP). If the display screen includes a touch panel, the display 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 voice component 1206 is configured to output and/or input voice signals.
  • the voice component 1206 includes a microphone (MIC).
  • the microphone When the terminal device is in an operating mode, such as a voice recognition mode, the microphone is configured to receive external voice signals.
  • the received voice signal may be further stored in the second memory 1202 or transmitted via the communication component 1203.
  • the voice component 1206 further includes a speaker for outputting voice signals.
  • the input/output interface 1207 provides an interface between the processing component 1200 and a peripheral interface module.
  • the peripheral interface module may be a click wheel, a button, or the like. These buttons may include, but are not limited to: volume buttons, start buttons, and lock buttons.
  • the sensor component 1208 includes one or more sensors, which are used to provide various aspects of state evaluation for the terminal device.
  • the sensor component 1208 can detect the open/close state of the terminal device, the relative positioning of the component, and the presence or absence of contact between the user and the terminal device.
  • the sensor component 1208 may include a proximity sensor configured to detect the presence of nearby objects when there is no physical contact, including detecting the distance between the user and the terminal device.
  • the sensor component 1208 may also include a camera and the like.
  • the communication component 1203 is configured to facilitate wired or wireless communication between the terminal device and other devices.
  • Terminal devices can access wireless networks based on communication standards, such as WiFi, 2G or 3G, or a combination of them.
  • the terminal device may include a SIM card slot for inserting a SIM card so that the terminal device can log in to the GPRS network and establish communication with the server via the Internet.
  • the communication component 1203, the voice component 1206, the input/output interface 1207, and the sensor component 1208 involved in the embodiment in FIG. 6 can all be used as implementations of the input device in the embodiment in FIG. 5.

Abstract

一种异常对象管理方法、系统、设备及机器可读介质。该方法包括：获取检测对象的多种类型图像（S11）；确定检测对象的目标检测区域（S12）；获取目标检测区域的检测指标（S13）；根据检测指标判断检测对象是否为异常对象（S14）。该方法和系统采用非接触式对检测指标进行检测，被检测人员无需停止、站立或做出任何动作，即可完成检测。同时，工作人员远离被测人群，有效地避免交叉感染。

