CN113639871B - Target object detection method, device and equipment and storage medium - Google Patents

Target object detection method, device and equipment and storage medium Download PDF

Info

Publication number
CN113639871B
CN113639871B CN202010335189.5A CN202010335189A CN113639871B CN 113639871 B CN113639871 B CN 113639871B CN 202010335189 A CN202010335189 A CN 202010335189A CN 113639871 B CN113639871 B CN 113639871B
Authority
CN
China
Prior art keywords
heat value
reference heat
position information
information
determining
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202010335189.5A
Other languages
Chinese (zh)
Other versions
CN113639871A (en
Inventor
毛恩云
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hangzhou Hikvision System Technology Co Ltd
Original Assignee
Hangzhou Hikvision System Technology Co Ltd
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 Hangzhou Hikvision System Technology Co Ltd filed Critical Hangzhou Hikvision System Technology Co Ltd
Priority to CN202010335189.5A priority Critical patent/CN113639871B/en
Publication of CN113639871A publication Critical patent/CN113639871A/en
Application granted granted Critical
Publication of CN113639871B publication Critical patent/CN113639871B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01JMEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
    • G01J5/00Radiation pyrometry, e.g. infrared or optical thermometry
    • G01J5/0022Radiation pyrometry, e.g. infrared or optical thermometry for sensing the radiation of moving bodies
    • G01J5/0025Living bodies
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/70Determining position or orientation of objects or cameras
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01JMEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
    • G01J5/00Radiation pyrometry, e.g. infrared or optical thermometry
    • G01J2005/0077Imaging
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/30Subject of image; Context of image processing
    • G06T2207/30196Human being; Person
    • G06T2207/30201Face

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • Geophysics And Detection Of Objects (AREA)
  • Image Analysis (AREA)

Abstract

The application provides a target object detection method, a target object detection device and a target object detection storage medium, which can improve the accuracy of detection results. The method comprises the following steps: acquiring first position information of a specified object and a heat value corresponding to the specified object; checking whether a reference heat value associated with the first position information exists in the recorded reference heat information; if yes, determining a reference heat value for determining whether the designated object is a heating target object according to the recorded reference heat value associated with the first position information and the heat value, determining whether the designated object is the heating target object according to the reference heat value, and adding the reference heat value to the reference heat value as the reference heat value associated with the first position information when the designated object is not the heating target object.

