Rear air window heating method and device based on image recognition, electronic equipment and vehicle

Abstract

The invention discloses a rear air window heating method and device based on image recognition, electronic equipment and a vehicle, and relates to the technical field of vehicles. The method comprises the following steps: acquiring image information of a target rear air window; transmitting the image information to a preset neural network model for image information similarity value calculation; determining a control signal according to the image information similarity value; and controlling a heating device of the target rear air window according to the control signal. The preset neural network is used for detecting the image information of the rear air window, heating of the rear air window is automatically started or stopped according to the image information so as to remove fog, accumulated snow or condensed water drops on the rear air window, and therefore it can be guaranteed to a certain extent that the sight of a driver is not affected, and driving safety and comfort are prompted.

Description

Technical Field

[0001] The present invention relates to the field of vehicle technology, and in particular to a rear windshield heating method based on image recognition, a rear windshield heating device based on image recognition, an electronic device, a computer-readable storage medium and a vehicle. Background Art

[0002] When people are driving or riding in vehicles, they not only pursue convenient transportation, but also pay more and more attention to intelligence, safety, comfort, etc. In rainy and snowy weather, the rear windshield of the vehicle is prone to fogging, snow accumulation or condensation, which seriously blocks the driver's rear view and increases driving risks. Summary of the invention

[0003] The present invention aims to solve at least one of the technical problems in the related art to a certain extent. To this end, the first purpose of the present invention is to propose a rear wind window heating method based on image recognition, to obtain image information of the target rear wind window; to transmit the image information to a preset neural network model to calculate the image information similarity value; to determine a control signal according to the image information similarity value; and to control the heating device of the target rear wind window according to the control signal. The present invention uses a preset neural network to detect the image information of the rear wind window, and automatically turns on or off the rear wind window heating according to the image information to remove fog, snow or condensed water droplets on the rear wind window. In this way, the driver's vision can be guaranteed to be unaffected to a certain extent, and the driving safety and comfort can be prompted.

[0004] The second objective of the present invention is to provide a rear windshield heating device based on image recognition.

[0005] A third objective of the present invention is to provide an electronic device.

[0006] A fourth object of the present invention is to provide a computer-readable storage medium.

[0007] A fifth object of the present invention is to provide a vehicle.

[0008] To achieve the above-mentioned purpose, the first aspect of the embodiment of the present invention proposes a rear wind window heating method based on image recognition, which obtains image information of the target rear wind window; transmits the image information to a preset neural network model to calculate the image information similarity value; determines a control signal according to the image information similarity value; and controls the heating device of the target rear wind window according to the control signal.

[0009] According to one embodiment of the present invention, a heating device of a target rear wind window is controlled according to a control signal, including: when the control signal includes a heating control signal to turn on, the heating device of the target rear wind window is controlled to heat the target rear wind window; when the control signal includes a heating control signal to turn off, the heating device of the target rear wind window is controlled to stop heating the target rear wind window.

[0010] According to one embodiment of the present invention, a control signal is determined based on an image information similarity value, including: when the image information similarity value is greater than a preset similarity value threshold, determining that the control signal is a heating on control signal; when the image information similarity value is less than or equal to the preset similarity value threshold, determining that the control signal is a heating off control signal.

[0011] According to one embodiment of the present invention, image information is transmitted to a preset neural network model to calculate the image information similarity value, including: extracting features from the image information to obtain a target feature vector; extracting features from each standard image information in a standard image information set to obtain multiple standard feature vectors, wherein the standard image information set includes multiple standard image information; and determining the similarity value between the image information and each standard image information based on the target feature vector and the standard feature vector.

[0012] According to an embodiment of the present invention, determining the similarity value between the image information and each standard image information according to the target feature vector and the standard feature vector includes: obtaining the Euclidean distance between the target feature vector and the standard feature vector as the similarity value.

[0013] According to one embodiment of the present invention, the above method also includes: acquiring a first image data set and a second image data set; using the first image data set to train a preset neural network model; using the second image data set to test the preset neural network model to obtain an accuracy value; when the accuracy value exceeds a preset accuracy threshold, determining that the training of the preset neural network model is completed.

[0014] To achieve the above-mentioned purpose, the second aspect of the embodiment of the present invention proposes a rear windshield heating device based on image recognition, and the device includes: an acquisition module, used to acquire image information of the target rear windshield; a calculation module, used to transmit the image information to a preset neural network model to calculate the image information similarity value; a determination module, used to determine a control signal according to the image information similarity value; and a control module, used to control the heating device of the target rear windshield according to the control signal.