Description

一种异常对象管理方法、系统、机器可读介质及设备 技术领域
本发明涉及异常情况检测领域，具体涉及一种异常对象管理方法、系统、机器可读介质及设备。
背景技术
目前世界各地传染病泛滥，如何快速找到人流量密集处的感染者，又不影响人们快速通关，同时降低检查人员的感染风险成了目前对抗疫情的难点。
我们知道，发热是各种传染病的共同表现，很多传染病甚至以“热”命名，如出血热、登革热、猩红热等，可见发热与传染病关系密切。发热通常是人体对致病因子的一种病理生理反应。一般认为口温高于37.3C或一日体温变化超过1.2C时称之为“发热”。
我们可以根据发热与传染病的关系，找出人群中的发热疑似人员，然后进行进一步排查。但是传统排查采用人工一人一测的方式，严重影响通关效率，而且也会增加检测人员的感染风险。
发明内容
鉴于以上所述现有技术的缺点，本发明的目的在于提供一种异常对象管理方法、系统、机器可读介质及设备，用于解决现有技术存在的问题。
为实现上述目的及其他相关目的，本发明提供一种异常对象管理方法，包括：
获取检测对象的多种类型图像；
确定所述检测对象的目标检测区域；
获取所述目标检测区域的检测指标；
根据所述检测指标判断所述检测对象是否为异常对象。
可选地，所述多种类型图像包括：可见光图像、红外图像、激光图像。
可选地，所述检测指标包括：温度、血液核酸特征。
可选地，若所述检测对象的图像包括可见光图像和红外图像；
则对所述可见光图像进行目标部位检测，得到目标部位位置；确定所述目标部位位置在检测对象的红外图像中的目标检测区域；
获取检测对象的所述目标检测区域的检测指标；
根据所述目标检测区域的检测指标判断检测对象是否为异常对象。
可选地，若所述检测对象的图像包括可见光图像和激光图像；
则对所述可见光图像进行目标部位检测，得到目标部位位置；确定所述目标部位位置在检测对象的激光图像中的目标检测区域；
获取检测对象的所述目标检测区域的检测指标；
根据所述目标检测区域的检测指标判断检测对象是否为异常对象。
可选地，所述目标部位包括人脸、手背、脖子、肩头，所述目标检测区域包括人脸区域、手背区域、脖子区域、肩头区域。
可选地，若所述检测指标为温度，则当检测对象的目标检测区域的温度超过温度阈值时，该检测对象为异常对象。
可选地，若所述检测指标为血液核酸特征，则当检测对象的目标检测区域的血液核酸特征符合预设条件时，则该检测对象为异常对象。
可选地，该方法还包括：
采用人脸识别技术或人体识别技术对所述异常对象进行追踪。
可选地，该方法还包括：
当检测到异常对象时，发出报警提示。
可选地，若所述检测指标为温度，则该方法还包括：
获取检测对象的年龄属性；
根据不同的年龄属性设定与不同年龄段对应的温度阈值。
可选地，该方法还包括：
基于检测对象与图像采集装置的距离对所述目标检测区域的温度进行补偿。
可选地，该方法还包括：
获取环境温度；
根据所述环境温度对所述目标检测区域的温度进行补偿。
可选地，若所述目标检测区域为人脸区域，该方法还包括：
判断所述检测对象是否存在抽烟行为；
若存在抽烟行为，则对抽烟区域进行屏蔽。
为实现上述目的及其他相关目的，本发明提供一种异常对象管理系统，包括：
图像获取模块，用于获取检测对象的多种类型图像；
检测区域确定模块，用于确定所述检测对象的目标检测区域；
指标检测模块，用于获取所述目标检测区域的检测指标；
异常判断模块，用于根据所述检测指标判断所述检测对象是否为异常对象。
可选地，所述多种类型图像包括：可见光图像、红外图像、激光图像。
可选地，所述检测指标包括：温度、血液核酸特征。
可选地，若所述检测对象的图像包括可见光图像和红外图像；
则对所述可见光图像进行目标部位检测，得到目标部位位置；
确定所述目标部位位置在检测对象的红外图像中的目标检测区域；
获取检测对象的所述目标检测区域的检测指标；
根据所述目标检测区域的检测指标判断检测对象是否为异常对象。
可选地，若所述检测对象的图像包括可见光图像和激光图像；
则对所述可见光图像进行目标部位检测，得到目标部位位置；确定所述目标部位位置在检测对象的激光图像中的目标检测区域；
获取激光图像的所述目标检测区域的检测指标；
根据所述目标检测区域的检测指标判断检测对象是否为异常对象。
可选地，所述目标部位包括人脸、手背、脖子、肩头，所述目标检测区域包括人脸区域、手背区域、脖子区域、肩头区域。
可选地，若所述检测指标为温度，则当检测对象的目标检测区域的温度超过温度阈值时，该检测对象为异常对象。
可选地，若所述检测指标为血液核酸特征，则当检测对象的目标检测区域的血液核酸特征符合预设条件时，则该检测对象为异常对象。
可选地，该系统还包括：
追踪模块，用于采用人脸识别技术或人体识别技术对所述异常对象进行追踪。
可选地，该系统还包括：
报警模块，用于在检测到异常对象时发出报警提示。
可选地，若所述检测指标为温度，则该系统还包括：
年龄属性获取模块，用于获取检测对象的年龄属性；
温度阈值设定模块，用于根据不同的年龄属性设定与不同年龄段对应的温度阈值。
可选地，该系统还包括：
第一温度补偿模块，基于检测对象与图像采集装置的距离对所述目标检测区域的温度进行补偿。
可选地，该系统还包括：
温度获取模块，用于获取环境温度；
第二温度补偿模块，用于根据所述环境温度对所述目标检测区域的温度进行补偿。
可选地，若所述目标检测区域为人脸区域，该系统还包括：
抽烟判断模块，用于判断所述检测对象是否存在抽烟行为；
屏蔽模块，用于在存在抽烟行为对抽烟区域进行屏蔽。
为实现上述目的及其他相关目的，本发明提供一种设备，包括：
一个或多个处理器；和
其上存储有指令的一个或多个机器可读介质，当所述一个或多个处理器执行时，使得所述设备执行前述的一个或多个所述的方法。
为实现上述目的及其他相关目的，本发明提供一个或多个机器可读介质，其上存储有指令，当由一个或多个处理器执行时，使得设备执行前述的一个或多个所述的方法。
如上所述，本发明提供的一种异常对象管理方法、系统、机器可读介质及设备，具有以下有益效果：
本发明通过获取检测对象的多种类型图像；确定所述检测对象的目标检测区域；获取所述目标检测区域的检测指标；根据所述检测指标判断所述检测对象是否为异常对象。本发明采用非接触式对检测指标进行检测，被检测人员无需停止、站立或做出任何动作，即可完成检测。同时，工作人员远离被测人群，有效地避免交叉感染。
附图说明
图1为本发明一实施例提供的一种异常对象管理方法的流程图；