Description

Target object detection method, device and equipment and storage medium
Technical Field
The present application relates to the field of monitoring technologies, and in particular, to a target object detection method, apparatus, device, and storage medium.
Background
The detection of body temperature of a human body or an animal subject, and the detection of a target subject with abnormal temperature, i.e., a target subject with fever, are effective means for preventing the spread of diseases such as SARS and novel coronavirus on a large scale. In the traditional mode, temperature acquisition is carried out on an object by adopting a temperature sensor manually, and whether the acquired temperature is abnormal or not is judged, but the efficiency of the mode is too low. With the continuous development of the thermal imaging technology, the automatic detection of the heating target object is realized by adopting a thermal imaging monitoring mode, so that the detection efficiency is improved.
In a related mode, after acquiring a heat value of a specified object from thermal imaging data acquired by thermal imaging equipment, converting the heat value into a corresponding temperature, comparing the temperature with a temperature threshold, and if the temperature is greater than the temperature threshold, determining that the specified object is a heating target object. Wherein, the corresponding relation between the heat value and the temperature is preset, and the corresponding relation is shared by a plurality of thermal imaging devices.
However, there may be differences in accuracy between different thermal imaging devices, and objects of the same temperature may appear as different thermal values in thermal imaging data acquired by different thermal imaging devices. In the above manner, for different devices, the temperatures actually corresponding to the same heat value may be different, and the corresponding relationship is adopted to determine the temperature corresponding to the heat value, and the determined temperature may have a greater entrance or exit with the actual temperature, resulting in an inaccurate detection result of the heating target.
Disclosure of Invention
In view of this, the present application provides a method, an apparatus, a device, and a storage medium for detecting a target object, which can improve the accuracy of a detection result.
A first aspect of the present application provides a target object detection method, including:
acquiring first position information of a specified object and a heat value corresponding to the specified object;
checking whether a reference heat value associated with the first position information exists in the recorded reference heat information;
if so, determining a reference heat value for determining whether the specified object is the heating target object according to the recorded reference heat value associated with the first position information and the heat value, determining whether the specified object is the heating target object according to the reference heat value, and adding the reference heat value to the reference heat information as the reference heat value associated with the first position information when the specified object is not the heating target object.
According to an embodiment of the application, the obtaining of the first position information of the designated object includes:
acquiring a visible light image and thermal imaging data of the specified object, which are acquired when the specified object is at a specified position;
and converting the second position information of the specified object in the visible light image according to a preset conversion relation to obtain the first position information, wherein the conversion relation is used for mutually converting the position information in the visible light image and the position information in the thermal imaging data.
According to an embodiment of the application, the first position information is area information of a target area where the specified object is located in thermal imaging data;
the obtaining of the heat value corresponding to the specified object includes:
and determining the corresponding heat value of the specified object according to the heat value of each coordinate position in the target area.
According to an embodiment of the application, the checking whether the reference heat value associated with the first position information exists in the recorded reference heat information comprises:
determining a searching range for searching a reference heat value associated with the first position information according to the first position information;
and checking whether a reference heat value corresponding to the target coordinate position in the search range exists in the recorded reference heat information, if so, determining that a reference heat value related to the first position information exists in the recorded reference heat information, and otherwise, determining that the reference heat value related to the first position information does not exist in the recorded reference heat information.
According to an embodiment of the application, the first position information is area information of a target area where the specified object is located in thermal imaging data;
the determining a search range for searching for the reference heat value associated with the first position information according to the first position information includes:
constructing a corresponding circular area in the thermal imaging data by taking the coordinate position of the central point in the target area as the center of a circle and a preset length as a radius; determining the circular area as the search range.
According to an embodiment of the application, the determining a reference heat value for determining whether the specified object is the heat generation target object according to the reference heat value and the heat value associated with the recorded first position information includes:
and setting and calculating the heat value and a reference heat value corresponding to the target coordinate position in the recorded reference heat information within the search range, and determining the obtained result as the reference heat value.
According to an embodiment of the present application, determining whether the specified object is a heat generation target object according to the reference heat value includes:
determining a corresponding heat threshold value according to the reference heat value;
and when the heat value is larger than the heat threshold value, determining that the specified object is a heating target object, otherwise, determining that the specified object is not the heating target object.
According to an embodiment of the present application, when the specified object is a heat generation target object, the method further includes:
carrying out heating alarm processing; and/or the presence of a gas in the gas,
adding a reference heat value as a reference heat value associated with the first position information to the reference heat information.
According to an embodiment of the application, the first position information is area information of a target area where the specified object is located in thermal imaging data;
recording the heat value as a reference heat value associated with first position information to the reference heat information includes: correspondingly recording the coordinate position of the central point in the target area and the heat value to the reference heat information;
the adding a reference heat value associated with a reference heat value as first position information to the reference heat information comprises: if the central point coordinate position does not exist in the reference heat information, correspondingly recording the central point coordinate position and the reference heat value to the reference heat information; if the central point coordinate position exists in the reference heat information, when the reference heat value corresponding to the central point coordinate position is different from the reference heat value, the reference heat value corresponding to the central point coordinate position is updated to be the reference heat value.
A second aspect of the present application provides a target object detection apparatus, the apparatus comprising:
the specified object information determining module is used for obtaining first position information of a specified object and a heat value corresponding to the specified object;
the reference heat value searching module is used for checking whether a reference heat value related to the first position information exists in the recorded reference heat information or not;
and if so, determining a reference heat value for determining whether the specified object is the heating target object according to the recorded reference heat value associated with the first position information and the heat value, determining whether the specified object is the heating target object according to the reference heat value, and adding the reference heat value to the reference heat value as the reference heat value associated with the first position information when the specified object is not the heating target object.
According to an embodiment of the present application, when the specified object information determining module obtains the first location information of the specified object, the specified object information determining module is specifically configured to:
acquiring a visible light image and thermal imaging data of the specified object, which are acquired when the specified object is at a specified position;
and converting the second position information of the specified object in the visible light image according to a preset conversion relation to obtain the first position information, wherein the conversion relation is used for mutually converting the position information in the visible light image and the position information in the thermal imaging data.
According to an embodiment of the application, the first position information is region information of a target region where the specified object is located in the thermal imaging data;
when the specified object information determining module obtains the heat value corresponding to the specified object, the specified object information determining module is specifically configured to:
and determining the corresponding heat value of the specified object according to the heat value of each coordinate position in the target area.
According to an embodiment of the present application, when the reference heat degree value searching module checks whether there is a reference heat degree value associated with the first position information in the recorded reference heat degree information, the reference heat degree value searching module is specifically configured to:
determining a searching range for searching a reference heat value associated with the first position information according to the first position information;
and checking whether a reference heat value corresponding to the target coordinate position in the search range exists in the recorded reference heat information, if so, determining that a reference heat value related to the first position information exists in the recorded reference heat information, and otherwise, determining that the reference heat value related to the first position information does not exist in the recorded reference heat information.
According to an embodiment of the application, the first position information is region information of a target region where the specified object is located in the thermal imaging data;
when the reference heat value searching module determines the searching range for searching the reference heat value associated with the first position information according to the first position information, the reference heat value searching module is specifically configured to:
constructing a corresponding circular area in the thermal imaging data by taking the coordinate position of the central point in the target area as the center of a circle and a preset length as a radius; determining the circular area as the search range.
According to an embodiment of the present application, when the heat detection module determines the reference heat value for determining whether the designated object is the heat target object according to the reference heat value associated with the recorded first position information and the heat value, the heat detection module is specifically configured to:
and setting and calculating the heat value and a reference heat value corresponding to the target coordinate position in the recorded reference heat information within the search range, and determining the obtained result as the reference heat value.
According to an embodiment of the present application, when the heating detection module determines whether the designated object is a heating target object according to the reference heat value, the heating detection module is specifically configured to:
determining a corresponding heat threshold value according to the reference heat value;
when the heat value is larger than the heat threshold value, determining that the designated object is a heating target object, otherwise, determining that the designated object is not the heating target object.
According to an embodiment of the present application, when the specified object is a heating target object, the heating detection module is further configured to:
carrying out heating alarm processing; and/or the presence of a gas in the gas,
adding a reference heat value as a reference heat value associated with the first position information to the reference heat information.
According to an embodiment of the application, the first position information is area information of a target area where the specified object is located in thermal imaging data;
when the reference heat value recording module records the heat value as a reference heat value associated with the first position information to the reference heat information, the reference heat value recording module is specifically configured to: correspondingly recording the coordinate position of the central point in the target area and the heat value to the reference heat information;