[0015] To achieve the above-mentioned purpose, an embodiment of the third aspect of the present invention proposes an electronic device, including a memory, a processor, and a rear window heating program based on image recognition stored in the memory and executable on the processor. When the processor executes the rear window heating program based on image recognition, the aforementioned rear window heating method based on image recognition is implemented.

[0016] To achieve the above-mentioned purpose, the fourth aspect of the present invention proposes a computer-readable storage medium, on which a rear wind window heating program based on image recognition is stored. When the rear wind window heating program based on image recognition is executed by a processor, the aforementioned rear wind window heating method based on image recognition is implemented.

[0017] To achieve the above-mentioned purpose, the fifth aspect of the present invention proposes a vehicle, including a memory, a processor, and a rear wind window heating program based on image recognition stored in the memory and executable on the processor. When the processor executes the rear wind window heating program based on image recognition, the aforementioned rear wind window heating method based on image recognition is implemented.

[0018] According to the rear windshield heating method, device, electronic device and vehicle based on image recognition of the embodiment of the present invention, image information of the target rear windshield is obtained; the image information is transmitted to a preset neural network model to calculate the image information similarity value; a control signal is determined according to the image information similarity value; and the heating device of the target rear windshield is controlled according to the control signal. The present invention uses a preset neural network to detect the image information of the rear windshield, and automatically turns on or off the rear windshield heating according to the image information to remove fog, snow or condensed water droplets on the rear windshield. In this way, the driver's vision can be guaranteed to be unaffected to a certain extent, and the driving safety and comfort can be prompted. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a flow chart of a rear windshield heating method based on image recognition according to some embodiments of the present invention;

[0020] Figure 2 is a flow chart of a rear windshield heating method based on image recognition according to some other embodiments of the present invention;

[0021] Figure 3 is a flowchart of a preset neural network model training method according to some embodiments of the present invention;

[0022] Figure 4 is a block diagram of a rear windshield heating device based on image recognition according to some embodiments of the present invention;

[0023] Figure 5 is a block diagram of an electronic device according to some embodiments of the present invention;

[0024] Figure 6is a block diagram of a vehicle according to some embodiments of the present invention. DETAILED DESCRIPTION

[0025] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0026] The following describes in detail a rear window heating method, device, electronic device and vehicle based on image recognition according to an embodiment of the present invention with reference to the accompanying drawings.

[0027] Figure 1 Flow chart of a rear windshield heating method based on image recognition according to some embodiments of the present invention. Figure 1 The rear windshield heating method based on image recognition in the embodiment of the present application may include the following steps:

[0028] S110, acquiring image information of the target rear windshield.

[0029] Specifically, the image information of the target rear windshield can be obtained in real time through a camera set on the target rear windshield, wherein the image information of the target rear windshield includes but is not limited to fogging image information, snow accumulation image information, condensation water droplet image information and normal image information (image information without fog, snow accumulation or condensation water droplets).

[0030] S120, transmitting the image information to a preset neural network model to calculate the image information similarity value.

[0031] Specifically, the preset neural network model can be a Siamese network, a twin network, a ResNet (Residual Network) and a DenseNet (Densely Connected Convolutional Networks), etc., and no specific restrictions are made here. After the image information is transmitted to the preset neural network model, the image similarity value can be calculated, for example, the image similarity value between the image information and a plurality of standard image information is calculated, wherein the plurality of standard image information includes a plurality of standard fogging image information, a plurality of standard snow image information and a plurality of standard condensation drop image information.

[0032] S130, determining a control signal according to the image information similarity value.

[0033] Specifically, the control signal can be determined to be a heating on control signal or a heating off control signal according to the image information similarity value. For example, when the image information similarity value is relatively large, it means that the image information is one or more of fogging image information, snow accumulation image information, and condensation water drop image information, and the control signal is determined to be a heating on control signal; when the image information similarity value is relatively small, it means that the image information is normal image information, and the control signal is determined to be a heating off control signal.

[0034] S140, controlling the heating device of the target rear windshield according to the control signal.

[0035] It should be noted that the heating device of the target rear windshield may be integrated inside the target rear windshield, or may be a separate heating device, and no specific limitation is made here.

[0036] The present invention uses a preset neural network to detect image information of the rear windshield, and automatically turns on or off the rear windshield heating according to the image information to remove fog, snow or condensed water droplets on the rear windshield. In this way, the driver's vision can be ensured to a certain extent without being affected, thereby ensuring driving safety and comfort.

