A target object recognition method and device, a camera and a medium

Abstract

The application relates to the field of target identification, in particular to a target object identification method and device, a camera and a medium. The method comprises the following steps: after detecting an image inspection instruction, acquiring a real-time shooting image and a real-time shooting target, then determining a target area based on the real-time shooting image and the real-time shooting target, then performing target definition identification on the target area to obtain target definition, then judging whether the target definition meets preset first definition, if the target definition meets the preset first definition, performing scene definition identification on the real-time shooting image to obtain scene definition, then judging whether the scene definition meets preset second definition, if the scene definition meets the preset second definition, generating inspection pass information, if the scene definition does not meet the preset second definition, generating inspection failure information, and the application has the effect of improving the shooting efficiency of the camera.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of target recognition, and in particular to a target object recognition method and device, a camera, and a medium. BACKGROUND

[0002] Target recognition refers to the process of distinguishing a special target (or a type of target) from other targets (or other types of targets). It includes the recognition of two very similar targets, as well as the recognition of a type of target from other types of targets.

[0003] Currently, when identifying a target object, a camera is usually used to capture the target object and the image in which the target object is located. Before a user uses the camera to capture an image, the camera's shooting mode and picture ratio need to be adjusted according to the current shooting scene and the scene position of the target object. Then, the target object is captured to obtain a target object image. The target object image is then imported into a processing device for target object image recognition to obtain the recognized target type and target position.

[0004] With respect to the above related technology, the inventors believe that the camera needs to be adjusted in real time by the user according to different shooting scenes and the scene position of the target object during the shooting process. The user cannot directly view whether the clarity of the captured image meets the requirements, thereby resulting in the low camera shooting efficiency. SUMMARY

[0005] To improve the camera shooting efficiency, the present application provides a target object recognition method, device, camera, and medium.

[0006] In a first aspect, the present application provides a target object recognition method, which adopts the following technical solution:

[0007] A target object recognition method, comprising:

[0008] After detecting an image inspection instruction, a real-time shooting image and a real-time shooting target are obtained. The real-time shooting image represents the image presented by the current camera, and the real-time shooting target is a shooting target selected by the user.

[0009] A target area is determined based on the real-time shooting image and the real-time shooting target.

[0010] A target clarity is obtained by performing target clarity recognition on the target area.

[0011] It is determined whether the target clarity meets a preset first clarity. If the target clarity meets the preset first clarity, a scene clarity is obtained by performing scene clarity recognition on the real-time shooting image.

[0012] determine whether the scene definition meets a preset second definition, and if the scene definition meets the preset second definition, generate a pass information, and if the scene definition does not meet the preset second definition, generate a fail information.

[0013] By using the above technical solution, when the definition of the image presented by the camera is detected, the real-time shooting image and the real-time shooting target are obtained, and then the target area is determined according to the real-time shooting image and the real-time shooting target. Then, the target definition is identified in the target area to obtain the target definition. Then, it is determined whether the target definition meets the preset first definition. When it meets, the scene definition of the real-time shooting image is identified to obtain the scene definition. Then, it is determined whether the scene definition meets the preset second definition. When it meets, the pass information is generated, which means that the definition of the current real-time shooting image and the real-time shooting target meets the standard. When the scene definition does not meet the preset second definition, the fail information is generated, which means that the definition of the current real-time shooting target meets the standard, and the definition of the real-time shooting image does not meet the standard. Therefore, in the shooting process of the camera, the user can directly observe whether the definition of the shooting image meets the standard, thereby improving the shooting efficiency of the camera.

[0014] In another possible implementation manner, the determining whether the scene definition meets the preset second definition comprises:

[0015] If the target definition does not meet the preset first definition or if the scene definition does not meet the preset second definition, the definition of the real-time shooting image is corrected to obtain a corrected image, and the first target definition and the first scene definition are determined according to the corrected image;

[0016] It is determined whether the first target definition meets the preset first definition and whether the first scene definition meets the preset second definition, respectively;

[0017] If the first target definition does not meet the preset first definition and / or the first scene definition does not meet the preset second definition, the steps of correcting the definition of the real-time shooting image to obtain a corrected image and determining the first target definition and the first scene definition according to the corrected image are repeatedly executed until the first target definition meets the preset first definition and the first scene definition meets the preset second definition.

[0018] By the technical solution, when the target definition does not meet the preset first definition or the scene definition does not meet the preset second definition, the definition of the real-time shooting image is corrected to obtain a corrected image, then the first target definition and the first scene definition are determined according to the corrected image, it is judged whether the first target definition meets the preset first definition and whether the first scene definition meets the preset second definition, when the first definition does not meet the preset second definition and / or the first scene definition does not meet the preset second definition, the definition of the real-time shooting image is repeatedly corrected to obtain a corrected image, and the first target definition and the first scene definition are determined according to the corrected image, until the first target definition meets the preset first definition and the first scene definition meets the preset second definition, and until the first target definition meets the preset first definition, thereby achieving the effect of automatically correcting and optimizing the definition of the real-time shooting image.