when the heat generation detection module adds the reference heat value as a reference heat value associated with the first position information to the reference heat information, the heat generation detection module is specifically configured to: if the central point coordinate position does not exist in the reference heat degree information, the central point coordinate position and the reference heat degree value are correspondingly recorded to the reference heat degree information; if the central point coordinate position exists in the reference heat information, when the reference heat value corresponding to the central point coordinate position is different from the reference heat value, the reference heat value corresponding to the central point coordinate position is updated to be the reference heat value.
A third aspect of the present application provides an electronic device comprising a processor and a memory; the memory stores a program that can be called by the processor; wherein the processor, when executing the program, implements the target object detection method as described in the foregoing embodiments.
A fourth aspect of the present application provides a machine-readable storage medium on which a program is stored, which, when executed by a processor, implements the target object detection method as described in the foregoing embodiments.
The embodiment of the application has the following beneficial effects:
in the embodiment of the application, first position information of a specified object and a heat value corresponding to the specified object can be obtained, the heat value can reflect the temperature of the specified object, whether a reference heat value associated with the first position information exists in recorded reference heat information can be checked, if yes, a reference heat value can be determined according to the reference heat value associated with the recorded first position information and the heat value, whether the specified object is a heating target object can be determined according to the reference heat value, when the specified object is not the heating target object, the reference heat value can reflect the normal temperature of the non-heating target object, the reference heat value is added to the reference heat information as the reference heat value associated with the first position information, in this way, more and more reference heat values determined based on the heat values of the non-heating objects can be recorded continuously, and in an actual heating scene, the temperatures of most objects are generally normal, so that the recorded reference heat value can basically reflect the normal temperatures of such objects, and whether the detected reference heat value is more accurate.
Drawings
FIG. 1 is a schematic flow chart diagram illustrating a target object detection method according to an exemplary embodiment of the present application;
FIG. 2 is a schematic illustration of thermal imaging data shown in an exemplary embodiment of the present application;
fig. 3 is a block diagram illustrating a structure of a target object detecting apparatus according to an exemplary embodiment of the present application;
fig. 4 is a block diagram illustrating an electronic device according to an exemplary embodiment of the present application.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. The following description refers to the accompanying drawings in which the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It will be understood that, although the terms first, second, third, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one type of device from another. For example, a first device may also be referred to as a second device, and similarly, a second device may also be referred to as a first device, without departing from the scope of the present application. The word "if," as used herein, may be interpreted as "at … …" or "at … …" or "in response to a determination," depending on the context.
In the manner mentioned in the background art, if the accuracy of the detection result is to be ensured, the corresponding heat value-temperature correspondence relationship needs to be calibrated for each thermal imaging device, which is difficult or impossible to achieve in practice. Therefore, it is necessary to provide a feasible scheme for improving the accuracy of the detection result.
In order to improve the accuracy of the detection result, in some ways, a constant temperature source, for example, a constant temperature source of 36 degrees, is set in a visible range of the thermal imaging device, so that a region where the constant temperature source is located in the acquired thermal imaging data has a corresponding heat value, and when a certain object is detected, whether the object is a heating target object may be determined according to a difference between the heat value of the region where the object is located in the thermal imaging data and the heat value of the region where the constant temperature source is located. However, in this method, a constant temperature source needs to be provided, which increases the cost of the apparatus.
In the embodiment of the application, first position information of a specified object and a heat value corresponding to the specified object can be obtained, the heat value can reflect the temperature of the specified object, whether a reference heat value associated with the first position information exists in recorded reference heat information can be checked, if yes, a reference heat value can be determined according to the reference heat value associated with the recorded first position information and the heat value, whether the specified object is a heating target object can be determined according to the reference heat value, when the specified object is not the heating target object, the reference heat value can reflect the normal temperature of the non-heating target object, the reference heat value is added to the reference heat information as the reference heat value associated with the first position information, in this way, more and more reference heat values determined based on the heat values of the non-heating objects can be recorded continuously, and in an actual heating scene, the temperatures of most objects are generally normal, so that the recorded reference heat value can basically reflect the normal temperatures of such objects, and whether the detected reference heat value is more accurate.
In addition, in the embodiment of the application, a constant temperature source does not need to be arranged in a scene, and the cost caused by arrangement of the constant temperature source can be saved.
The embodiment of the application can be applied to scenes needing temperature detection, such as a series of outdoor scenes including a residential quarter doorway, a park doorway and the like, or a series of indoor scenes including a workshop, a hospital, a market and the like, is certainly not limited thereto, and can also be applied to other scenes, such as a livestock breeding place including a pig farm and the like.
The following describes the target object detection method in the embodiment of the present application in detail, but the present application is not limited thereto.
In one embodiment, referring to fig. 1, a target object detection method may include the steps of:
s100: acquiring first position information of a specified object and a heat value corresponding to the specified object;
s200: checking whether a reference heat value associated with the first position information exists in the recorded reference heat information;
s300: if so, determining a reference heat value for determining whether the specified object is the heating target object according to the recorded reference heat value associated with the first position information and the heat value, determining whether the specified object is the heating target object according to the reference heat value, and adding the reference heat value to the reference heat information as the reference heat value associated with the first position information when the specified object is not the heating target object.
An execution subject of the target object detection method in the embodiment of the present application may be an electronic device, and further may be a processor of the electronic device, where the processor may be one or more processors, and the processor may be a general-purpose processor or a special-purpose processor.
The electronic device comprises, for example, a thermal imaging device that can acquire thermal imaging data. Of course, the electronic device may also be another type of device, and is connected to the external thermal imaging device, and may acquire the thermal imaging data acquired by the external thermal imaging device for processing.
In the following, the description is given taking the execution subject as the thermal imaging apparatus as an example, but it should be noted that it should not be limited thereto.
In the embodiment of the present application, the heat value may refer to original heat data generated by the thermal imaging device, and the heat value is not a temperature but may reflect a temperature, for example, the higher the temperature is, the larger the heat value is. The thermal imaging device may generate thermal imaging data, typically in RAW format, for a scene within a field of view, with a corresponding heat value at each coordinate location in the thermal imaging data. The thermal imaging data is processed to form a thermal imaging image, wherein each coordinate position of the thermal imaging data corresponds to a pixel position of the thermal imaging image.
In step S100, first position information of a designated object and a corresponding heat value of the designated object are obtained.
The designated objects may include, for example, human bodies, human faces, animals, etc., where the animals further include, but are not limited to, sparsely populated with short, shallow hairs of poultry or livestock animals, such as pigs, cattle, etc. It is understood that the above objects are only examples, and the specified object may be any object that needs temperature detection, such as a device, a line, and the like.
The designated object may be a currently detected object, and the detection device may include, but is not limited to: a visible light imaging device, a position detection device such as a radar device, or a thermal imaging device itself, or the like, is not particularly limited thereto.
First position information of the designated object may be determined according to the detected position information of the designated object. For example, when the visible light component in the visible light imaging device or the thermal imaging device detects the specified object in the collected visible light image, the first position information may be determined according to the position information of the specified object in the visible light image, and of course, the positions of the specified object in the visible light image and the thermal imaging data in the scene are the same. For another example, when the position detection device detects the specified object, the first position information is determined according to the position information of the specified object in the scene output by the position detection device. As another example, target detection may be performed on currently acquired thermal imaging data (the thermal imaging data may be processed to obtain a thermal imaging image), and when a specific object is detected, first position information of the specific object may be determined according to the detection result.
Specifically, for example, a thermal imaging device is integrated with a visible light component, that is, the thermal imaging device is a thermal imaging and visible light dual-light fusion thermal imaging device, a visible range of the visible light component is the same as a visible range of a thermal imaging component in the thermal imaging device, the visible light component and the thermal imaging component can respectively collect a visible light image and thermal imaging data at the same frame rate, the thermal imaging device can perform target detection (such as a face detection algorithm, the specific type of the algorithm is not limited) on the visible light image collected each time according to a preset target detection algorithm, the target detection algorithm can output position information of a specified object in the visible light image when the specified object is detected, and the thermal imaging device can determine first position information of the specified object according to the position information output by the target detection algorithm.
It will be appreciated that the visible light image and the thermographic data described above may be fused, if desired, to obtain an image that includes heat information and detail information of the visible light image (such as contour information of a specified object) that may be used for display. For example, the color (chroma component) of the corresponding pixel position in the visible light image may be modified according to the heat value of each coordinate position in the thermal imaging data, such as the higher the heat, the more red the color, and the blacker the color is otherwise. Of course, the thermal imaging data may also be processed separately to form the thermal imaging data for display, and is not limited to this.
The determined first position information may specifically be position information of the specified object in thermal imaging data currently acquired by the thermal imaging device. The first position information may be point coordinate position information, or may be area position information, which may be determined according to a detection manner and actual needs.
When the heat value corresponding to the designated object is obtained, the heat value corresponding to the designated object can be determined from the currently acquired thermal imaging data according to the first position information of the designated object, and further the heat value corresponding to the designated object can be determined according to the heat value corresponding to the first position information in the thermal imaging data. The heat value corresponding to the designated object may reflect the current temperature of the designated object, and may also be referred to as a real-time heat value of the designated object.