[0037] In some embodiments, the heating device of the target rear wind window is controlled according to a control signal, including: when the control signal includes a heating control signal to turn on, the heating device of the target rear wind window is controlled to heat the target rear wind window; when the control signal includes a heating control signal to turn off, the heating device of the target rear wind window is controlled to stop heating the target rear wind window.

[0038] Exemplarily, if the control signal includes a heating control signal to turn on, indicating that one or more of fogging, snow accumulation or condensation droplets appear on the rear wind window, then the heating device of the target rear wind window needs to be controlled to heat the target rear wind window to remove the fog, snow accumulation or condensation droplets on the rear wind window; if the control signal includes a heating control signal to turn off, indicating that fogging, snow accumulation or condensation droplets do not appear on the rear wind window, or the heating device of the target rear wind window has removed the fog, snow accumulation or condensation droplets on the rear wind window, then the heating device of the target rear wind window needs to be controlled to stop heating the target rear wind window, which can avoid damage to the rear wind window caused by long-term heating to a certain extent.

[0039] In some embodiments, determining the control signal according to the image information similarity value includes: determining the control signal as a heating on control signal when the image information similarity value is greater than a preset similarity value threshold; and determining the control signal as a heating off control signal when the image information similarity value is less than or equal to the preset similarity value threshold. The preset similarity value threshold can be determined according to actual conditions and is not specifically limited here.

[0040] Specifically, the control signal can be determined by comparing the image information similarity value with a preset similarity value threshold. Exemplarily, if the image information similarity value is greater than the preset similarity value threshold, it means that the image information is one or more of fogging image information, snow image information, and condensed water drop image information, and the control signal is determined to be a heating on control signal; if the image information similarity value is less than or equal to the preset similarity value threshold, it means that the image information is normal image information, and the control signal is determined to be a heating off control signal.

[0041] In some embodiments, the image information is transmitted to a preset neural network model to calculate the image information similarity value, including: extracting features from the image information to obtain a target feature vector; extracting features from each standard image information in a standard image information set to obtain multiple standard feature vectors, wherein the standard image information set includes multiple standard image information; and determining the similarity value between the image information and each standard image information based on the target feature vector and the standard feature vector.

[0042] In some embodiments, determining the similarity value between the image information and each standard image information according to the target feature vector and the standard feature vector includes: obtaining the Euclidean distance between the target feature vector and the standard feature vector as the similarity value.

[0043] Specifically, the standard image information set includes a plurality of standard fogging image information, a plurality of standard snow image information, and a plurality of standard condensation water drop image information. After the image information is transmitted to the preset neural network model, the preset neural network model calculates the similarity between the image information and each standard image information in the standard image information set, for example, obtaining the Euclidean distance between the image information and the standard image information.

[0044] Exemplarily, the image information and each standard image information are first preprocessed, such as image resizing, normalization and data enhancement, and then feature extraction is performed on the preprocessed image information and each standard image information to obtain corresponding feature vectors. For example, feature extraction is performed on the image information to obtain a target feature vector, and feature extraction is performed on each standard image information to obtain a corresponding standard feature vector. Finally, the Euclidean distance between the target feature vector and the standard feature vector is calculated, and the Euclidean distance is the similarity value.

[0045] In some embodiments, the method further includes: acquiring a first image data set and a second image data set; training a preset neural network model using the first image data set; testing the preset neural network model using the second image data set to obtain an accuracy value; and determining that the training of the preset neural network model is completed when the accuracy value exceeds a preset accuracy threshold. The preset accuracy threshold is determined according to actual conditions, for example, the preset accuracy threshold may be 98%, which is not specifically limited here.

[0046] Specifically, when training the preset neural network, it is necessary to obtain the original image data set of the rear windshield, which includes but is not limited to multiple fogging image information, multiple snow image information and multiple condensation water drop image information, and then process each image information in the original image data set, for example, separate the label of the original rear windshield image information from the pixel data, and synthesize the pixel values ​​of each data row into each 48*48 image information, and finally divide the processed original image data set into a first image data set and a second image data set, for example, 80% of the original image data set is used as the first image data set (training set), and 20% of the original image data set is used as the second image data set (test set). Further, the first image data set is used to train the preset neural network model, and then the second image data set is used to test the preset neural network model to obtain an accuracy value, and the accuracy value is compared with the preset accuracy threshold to determine whether the preset neural network model has been trained.

[0047] Exemplarily, if the accuracy value exceeds the preset accuracy threshold, it is determined that the training of the preset neural network model is completed; if the accuracy value does not exceed the preset accuracy threshold, a new round of training is required for the preset neural network model until the accuracy value exceeds the preset accuracy threshold.