[0019] In another possible implementation manner, the judging whether the scene definition meets the preset second definition further includes:

[0020] The corrected image is input into the trained image network model for training to obtain image features and feature label information corresponding to the image features;

[0021] It is judged whether the feature label information meets preset label information, and if the feature label information meets the preset label information, the image features are labeled.

[0022] By the technical solution, after the definition of the real-time shooting image is corrected, the corrected image is input into the trained image network model for training to obtain image features and feature label information corresponding to the image features, then it is judged whether the feature label information meets preset label information, and the preset label information includes spikes and puddles, and when it meets, the image features are labeled to facilitate the prevention of the labeled image features.

[0023] In another possible implementation manner, the inputting the corrected image into the trained image network model for training further includes:

[0024] An image training sample is obtained, and the image training sample includes an object sample image and feature label information corresponding to each object in the object sample image;

[0025] An image network model is created, and the image network model is trained based on the object training sample to obtain a trained object network model.

[0026] By the technical solution, the image training sample is collected in advance, the image training sample includes an object sample image and feature label information corresponding to each person in the object sample image, the object sample image is a sample harmful to human body, and the feature label information includes a harmful object name, then an image network model is created, and the object training sample is input into the image network model to perform feature label information labeling on object information of the object training sample, so as to obtain a trained image network model, and then subsequent correction images are conveniently identified.

[0027] In another possible implementation manner, the method further includes:

[0028] obtaining working state information, the working state information being working state information of the camera;

[0029] determining whether the working state information has not changed within a preset time, and if the working state information has not changed within the preset time, generating a device standby instruction.

[0030] By the technical solution, when a user finishes shooting by using the camera, the camera is not closed in time, so that the working state information of the camera is in a working state for a long time, and the storage capacity of the camera is consumed. Therefore, it is determined whether the working state information of the current camera has not changed within a preset time, and if the working state information has not changed within the preset time, a device standby instruction is generated to control the camera to standby, so as to reduce the consumption of the storage capacity of the camera.

[0031] In another possible implementation manner, the obtaining of the working state information further includes:

[0032] performing data detection on the working state information to obtain device temperature data;

[0033] determining whether the device temperature data exceeds a preset temperature threshold;

[0034] if the device temperature data exceeds the preset temperature threshold, the device temperature data is labeled and a cooling prompt information is generated;

[0035] displaying the labeled device temperature data and the cooling prompt information.

[0036] By the technical solution, the temperature of the camera device is detected to determine the device temperature data of the camera device in the current working state, and then it is determined whether the device temperature data exceeds a preset temperature threshold. If the device temperature data exceeds the preset temperature threshold, the device temperature data is labeled and a cooling prompt information is generated, and the cooling prompt information and the labeled device temperature data are displayed on the camera lens, so that a user can cool the camera device according to the cooling prompt information.

[0037] In another possible implementation manner, the acquiring the real-time photographed image and the real-time photographed target further includes:

[0038] acquiring personnel identity information when the detection device opening instruction is detected;

[0039] determining whether the personnel identity information meets preset personnel identity information, the preset personnel identity information being used to represent personnel identity information allowed to use the device;

[0040] generating an early warning information if the personnel identity information does not meet the preset personnel identity information, and simultaneously controlling an alarm device to output an alarm signal through a preset mode, the preset mode including at least one of the following: an output sound mode and a light output mode.

[0041] With the above technical solution, when a user clicks an opening key of a camera to generate an opening instruction during photographing by using the camera, personnel identity information is acquired, and it is determined whether the personnel identity information meets preset personnel identity information, wherein the preset personnel identity information is used to represent personnel identity information allowed to use the device. When the personnel identity information does not meet the preset personnel identity information, an early warning information is generated, and simultaneously an alarm device is controlled to output an alarm signal through a preset mode, wherein the preset mode includes at least one of the following: an output sound mode and a light output mode, thereby improving the security of the camera device.

[0042] In a second aspect, the present application provides a target object recognition device, which adopts the following technical solution:

[0043] A target object recognition device includes:

[0044] an acquiring module configured to acquire a real-time photographed image and a real-time photographed target when an image inspection instruction is detected, the real-time photographed image being used to represent a current camera image, and the real-time photographed target being a photographing target selected by a user;

[0045] a determining module configured to determine a target region based on the real-time photographed image and the real-time photographed target;

[0046] an identifying module configured to perform target definition identification on the target region to obtain a target definition;

[0047] a first determining module configured to determine whether the target definition meets a preset first definition, and if the target definition meets the preset first definition, perform scene definition identification on the real-time photographed image to obtain a scene definition;

[0048] The second judging module is configured to judge whether the scene definition meets a preset second definition, and if the scene definition meets the preset second definition, generate the check pass information, and if the scene definition does not meet the preset second definition, generate the check fail information.