For example, when the first position information is position information of an area where the designated object is located in the thermal imaging data, the heat value corresponding to the designated object may be determined according to the heat value at each coordinate position in the area. For another example, when the first position information is coordinate position information of a point included in the specified object in the thermal imaging data, the heat value corresponding to the specified object may be determined according to the heat value at the coordinate position of the point in the thermal imaging data. Of course, the two ways are not limited herein, and there may be other ways to determine the heat value corresponding to the designated object.
In step S200, it is checked whether or not there is a reference heat value associated with the first position information in the recorded reference heat information.
The recorded reference thermal information may include a reference thermal value determined based on a thermal value corresponding to an object in the previously acquired historical thermal imaging data, where the object in the historical thermal imaging data may include a specific object and/or other objects, and of course, the types of the objects are the same, such as human faces.
Alternatively, the historical thermal imaging data and the currently acquired thermal imaging data may be acquired by the same thermal imaging device. As described in the background art, there may be a difference in accuracy between different thermal imaging apparatuses, but the difference does not exist in the same thermal imaging apparatus, and thus, with the reference thermal value determined based on the thermal value corresponding to the object in the historical thermal imaging data acquired by the same thermal imaging apparatus before, the problem of a large difference in thermal value between objects at the same temperature in the thermal imaging data acquired by different apparatuses can be avoided.
The recorded reference heat information is empty initially, and at this time, the designated object is the first object to be detected, so that the reference heat value associated with the first position information is not necessarily present in the recorded reference heat information. As the target object detection method continues, the reference heat value associated with each position information is accumulated in the reference heat information, and in this case, the reference heat value associated with the first position information may or may not exist in the recorded reference heat information.
Therefore, after the first position information of the specified object is obtained, it is possible to check whether or not there is a reference heat value associated with the first position information in the recorded reference heat information based on the first position information.
For example, if the reference heat information records the position information and the corresponding reference heat value, the reference heat value corresponding to the first position information may be searched in the recorded reference heat information, and if the reference heat value is found, it is determined that the position information exists, otherwise, it does not exist. Or, a reference heat value corresponding to position information, of which the distance from the first position information is smaller than a specified distance, may be searched for in the recorded reference heat information, and if the reference heat value is found, it is determined to exist, otherwise, it does not exist.
Of course, the above-described method of checking whether or not the reference heat value associated with the first position information exists in the recorded reference heat information is not limited to this, and other methods are also possible.
In step S300, if yes, a reference heat value for determining whether the designated object is a heat generation target object is determined according to the recorded reference heat value associated with the first position information and the heat value, whether the designated object is the heat generation target object is determined according to the reference heat value, and when the designated object is not the heat generation target object, the reference heat value is added to the reference heat information as the reference heat value associated with the first position information.
When determining the reference heat value for determining whether the specified object is the heating target object according to the reference heat value associated with the recorded first position information and the heat value, a certain mathematical operation may be performed on the reference heat value and the heat value, such as averaging, although not limited to this, and other manners, such as median calculation, may also be used.
When determining whether the designated object is a heating target object according to the reference heat value, a difference between the heat value and the reference heat value may be calculated, and if the difference is greater than a set difference, the designated object may be determined to be the heating target object. Of course, this is merely an example, and there may be other ways to determine whether the specified object is a heating target object according to the reference heat value, which are not listed here.
Therefore, the reference heat value of the heat value corresponding to the non-heating target object based on normal temperature can be recorded in the reference heat information, and the sustainability of subsequent detection and the accuracy of a subsequent detection result are ensured.
Generally, in a scene with a complex ambient temperature (a scene containing a plurality of different ambient temperatures), such as a scene with a part being ventilated (generally low temperature) and a part being not ventilated, the temperature of an object in a ventilated environment is generally taken away by wind, in which case the measured temperature is low, and the measured temperature in a non-ventilated environment is normal temperature. Taking a human body with a temperature of 36.5 degrees in a ventilated environment and a non-ventilated environment as an example, the thermal value in the collected thermal imaging data has a large difference, for example, the thermal value corresponding to the ventilated environment is 33 degrees (the temperature is reduced by wind), and the thermal value corresponding to the non-ventilated environment is 36.5 degrees.
Then, in the above scenario, if the reference heat value is determined according to all the recorded reference heat values in the reference heat information, and the reference heat value is added to the reference heat information as the reference heat value, the reference heat value in the reference heat information may greatly deviate from the heat value corresponding to the normal temperature, for example, the reference heat value corresponding to the non-ventilated environment may be influenced by the heat value corresponding to the ventilated environment and be lower, and the reference heat value in the ventilated environment may be higher, which may result in inaccurate detection result.
In the embodiment of the present application, in order to solve the above problem, when determining the reference heat value of the specified object, it is considered that the reference heat value associated with the first position information of the specified object in the reference heat information is not all the reference heat values in the reference heat information, and generally, the position corresponding to the ventilated environment and the unventilated environment in the thermal imaging data is kept unchanged, so if the first position information is in the ventilated environment, the reference heat value associated with the first position information is basically the reference heat value corresponding to the ventilated environment, and too many reference heat values corresponding to the unventilated environment are not introduced, so that the problem that the detection result is inaccurate due to different environmental temperatures at different positions can be avoided as much as possible, for example, the reference heat value corresponding to the ventilated scene can be prevented from affecting the detection of whether the object is the heating target object in the unventilated scene.
Of course, the above method is particularly suitable for scenes with complex ambient temperatures, but does not mean that the above method is only suitable for such scenes, and in fact, the above method is also suitable for scenes with single ambient temperatures, such as an outdoor scene without shielding or an indoor scene without ventilation.
In one embodiment, in step S100, the obtaining the first position information of the designated object may include:
s101: acquiring a visible light image and thermal imaging data of the specified object, which are acquired when the specified object is at a specified position;
s102: and converting the second position information of the specified object in the visible light image according to a preset conversion relation to obtain the first position information, wherein the conversion relation is used for mutually converting the position information in the visible light image and the position information in the thermal imaging data.
In this embodiment, the method is applicable to a case where the thermal imaging device is a dual-optical fusion thermal imaging device, in this case, the thermal imaging device may control the visible light component and the thermal imaging component to perform acquisition synchronously, and the visible light component and the thermal imaging component have the same visible range; or, the method can be applied to the case that the thermal imaging device is connected with the visible light device, in this case, the thermal imaging device can also control the device to synchronously acquire with the visible light device, and the visible range of the visible light device is the same as that of the thermal imaging device.
In other words, the visible light image and the thermal imaging data may be acquired synchronously and contain the same scene. When an object is at any position in the scene, the object is also included in the thermal imaging data as long as the object is included in the visible light image. The specified location may be any of the locations in the scene described above.
In this way, the acquired visible light image and thermal imaging data of the designated object, which are acquired when the designated object is at the designated position, both include the designated object, and the positions of the included designated objects in the scene are the same and both are designated positions.
After the visible light image and the thermal imaging data are acquired, second position information of the designated object in the visible light image may be determined, and then the second position information of the designated object in the visible light image is converted according to a preset conversion relationship to obtain the first position information.
The conversion relationship is a conversion relationship that is set in advance and is used for mutually converting the position information in the visible light image and the position information in the thermal imaging data. Further, the transformation relationship may be a transformation relationship between a first coordinate system for visible light image application and a second coordinate system for thermal imaging data application.
When the conversion relationship is set, a plurality of calibration objects may be set in a scene, and the conversion relationship is determined according to positions of the calibration objects in the collected calibration visible light image and calibration thermal imaging data.
Of course, if the size of the visible light image is the same as that of the thermal imaging data and the same coordinate system is used, the second position information of the specified object in the visible light image may also be directly used as the first position information.
In one embodiment, the first position information is region information of a target region in which the specified object is located in the thermal imaging data.
The first position information is the area information of the target area, and may be represented by, for example, position information of a rectangular frame surrounding the specified object, and may be any vertex coordinates of the rectangular frame and the length and width of the rectangular frame, although the first position information is not particularly limited thereto.
Correspondingly, in step S100, the obtaining of the heat value corresponding to the specified object may include the following steps:
s103: and determining the corresponding heat value of the specified object according to the heat value of each coordinate position in the target area.
The target area comprises a plurality of coordinate positions, each coordinate position is provided with a corresponding heat value, and the corresponding heat value of the specified object can be determined according to the heat values.
For example, when the heat value corresponding to the designated object is determined according to the heat value at each coordinate position in the target area, the maximum heat value among the heat values at each coordinate position in the target area may be used as the heat value corresponding to the designated object.
Optionally, in order to avoid the problem that the heat value corresponding to the designated object is inaccurate due to the interference factor, after the heat values at the coordinate positions in the target area are obtained, the interference value in the heat values may be removed, for example, the heat values deviating from other heat values or deviating from a normal value by a large amount are removed, and the maximum heat value is selected from the heat values after the interference value is removed as the heat value corresponding to the designated object.
Of course, the above example is only a preferable embodiment, and the specific method for determining the heat value corresponding to the designated object is not limited thereto, and for example, a central block may be extracted from the target area, the central block has the same central position as the target area but a smaller size than the target area, and an average value of the heat values at the coordinate positions in the central block may be calculated as the heat value corresponding to the designated object.