[0048] As a specific example, image information of the target rear wind window is obtained in real time through a camera set on the target rear wind window, and then the image information is transmitted to a controller. A preset neural network model built into the controller calculates an image information similarity value based on the image information, determines a control signal based on the image information similarity value, and sends the control signal to an actuator. The actuator controls the heating device of the target rear wind window according to the control signal sent by the controller.

[0049] As another specific example, see Figure 2 The rear windshield heating method based on image recognition in the embodiment of the present application may further include the following steps:

[0050] S201, vehicle starts.

[0051] S202, acquiring image information of the target rear windshield, and transmitting the image information to a preset neural network model to calculate the image information similarity value.

[0052] S203, determine whether the similarity value is greater than a preset similarity value threshold. If yes, execute S204; otherwise, execute S205.

[0053] S204, controlling a heating device of the target rear wind window to heat the target rear wind window.

[0054] S205, controlling the heating device of the target rear wind window to stop heating the target rear wind window.

[0055] As another specific example, refer to Figure 3 The preset neural network model training method of the embodiment of the present application may also include the following steps:

[0056] S301, establishing a first image data set and a second image data set.

[0057] S302: Use the first image data set to train a preset neural network model.

[0058] S303, after one round of training is completed, the second image data set is used for testing and the accuracy value is calculated.

[0059] S304, determine whether the accuracy value is greater than a preset accuracy threshold. If yes, execute S305; otherwise, execute S302.

[0060] S305, determining that the training of the preset neural network model is completed.

[0061] To sum up, the present invention uses a preset neural network to detect image information of the rear windshield, and automatically turns on or off the rear windshield heating according to the image information to remove fog, snow or condensed water droplets on the rear windshield. In this way, the driver's vision can be ensured to a certain extent without being affected, thereby ensuring driving safety and comfort.

[0062] Corresponding to the above-mentioned embodiment, the present application also proposes a rear window heating device based on image recognition.

[0063] In some embodiments, reference Figure 4 The rear windshield heating device 400 based on image recognition includes: an acquisition module 410 , a calculation module 420 , a determination module 430 and a control module 440 .

[0064] Among them, the acquisition module 410 is used to acquire the image information of the target rear windshield. The calculation module 420 is used to transmit the image information to the preset neural network model to calculate the image information similarity value. The determination module 430 is used to determine the control signal according to the image information similarity value. The control module 440 is used to control the heating device of the target rear windshield according to the control signal.

[0065] According to one embodiment of the present invention, the control module 440 is specifically used to control the heating device of the target rear wind window to heat the target rear wind window when the control signal includes a heating control signal to turn on the heating control signal; and to control the heating device of the target rear wind window to stop heating the target rear wind window when the control signal includes a heating control signal to turn off the heating control signal.

[0066] According to one embodiment of the present invention, the determination module 430 is specifically used to determine that the control signal is a heating control signal when the image information similarity value is greater than a preset similarity value threshold; and to determine that the control signal is a heating control signal when the image information similarity value is less than or equal to the preset similarity value threshold.

[0067] According to one embodiment of the present invention, the computing module 420 is specifically used to perform feature extraction on image information to obtain a target feature vector; perform feature extraction on each standard image information in a standard image information set to obtain multiple standard feature vectors, wherein the standard image information set includes multiple standard image information; and determine a similarity value between the image information and each standard image information based on the target feature vector and the standard feature vector.

[0068] According to an embodiment of the present invention, the calculation module 420 is further configured to obtain the Euclidean distance between the target feature vector and the standard feature vector as a similarity value.

[0069] According to one embodiment of the present invention, a first image data set and a second image data set are obtained; a preset neural network model is trained using the first image data set; the preset neural network model is tested using the second image data set to obtain an accuracy value; and when the accuracy value exceeds a preset accuracy threshold, it is determined that the training of the preset neural network model is completed.

[0070] It should be pointed out that the above explanation of the embodiment and beneficial effects of the rear window heating method based on image recognition is also applicable to the rear window heating device based on image recognition in the embodiment of the present invention. To avoid redundancy, it will not be elaborated here.

[0071] Corresponding to the above embodiment, the present application also proposes an electronic device.

[0072] See also Figure 5 As shown, the electronic device 500 of the present application includes a memory 510, a processor 520, and a rear wind window heating program based on image recognition stored in the memory 510 and executable on the processor 520. When the processor executes the rear wind window heating program based on image recognition, the aforementioned rear wind window heating method based on image recognition is implemented.