[0049] By using the above technical scheme, when the definition of the image presented by the camera is detected, the real-time shooting image and the real-time shooting target are acquired, then the target region is determined according to the real-time shooting image and the real-time shooting target, then the target definition is identified for the target region to obtain the target definition, then it is judged whether the target definition meets the preset first definition, when it meets, the scene definition is identified for the real-time shooting image to obtain the scene definition, then it is judged whether the scene definition meets the preset second definition, when it meets, the check pass information is generated, which means that the definition of the current real-time shooting image and the real-time shooting target meets the standard, when the scene definition does not meet the preset second definition, the check fail information is generated, which means that the definition of the current real-time shooting target meets the standard and the definition of the real-time shooting image does not meet the standard, so that the user can directly view whether the definition of the shooting image meets the standard during the shooting of the camera, and the shooting efficiency of the camera is improved.

[0050] In a possible implementation, when judging whether the scene definition meets the preset second definition, the second judging module is specifically configured to:

[0051] If the target definition does not meet the preset first definition or if the scene definition does not meet the preset second definition, the definition of the real-time shooting image is corrected to obtain a corrected image, and the first target definition and the first scene definition are determined according to the corrected image;

[0052] It is judged whether the first target definition meets the preset first definition and whether the first scene definition meets the preset second definition, respectively;

[0053] If the first target definition does not meet the preset first definition and / or the first scene definition does not meet the preset second definition, the steps of correcting the definition of the real-time shooting image to obtain a corrected image and determining the first target definition and the first scene definition according to the corrected image are repeatedly executed until the first target definition meets the preset first definition and the first scene definition meets the preset second definition.

[0054] In another possible implementation, the device further includes an image training module and a label judging module, wherein,

[0055] The image training module is configured to input the corrected image into the trained image network model for training to obtain image features and feature label information corresponding to the image features.

[0056] The label judging module is configured to judge whether the feature label information meets preset label information, and if the feature label information meets the preset label information, label the image features.

[0057] In another possible implementation, the apparatus further includes a sample obtaining module and a network creating module, wherein,

[0058] The sample obtaining module is configured to obtain image training samples, the image training samples including object sample images and feature label information corresponding to each object in the object sample images.

[0059] The network creating module is configured to create an image network model, and train the image network model based on the object training samples to obtain a trained object network model.

[0060] In another possible implementation, the apparatus further includes an information obtaining module and a state judging module, wherein,

[0061] The information obtaining module is configured to obtain working state information, the working state information being working state information of the camera.

[0062] The state judging module is configured to judge whether the working state information has not changed within a preset time, and if the working state information has not changed within the preset time, generate a device standby instruction.

[0063] In another possible implementation, the apparatus further includes an information detecting module, a data determining module, a label generating module and a control display module, wherein,

[0064] The information detecting module is configured to perform data detection on the working state information to obtain device temperature data.

[0065] The data determining module is configured to determine whether the device temperature data exceeds a preset temperature threshold.

[0066] The label generating module is configured to, when the device temperature data exceeds the preset temperature threshold, perform label processing on the real-time temperature data and generate cooling prompt information.

[0067] The control display module is configured to control display of the labeled real-time temperature data and the cooling prompt information.

[0068] In another possible implementation, the apparatus further includes an identity obtaining module, an identity judging module, and a pre-warning module, wherein

[0069] The identity obtaining module is configured to obtain the personnel identity information when detecting a device start instruction.

[0070] The identity judging module is configured to judge whether the personnel identity information meets preset personnel identity information, the preset personnel identity information being used to represent personnel identity information allowed to use the device.

[0071] The pre-warning module is configured to generate a pre-warning information when the personnel identity information does not meet the preset personnel identity information, and control an alarm device to output an alarm signal through a preset mode, the preset mode including at least one of the following: an output sound mode and a light output mode.

[0072] In a third aspect, the present application provides a camera, which adopts the following technical solution:

[0073] A camera, comprising:

[0074] at least one processor;

[0075] a memory;

[0076] at least one application program, wherein the at least one application program is stored in the memory and is configured to be executed by the at least one processor, and the at least one application program is configured to execute the target object recognition method.

[0077] In a fourth aspect, the present application provides a computer readable storage medium, which adopts the following technical solution:

[0078] A computer readable storage medium, comprising a computer program stored therein and capable of being loaded by a processor and executing the target object recognition method.

[0079] In summary, the present application has the following beneficial technical effects:

[0080] 1. In the sharpness detection of the image presented by the camera, the real-time shooting image and the real-time shooting target are obtained, then the target area is determined according to the real-time shooting image and the real-time shooting target, then the target sharpness is identified, the target sharpness is obtained, then it is judged whether the target sharpness meets the preset first sharpness, when it meets, the scene sharpness of the real-time shooting image is identified, the scene sharpness is obtained, then it is judged whether the scene sharpness meets the preset second sharpness, when it meets, the check pass information is generated, which means that the sharpness of the current real-time shooting image and the real-time shooting target meets the standard, when the scene sharpness does not meet the preset second sharpness, the check identification information is generated, which means that the sharpness of the current real-time shooting target meets the standard, the sharpness of the real-time shooting image does not meet the standard, so that the user can directly observe whether the sharpness of the shooting image meets the standard in the shooting process of the camera, thereby improving the shooting efficiency of the camera.

[0081] 2. When using the camera to shoot, the user clicks the start key of the camera to generate a start instruction, obtains personnel identity information, and judges whether the personnel identity information meets the preset personnel identity information, wherein the preset personnel identity information is used to represent the personnel identity information allowed to use the equipment, when the personnel identity information does not meet the preset personnel identity information, the warning information is generated, and the alarm device is controlled to output the alarm signal through the preset mode, wherein the preset mode includes at least one of the following: sound output mode and light output mode, thereby improving the safety of the camera equipment. BRIEF DESCRIPTION OF DRAWINGS

[0082] Figure 1 is a flow diagram of a target object identification method according to an embodiment of the present application;

[0083] Figure 2 is a block diagram of a target object identification method according to an embodiment of the present application;

[0084] Figure 3 is a schematic diagram of a camera according to an embodiment of the present application. DETAILED DESCRIPTION

[0085] The following will be described in detail in combination with the accompanying drawings Figures 1-3 The present application will be further described in detail.

[0086] The person skilled in the art can make modifications to the present embodiment without creative contribution after reading the present specification, but as long as it is within the scope of the claims of the present application, it is protected by the patent law.

[0087] In order to make the purposes, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0088] In addition, the term "and / or" in the present application is only used to describe the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can mean that A exists alone, A and B exist together, and B exists alone. In addition, the character " / " in the present application generally represents an "or" relationship between the front and rear associated objects unless otherwise specified.

[0089] The embodiments of the present application will be described in further detail below with reference to the drawings of the specification.

[0090] The embodiments of the present application provide a target object recognition method, which is executed by a camera, as shown in the method comprises the following steps. Figure 1

[0091] Step S10, after detecting an image verification instruction, acquiring a real-time shooting image and a real-time shooting target, the real-time shooting image is used to represent the image presented by the current camera, and the real-time shooting target is a shooting target selected by a user.

[0092] In the embodiments of the present application, when a user triggers an image verification button installed on the surface of the camera, an image verification instruction is generated, at this time, the image shot by the camera lens is intercepted as a real-time shooting image, and the user obtains a real-time shooting target by clicking a corresponding shooting target in the camera screen.

[0093] Step S11, determining a target region based on the real-time shooting image and the real-time shooting target.

[0094] Specifically, the target region refers to the region position of the real-time shooting image where the real-time shooting target is located, for example, there are target personnel, vehicles, and trees in the real-time shooting image, the user generates a red selection box by clicking the picture presented by the target personnel, and the position enclosed in the red selection box is the shooting target position.

[0095] Step S12, performing target sharpness recognition on the target region to obtain target sharpness.

[0096] Step S13, judging whether the target sharpness meets a preset first sharpness, if the target sharpness meets the preset first sharpness, performing scene sharpness recognition on the real-time shooting image to obtain scene sharpness.

[0097] ​Step S14, judging whether the scene sharpness meets the preset second sharpness, if the scene sharpness meets the preset second sharpness, generating the check pass information, if the scene sharpness does not meet the preset second sharpness, generating the check failure information.

[0098] For the embodiment of the application, the judgment of the target sharpness and the scene sharpness is realized by using opencv to obtain, the sharpness of the target region and the sharpness of the shooting scene are identified respectively, and the identified sharpness is checked. When the target sharpness and / or the scene sharpness are insufficient, it may be due to the influence of external factors (light and rain, etc.), and the image captured by the camera is prone to blur, thus leading to a decrease in sharpness.

[0099] The embodiment of the application provides a target object identification method. When the sharpness of the image presented by the camera is detected, a real-time shooting image and a real-time shooting target are obtained, then a target region is determined according to the real-time shooting image and the real-time shooting target, then the target region is subjected to target sharpness identification to obtain a target sharpness, then it is judged whether the target sharpness meets a preset first sharpness, when the target sharpness meets the preset first sharpness, the real-time shooting image is subjected to scene sharpness identification to obtain a scene sharpness, then it is judged whether the scene sharpness meets a preset second sharpness, when the scene sharpness meets the preset second sharpness, check pass information is generated, which means that the sharpness of the current real-time shooting image and the real-time shooting target meets the standard, when the scene sharpness does not meet the preset second sharpness, check identification information is generated, which means that the sharpness of the current real-time shooting target meets the standard, and the sharpness of the real-time shooting image does not meet the standard, so that the user can directly view whether the sharpness of the captured image meets the standard during the shooting of the camera, thereby improving the shooting efficiency of the camera and the information query efficiency.

[0100] In a possible implementation of the embodiment of the application, step S14 specifically includes step S141 (not shown in the figure), step S142 (not shown in the figure) and step S143 (not shown in the figure), wherein,

[0101] Step S121, if the target sharpness does not meet the preset first sharpness or if the scene sharpness does not meet the preset second sharpness, the real-time shooting image is subjected to sharpness correction to obtain a corrected image, and the first target sharpness and the first scene sharpness are determined according to the corrected image.

[0102] In the embodiments of the present application, the interference factors of the image are automatically identified, the interference reasons causing the target definition and the scene definition not to meet the first definition and the second definition are determined, and then the shooting mode of the camera is adjusted according to the interference reasons to reduce the influence of the image interference factors. For example, when shooting in a cloudy and rainy day, the light in the cloudy and rainy day is scattering light. Under this light condition, the contrast of the picture is small, and there is no strong light and dark contrast. In addition, due to the weather, the scene appears chaotic and blurred, thereby giving a person a sense of dimness or oppression. The following methods can be used to adjust the interference:

[0103] 1. Different shutter speeds show different picture effects. A faster shutter speed can obtain the effect of raindrops freezing in the air; a slower shutter speed can obtain longer rain strips. Generally, the shutter speed is set to 1 / 30 second to 1 / 60 second, and the shutter speed is appropriate at this time, which can be used to emphasize the dynamic feeling of the falling rain.

[0104] 2. The light in the cloudy and rainy day is relatively dim. When using a high-speed shutter, the values of the aperture and the sensitivity must be adjusted to obtain appropriate exposure of the picture.

[0105] 3. When shooting in the cloudy and rainy day, attention must be paid to exposure, and the principle of “prefer underexposure to overexposure” must be followed. Overexposure will cause the picture details to be lost, and the picture cannot be recovered in the later period. Shooting in the rainy day is often prone to overexposure, and therefore the exposure compensation needs to be appropriately reduced, and the image contrast needs to be increased to facilitate the adjustment of the picture in the later period.

[0106] Step S122, whether the first target definition meets the preset first definition and whether the first scene definition meets the preset second definition are respectively judged.

[0107] Step S123, if the first target definition does not meet the preset first definition and / or the first scene definition does not meet the preset second definition, the steps of performing definition correction on the real-time shooting image to obtain a corrected image and determining the first target definition and the first scene definition according to the corrected image are repeatedly executed until the first target definition meets the preset first definition and the first scene definition meets the preset second definition.

[0108] Specifically, when the first target definition does not meet the preset first definition and / or the first scene definition does not meet the preset second definition, the definition correction process method is repeatedly executed until the first target definition meets the preset first definition and the first scene definition meets the preset second definition.

[0109] In one possible implementation of the embodiments of the present application, after step S14, steps Sa (not shown in the figure) and Sb (not shown in the figure) are further included, wherein,

[0110] Step Sa, inputting the corrected image into the trained image network model for training to obtain image features and feature label information corresponding to the image features.

[0111] Specifically, the corrected image is inputted into the image network model for training to obtain image features and corresponding feature label information. For the embodiment of the present application, the image features are features of harmful human bodies contained in the corrected image, and the feature label information is the name corresponding to the features, for example, the corrected image contains a sharp feature, a water accumulation feature, and a pit feature.

[0112] Step Sb, judging whether the feature label information meets preset label information, and if the feature label information meets the preset label information, labeling the image features.

[0113] Specifically, the recognized image features are labeled in the form of a red circle.

[0114] In a possible implementation of the embodiment of the present application, the step Sa further includes the following steps before the step Sa:

[0115] Obtaining image training samples, the image training samples including object sample images and feature label information corresponding to each object in the object sample images.

[0116] Creating an image network model, and training the image network model based on the object training samples to obtain a trained object network model.

[0117] In a possible implementation of the embodiment of the present application, the step S14 further includes a step S15 (not shown in the figure) and a step S16 (not shown in the figure), wherein,

[0118] Step S15, obtaining working state information, the working state information being working state information of the camera.

[0119] In the embodiment of the present application, the working state information includes an open non-working state, device state information, and an open working state. When the user does not use the camera during the shooting interval, the camera remains in the open non-working state. When the user starts shooting, the camera is switched from the open non-working state to the open working state.

[0120] Step S16, judging whether the working state information has not changed within a preset time, and if the working state information has not changed within the preset time, generating a device standby instruction.

[0121] For the embodiment of the present application, the preset time is 30 minutes, that is, judging whether the working state information remains in a state without change within 30 minutes (there is only one possible state, the open non-working state), and if so, generating a device standby instruction to control the camera to standby.

[0122] In a possible implementation of the embodiment of the application, after step S15 (not shown in the figure), the method further includes step S151 (not shown in the figure), step S152 (not shown in the figure), step S153 (not shown in the figure), and step S154 (not shown in the figure), wherein,

[0123] In step S151, the working state information is subjected to data detection to obtain device temperature data.

[0124] Specifically, the device state information in the working state information is filtered, and the filtered information is subjected to data detection to obtain the device temperature data.

[0125] Specifically, when the temperature information of the camera in the working state is detected, the thermometer method can be used to directly convert the temperature signal measured by the temperature sensor into a voltage signal that is transformed according to a certain rule, and the voltage signal is directly connected to the PC through one or two A / D conversion cards, and the device temperature data of the camera can be tested by using a special temperature test software.

[0126] In step S152, it is determined whether the device temperature data exceeds a preset temperature threshold.

[0127] In the embodiment of the application, the preset temperature threshold is 60 degrees Celsius.

[0128] In step S153, if the device temperature data exceeds the preset temperature threshold, the real-time temperature data is subjected to marking processing, and cooling prompt information is generated.

[0129] Specifically, the temperature value that has exceeded the preset temperature threshold is saved, and the saved temperature value is subjected to red marking processing, for example, ‘ <span style=""color:red”">{Device temperature data} ’ is added to the temperature value. Meanwhile, the part of the camera that exceeds the preset temperature threshold is determined, the current part is matched with the cooling prompt information stored in the database according to the part, and the cooling prompt information is generated.

[0130] In step S154, the real-time temperature data after marking and the cooling prompt information are controlled to be displayed.

[0131] Specifically, the real-time temperature data and the cooling prompt information are acquired through a controller, a service, and a data access layer (dao). The data access layer is only responsible for data interaction with the database, and performs a reading operation on the data. The service needs to write logical code according to the actual business requirements of the system. The service logic layer calls the related methods of the data access layer to realize the interaction with the database, and feeds back the execution result to the controller. The controller sends the position information to a view renderer, and the real-time temperature data and the cooling prompt information are subjected to view rendering and echoing.

[0132] In one possible implementation of this application embodiment, step S14 is followed by steps S17 (not shown in the figure) and S18 (not shown in the figure), wherein...

[0133] Step S17: After the detection device is activated, obtain the personnel's identity information.

[0134] In this embodiment of the application, iris verification is used to obtain personnel identity information.

[0135] Step S18: Determine whether the personnel identity information meets the preset personnel identity information. The preset personnel identity information is used to represent the personnel identity information who are allowed to use the equipment.

[0136] Step S19: If the personnel identity information does not meet the preset personnel identity information, an early warning information is generated, and the alarm device is controlled to output an alarm signal in a preset manner. The preset manner includes at least one of the following: sound output and light output.

[0137] Devices that emit alarm signals by sound include buzzers, bells, whistles, and sirens, while devices that emit alarm signals by light output include breathing lights, flashing lights, and engineering warning lights.

[0138] The above embodiments describe a target object recognition method from the perspective of process flow. The following embodiments describe a target object recognition device from the perspective of virtual module or virtual unit. For details, please refer to the following embodiments.

[0139] This application provides a target object recognition device, such as... Figure 2 As shown, the target object recognition device 20 may specifically include: an acquisition module 21, a determination module 22, a recognition module 23, a first judgment module 24, and a second judgment module 25, wherein,

[0140] The acquisition module 21 is used to acquire the real-time captured image and the real-time captured target when an image inspection command is detected. The real-time captured image is used to represent the image presented by the current camera, and the real-time captured target is the captured target selected by the user.

[0141] The determination module 22 is used to determine the target area based on the real-time captured images and the real-time captured target;

[0142] The recognition module 23 is used to identify the target clarity of the target area and obtain the target clarity.

[0143] The first judgment module 24 is used to judge whether the target clarity meets the preset first clarity. If the target clarity meets the preset first clarity, the scene clarity is identified by the real-time captured image to obtain the scene clarity.

[0144] The second judging module 25 is configured to judge whether the scene sharpness meets a preset second sharpness, and generate a check pass information if the scene sharpness meets the preset second sharpness, or generate a check fail information if the scene sharpness does not meet the preset second sharpness.

[0145] In a possible implementation of the embodiment, when judging whether the scene sharpness meets the preset second sharpness, the second judging module 25 is specifically configured to:

[0146] If the target sharpness does not meet the preset first sharpness or if the scene sharpness does not meet the preset second sharpness, the real-time shooting image is subjected to sharpness correction to obtain a corrected image, and the first target sharpness and the first scene sharpness are determined according to the corrected image;

[0147] It is judged whether the first target sharpness meets the preset first sharpness and whether the first scene sharpness meets the preset second sharpness, respectively.

[0148] If the first target sharpness does not meet the preset first sharpness and / or the first scene sharpness does not meet the preset second sharpness, the steps of subjecting the real-time shooting image to sharpness correction to obtain a corrected image, and determining the first target sharpness and the first scene sharpness according to the corrected image are repeatedly executed until the first target sharpness meets the preset first sharpness and the first scene sharpness meets the preset second sharpness.

[0149] In another possible implementation of the embodiment, the device 20 further includes an image training module and a label judging module, wherein

[0150] The image training module is configured to input the corrected image into the trained image network model for training to obtain an image feature and a feature label information corresponding to the image feature.

[0151] The label judging module is configured to judge whether the feature label information meets a preset label information, and label the image feature if the feature label information meets the preset label information.

[0152] In another possible implementation of the embodiment, the device 20 further includes a sample obtaining module and a network creating module, wherein

[0153] The sample obtaining module is configured to obtain an image training sample, and the image training sample includes an object sample image and a feature label information corresponding to each object in the object sample image.

[0154] The network creating module is configured to create an image network model, and train the image network model based on the object training sample to obtain a trained object network model.

[0155] In a possible implementation of the present application, the device 20 further comprises an information acquisition module and a state judgment module, wherein,

[0156] The information acquisition module is configured to acquire the working state information, the working state information being the working state information of the camera.

[0157] The state judgment module is configured to judge whether the working state information has not changed within a preset time, and generate the device standby instruction if the working state information has not changed within the preset time.

[0158] In a possible implementation of the present application, the device 20 further comprises an information detection module, a data determination module, a label generation module and a control display module, wherein,

[0159] The information detection module is configured to perform data detection on the working state information to obtain device temperature data.

[0160] The data determination module is configured to determine whether the device temperature data exceeds a preset temperature threshold.

[0161] The label generation module is configured to perform label processing on the real-time temperature data and generate a cooling prompt information when the device temperature data exceeds the preset temperature threshold.

[0162] The control display module is configured to control display of the labeled real-time temperature data and the cooling prompt information.

[0163] In a possible implementation of the present application, the device 20 further comprises an identity acquisition module, an identity judgment module and a warning module, wherein,

[0164] The identity acquisition module is configured to acquire personnel identity information when detecting the device opening instruction.

[0165] The identity judgment module is configured to judge whether the personnel identity information meets a preset personnel identity information, the preset personnel identity information being used to represent the personnel identity information allowed to use the device.

[0166] The warning module is configured to generate a warning information when the personnel identity information does not meet the preset personnel identity information, and control an alarm device to output an alarm signal through a preset mode, the preset mode comprising at least one of the following: an output sound mode and a light output mode.

[0167] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, device and unit described above can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0168] The embodiment of the present application also introduces a camera from the perspective of an entity device, as shown in Figure 3 Figure 3 The camera 300 shown in the figure comprises a processor 301 and a memory 303 in addition to a conventional configuration device. The processor 301 and the memory 303 are connected, for example, through a bus 302. Optionally, the camera 300 can also comprise a transceiver 304. It should be noted that the transceiver 304 is not limited to one in actual application, and the structure of the camera 300 does not constitute a limitation on the embodiment of the present application.

[0169] The processor 301 can be a CPU (Central Processing Unit, central processor), a general-purpose processor, a DSP (Digital Signal Processor, data signal processor), an ASIC (Application Specific Integrated Circuit, application specific integrated circuit), an FPGA (Field Programmable Gate Array, field programmable gate array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It can implement or execute various exemplary logical blocks, modules and circuits described in combination with the disclosure content of the present application. The processor 301 can also be a combination of computing functions, such as one or more microprocessor combinations, combinations of DSP and microprocessor, etc.

[0170] The bus 302 can comprise a channel for transmitting information between the above-mentioned components. The bus 302 can be a PCI (Peripheral Component Interconnect, peripheral component interconnect) bus or an EISA (Extended Industry Standard Architecture, extended industry standard architecture) bus, etc. The bus 302 can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, Figure 3 only one thick line is used in the figure, but it does not mean that there is only one bus or only one type of bus.

[0171] ​The memory 303 can be a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions; a RAM (Random Access Memory) or other type of dynamic storage device that can store information and instructions; an EEPROM (Electrically Erasable Programmable Read-Only Memory), a CD-ROM (Compact Disc Read-Only Memory) or other optical disk storage, a magnetic disk storage or other magnetic storage devices, or any other medium capable of storing desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited thereto.

[0172] The memory 303 is configured to store application program codes for implementing the solutions of the present application, and the processor 301 is configured to control the execution of the application program codes. The processor 301 is configured to execute the application program codes stored in the memory 303 to implement the content shown in the foregoing method embodiments.

[0173] The camera includes, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (Personal Digital Assistant), a PAD (Tablet Personal Computer), a PMP (Portable Multimedia Player), a vehicle-mounted terminal (e.g., a vehicle-mounted navigation terminal), and the like, and a fixed terminal such as a digital TV, a desktop computer, and the like. The camera can also be a server or the like. Figure 3 The illustrated camera is merely an example and should not impose any limitation on the functions and use range of the embodiments of the present application.

[0174] It should be understood that, although the steps in the flowchart of the accompanying drawings are shown in sequence according to the direction of the arrows, these steps are not necessarily executed in sequence according to the direction of the arrows. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and they can be executed in other sequences. Moreover, at least some of the steps in the flowchart of the accompanying drawings can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence is not necessarily sequential, but can be executed in rotation or alternation with at least some of the other steps or sub-steps or stages of the other steps.

[0175] The above merely preferred embodiments of the present application, it should be noted that for those skilled in the art, without departing from the principles of the present application, can make several improvements and refinements, these improvements and refinements should also be considered as the scope of protection of the present application.

Claims

1. A method for identifying a target object, characterized in that, include Upon detecting an image inspection command, the system acquires a real-time captured image and a real-time captured target. The real-time captured image represents the image currently displayed by the camera, and the real-time captured target is the captured target selected by the user. The target area is determined based on the real-time captured image and the real-time captured target. The target region is subjected to target sharpness identification to obtain the target sharpness. Determine whether the target sharpness meets a preset first sharpness. If the target sharpness meets the preset first sharpness, then perform scene sharpness recognition on the real-time captured image to obtain the scene sharpness. Determine whether the scene clarity meets the preset second clarity. If the scene clarity meets the preset second clarity, generate a verification pass message. If the scene clarity does not meet the preset second clarity, generate a verification failure message. The step of determining whether the scene sharpness meets the preset second sharpness includes: If the target sharpness does not meet the preset first sharpness or if the scene sharpness does not meet the preset second sharpness, then the sharpness of the real-time captured image is corrected to obtain a corrected image, and the first target sharpness and the first scene sharpness are determined based on the corrected image. Determine whether the first target's sharpness meets a preset first sharpness and whether the first scene's sharpness meets a preset second sharpness; If the first target sharpness does not meet the preset first sharpness and / or the first scene sharpness does not meet the preset second sharpness, then the steps of performing sharpness correction on the real-time captured image to obtain a corrected image, and determining the first target sharpness and the first scene sharpness based on the corrected image are executed repeatedly until the first target sharpness meets the preset first sharpness and the first scene sharpness meets the preset second sharpness.

2. The method according to claim 1, characterized in that, The step of determining whether the scene sharpness meets the preset second sharpness also includes: The corrected image is input into the trained image network model for training to obtain image features and feature label information corresponding to the image features; Determine whether the feature label information matches the preset label information. If the feature label information matches the preset label information, then label the image features.

3. The method according to claim 2, characterized in that, Before inputting the corrected image into the trained image network model for training, the process further includes: Obtain image training samples, which include object sample images and feature label information corresponding to each object in the object sample images; An image network model is created, and the image network model is trained based on the object training samples to obtain a trained object network model.

4. The method according to claim 1, characterized in that, The method further includes: Acquire working status information, wherein the working status information is the working status information of the camera; Determine whether the working status information has not changed within a preset time. If the working status information has not changed within the preset time, generate a device standby command.

5. The method according to claim 4, characterized in that, The process of obtaining the working status information further includes: The operating status information is analyzed to obtain equipment temperature data; Determine whether the device temperature data exceeds a preset temperature threshold; If the device temperature data exceeds the preset temperature threshold, the device temperature data will be annotated and a cooling prompt message will be generated. The control displays the labeled equipment temperature data and cooling prompts.

6. The method according to claim 1, characterized in that, The process of acquiring real-time captured images and real-time captured targets also includes, prior to: When the detection equipment is activated, it acquires the personnel's identity information; Determine whether the personnel identity information meets the preset personnel identity information, which is used to characterize the personnel identity information who are allowed to use the device; If the personnel identity information does not meet the preset personnel identity information, an early warning message is generated, and the alarm device is controlled to output an alarm signal in a preset manner. The preset manner includes at least one of the following: sound output and light output.

7. A target object recognition device, characterized in that, include: The acquisition module is used to acquire a real-time captured image and a real-time captured target when an image inspection command is detected. The real-time captured image represents the image currently presented by the camera, and the real-time captured target is the captured target selected by the user. The determination module is used to determine the target area based on the real-time captured image and the real-time captured target; The recognition module is used to identify the target area and obtain the target clarity. The first judgment module is used to determine whether the target clarity meets the preset first clarity. If the target clarity meets the preset first clarity, the scene clarity is identified by the real-time captured image to obtain the scene clarity. The second judgment module is used to determine whether the scene clarity meets the preset second clarity. If the scene clarity meets the preset second clarity, a verification pass message is generated. If the scene clarity does not meet the preset second clarity, a verification failure message is generated. When determining whether the scene sharpness meets the preset second sharpness, the second judgment module is specifically used for: If the target sharpness does not meet the preset first sharpness or if the scene sharpness does not meet the preset second sharpness, then the sharpness of the real-time captured image is corrected to obtain a corrected image, and the first target sharpness and the first scene sharpness are determined based on the corrected image. Determine whether the first target's sharpness meets a preset first sharpness and whether the first scene's sharpness meets a preset second sharpness; If the first target sharpness does not meet the preset first sharpness and / or the first scene sharpness does not meet the preset second sharpness, then the steps of performing sharpness correction on the real-time captured image to obtain a corrected image, and determining the first target sharpness and the first scene sharpness based on the corrected image are executed repeatedly until the first target sharpness meets the preset first sharpness and the first scene sharpness meets the preset second sharpness.

8. A camera, characterized in that, The camera includes: At least one processor; Memory; At least one application, wherein the at least one application is stored in memory and configured to be executed by at least one processor, said at least one application being configured to: perform the target object recognition method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed in the computer, the computer is instructed to perform the target object recognition method according to any one of claims 1 to 6.

Images