In one embodiment, in step S200, the checking whether there is a reference heat value associated with the first position information in the recorded reference heat information may include:
s201: determining a searching range for searching a reference heat value associated with the first position information according to the first position information;
s202: and checking whether a reference heat value corresponding to the target coordinate position in the search range exists in the recorded reference heat information, if so, determining that a reference heat value related to the first position information exists in the recorded reference heat information, and otherwise, determining that the reference heat value related to the first position information does not exist in the recorded reference heat information.
The first position information may be point coordinate position information or area position information, and whether the position information of a point or an area may determine a search range for searching for a reference calorific value associated with the first position information.
Taking the first position information as the point coordinate position information as an example, a circular area may be determined with the first position information as a center of a circle and a preset length as a radius, and the circular area may be used as a search range. Of course, the shape of the search range here is merely an example, and is not particularly limited to a circular shape. Taking the first position information as the area position information as an example, the area position information may be determined as the search range, or a search area including a larger area corresponding to the area position information and including the area may be determined, and the determined search area may be determined as the search range. It is to be understood that how to determine the search range based on the first position information is not limiting.
Preferably, the search range may contain a target region in which the specified object is located in the thermal imaging data. For example, if the specified object is a human face, the search range at least includes a range in which the human face is located in the thermal imaging data. Of course, the search range is less than the entire area range of the thermographic data.
Optionally, the search range may be N times of the target area, where N is a set value, may be greater than 1, and certainly cannot be infinite, for example, a value may be taken from 2 to 10, and is not limited specifically. The determination of N may be based on the size of the doorway and the size of the face at the doorway, which may be practical depending on the application scenario, for example, when the thermal imaging device is to detect a face entering the doorway.
After the search range is determined, whether a reference heat value corresponding to the target coordinate position within the search range exists in the recorded reference heat information or not can be checked, if yes, the reference heat value related to the first position information exists in the recorded reference heat information, and otherwise, the reference heat value related to the first position information does not exist in the recorded reference heat information.
In this embodiment, a search range determined according to the first position information is used to search for a reference heat value associated with the first position information from the recorded reference heat information, and a reference heat value corresponding to a coordinate position in the search range in the recorded reference heat information is used as the reference heat value associated with the first position information.
The method has the advantages that when the reference heat value is recorded in the reference heat value information, the corresponding reference heat value is recorded by taking the coordinate position as a unit, the recording mode is finer in granularity compared with the area position information, when the reference heat value is determined, the reference heat value is not determined only according to the reference heat value corresponding to one coordinate position, but the reference heat values corresponding to all recorded coordinate positions in a search range are considered, the search range is determined according to the first position information, the reference heat value corresponding to the environment with different environment temperatures of the first position information can be avoided as far as possible from being introduced, meanwhile, more reference heat values can be used for determining the reference heat value as a reference for judging whether the reference heat value is a heating target object, the result inaccuracy caused by extreme data inaccuracy is avoided, and the detection result can be more accurate.
In one embodiment, the first position information is region information of a target region in which the specified object is located in the thermal imaging data.
The first position information is the area information of the target area, and may be represented by, for example, position information of a rectangular frame surrounding the specified object, and may be any vertex coordinates of the rectangular frame and the length and width of the rectangular frame, although the first position information is not particularly limited thereto.
Accordingly, in step S201, the determining, according to the first position information, a search range for searching for the reference heating value associated with the first position information includes:
constructing a corresponding circular area in the thermal imaging data by taking the coordinate position of the central point in the target area as the center of a circle and a preset length as a radius; determining the circular area as the search range.
The preset length may be determined according to an application scenario, for example, when the thermal imaging device is to detect a human face entering a doorway, the preset length may be determined according to a size of the doorway and a size of the human face at the doorway, and may be, for example, half of a width of the doorway. Of course, this is merely an example, and is not particularly limited thereto.
The center of the circle is not limited to the coordinate position of the center point in the target area, and may be a coordinate of the target area deviating from the coordinate position of the center point, or may be a vertex coordinate of the target area.
The search range is not limited to a circular area, and may be a rectangular area, a triangular area, or the like, and the determination method of the search range may be adjusted according to the shape of the search range.
Referring to fig. 2, assuming that Z1 is thermal imaging data, T1 is a designated object, and Z11 is a target area where the designated object T1 is located, a circular search range Z12 can be determined with the target area Z11 as a center and a preset length as a radius.
It is to be understood that the above-mentioned manner of determining the search range is only a preferable manner, and is not particularly limited thereto.
In one embodiment, in step S300, the determining a reference heat value for determining whether the designated object is the heat generation target object according to the reference heat value and the heat value associated with the recorded first position information may include:
s301: and setting and calculating the heat value and a reference heat value corresponding to the target coordinate position in the recorded reference heat information within the search range, and determining the obtained result as the reference heat value.
Optionally, the setting and calculating the heat value and the reference heat value corresponding to the target coordinate position in the recorded reference heat information within the search range may include: calculating the sum of the number of the heat value corresponding to the specified object and the number of the reference heat values corresponding to the target coordinate position in the search range to obtain the number of the heat values; calculating the sum of the heat value corresponding to the specified object and the reference heat value corresponding to the target coordinate position in the search range to obtain the sum of the heat values; determining a ratio between the sum of the heat values and the number of heat values as the reference heat value.
For example, if the heat value corresponding to the designated object is Cn, and n-1 reference heat values, which are C1 and C2 … … Cn-1, are found, the reference heat value may be: (C1 + C2+. + Cn)/n.
Of course, the operation method is not limited here, and other methods are possible, for example, a median value of the heat value and the reference heat value corresponding to the target coordinate position within the search range in the recorded reference heat information may be obtained, and the median value may be determined as the reference heat value.
In one embodiment, the step S300 of determining whether the designated object is a heating target object according to the reference heat value may include the steps of:
s302: determining a corresponding heat threshold value according to the reference heat value;
s303: and when the heat value is larger than the heat threshold value, determining that the specified object is a heating target object, otherwise, determining that the specified object is not the heating target object.
When determining the corresponding heat threshold according to the reference heat value, calculating a product of the reference heat value and a preset ratio to obtain the heat threshold, wherein the preset ratio is greater than 1. In this way, the calculated heat threshold value is larger than the reference heat value, and can represent the heat value corresponding to the temperature of the heating target object. Of course, the specific value of the preset ratio is not limited, and may be determined according to the temperature range of the object when the object generates heat.
After the heat threshold is determined, the heat value corresponding to the designated object may be compared with the heat threshold, and if the comparison result is greater than the heat threshold, that is, the heat value is greater than the heat threshold, the designated object is determined to be the heating target object, otherwise, the designated object is not the heating target object.
For example, if the predetermined ratio is 1.02 and the reference heat value is 36.5 degrees, the calculated heat threshold is 37.23, and if the heat value corresponding to the designated object is 37.3, the designated object is determined to be the heating target object.
In one embodiment, when the designated object is a heat-generating target object, the method further comprises:
s400: and carrying out heating alarm processing.
Optionally, the heating alarm processing may include performing an acoustic and/or optical signal alarm, or transmitting alarm information to the server, so that the server performs an alarm through an alarm device in the scene. Of course, the manner of the heat alarm processing is not limited to this, and may be determined according to actual needs or actual conditions.
In one embodiment, when the designated object is a heat-generating target object, the method further comprises:
s500: adding a reference heat value as a reference heat value associated with the first position information to the reference heat information.
In other words, in the present embodiment, when the specified object is the heat generation target object or is not the heat generation target object (i.e., regardless of whether the specified object is the heat generation target object or not), the reference heat value associated as the first position information is added to the reference heat information, which can simplify the execution logic.
Although the temperature of the heat generation target object is higher than the normal temperature, when the flow rate of the object to be detected is large, the heat value corresponding to some abnormal temperature is included therein, and the final result is hardly affected.
Of course, the above-mentioned method is not limited, and only when the designated object is not the heating target object, the reference heat value may be added to the reference heat information as the reference heat value associated with the first position information.
In one embodiment, the first position information is region information of a target region in which the specified object is located in thermal imaging data.
The first position information is the area information of the target area, and may be represented by, for example, position information of a rectangular frame surrounding the specified object, and may be any vertex coordinates of the rectangular frame and the length and width of the rectangular frame, although the first position information is not particularly limited thereto.
Accordingly, in step S300 or step S500, the adding the reference heat value as the reference heat value associated with the first position information to the reference heat information includes:
if the central point coordinate position does not exist in the reference heat information, correspondingly recording the central point coordinate position and the reference heat value to the reference heat information; if the central point coordinate position exists in the reference heat information, when the reference heat value corresponding to the central point coordinate position is different from the reference heat value, the reference heat value corresponding to the central point coordinate position is updated to be the reference heat value.
For example, if the coordinate position of the center point in the target region is P1, and the reference heat value is (C1 + C2+.. + Cn)/n, it is checked whether P1 is included in the reference heat information, and if so, the reference heat value corresponding to P1 is replaced by (C1 + C2+.. + Cn)/n; if not, (P1, (C1 + C2+ ·+ Cn)/n) is recorded to the reference heat information.
In one embodiment, the method further comprises:
s600: and if the recorded reference heat information does not have the reference heat value associated with the first position information, recording the heat value as the reference heat value associated with the first position information to the reference heat information.
In this case, since the reference heat value associated with the first position information does not exist in the recorded reference heat information, the heat value corresponding to the specified object can be recorded as the reference heat value associated with the first position information to the reference heat information.
In order to avoid inaccuracy of the reference heat value recorded at the beginning in the reference heat information, when the target object detection is started, thermal imaging data of an object with normal temperature can be collected, and the heat value corresponding to the non-heating target object is determined and recorded into the reference heat information as the reference heat value. Of course, not limited thereto, even if the reference heat value recorded at the beginning in the reference heat information is inaccurate, the reference heat value recorded in the reference heat information gradually becomes accurate as the number of detected objects increases and the temperature of most objects is normal.
It is to be understood that the above-mentioned method is not the only method for determining the initial reference heat information, and other methods are possible, such as:
the first method is as follows: if the recorded reference heat value associated with the first position information does not exist in the recorded reference heat information, whether the heat value associated with the first position information exists or not can be checked in the recorded candidate heat information, if so, when the number of the heat values associated with the first position information in the candidate heat information reaches a set number, the average value of the heat values associated with the first position information in the candidate heat information is calculated, and the average value is taken as the reference heat value associated with the first position information and recorded to the reference heat information.
The second method comprises the following steps: if the recorded reference heat information does not have the reference heat value associated with the first position information (for example, in step S202, the recorded reference heat information does not have the reference heat value corresponding to the target coordinate position within the search range), checking whether the search range exceeds a preset range (for example, the whole area range of the thermal imaging data), if not, expanding the search range (for example, the circle center of the search range is unchanged, but the radius is increased), and returning to step S202 until the whole area range of the thermal imaging data does not have the corresponding reference heat value, at this time, recording the heat value as the reference heat value associated with the first position information to the reference heat information, or adopting the first method.
Alternatively, when there is no reference heat value associated with the first position information in the recorded reference heat information, it may be directly determined that the designated object is not the heat generation target object. In this case, it is needless to say that the determination as to whether or not the designated object is the target object of heat generation may not be performed.
In one embodiment, the first position information is region information of a target region in which the specified object is located in thermal imaging data.
The first position information is the area information of the target area, and may be represented by, for example, position information of a rectangular frame surrounding the specified object, and may be any vertex coordinates of the rectangular frame and the length and width of the rectangular frame, although the first position information is not particularly limited thereto.
Accordingly, recording the heat value as a reference heat value associated with the first position information to the reference heat information in step S600 may include:
and correspondingly recording the coordinate position of the central point in the target area and the heat value to the reference heat information.
For example, if the coordinate position of the center point in the target area is P1, and the corresponding heat value of the designated object is Cn, then (P1, cn) may be added to the reference heat information. In subsequent detection, corresponding Cn may be found according to P1, for example, according to whether P1 is in the search range.
The present application also provides a target object detection apparatus, referring to fig. 3, the target object detection apparatus 100 includes:
a designated object information determining module 101, configured to obtain first position information of a designated object and a heat value corresponding to the designated object;
a reference heat value searching module 102, configured to check whether a reference heat value associated with the first position information exists in the recorded reference heat information;
and the heating detection module 103 is used for determining whether the specified object is a heating target object according to the reference heat value associated with the recorded first position information and the heat value if the specified object is the heating target object, determining whether the specified object is the heating target object according to the reference heat value, and adding the reference heat value to the reference heat value as the reference heat value associated with the first position information when the specified object is not the heating target object.
In an embodiment, when the specified object information determining module obtains the first location information of the specified object, it is specifically configured to:
acquiring a visible light image and thermal imaging data of the specified object, which are acquired when the specified object is at a specified position;
and converting the second position information of the specified object in the visible light image according to a preset conversion relation to obtain the first position information, wherein the conversion relation is used for mutually converting the position information in the visible light image and the position information in the thermal imaging data.
In one embodiment, the first position information is region information of a target region in which the specified object is located in thermal imaging data;
when the specified object information determining module obtains the heat value corresponding to the specified object, the specified object information determining module is specifically configured to:
and determining the corresponding heat value of the specified object according to the heat value of each coordinate position in the target area.
In an embodiment, when the reference heat value searching module checks whether there is a reference heat value associated with the first position information in the recorded reference heat information, the reference heat value searching module is specifically configured to:
determining a searching range for searching a reference heat value associated with the first position information according to the first position information;
and checking whether a reference heat value corresponding to the target coordinate position in the search range exists in the recorded reference heat information, if so, determining that a reference heat value related to the first position information exists in the recorded reference heat information, and otherwise, determining that the reference heat value related to the first position information does not exist in the recorded reference heat information.
In one embodiment, the first position information is region information of a target region in which the specified object is located in thermal imaging data;
when the reference heat value searching module determines the searching range for searching the reference heat value associated with the first position information according to the first position information, the reference heat value searching module is specifically configured to:
constructing a corresponding circular area in the thermal imaging data by taking the coordinate position of the central point in the target area as the center of a circle and a preset length as a radius; and determining the circular area as the search range.
In an embodiment, when the heating detection module determines the reference heat value for determining whether the designated object is the heating target object according to the reference heat value and the heat value associated with the recorded first position information, the heating detection module is specifically configured to:
and setting and calculating the heat value and a reference heat value corresponding to the target coordinate position in the recorded reference heat information within the search range, and determining the obtained result as the reference heat value.
In an embodiment, when the heating detection module determines whether the designated object is a heating target object according to the reference heat value, the heating detection module is specifically configured to:
determining a corresponding heat threshold value according to the reference heat value;
and when the heat value is larger than the heat threshold value, determining that the specified object is a heating target object, otherwise, determining that the specified object is not the heating target object.
In one embodiment, the heating detection module, when the specified object is a heating target object, is further configured to:
carrying out heating alarm processing; and/or the presence of a gas in the gas,
adding a reference heat value as a reference heat value associated with the first position information to the reference heat information.
In one embodiment, the first position information is region information of a target region in which the specified object is located in thermal imaging data;
when the reference heat value recording module records the heat value as a reference heat value associated with the first position information to the reference heat information, the reference heat value recording module is specifically configured to: correspondingly recording the coordinate position of the central point in the target area and the heat value to the reference heat information;
when the heat generation detection module adds the reference heat value as a reference heat value associated with the first position information to the reference heat information, the heat generation detection module is specifically configured to: if the central point coordinate position does not exist in the reference heat information, correspondingly recording the central point coordinate position and the reference heat value to the reference heat information; if the central point coordinate position exists in the reference heat information, when the reference heat value corresponding to the central point coordinate position is different from the reference heat value, the reference heat value corresponding to the central point coordinate position is updated to be the reference heat value.
The implementation process of the functions and actions of each unit in the above device is specifically described in the implementation process of the corresponding step in the above method, and is not described herein again.
For the device embodiments, since they substantially correspond to the method embodiments, reference may be made to the partial description of the method embodiments for relevant points. The above-described embodiments of the apparatus are merely illustrative, wherein the units described as separate parts may or may not be physically separate, and the parts shown as units may or may not be physical units.
The application also provides an electronic device, which comprises a processor and a memory; the memory stores a program that can be called by the processor; wherein the processor, when executing the program, implements the target object detection method as described in the foregoing embodiments.
The embodiment of the target object detection device can be applied to electronic equipment. Taking a software implementation as an example, as a logical device, the device is formed by reading, by a processor of the electronic device where the device is located, a corresponding computer program instruction in the nonvolatile memory into the memory for operation. In terms of hardware, as shown in fig. 4, fig. 4 is a hardware structure diagram of an electronic device where the target object detection apparatus 100 is located according to an exemplary embodiment of the present application, and besides the processor 510, the memory 530, the interface 520, and the nonvolatile memory 540 shown in fig. 4, the electronic device where the apparatus 100 is located in the embodiment may also include other hardware according to an actual function of the electronic device, which is not described again.
The present application also provides a machine-readable storage medium on which a program is stored, which when executed by a processor, implements the target object detection method as described in any one of the foregoing embodiments.
This application may take the form of a computer program product embodied on one or more storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having program code embodied therein. Machine-readable storage media include both permanent and non-permanent, removable and non-removable media, and the storage of information may be accomplished by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of machine-readable storage media include, but are not limited to: phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technologies, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic tape storage or other magnetic storage devices, or any other non-transmission medium, may be used to store information that may be accessed by a computing device.
The above description is only exemplary of the present application and should not be taken as limiting the present application, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the scope of protection of the present application.