[0073] It should be pointed out that the above-mentioned explanation of the embodiment and beneficial effects of the rear windshield heating method based on image recognition is also applicable to the electronic device of the embodiment of the present invention, and will not be elaborated here in order to avoid redundancy.

[0074] Corresponding to the above embodiments, the present application also proposes a computer-readable storage medium.

[0075] The computer-readable storage medium of the present application stores a rear windshield heating program based on image recognition, and when the rear windshield heating program based on image recognition is executed by a processor, the aforementioned rear windshield heating method based on image recognition is implemented. It should be noted that the above explanation of the embodiment and beneficial effects of the rear windshield heating method based on image recognition is also applicable to the computer-readable storage medium of the embodiment of the present invention, and will not be elaborated here in detail to avoid redundancy.

[0076] Corresponding to the above embodiments, the present application also proposes a vehicle.

[0077] See also Figure 6 As shown, the vehicle 600 of the present application includes a memory 610, a processor 620, and a rear wind window heating program based on image recognition stored in the memory 610 and executable on the processor 620. When the processor executes the rear wind window heating program based on image recognition, the aforementioned rear wind window heating method based on image recognition is implemented.

[0078] It should be pointed out that the above-mentioned explanation of the embodiment and beneficial effects of the rear windshield heating method based on image recognition is also applicable to the vehicle of the embodiment of the present invention, and will not be elaborated here in detail to avoid redundancy.

[0079] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0080] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0081] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0082] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0083] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0084] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A rear windshield heating method based on image recognition, characterized in that: The method comprises: Obtain image information of the target rear windshield; Transmitting the image information to a preset neural network model to calculate the image information similarity value; Determining a control signal according to the image information similarity value; The heating device of the target rear windshield is controlled according to the control signal.

2. The rear windshield heating method based on image recognition according to claim 1, characterized in that: Controlling the heating device of the target rear windshield according to the control signal includes: When the control signal includes a heating control signal, controlling the heating device of the target rear wind window to heat the target rear wind window; In a case where the control signal includes a heating-off control signal, the heating device of the target rear wind window is controlled to stop heating the target rear wind window.

3. The rear windshield heating method based on image recognition according to claim 1, characterized in that: Determining a control signal according to the image information similarity value includes: In a case where the image information similarity value is greater than a preset similarity value threshold, determining that the control signal is a heating start control signal; When the image information similarity value is less than or equal to a preset similarity value threshold, it is determined that the control signal is a heating off control signal.

4. The rear windshield heating method based on image recognition according to claim 1, characterized in that: The image information is transmitted to a preset neural network model to calculate the image information similarity value, including: Performing feature extraction on the image information to obtain a target feature vector; Extracting features from each standard image information in a standard image information set to obtain a plurality of standard feature vectors, wherein the standard image information set includes a plurality of the standard image information; The similarity value between the image information and each of the standard image information is determined according to the target feature vector and the standard feature vector.

5. The rear windshield heating method based on image recognition according to claim 4, characterized in that: Determining the similarity value between the image information and each of the standard image information according to the target feature vector and the standard feature vector includes: The Euclidean distance between the target feature vector and the standard feature vector is obtained as the similarity value.

6. The rear windshield heating method based on image recognition according to claim 1, characterized in that: The method further comprises: Acquire a first image data set and a second image data set; Using the first image data set to train the preset neural network model; Using the second image data set to test the preset neural network model to obtain an accuracy value; When the accuracy value exceeds a preset accuracy threshold, it is determined that the training of the preset neural network model is completed.

7. A rear windshield heating device based on image recognition, characterized in that: The device comprises: An acquisition module is used to acquire image information of the target rear windshield; A calculation module, used for transmitting the image information to a preset neural network model to calculate the image information similarity value; A determination module, used to determine a control signal according to the image information similarity value; A control module is used to control the heating device of the target rear windshield according to the control signal.

8. An electronic device, characterized in that: It comprises a memory, a processor and a rear wind window heating program based on image recognition which is stored in the memory and can be run on the processor. When the processor executes the rear wind window heating program based on image recognition, the rear wind window heating method based on image recognition according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium, characterized in that: A rear wind window heating program based on image recognition is stored thereon, and when the rear wind window heating program based on image recognition is executed by a processor, a rear wind window heating method based on image recognition according to any one of claims 1-6 is implemented.

10. A vehicle, characterized in that: It comprises a memory, a processor and a rear wind window heating program based on image recognition which is stored in the memory and can be run on the processor. When the processor executes the rear wind window heating program based on image recognition, the rear wind window heating method based on image recognition according to any one of claims 1 to 6 is implemented.

Images