图2为本发明另一实施例提供的一种异常对象管理方法的流程图；
图3为本发明又一实施例提供的一种异常对象管理方法的流程图；
图4为本发明一实施例提供的一种异常对象管理系统的硬件结构示意图；
图5为本发明一实施例提供的终端设备的硬件结构示意图；
图6为本发明另一实施例提供的终端设备的硬件结构示意图。
具体实施方式
以下通过特定的具体实例说明本发明的实施方式，本领域技术人员可由本说明书所揭露的内容轻易地了解本发明的其他优点与功效。本发明还可以通过另外不同的具体实施方式加以实施或应用，本说明书中的各项细节也可以基于不同观点与应用，在没有背离本发明的精神下进行各种修饰或改变。需说明的是，在不冲突的情况下，以下实施例及实施例中的特征可以相互组合。
需要说明的是，以下实施例中所提供的图示仅以示意方式说明本发明的基本构想，遂图式中仅显示与本发明中有关的组件而非按照实际实施时的组件数目、形状及尺寸绘制，其实际实施时各组件的型态、数量及比例可为一种随意的改变，且其组件布局型态也可能更为复杂。
如图1所示，一种异常对象管理方法，包括：
S11获取检测对象的多种类型图像；
S12确定所述检测对象的目标检测区域；
S13获取所述目标检测区域的检测指标；
S14根据所述检测指标判断所述检测对象是否为异常对象。
本发明通过获取检测对象的多种类型图像；确定所述检测对象的目标检测区域；获取所述目标检测区域的检测指标；根据所述检测指标判断所述检测对象是否为异常对象。本发明采用非接触式对检测指标进行检测，被检测人员无需停止、站立或做出任何动作，即可完成检测。同时，工作人员远离被测人群，有效地避免交叉感染。
在本实施例中，所述多种类型图像可以包括：可见光图像、红外图像、激光图像。其中，可见光图像可以通过可见光图像采集传感器进行采集，红外图像可以通过红外图像采集传感器进行采集，当然，也可以由RGB-IR图像传感器(可同时接收RGB分量和IR分量)采集图像后，通过RGB-IR处理单元将接收到的RGB-IR图像数据，经过分离，得到同步的RGB图像(可见光图像)和IR图像(红外图像)；激光图像可以通过激光图像采集传感器获取模块进行获取。当然，在另一实施例中，可以采用通过一个设备对其中的至少两种图像进行采集，例如，可以同时对可见光图像和红外图像进行采集的红外测温探头，或者可以同时对激光图像和红外图像进行采集的激光测温探头或者具有相同功能的其他图像采集设备；或者可以同时采采可见光图像、红外图像、激光图像的图像采集设备。
在本实施例中，目标检测区域的检测指标包括：温度、血液核酸特征。
若所述检测指标为温度，则当检测对象的目标检测区域的温度超过温度阈值时，该检测对象为异常对象。最后，当检测到异常对象时，发出报警提示。
可以理解的是，用户可以对报警参数进行设置，比如预设温度阈值、报警灵敏度等。比如，当目标检测区域的温度超过37.3度时，进行报警。其中，报警的方式有多种，比如声光指示报警，或者语音报警。
在呈现红外图像或激光图像的屏幕上用醒目颜色显示，并可对报警等级进行设定，可以用不同色彩显示不同报警等级，不同的报警等级发出不同的报警信号。比如，报警等级低，可以只发出声光报警，报警等极较高的发出语言报警，报警等级高的，同时发出声光报警和语音报警。
若所述检测指标为血液核酸特征，则当检测对象的目标检测区域的血液核酸特征符合预设条件时，则该检测对象为异常对象。可以理解的是，需预先设置有一异常核酸特征库，其中存有若干核酸特征，这些核酸特征能够反映人体的不正常状态，通过这些核酸特征可以确定与之对应的异常症状。符合预设条件则可以认为是检测对象的血液核酸特征为异常核酸特征库中的一种。最后，当检测到异常对象时，发出报警提示。发出报警的提示可以参考前述实施例，此处不再进行赘述。
在一实施例中，基于多种类型图像可以确定所述检测对象的目标检测区域，然后根据目标检测区域的检测指标判断检测对象是否为异常对象。以可见光图像与红外图像为例。如图2所示，具体的流程包括：
S21对所述可见光图像进行目标部位检测，得到目标部位位置；确定所述目标部位位置在检测对象的红外图像中的目标检测区域；
S22获取检测对象的所述目标检测区域的检测指标；
S23根据所述目标检测区域的检测指标判断检测对象是否为异常对象。
其中，目标部位包括人脸、手背、脖子、肩头，所述目标检测区域包括人脸区域、手背区域、脖子区域、肩头区域。
下面以目标部位为人脸，目标检测区域为人脸区域，检测指标为温度进行说明。
可以理解的是，由于红外探测是一个持续的过程，会在一段时间内持续性地进行检测以获得多个红外图像。因此，在进行人脸区域的温度检测时，需要获得同一时刻的图像，即当前时刻的红外图像和当前时刻的可见光图像。在人脸区域确定过程中，先对当前时刻的可见光图像进行人脸检测，获得人脸的位置，然后将当前时刻的可见光图像中的人脸位置映射到所述检测对象当前时刻的红外图像中，得到该检测对象在当前时刻的红外图像中的人脸区域。
确定好人脸区域后，就可以对当前时刻红外图像中的人脸区域进行测温，以获人脸区域的温度。
可以理解的是，人脸区域的图像为红外图像，可以预先获取颜色与温度之间的对应关系，根据颜色与温度之间的对应关系，确定人脸区域中的颜色对应的温度，从而可以确定人脸区域的温度。
本实施例采用的是人脸检测技术，可对视频画面内多人脸同时进行检测，以获取检测对象的人脸数据。进一步，可以通过人脸数据获得最佳人脸，测量人脸温度以最佳人脸时的人脸区域作为测温对象。最佳人脸可以通过人脸质量分、人脸大小、人脸角度、人脸遮挡率等多维度综合选择。
在另一实施例中，基于多种类型图像可以确定所述检测对象的目标检测区域，然后根据目标检测区域的检测指标判断检测对象是否为异常对象。以可见光图像与激光图像为例。如图3所示，具体的流程包括：
S31对所述可见光图像进行目标部位检测，得到目标部位位置；确定所述目标部位位置在检测对象的激光图像中的目标检测区域；
S32获取检测对象的所述目标检测区域的检测指标；
S33根据所述目标检测区域的检测指标判断检测对象是否为异常对象。
其中，目标部位包括人脸、手背、脖子、肩头，所述目标检测区域包括人脸区域、手背区域、脖子区域、肩头区域。
下面以目标部位为人脸，目标检测区域为人脸区域，检测指标为温度进行说明。
可以理解的是，在进行人脸区域的温度检测时，需要获得同一时刻的图像，即当前时刻的可见光图像和当前时刻的激光图像。在人脸区域确定过程中，先对当前时刻的可见光进行人脸检测，获得人脸的位置，然后将当前时刻的可见光图像中的人脸位置映射到所述检测对象当前时刻的激光图像中，得到该检测对象在当前时刻的激光图像中的人脸区域。
确定好人脸区域后，就可以对当前时刻激光图像中的人脸区域进行测温，以获人脸区域的温度。
本实施例采用的是人脸检测技术，可对视频画面内多人脸同时进行检测，以获取检测对象的人脸数据。进一步，可以通过人脸数据获得最佳人脸，测量人脸温度以最佳人脸时的人脸区域作为测温对象。最佳人脸可以通过人脸质量分、人脸大小、人脸角度、人脸遮挡率等多维度综合选择。
由于不同的年龄会有不同的温度，因此，该方法还包括：
获取检测对象的年龄属性；
根据不同的年龄属性设定与不同年龄段对应的温度阈值。
例如，小孩代谢率较高，体温较成人稍高，对应小孩的温度阈值可设置稍高一点；年老者代谢率较低，温度可比青壮年稍低，因此，对应年老者阈值可设置稍低一点。
在实施例中，还可以采用人脸识别技术或人体识别技术对所述异常对象进行追踪。
抓拍检测对象人脸或人体后，通过对检测指标进行检测，判断为异常对象后，通过识别出的人脸或人体特征，对异常对象进行追踪。
或者，抓拍检测对象的人脸或人体后，与异常对象库中的人脸或人体进行比对，比对成功的，则对该检测对象进行跟踪。
在一实施例中，若所述目标检测区域为人脸区域，该方法还包括：
判断所述检测对象是否存在抽烟行为；
若存在抽烟行为，则对抽烟区域进行屏蔽。
可以认为，燃烧的烟头属于外来热源，会对人脸区域温度的检测产生干扰，因此如果检测对象存在抽烟行为，则对抽烟区域进行屏蔽。
其中，是否存在抽烟行为可以通过以下方法进行判断。例如：
先获取检测对象的行为图片；
然后将所述行为图片输入至预先训练好的基于神经网络的行为识别模型中进行行为识别处理，得到用于标记检测对象的行为的行为标识；
若所述行为标识为预设的抽烟行为标识，则确定所述检测对象的行为属于抽烟行为。
可以理解的是，目标检测区域的温度与获取图像的图像采集装置和目标检测区域之间的距离相关，因此，在一实施例中，该方法还包括：基于检测对象与所述图像采集装置的距离对所述目标检测区域的温度进行补偿。通过对目标检测区域的温度进行补偿提高了测量的精度。
由于在进行红外测温的时候，环境因素会对测温的准确性产生影响，因此需要对目标检测区的温度进行补偿。具体地，获取环境温度，根据所述环境温度对所述目标检测区域的温度进行补偿。更加具体地，在环境温度较低情况下，检测温度值会低于真实体温，此时应该根据环境温度对红外传感测量值做适当提升；在环境温度较高情况下，检测温度值可能会高于真实体温，此时应该根据环境温度对红外传感测量值做适当降低。
本发明通过红外图像、可见光图像、激光图像，同时结合人工智能算法，可对发热人员自动跟踪、测量、告警，达到正常人员无感快速通关、发热人员及时告警，降低检查人员感染的风险。
如图4所示，一种异常对象管理系统，包括：
图像获取模块41，用于获取检测对象的多种类型图像；
检测区域确定模块42，用于确定所述检测对象的目标检测区域；
指标检测模块43，用于获取所述目标检测区域的检测指标；
异常判断模块44，用于根据所述检测指标判断所述检测对象是否为异常对象。
本发明通过获取检测对象的多种类型图像；确定所述检测对象的目标检测区域；获取所述目标检测区域的检测指标；根据所述检测指标判断所述检测对象是否为异常对象。本发明采用非接触式对检测指标进行检测，被检测人员无需停止、站立或做出任何动作，即可完成检测。同时，工作人员远离被测人群，有效地避免交叉感染。
在本实施例中，所述多种类型图像可以包括：可见光图像、红外图像、激光图像。其中，可见光图像可以通过可见光相机进行采集，红外图像可以通过红外图像采集传感器进行采集，激光图像可以通过激光图像获取模块进行获取。当然，在另一实施例中，可以采用通过一个设备对其中的至少两种图像进行采集，例如，可以同时对可见光图像和红外图像进行采集的红外测温探头，或者可以同时对激光图像和红外图像进行采集的激光测温探头或者具有相同功能的其他图像采集设备；当然，也可以由RGB-IR图像传感器(可同时接收RGB分量和IR分量)采集图像后，通过RGB-IR处理单元将接收到的RGB-IR图像数据，经过分离，得到同步的RGB图像(可见光图像)和IR图像(红外图像)；还可以同时采采可见光图像、红外图像、激光图像的图像采集设备。
在本实施例中，目标检测区域的检测指标包括：温度、血液核酸特征。
若所述检测指标为温度，则当检测对象的目标检测区域的温度超过温度阈值时，该检测对象为异常对象。最后，通过报警提示模块，在检测到异常对象时，发出报警提示。
可以理解的是，用户可以对报警参数进行设置，比如预设温度阈值、报警灵敏度等。比如，当目标检测区域的温度超过37.3度时，进行报警。其中，报警的方式有多种，比如声光指示报警，或者语音报警。
或者，在呈现红外图像的屏幕上用醒目颜色显示，并可对报警等级进行设定，可以用不同色彩显示不同报警等级，不同的报警等级发出不同的报警信号。比如，报警等级低，可以只发出声光报警，报警等极较高的发出语言报警，报警等级高的，同时发出声光报警和语音报警。
若所述检测指标为血液核酸特征，则当检测对象的目标检测区域的血液核酸特征符合预设条件时，则该检测对象为异常对象。可以理解的是，需预先设置有一异常核酸特征库，其中存有若干核酸特征，这些核酸特征能够反映人体的不正常状态，通过这些核酸特征可以确定与之 对应的异常症状。符合预设条件则可以认为是检测对象的血液核酸特征为异常核酸特征库中的一种。最后，当检测到异常对象时，发出报警提示。发出报警的提示可以参考前述实施例，此处不再进行赘述。
在一实施例中，基于多种类型图像可以确定所述检测对象的目标检测区域，然后根据目标检测区域的检测指标判断检测对象是否为异常对象。以可见光图像与红外图像为例。具体的流程包括：
对所述可见光图像进行目标部位检测，得到目标部位位置；确定所述目标部位位置在检测对象的红外图像中的目标检测区域；
获取检测对象的所述目标检测区域的检测指标；
根据所述目标检测区域的检测指标判断检测对象是否为异常对象。
其中，目标部位包括人脸、手背、脖子、肩头，所述目标检测区域包括人脸区域、手背区域、脖子区域、肩头区域。
下面以目标部位为人脸，目标检测区域为人脸区域进行说明。
可以理解的是，由于红外探测是一个持续的过程，会在一段时间内持续性地进行检测以获得多个红外图像。因此，在进行人脸区域的温度检测时，需要获得同一时刻的图像，即当前时刻的红外图像和当前时刻的可见光图像。在人脸区域确定过程中，先对当前时刻的可见光图像进行人脸检测，获得人脸的位置，然后将当前时刻的可见光图像中的人脸位置映射到所述检测对象当前时刻的红外图像中，得到该检测对象在当前时刻的红外图像中的人脸区域。
确定好人脸区域后，就可以对当前时刻红外图像中的人脸区域进行测温，以获人脸区域的温度。
可以理解的是，人脸区域的图像为红外图像，可以预先获取颜色与温度之间的对应关系，根据颜色与温度之间的对应关系，确定人脸区域中的颜色对应的温度，从而可以确定人脸区域的温度。
本实施例采用的是人脸检测技术，可对视频画面内多人脸同时进行检测，以获取检测对象的人脸数据。进一步，可以通过人脸数据获得最佳人脸，测量人脸温度以最佳人脸时的人脸区域作为测温对象。最佳人脸可以通过人脸质量分、人脸大小、人脸角度、人脸遮挡率等多维度综合选择。
在另一实施例中，基于多种类型图像可以确定所述检测对象的目标检测区域，然后根据目标检测区域的检测指标判断检测对象是否为异常对象。以可见光图像与激光图像为例。具体的流程包括：
对所述可见光图像进行目标部位检测，得到目标部位位置；确定所述目标部位位置在检测对象的激光图像中的目标检测区域；
获取激光图像的所述目标检测区域的检测指标；
根据所述目标检测区域的检测指标判断检测对象是否为异常对象。
其中，目标部位包括人脸、手背、脖子、肩头，所述目标检测区域包括人脸区域、手背区域、脖子区域、肩头区域。
下面以目标部位为人脸，目标检测区域为人脸区域进行说明。
可以理解的是，在进行人脸区域的温度检测时，需要获得同一时刻的图像，即当前时刻的可见光图像和当前时刻的激光图像。在人脸区域确定过程中，先对当前时刻的可见光图像进行人脸检测，获得人脸的位置，然后将当前时刻的可见光图像中的人脸位置映射到所述检测对象当前时刻的激光图像中，得到该检测对象在当前时刻的激光图像中的人脸区域。
确定好人脸区域后，就可以对当前时刻激光像中的人脸区域进行测温，以获人脸区域的温度。
可以理解的是，人脸区域的图像为激光图像，可以预先获取颜色与温度之间的对应关系，根据颜色与温度之间的对应关系，确定人脸区域中的颜色对应的温度，从而可以确定人脸区域的温度。
本实施例采用的是人脸检测技术，可对视频画面内多人脸同时进行检测，以获取检测对象的人脸数据。进一步，可以通过人脸数据获得最佳人脸，测量人脸温度以最佳人脸时的人脸区域作为测温对象。最佳人脸可以通过人脸质量分、人脸大小、人脸角度、人脸遮挡率等多维度综合选择。
由于不同的年龄会有不同的温度，因此，该系统还包括：
年龄属性获取模块，用于获取检测对象的年龄属性；
温度阈值设定模块，用于根据不同的年龄属性设定与不同年龄段对应的温度阈值。
例如，小孩代谢率较高，体温较成人稍高，对应小孩的温度阈值可设置稍高一点；年老者代谢率较低，温度可比青壮年稍低，因此，对应年老者阈值可设置稍低一点。
在实施例中，该系统还包括：
追踪模块，用于采用人脸识别技术或人体识别技术对所述异常对象进行追踪。
抓拍检测对象人脸或人体后，通过对检测指标进行检测，判断为异常对象后，通过识别出的人脸或人体特征，对异常对象进行追踪。
或者，抓拍检测对象的人脸或人体后，与异常对象库中的人脸或人体进行比对，比对成功 的，则对该检测对象进行跟踪。
在一实施例中，若所述目标检测区域为人脸区域，该系统还包括：
抽烟判断模块，用于判断所述检测对象是否存在抽烟行为；
屏蔽模块，用于在存在抽烟行为对抽烟区域进行屏蔽。
可以认为，燃烧的烟头属于外来热源，会对人脸区域温度的检测产生干扰，因此如果检测对象存在抽烟行为，则对抽烟区域进行屏蔽。
其中，是否存在抽烟行为可以通过以下方法进行判断。例如：
先获取检测对象的行为图片；
然后将所述行为图片输入至预先训练好的基于神经网络的行为识别模型中进行行为识别处理，得到用于标记检测对象的行为的行为标识；
若所述行为标识为预设的抽烟行为标识，则确定所述检测对象的行为属于抽烟行为。
可以理解的是，目标检测区域的温度与获取图像的图像采集装置和目标检测区域之间的距离相关，因此，在一实施例中，该系统还包括：
第一温度补偿模块，基于检测对象与图像采集装置的距离对所述目标检测区域的温度进行补偿。通过对目标检测区域的温度进行补偿提高了测量的精度。
由于在进行红外测温的时候，环境因素会对测温的准确性产生影响，因此需要对目标检测区的温度进行补偿。因此，该系统还包括：
温度获取模块，用于获取环境温度；
第二温度补偿模块，用于根据所述环境温度对所述目标检测区域的温度进行补偿。
具体地，更加具体地，在环境温度较低情况下，检测温度值会低于真实体温，此时应该根据环境温度对红外传感测量值做适当提升；在环境温度较高情况下，检测温度值可能会高于真实体温，此时应该根据环境温度对红外传感测量值做适当降低。
本发明通过红外图像、可见光图像、激光图像，同时结合人工智能算法，可对发热人员自动跟踪、测量、告警，达到正常人员无感快速通关、发热人员及时告警，降低检查人员感染的风险。
本发明采用非接触式测温，被检测人员无需停止、站立或做出任何动作，即可完成体温检测。同时，工作人员远离被测人群，有效地避免交叉感染。图像响应速度为0.04ms，测温响应速度快，能够在30毫秒内完成16个目标检测，可同时对16个目标实时测温，具有非接触快速、方便、直观、安全等特点，克服了传统的体温计、额温计、点温计和耳温计等仅针对个体测量，(如使用传统的体温计检测一般需要3分钟/人次，普通点温计、额温计、耳温计为单 个人体检测，一般检测时间需要4～5秒/人次)。
本发明测温范围为：0℃～60℃，测温精度：28℃～45℃≤±0.3℃，内置自动测温修正。人脸检疫体温筛查预警避免了耗时多、易交叉感染等不足，而可有效的控制疫情扩散，减少人员伤亡，非常适合于在机场、码头、车站、银行、医院和商场等人流量较大的场合进行体温快速排查。
本发明能够进行远距离、大面积检测
热成像分辨率384*288；焦距6.8/15mm：1.2-2米检测距离，15mm焦距：3-7米检测距离；
可见光分辨率：1920*1080，焦距5mm；
本申请实施例还提供了一种设备，该设备可以包括：一个或多个处理器；和其上存储有指令的一个或多个机器可读介质，当由所述一个或多个处理器执行时，使得所述设备执行图1所述的方法。在实际应用中，该设备可以作为终端设备，也可以作为服务器，终端设备的例子可以包括：智能手机、平板电脑、电子书阅读器、MP3(动态影像专家压缩标准语音层面3，Moving Picture Experts GroupAudio Layer III)播放器、MP4(动态影像专家压缩标准语音层面4，Moving Picture Experts Group Audio Layer IV)播放器、膝上型便携计算机、车载电脑、台式计算机、机顶盒、智能电视机、可穿戴设备等等，本申请实施例对于具体的设备不加以限制。
本申请实施例还提供了一种非易失性可读存储介质，该存储介质中存储有一个或多个模块(programs)，该一个或多个模块被应用在设备时，可以使得该设备执行本申请实施例的图1中方法所包含步骤的指令(instructions)。
图5为本申请一实施例提供的终端设备的硬件结构示意图。如图所示，该终端设备可以包括：输入设备1100、第一处理器1101、输出设备1102、第一存储器1103和至少一个通信总线1104。通信总线1104用于实现元件之间的通信连接。第一存储器1103可能包含高速RAM存储器，也可能还包括非易失性存储NVM，例如至少一个磁盘存储器，第一存储器1103中可以存储各种程序，用于完成各种处理功能以及实现本实施例的方法步骤。
可选的，上述第一处理器1101例如可以为中央处理器(Central Processing Unit，简称CPU)、应用专用集成电路(ASIC)、数字信号处理器(DSP)、数字信号处理设备(DSPD)、可编程逻辑器件(PLD)、现场可编程门阵列(FPGA)、控制器、微控制器、微处理器或其他电子元件实现，该第一处理器1101通过有线或无线连接耦合到上述输入设备1100和输出设备1102。
可选的，上述输入设备1100可以包括多种输入设备，例如可以包括面向用户的用户接口、面向设备的设备接口、软件的可编程接口、摄像头、传感器中至少一种。可选的，该面向设备的设备接口可以是用于设备与设备之间进行数据传输的有线接口、还可以是用于设备与设备之 间进行数据传输的硬件插入接口(例如USB接口、串口等)；可选的，该面向用户的用户接口例如可以是面向用户的控制按键、用于接收语音输入的语音输入设备以及用户接收用户触摸输入的触摸感知设备(例如具有触摸感应功能的触摸屏、触控板等)；可选的，上述软件的可编程接口例如可以是供用户编辑或者修改程序的入口，例如芯片的输入引脚接口或者输入接口等；输出设备1102可以包括显示器、音响等输出设备。
在本实施例中，该终端设备的处理器包括用于执行各设备中各模块的功能，具体功能和技术效果参照上述实施例即可，此处不再赘述。
图6为本申请的一个实施例提供的终端设备的硬件结构示意图。图6是对图5在实现过程中的一个具体的实施例。如图所示，本实施例的终端设备可以包括第二处理器1201以及第二存储器1202。
第二处理器1201执行第二存储器1202所存放的计算机程序代码，实现上述实施例中图1所述方法。
第二存储器1202被配置为存储各种类型的数据以支持在终端设备的操作。这些数据的示例包括用于在终端设备上操作的任何应用程序或方法的指令，例如消息，图片，视频等。第二存储器1202可能包含随机存取存储器(random access memory，简称RAM)，也可能还包括非易失性存储器(non-volatile memory)，例如至少一个磁盘存储器。
可选地，第二处理器1201设置在处理组件1200中。该终端设备还可以包括：通信组件1203，电源组件1204，多媒体组件1205，语音组件1206，输入/输出接口1207和/或传感器组件1208。终端设备具体所包含的组件等依据实际需求设定，本实施例对此不作限定。
处理组件1200通常控制终端设备的整体操作。处理组件1200可以包括一个或多个第二处理器1201来执行指令，以完成上述数据处理方法中的全部或部分步骤。此外，处理组件1200可以包括一个或多个模块，便于处理组件1200和其他组件之间的交互。例如，处理组件1200可以包括多媒体模块，以方便多媒体组件1205和处理组件1200之间的交互。
电源组件1204为终端设备的各种组件提供电力。电源组件1204可以包括电源管理系统，一个或多个电源，及其他与为终端设备生成、管理和分配电力相关联的组件。
多媒体组件1205包括在终端设备和用户之间的提供一个输出接口的显示屏。在一些实施例中，显示屏可以包括液晶显示器(LCD)和触摸面板(TP)。如果显示屏包括触摸面板，显示屏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。
语音组件1206被配置为输出和/或输入语音信号。例如，语音组件1206包括一个麦克风(MIC)，当终端设备处于操作模式，如语音识别模式时，麦克风被配置为接收外部语音信号。所接收的语音信号可以被进一步存储在第二存储器1202或经由通信组件1203发送。在一些实施例中，语音组件1206还包括一个扬声器，用于输出语音信号。
输入/输出接口1207为处理组件1200和外围接口模块之间提供接口，上述外围接口模块可以是点击轮，按钮等。这些按钮可包括但不限于：音量按钮、启动按钮和锁定按钮。
传感器组件1208包括一个或多个传感器，用于为终端设备提供各个方面的状态评估。例如，传感器组件1208可以检测到终端设备的打开/关闭状态，组件的相对定位，用户与终端设备接触的存在或不存在。传感器组件1208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，包括检测用户与终端设备间的距离。在一些实施例中，该传感器组件1208还可以包括摄像头等。
通信组件1203被配置为便于终端设备和其他设备之间有线或无线方式的通信。终端设备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。在一个实施例中，该终端设备中可以包括SIM卡插槽，该SIM卡插槽用于插入SIM卡，使得终端设备可以登录GPRS网络，通过互联网与服务器建立通信。
由上可知，在图6实施例中所涉及的通信组件1203、语音组件1206以及输入/输出接口1207、传感器组件1208均可以作为图5实施例中的输入设备的实现方式。
上述实施例仅例示性说明本发明的原理及其功效，而非用于限制本发明。任何熟悉此技术的人士皆可在不违背本发明的精神及范畴下，对上述实施例进行修饰或改变。因此，举凡所属技术领域中具有通常知识者在未脱离本发明所揭示的精神与技术思想下所完成的一切等效修饰或改变，仍应由本发明的权利要求所涵盖。

Claims (30)

  1. 一种异常对象管理方法，其特征在于，包括：
    获取检测对象的多种类型图像；
    确定所述检测对象的目标检测区域；
    获取所述目标检测区域的检测指标；
    根据所述检测指标判断所述检测对象是否为异常对象。
  2. 根据权利要求1所述的异常对象管理方法，其特征在于，所述多种类型图像包括：可见光图像、红外图像、激光图像。
  3. 根据权利要求2所述的异常对象管理方法，其特征在于，所述检测指标包括：温度、血液核酸特征。
  4. 根据权利要求2所述的异常对象管理方法，其特征在于，若所述检测对象的图像包括可见光图像和红外图像；
    则对所述可见光图像进行目标部位检测，得到目标部位位置；确定所述目标部位位置在检测对象的红外图像中的目标检测区域；
    获取检测对象的所述目标检测区域的检测指标；
    根据所述目标检测区域的检测指标判断检测对象是否为异常对象。
  5. 根据权利要求2所述的异常对象管理方法，其特征在于，若所述检测对象的图像包括可见光图像和激光图像；
    则对所述可见光图像进行目标部位检测，得到目标部位位置；确定所述目标部位位置在检测对象的激光图像中的目标检测区域；
    获取检测对象的所述目标检测区域的检测指标；
    根据所述目标检测区域的检测指标判断检测对象是否为异常对象。
  6. 根据权利要求4或5所述的异常对象管理方法，其特征在于，所述目标部位包括人脸、手背、脖子、肩头，所述目标检测区域包括人脸区域、手背区域、脖子区域、肩头区域。
  7. 根据权利要求6所述的异常对象管理方法，其特征在于，若所述检测指标为温度，则当检 测对象的目标检测区域的温度超过温度阈值时，该检测对象为异常对象。
  8. 根据权利要求6所述的异常对象管理方法，其特征在于，若所述检测指标为血液核酸特征，则当检测对象的目标检测区域的血液核酸特征符合预设条件时，则该检测对象为异常对象。
  9. 根据权利要求1所述的异常对象管理方法，其特征在于，该方法还包括：
    采用人脸识别技术或人体识别技术对所述异常对象进行追踪。
  10. 根据权利要求1所述的异常对象管理方法，其特征在于，该方法还包括：
    当检测到异常对象时，发出报警提示。
  11. 根据权利要求7所述的异常对象管理方法，其特征在于，若所述检测指标为温度，则该方法还包括：
    获取检测对象的年龄属性；
    根据不同的年龄属性设定与不同年龄段对应的温度阈值。
  12. 根据权利要求7所述的异常对象管理方法，其特征在于，该方法还包括：
    基于检测对象与图像采集装置的距离对所述目标检测区域的温度进行补偿。
  13. 根据权利要求7所述的异常对象管理方法，其特征在于，该方法还包括：
    获取环境温度；
    根据所述环境温度对所述目标检测区域的温度进行补偿。
  14. 根据权利要求7所述的异常对象管理方法，其特征在于，若所述目标检测区域为人脸区域，该方法还包括：
    判断所述检测对象是否存在抽烟行为；
    若存在抽烟行为，则对抽烟区域进行屏蔽。
  15. 一种异常对象管理系统，其特征在于，包括：
    图像获取模块，用于获取检测对象的多种类型图像；
    检测区域确定模块，用于确定所述检测对象的目标检测区域；
    指标检测模块，用于获取所述目标检测区域的检测指标；
    异常判断模块，用于根据所述检测指标判断所述检测对象是否为异常对象。
  16. 根据权利要求15所述的异常对象管理系统，其特征在于，所述多种类型图像包括：可见光图像、红外图像、激光图像。
  17. 根据权利要求16所述的异常对象管理系统，其特征在于，所述检测指标包括：温度、血液核酸特征。
  18. 根据权利要求16所述的异常对象管理系统，其特征在于，若所述检测对象的图像包括可见光图像和红外图像；
    则对所述可见光图像进行目标部位检测，得到目标部位位置；确定所述目标部位位置在检测对象的红外图像中的目标检测区域；
    获取检测对象的所述目标检测区域的检测指标；
    根据所述目标检测区域的检测指标判断检测对象是否为异常对象。
  19. 根据权利要求16所述的异常对象管理系统，其特征在于，若所述检测对象的图像包括可见光图像和激光图像；
    则对所述可见光图像进行目标部位检测，得到目标部位位置；确定所述目标部位位置在检测对象的激光图像中的目标检测区域；
    获取检测对象的所述目标检测区域的检测指标；
    根据所述目标检测区域的检测指标判断检测对象是否为异常对象。
  20. 根据权利要求18或19所述的异常对象管理系统，其特征在于，所述目标部位包括人脸、手背、脖子、肩头，所述目标检测区域包括人脸区域、手背区域、脖子区域、肩头区域。
  21. 根据权利要求17所述的异常对象管理系统，其特征在于，若所述检测指标为温度，则当检测对象的目标检测区域的温度超过温度阈值时，该检测对象为异常对象。
  22. 根据权利要求17所述的异常对象管理系统，其特征在于，若所述检测指标为血液核酸特征，则当检测对象的目标检测区域的血液核酸特征符合预设条件时，则该检测对象为异常对象。
  23. 根据权利要求15所述的异常对象管理系统，其特征在于，该系统还包括：
    追踪模块，用于采用人脸识别技术或人体识别技术对所述异常对象进行追踪。
  24. 根据权利要求15所述的异常对象管理系统，其特征在于，该系统还包括：
    报警模块，用于在检测到异常对象时发出报警提示。
  25. 根据权利要求21所述的异常对象管理系统，其特征在于，若所述检测指标为温度，则该系统还包括：
    年龄属性获取模块，用于获取检测对象的年龄属性；
    温度阈值设定模块，用于根据不同的年龄属性设定与不同年龄段对应的温度阈值。
  26. 根据权利要求21所述的异常对象管理系统，其特征在于，该系统还包括：
    第一温度补偿模块，基于检测对象与图像采集装置的距离对所述目标检测区域的温度进行补偿。
  27. 根据权利要求21所述的异常对象管理系统，其特征在于，若所述目标检测区域为人脸区域，该系统还包括：
    温度获取模块，用于获取环境温度；
    第二温度补偿模块，用于根据所述环境温度对所述目标检测区域的温度进行补偿。
  28. 根据权利要求21所述的异常对象管理系统，其特征在于，该系统还包括：
    抽烟判断模块，用于判断所述检测对象是否存在抽烟行为；
    屏蔽模块，用于在存在抽烟行为对抽烟区域进行屏蔽。
  29. 一种设备，其特征在于，包括：
    一个或多个处理器；和
    其上存储有指令的一个或多个机器可读介质，当所述一个或多个处理器执行时，使得所述设备执行如权利要求1-14所述的一个或多个所述的方法。
  30. 一个或多个机器可读介质，其特征在于，其上存储有指令，当由一个或多个处理器执行时，使得设备执行如权利要求1-14所述的一个或多个所述的方法。
PCT/CN2020/110454 2020-02-12 2020-08-21 一种异常对象管理方法、系统、机器可读介质及设备 WO2021159682A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010089232.4A CN111202504A (zh) 2020-02-12 2020-02-12 一种异常对象管理方法、系统、机器可读介质及设备
CN202010089232.4 2020-02-12

Publications (1)

Publication Number Publication Date
WO2021159682A1 true WO2021159682A1 (zh) 2021-08-19

Family

ID=70781028

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/110454 WO2021159682A1 (zh) 2020-02-12 2020-08-21 一种异常对象管理方法、系统、机器可读介质及设备

Country Status (2)

Country Link
CN (1) CN111202504A (zh)
WO (1) WO2021159682A1 (zh)

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111202504A (zh) * 2020-02-12 2020-05-29 上海云从汇临人工智能科技有限公司 一种异常对象管理方法、系统、机器可读介质及设备
CN111310692B (zh) * 2020-02-25 2021-04-02 云从科技集团股份有限公司 一种检测对象管理方法、系统、机器可读介质及设备
CN111458037A (zh) * 2020-06-08 2020-07-28 深圳市迪米科技有限公司 一种体温筛查记录装置及体温筛查处理方法
CN111695509A (zh) * 2020-06-12 2020-09-22 云从科技集团股份有限公司 一种身份验证方法、装置、机器可读介质及设备
CN111693147A (zh) * 2020-06-12 2020-09-22 北京百度网讯科技有限公司 温度补偿的方法、装置、电子设备及计算机可读存储介质
CN111738132B (zh) * 2020-06-17 2024-03-05 银河水滴科技（北京）有限公司 人体温度的测量方法、装置、电子设备及可读存储介质
CN113834571A (zh) * 2020-06-24 2021-12-24 杭州海康威视数字技术股份有限公司 一种目标测温方法、装置及测温系统
CN113139413A (zh) * 2020-08-07 2021-07-20 西安天和防务技术股份有限公司 人员管理方法、装置及电子设备
CN113343859A (zh) * 2021-06-10 2021-09-03 浙江大华技术股份有限公司 吸烟行为检测方法、装置、存储介质及电子装置
CN113420629B (zh) * 2021-06-17 2023-04-28 浙江大华技术股份有限公司 一种图像处理方法、装置、设备及介质
CN117373110A (zh) * 2023-08-30 2024-01-09 武汉星巡智能科技有限公司 可见光-热红外成像的婴幼儿行为识别方法、装置及设备

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102147835A (zh) * 2010-11-26 2011-08-10 中华人民共和国深圳出入境检验检疫局 用于口岸车道的司机体温自动测量系统及实现方法
CN108344525A (zh) * 2018-02-09 2018-07-31 英华达（上海）科技有限公司 自适应体温监控方法及系统
CN110160670A (zh) * 2019-05-05 2019-08-23 深圳中集智能科技有限公司 人体体温检测装置
CN110411570A (zh) * 2019-06-28 2019-11-05 武汉高德智感科技有限公司 基于人体检测和人体跟踪技术的红外人体温度筛查方法
CN111202504A (zh) * 2020-02-12 2020-05-29 上海云从汇临人工智能科技有限公司 一种异常对象管理方法、系统、机器可读介质及设备
CN111325127A (zh) * 2020-02-12 2020-06-23 上海云从汇临人工智能科技有限公司 一种异常对象判断方法、系统、机器可读介质及设备

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105931254B (zh) * 2016-05-17 2019-03-26 北京市检验检疫科学技术研究院 一种国境口岸出入境检验检疫低温查验方法及系统

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102147835A (zh) * 2010-11-26 2011-08-10 中华人民共和国深圳出入境检验检疫局 用于口岸车道的司机体温自动测量系统及实现方法
CN108344525A (zh) * 2018-02-09 2018-07-31 英华达（上海）科技有限公司 自适应体温监控方法及系统
CN110160670A (zh) * 2019-05-05 2019-08-23 深圳中集智能科技有限公司 人体体温检测装置
CN110411570A (zh) * 2019-06-28 2019-11-05 武汉高德智感科技有限公司 基于人体检测和人体跟踪技术的红外人体温度筛查方法
CN111202504A (zh) * 2020-02-12 2020-05-29 上海云从汇临人工智能科技有限公司 一种异常对象管理方法、系统、机器可读介质及设备
CN111325127A (zh) * 2020-02-12 2020-06-23 上海云从汇临人工智能科技有限公司 一种异常对象判断方法、系统、机器可读介质及设备

Also Published As

Publication number Publication date
CN111202504A (zh) 2020-05-29

Similar Documents

Publication Publication Date Title
WO2021159682A1 (zh) 一种异常对象管理方法、系统、机器可读介质及设备
WO2021159683A1 (zh) 一种异常对象判断方法、系统、机器可读介质及设备
CN111310692B (zh) 一种检测对象管理方法、系统、机器可读介质及设备
US10145980B2 (en) Wrist-detection algorithm
CN103955272B (zh) 一种终端设备用户姿态检测系统
CN111223225A (zh) 一套集成测温和人脸识别闸机伴侣的检测通行系统
CN110196103A (zh) 温度测量方法及相关设备
US20120075463A1 (en) User interface system and method using thermal imaging
US10959646B2 (en) Image detection method and image detection device for determining position of user
CN111297337A (zh) 一种检测对象判断方法、系统、机器可读介质及设备
WO2021259365A1 (zh) 一种目标测温方法、装置及测温系统
TWM602631U (zh) 人臉追蹤測溫系統
CN112806962A (zh) 基于tof及红外模组的小孩睡眠状态监测方法及装置
Wu et al. IoT-based wearable health monitoring device and its validation for potential critical and emergency applications
WO2022143384A1 (zh) 智能手环及其控制方法
WO2022007348A1 (zh) 温度检测方法、装置、介质及电子设备
CN107669282A (zh) 基于面部识别的测谎仪
CN105310697B (zh) 测量血氧饱和度的方法及装置
CN104754301A (zh) 具近端看护功能及云端传送的自动监视系统
CN108652621A (zh) 一种吞咽实时监测方法及其系统
TWI335181B (en) Human behavior event detection system, method and device
CN204442550U (zh) 具近端看护功能及云端传送的自动监视设备
Rethnakumar et al. Smartphone based application for body temperature and heart rate measurements
Wahyuni et al. IoT-Based Pulse Oximetry Design as Early Detection of Covid-19 Symptoms.
US11087157B2 (en) Image detection method and image detection device utilizing dual analysis

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: 20918328

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20918328

Country of ref document: EP

Kind code of ref document: A1

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 1205 DATED 28.02.2023)

122 Ep: pct application non-entry in european phase

Ref document number: 20918328

Country of ref document: EP

Kind code of ref document: A1