Claims (10)

1. A method of detecting a target object, the method comprising:
determining first position information of the designated object according to the detected position information of the designated object, and obtaining a heat value corresponding to the designated object;
checking whether a reference heat value associated with the first position information exists in the recorded reference heat information;
if so, determining a reference heat value for determining whether the specified object is the heating target object according to the recorded reference heat value associated with the first position information and the heat value, determining whether the specified object is the heating target object according to the reference heat value, and adding the reference heat value to the reference heat information as the reference heat value associated with the first position information when the specified object is not the heating target object.
2. The target object detection method of claim 1, wherein the determining first position information of the designated object based on the detected position information of the designated object comprises:
acquiring a visible light image and thermal imaging data of the specified object, which are acquired when the specified object is at a specified position;
and converting the second position information of the specified object in the visible light image according to a preset conversion relation to obtain the first position information, wherein the conversion relation is used for mutually converting the position information in the visible light image and the position information in the thermal imaging data.
3. The target object detecting method according to claim 1, wherein the first position information is area information of a target area where the specified object is located in thermal imaging data;
the obtaining of the heat value corresponding to the specified object includes:
and determining the corresponding heat value of the specified object according to the heat value of each coordinate position in the target area.
4. The target object detection method according to claim 1, wherein the checking whether there is a reference heat value associated with the first position information in the recorded reference heat information includes:
determining a searching range for searching a reference heat value associated with the first position information according to the first position information;
and checking whether a reference heat value corresponding to the target coordinate position in the search range exists in the recorded reference heat information, if so, determining that a reference heat value related to the first position information exists in the recorded reference heat information, and otherwise, determining that the reference heat value related to the first position information does not exist in the recorded reference heat information.
5. The target object detecting method according to claim 4, wherein the first position information is area information of a target area where the specified object is located in thermal imaging data;
the determining a search range for searching for the reference heat value associated with the first position information according to the first position information includes:
constructing a corresponding circular area in the thermal imaging data by taking the coordinate position of the central point in the target area as the center of a circle and a preset length as a radius; determining the circular area as the search range.
6. The target object detection method according to claim 4, wherein the determining a reference heat value for determining whether the specified object is a heat-generating target object based on the reference heat value and the heat value associated with the recorded first position information includes:
and setting and calculating the heat value and a reference heat value corresponding to the target coordinate position in the recorded reference heat information within the search range, and determining the obtained result as the reference heat value.
7. The target object detecting method according to claim 1, wherein the first position information is area information of a target area where the specified object is located in thermal imaging data;
recording the heat value as a reference heat value associated with first position information to the reference heat information includes: correspondingly recording the coordinate position of the central point in the target area and the heat value to the reference heat information;
the adding a reference heat value associated with a reference heat value as first position information to the reference heat information comprises: if the central point coordinate position does not exist in the reference heat information, correspondingly recording the central point coordinate position and the reference heat value to the reference heat information; if the central point coordinate position exists in the reference heat information, when the reference heat value corresponding to the central point coordinate position is different from the reference heat value, the reference heat value corresponding to the central point coordinate position is updated to be the reference heat value.
8. A target object detection apparatus, characterized in that the apparatus comprises:
the specified object information determining module is used for determining first position information of the specified object according to the detected position information of the specified object and acquiring a heat value corresponding to the specified object;
the reference heat value searching module is used for checking whether a reference heat value related to the first position information exists in the recorded reference heat information or not;
and if so, determining a reference heat value for determining whether the specified object is the heating target object according to the recorded reference heat value associated with the first position information and the heat value, determining whether the specified object is the heating target object according to the reference heat value, and adding the reference heat value to the reference heat value as the reference heat value associated with the first position information when the specified object is not the heating target object.
9. An electronic device comprising a processor and a memory; the memory stores a program that can be called by the processor; wherein the processor, when executing the program, implements the target object detection method of any one of claims 1-7.
10. A machine-readable storage medium, having stored thereon a program which, when executed by a processor, implements the target object detection method according to any one of claims 1 to 7.
CN202010335189.5A 2020-04-24 2020-04-24 Target object detection method, device and equipment and storage medium Active CN113639871B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010335189.5A CN113639871B (en) 2020-04-24 2020-04-24 Target object detection method, device and equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010335189.5A CN113639871B (en) 2020-04-24 2020-04-24 Target object detection method, device and equipment and storage medium

Publications (2)

Publication Number Publication Date
CN113639871A CN113639871A (en) 2021-11-12
CN113639871B true CN113639871B (en) 2022-12-23

Family

ID=78414866

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010335189.5A Active CN113639871B (en) 2020-04-24 2020-04-24 Target object detection method, device and equipment and storage medium

Country Status (1)

Country Link
CN (1) CN113639871B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108875535A (en) * 2018-02-06 2018-11-23 北京旷视科技有限公司 image detecting method, device and system and storage medium
CN109345798A (en) * 2018-11-26 2019-02-15 日立楼宇技术(广州)有限公司 A kind of farm's monitoring method, device, equipment and storage medium
CN110660186A (en) * 2018-06-29 2020-01-07 杭州海康威视数字技术股份有限公司 Method and device for identifying target object in video image based on radar signal
CN110801229A (en) * 2019-11-15 2020-02-18 英华达(上海)科技有限公司 Eyesight protection monitoring method, system, equipment and storage medium

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103105234B (en) * 2012-01-12 2016-05-11 杭州美盛红外光电技术有限公司 Thermal imagery device and thermal imagery specification image pickup method

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108875535A (en) * 2018-02-06 2018-11-23 北京旷视科技有限公司 image detecting method, device and system and storage medium
CN110660186A (en) * 2018-06-29 2020-01-07 杭州海康威视数字技术股份有限公司 Method and device for identifying target object in video image based on radar signal
CN109345798A (en) * 2018-11-26 2019-02-15 日立楼宇技术(广州)有限公司 A kind of farm's monitoring method, device, equipment and storage medium
CN110801229A (en) * 2019-11-15 2020-02-18 英华达(上海)科技有限公司 Eyesight protection monitoring method, system, equipment and storage medium

Also Published As

Publication number Publication date
CN113639871A (en) 2021-11-12

Similar Documents

Publication Publication Date Title
CN111242946B (en) Human body temperature abnormality detection method and device based on infrared thermal imaging
US10810858B2 (en) Infrared imaging systems and methods for gas leak detection
US10914653B2 (en) Infrared imaging systems and methods for oil leak detection
CN111626125B (en) Face temperature detection method, system, device and computer equipment
EP2315433B1 (en) Calculating energy dissipation in an IR image
JP2011508191A (en) Method, system and computer program for determining heat or energy loss in a building
US20210319572A1 (en) Error reduction in depth maps
CN113176270B (en) Dimming method, device and equipment
CN113240880A (en) Fire detection method and device, electronic equipment and storage medium
US20190349577A1 (en) Method and device for detecting digital camera
CN113639871B (en) Target object detection method, device and equipment and storage medium
CN108875709A (en) One kind flocks together behavioral value method, apparatus, electronic equipment and storage medium
US20220122204A1 (en) Predictive property maintenance
CN113566981B (en) Self-adaptive adjusting method and device of infrared detector
JP7080417B1 (en) Satisfaction calculator, satisfaction calculation method and satisfaction calculation program
US20090153326A1 (en) Method for locating intruder
Woods et al. Estimating animal location from non-overhead camera views
CN113405664B (en) Temperature measurement method, temperature measurement equipment and machine-readable storage medium
JP7125373B2 (en) Information processing device, determination method, determination program, and determination system
CN112665730B (en) Pre-earthquake temperature anomaly detection method, pre-earthquake temperature anomaly detection device, pre-earthquake temperature anomaly detection equipment and storage medium
CN115265805A (en) Temperature calibration method based on thermopile, storage medium and related equipment
CN204833300U (en) Live body detecting system
JP6024510B2 (en) Energy consumption analysis apparatus, energy consumption analysis method, and computer program
CN114427913B (en) Temperature measurement method and device, electronic equipment and storage medium
CN115661438B (en) Off-site water level monitoring and flood prevention early warning method based on machine vision

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant