Defogging method, electronic device and storage medium

Abstract

An embodiment of the present invention provides a defogger method, an electronic device, and a storage medium. The defogger method includes: in response to recognizing that a user's hand motion trajectory matches a preset hand motion trajectory, acquiring and analyzing a target image, the target image being an image of a vehicle window and / or windshield; in response to the target image including a first water mist trace, determining whether fog is generated in the vehicle based on the first water mist trace and the hand motion trajectory; and in response to determining that fog is generated in the vehicle, turning on a defogger mode. In an embodiment of the present invention, while the vehicle is driving, if the user wants to turn on the defogger mode, the user can slide on the vehicle window and / or windshield to form a preset hand motion trajectory, and a first water mist trace will appear on the vehicle window and / or windshield. After the processor determines that fog is generated in the vehicle based on the first water mist trace and the hand motion trajectory, the defogger mode can be automatically turned on, without the driver having to manually turn on the defogger. The processing process is simple, and the defogger is more timely.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle control, and in particular to a defogging method, electronic equipment and storage medium. Background Art

[0002] As people's living standards improve, cars are becoming more and more popular and have become an important means of transportation for people.

[0003] While driving, weather conditions often cause a significant difference in temperature and humidity between the inside and outside of the car, causing the windshield to fog up and obstruct the driver's vision. In such cases, the driver is often forced to manually turn on the air conditioner to defog the windshield. However, manually turning on the air conditioner while driving distracts the driver, posing a safety hazard and potentially delaying the operation, which can degrade the user experience. Summary of the Invention

[0004] In view of the above problems, embodiments of the present invention provide a defogging method, an electronic device, and a storage medium to achieve automatic defogging.

[0005] One aspect of an embodiment of the present invention provides a demisting method, the method comprising:

[0006] In response to identifying that the user's hand motion trajectory matches a preset hand motion trajectory, acquiring and analyzing a target image, the target image being an image of a vehicle window and / or windshield;

[0007] In response to the target image including a first water mist trace, determining whether fog is generated in the vehicle according to the first water mist trace and the hand movement trajectory;

[0008] In response to determining that fog is generated in the vehicle interior, a defog mode is activated.

[0009] Another aspect of an embodiment of the present invention provides an electronic device, comprising: one or more processors; and one or more computer-readable storage media having instructions stored thereon; when the instructions are executed by the one or more processors, the processors execute the defogging method as described in any one of the above items.

[0010] In another aspect of the embodiments of the present invention, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the defogging method as described in any one of the above items is implemented.

[0011] In an embodiment of the present invention, in response to recognizing that the user's hand motion trajectory matches a preset hand motion trajectory, a target image is acquired and analyzed, and the target image is an image of a vehicle window and / or windshield; in response to the target image including a first water mist trace, whether fog is generated in the vehicle is determined based on the first water mist trace and the hand motion trajectory; in response to determining that fog is generated in the vehicle, the defogger mode is turned on. It can be seen from this that in an embodiment of the present invention, during the driving of the vehicle, if the defogger mode is desired to be turned on, the user can slide on the vehicle window and / or windshield to form a preset hand motion trajectory, and a first water mist trace appears on the vehicle window and / or windshield. After the processor determines that fog is generated in the vehicle based on the first water mist trace and the hand motion trajectory, the defogger mode can be automatically turned on, without the driver having to manually turn on the defogger, so that the processing process is simple and the defogger is more timely. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0013] Figure 1 This is a schematic diagram of device interaction according to an embodiment of the present invention.

[0014] Figure 2 This is a flow chart of the steps of a demisting method according to an embodiment of the present invention.

[0015] Figure 3 This is a flowchart of another demisting method according to an embodiment of the present invention.

[0016] Figure 4 Schematic diagram of the center line of a water mist trace according to an embodiment of the present invention.

[0017] Figure 5 It is a structural diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the embodiments of the present invention.

[0019] Reference Figure 1 , shows a schematic diagram of device interaction according to an embodiment of the present invention. Figure 1 As shown, a camera is installed on the vehicle, which captures video or images and transmits them to a processor. The processor automatically analyzes the video or images and automatically controls the defogger based on the analysis results.

[0020] Optionally, a camera can be installed inside and / or outside the vehicle, and one or more cameras can be installed. The camera can capture video or images in real time or at a fixed time, and transmit the captured video or images to the processor. The video can be a user video, a video of the vehicle window and / or windshield, and the image can be an image of the user, an image of the vehicle window and / or windshield.

[0021] Optionally, the processor can be a local processor on the intelligent vehicle computer or a cloud processor. If the processor is a local processor on the vehicle computer, the camera transmits the video or image to the local processor on the vehicle computer. If the processor is a cloud processor, the camera transmits the video or image to the vehicle computer, which then transmits the video or image to the cloud processor.

[0022] The defogging method according to the embodiment of the present invention is applied to a processor.

[0023] Reference Figure 2 , shows a step flow chart of a defogging method according to an embodiment of the present invention.

[0024] like Figure 2 As shown, the demisting method may include the following steps:

[0025] Step 201 : In response to identifying that the user's hand motion trajectory matches a preset hand motion trajectory, acquiring and analyzing a target image.

[0026] If the user's hand motion trajectory appears in the video or image captured by the camera, the processor will identify whether the user's hand motion trajectory matches the preset hand motion trajectory after obtaining the user's hand motion trajectory.

[0027] If the user wishes to activate the defogger mode, the user can extend their hand and slide it along the vehicle window and / or windshield in a predetermined hand motion trajectory, thereby forming a user's hand motion trajectory. In this case, the processor will recognize that the user's hand motion trajectory matches the predetermined hand motion trajectory, and then the processor will obtain a target image from the video or image uploaded by the camera and analyze the target image to further determine whether to automatically activate the defogger mode.

[0028] If the user does not want to turn on the defog mode and does not slide according to the preset hand motion trajectory, but instead randomly slides his hand on the car window and / or windshield, thereby forming the user's hand motion trajectory, in this case, the processor will recognize that the user's hand motion trajectory does not match the preset hand motion trajectory, and the processor will temporarily not acquire and analyze the target image.

[0029] The target image is a vehicle window and / or windshield image.

[0030] Optionally, the preset hand motion trajectory may be one or more. The preset hand motion trajectory may be a motion trajectory of any applicable style, such as a straight line, a curve, a letter, and the like.

[0031] Step 202 : In response to the target image including a first water mist trace, determine whether fog is generated in the vehicle based on the first water mist trace and the hand motion trajectory.

[0032] If fog is generated inside the car, after the user slides his hand on the car window and / or windshield, the fog at the position where the user slides will disappear, thereby generating sliding marks on the car window and / or windshield. In the embodiment of the present invention, such sliding marks are called water mist marks.

[0033] Therefore, after acquiring the target image, the processor analyzes whether the target image includes the first water mist trace. If the target image includes the first water mist trace, whether fog has formed inside the vehicle is determined based on the first water mist trace and the hand movement trajectory. If the target image does not include the first water mist trace, there is no need to determine whether fog has formed inside the vehicle.

[0034] Step 203 : In response to determining that fog is generated in the vehicle, a defogger mode is activated.

[0035] In an embodiment of the present invention, if the user wishes to activate defog mode while the vehicle is in motion, they can swipe across the vehicle windows and / or windshield to create a predetermined hand motion trajectory, resulting in the appearance of a first mist trail on the vehicle windows and / or windshield. Upon determining that fog has formed inside the vehicle based on the first mist trail and the hand motion trajectory, the processor can automatically activate defog mode, eliminating the need for the driver to manually activate defog. This simplifies the process and allows for more timely defog operation.

[0036] Reference Figure 3 , shows a step flow chart of another demisting method according to an embodiment of the present invention.

[0037] like Figure 3 As shown, the demisting method may include the following steps:

[0038] Step 301: Acquire the user's hand motion trajectory through image recognition technology.

[0039] Optionally, the camera captures user video and transmits the user video to the processor. After receiving the user video, the processor obtains and analyzes the user video, uses image recognition technology to obtain multiple consecutive images containing a person's hand from the user video, and generates the user's hand movement trajectory based on the multiple consecutive images.

[0040] The processor performs hand detection on each frame of the user's video, so as to detect whether the image contains a human hand.

[0041] Hand detection is the process of detecting the presence of hands in an image and obtaining their positions. Optionally, hand detection can be achieved using HOG (Histogram of Oriented Gradients) + SVM (Support Vector Machine). For any frame of image, the HOG feature vector of the image is first extracted, and then the HOG feature vector is input into the SVM for classification detection, thereby detecting whether the frame of image contains a hand and the position of the hand contained in the image.

[0042] After completing the hand detection, multiple consecutive images containing the human hand are obtained, and the points at the position of the same finger are extracted from each acquired image. The points extracted from the multiple consecutive images are connected in sequence to obtain the user's hand movement trajectory.

[0043] Step 302 : In response to identifying that the user's hand motion trajectory matches a preset hand motion trajectory, acquiring and analyzing a target image.

[0044] After the processor obtains the user's hand motion trajectory, it matches the user's hand motion trajectory with a preset hand motion trajectory.

[0045] After obtaining the user's hand motion trajectory, the processor can also obtain the coordinates of each point included in the hand motion trajectory. Furthermore, given the coordinates of multiple points included in the preset hand motion trajectory, the processor can match the user's hand motion trajectory with the preset hand motion trajectory in the following manner. The following uses the user's hand motion trajectory and a preset hand motion trajectory as an example for illustration.

[0046] In an optional embodiment, the processor can draw the user's hand motion trajectory and the preset hand motion trajectory into the same coordinate system, and make the starting point of the user's hand motion trajectory and the starting point of the preset hand motion trajectory located at the same coordinate. The processor calculates the minimum distance between each point included in the user's hand motion trajectory and the points included in the preset hand motion trajectory, and obtains the minimum distance corresponding to each point included in the user's hand motion trajectory. If the number of points whose corresponding minimum distance is less than the preset distance exceeds a preset ratio, it can be determined that the user's hand motion trajectory matches the preset hand motion trajectory. For the preset distance and the preset ratio, any applicable numerical value can be set based on actual experience, and the embodiment of the present invention does not impose any restrictions on this.

[0047] In another optional embodiment, the processor may separately generate an image containing the user's hand motion trajectory and an image containing a preset hand motion trajectory, and position the starting point of the user's hand motion trajectory and the starting point of the preset hand motion trajectory at the same pixel. The processor calculates the similarity between the image containing the user's hand motion trajectory and the image containing the preset hand motion trajectory. If the similarity is greater than a preset similarity, it can be determined that the user's hand motion trajectory matches the preset hand motion trajectory. The preset similarity can be set to any applicable value based on actual experience, and this embodiment of the present invention does not impose any limitation on this.

[0048] Alternatively, image pairs can be acquired in advance and labeled with their actual similarities. A neural network model can then be trained using the image pairs and the labels as sample data. The neural network model takes the image pairs as input and outputs the predicted similarities of the image pairs. Thus, the neural network model can be used to calculate the similarity between an image containing the user's hand motion trajectory and an image containing a preset hand motion trajectory.

[0049] In response to identifying that the user's hand motion trajectory matches a preset hand motion trajectory, the processor acquires and analyzes a target image, wherein the target image is an image of the vehicle window and / or windshield uploaded by the camera.

[0050] Alternatively, similar to the above-mentioned hand detection, the processor can implement water mist trace detection using a HOG+SVM approach. For any image frame, the HOG feature vector of the image is first extracted, and then the HOG feature vector is input into an SVM for classification detection, thereby detecting whether the image contains the first water mist trace and the location of the first water mist trace in the image.

[0051] Step 303 : In response to the target image including a first water mist trace, determine whether fog is generated in the vehicle based on the first water mist trace and the hand motion trajectory.

[0052] After detecting that the target image includes the first water mist trace, the processor matches the first water mist trace with the hand movement trajectory to determine whether fog is generated in the car.

[0053] Optionally, considering that the user's hand motion trajectory is a trajectory consisting of multiple points and the first water mist trace is a graphic covering a certain area, the following steps A1 to A3 can be used to determine whether fog is generated in the vehicle based on the first water mist trace and the hand motion trajectory:

[0054] A1. Obtain a center line of the first water mist trace, and use the center line as a trajectory corresponding to the first water mist trace.

[0055] If fog is generated inside the vehicle, a sliding pattern covering a certain area will be generated as a first water mist trace after sliding the window and / or windshield. In order to match the first water mist trace with the hand motion trajectory, the first water mist trace can be first converted into a corresponding trajectory.

[0056] Optionally, considering that the center line of the first water mist trace can represent the trajectory change of the first water mist trace, the center line of the first water mist trace can be obtained and used as the trajectory corresponding to the first water mist trace.

[0057] In practice, the first water mist trace can be divided into multiple sub-graphs at a certain granularity, the center point of each sub-graph can be obtained, and then the center points of the sub-graphs can be connected in sequence, and the resulting line can be used as the center line of the first water mist trace. At the same time, the coordinates of each point on the center line (i.e., the aforementioned center point) can also be obtained.

[0058] Figure 4 Schematic diagram of the center line of a water mist trace according to an embodiment of the present invention. Figure 4 As shown, the first water mist trace is a figure similar to a "V" shape. Figure 4 The center line of the first water mist trace is obtained by the above method, which is Figure 4 The dotted line in the “V” shape is the center line of the trajectory corresponding to the first water mist trace.

[0059] A2: Determine whether the trajectory corresponding to the first water mist mark matches the hand movement trajectory.

[0060] After obtaining the user's hand motion trajectory, the processor can obtain the coordinates of each point included in the hand motion trajectory. After obtaining the trajectory corresponding to the first water mist trace, the processor can obtain the coordinates of each point included in the trajectory corresponding to the first water mist trace. Based on this, the processor can match the trajectory corresponding to the first water mist trace with the hand motion trajectory in the following manner.

[0061] In an optional embodiment, the processor may plot the user's hand motion trajectory and the trajectory corresponding to the first water mist trace within the same coordinate system, with the starting point of the user's hand motion trajectory and the starting point of the trajectory corresponding to the first water mist trace located at the same coordinate system. The processor calculates, for each point in the user's hand motion trajectory, the minimum distance between that point and the points in the trajectory corresponding to the first water mist trace, thereby obtaining the minimum distance corresponding to each point in the user's hand motion trajectory. If more than a preset proportion of points have a corresponding minimum distance less than a preset distance, then it can be determined that the user's hand motion trajectory matches the trajectory corresponding to the first water mist trace.

[0062] In another optional embodiment, the processor can separately generate an image containing the user's hand motion trajectory and an image containing the trajectory corresponding to the first water mist mark, and position the starting point of the user's hand motion trajectory and the starting point of the trajectory corresponding to the first water mist mark at the same pixel. The processor calculates the similarity between the image containing the user's hand motion trajectory and the image containing the trajectory corresponding to the first water mist mark. If the similarity is greater than a preset similarity, it can be determined that the user's hand motion trajectory matches the trajectory corresponding to the first water mist mark. Optionally, the aforementioned neural network model can be used to calculate the similarity between the image containing the user's hand motion trajectory and the image containing the trajectory corresponding to the first water mist mark.

[0063] A3: If the trajectory corresponding to the first water mist mark matches the hand movement trajectory, it is determined that fog has formed in the vehicle. If the trajectory corresponding to the first water mist mark does not match the hand movement trajectory, it is determined that no fog has formed in the vehicle.

[0064] Step 304 , in response to determining that fog is generated in the vehicle, turning on the defogger mode.

[0065] After determining that fog is generated in the vehicle, the processor turns on the defogging mode in response to determining that fog is generated in the vehicle. In implementation, the processor may send an instruction to turn on the defogging mode to the air conditioner in the vehicle so as to control the air conditioner to turn on the defogging mode.

[0066] Considering that, generally, the thicker the fog inside the vehicle, the clearer the edge of the first mist trail created by the user's sliding movement will be, i.e., the edge clarity of the first mist trail will be higher, the edge clarity of the first mist trail can therefore represent the thickness of the fog. Different defogger intensities can be used for defoggering fog of different thicknesses. Therefore, in an optional embodiment, the processor can obtain the edge clarity of the first mist trail, determine the defogger intensity based on the edge clarity, and activate the defogger mode according to the defogger intensity. The defogger intensity is positively correlated with the edge clarity.

[0067] Considering that, generally, a stronger edge strength of the first water mist mark indicates a higher edge definition of the first water mist mark, the edge strength of the first water mist mark can represent the edge definition of the first water mist mark. Therefore, in an alternative embodiment, the edge definition of the first water mist mark can be obtained by: identifying the first water mist mark from the target image, obtaining the edge strength of the first water mist mark, and then obtaining the edge definition of the first water mist mark based on the edge strength. The edge strength is positively correlated with the edge definition.

[0068] Edges are a fundamental feature of images. An edge is a collection of pixels whose surrounding pixels experience a step-change in grayscale. It exists between the target and the background and, therefore, is the most important feature for image segmentation. Classic edge extraction is based on the original image. For each pixel in the image, the grayscale variations within a certain area are examined, and edges are detected using the variation patterns of the first- or second-order directional derivatives of the edge's neighborhood. An edge point is one where the grayscale values ​​of the pixels on either side of it differ significantly. An edge point exists between a pair of adjacent points: one within a brighter area and the other outside.

[0069] Edge strength is essentially the amplitude of the gradient at an edge point. Optionally, for each pixel of the first water mist trace, the first-order difference of the pixel in the x and y directions is calculated. The gradient value of the pixel is calculated based on the first-order difference in the x and y directions. If the gradient value is greater than a preset threshold, the pixel is considered an edge point. The gradient value of the edge point is used as the edge strength of the edge point. The average edge strength of each edge point is calculated, and the average value is used as the edge strength of the first water mist trace.

[0070] Step 305: Determine whether the first water mist trace is eliminated.

[0071] Step 306: In response to determining that the first water mist trace has been eliminated for a preset time period, turning off the defog mode.

[0072] After defogging mode is activated, the fog inside the vehicle gradually dissipates. Once the fog inside the vehicle is dissipated, the first mist trace on the window and / or windshield image uploaded by the camera will also be removed. Therefore, the processor continuously analyzes the window and / or windshield image, detects the mist trace on the image, and determines whether the first mist trace has been removed. Similarly, the processor can use the HOG+SVM method to detect the mist trace.

[0073] After determining that the first water mist trace has been eliminated, the processor records the duration of the elimination of the first water mist trace and, in response to determining that the first water mist trace has been eliminated for a preset time period, turns off the defog mode. In implementation, the processor may send a command to the air conditioner in the vehicle to turn off the defog mode, thereby controlling the air conditioner to turn off the defog mode, thereby achieving energy conservation.

[0074] Step 307 : Acquire and analyze an image, and in response to the image including a second water mist trace, determine whether the second water mist trace matches the first water mist trace.

[0075] Because human hands are greasy, if mist reappears after the defogger mode has been turned off for a period of time, a second mist trace will regenerate in the location of the original first mist trace. Therefore, the processor can continue to acquire images uploaded by the camera and analyze whether the images contain the second mist trace. Similarly, the processor can use the HOG+SVM method to analyze whether the images contain the second mist trace.

[0076] After detecting that the image includes the second water mist mark, the processor matches the second water mist mark with the first water mist mark. Optionally, for the image including the first water mist mark and the image including the second water mist mark, the aforementioned neural network model can be used to calculate a similarity between the image including the first water mist mark and the image including the second water mist mark. If the similarity is greater than a preset similarity, it can be determined that the first water mist mark and the second water mist mark match.

[0077] Step 308: In response to determining that the second water mist trace matches the first water mist trace, turning on the defogger mode.

[0078] After the processor determines that the second water mist trace matches the first water mist trace, it can be determined that fog has been generated in the car again, so the defogger mode can be turned on again.

[0079] In an optional embodiment, the processor may further obtain the time interval between the two activations of the defog mode and the duration of the first of the two activations of the defog mode, and activate the defog mode according to the time interval and the duration. For example, if the time interval between the two activations of the defog mode is 30 minutes, and the duration of the first defogging mode is 10 minutes, the processor will activate the defog mode every 30 minutes, and the duration of each defogging mode is 10 minutes.

[0080] In an optional embodiment, the user can also choose to actively turn off the defog mode.

[0081] Optionally, the user may slide his hand on the vehicle window and / or windshield at will instead of sliding according to the preset hand motion trajectory. The camera captures the user video and transmits the user video to the processor. After receiving the user video, the processor obtains and analyzes the user video, uses image recognition technology to obtain multiple consecutive images containing human hands from the user video, and generates the user's hand motion trajectory based on the multiple consecutive images. After the processor obtains the user's hand motion trajectory, it matches the user's hand motion trajectory with the preset hand motion trajectory. In response to recognizing that the user's hand motion trajectory does not match the preset hand motion trajectory, the processor turns off the defogger mode.

[0082] Optionally, the user can slide his hands on the car windows and / or windshield according to a preset hand motion trajectory. The camera captures the user video and transmits the user video to the processor. After receiving the user video, the processor obtains and analyzes the user video, uses image recognition technology to obtain multiple consecutive images containing human hands from the user video, and generates the user's hand motion trajectory based on the multiple consecutive images. After obtaining the user's hand motion trajectory, the processor matches the user's hand motion trajectory with the preset hand motion trajectory. In response to recognizing that the user's hand motion trajectory matches the preset hand motion trajectory, the processor obtains and analyzes the image and detects water mist traces on the image. After detecting that the image does not include water mist traces, the processor can turn off the defogger mode.

[0083] In the embodiments of the present invention, on the one hand, the life phenomenon of water mist traces produced by hands sliding on water mist is cleverly utilized, and image recognition and gesture recognition technology are combined to reduce the dependence on the accuracy of gesture recognition. By obtaining the hand movement trajectory and then performing image matching, the fog situation in the car can be accurately recognized and judged, and it is relatively feasible for the driver to touch any area of ​​the windshield or window while driving. When the windshield or window is foggy, reaching out to touch it is in line with people's primitive impulses and conforms to user psychology; on the other hand, the life phenomenon of water mist traces produced by hands sliding on water mist is cleverly utilized. When the traces are eliminated, water mist traces will be produced again, and the continuous monitoring capability of water mist traces is obtained, realizing an intelligent energy-saving mode; on the other hand, the estimation of water mist thickness is obtained by analyzing the edge strength of water mist traces, so as to intelligently select the defogger intensity.

[0084] In an embodiment of the present invention, an electronic device is also provided. The electronic device may include one or more processors and one or more computer-readable storage media storing instructions, such as application programs. When the instructions are executed by the one or more processors, the processors perform the defogging method of any of the above-described embodiments.

[0085] Figure 5FIG. 5 shows a schematic structural diagram of an electronic device 500 according to an embodiment of the present invention. Figure 5 As shown, the electronic device 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes according to computer program instructions stored in a read-only memory (ROM) 502 or computer program instructions loaded from a storage unit 508 into a random access memory (RAM) 503. Various programs and data required for the operation of the electronic device 500 can also be stored in the RAM 503. The CPU 501, ROM 502, and RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0086] Multiple components in the electronic device 500 are connected to the I / O interface 505, including an input unit 506, such as a keyboard, a mouse, a microphone, etc.; an output unit 507, such as various types of displays, speakers, etc.; a storage unit 508, such as a magnetic disk, an optical disk, etc.; and a communication unit 509, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 509 allows the electronic device 500 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0087] The various processes and processing described above may be executed by the processing unit 501. For example, the method of any of the above embodiments may be implemented as a computer software program, which is tangibly contained in a computer-readable medium, such as the storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the CPU 501, one or more actions in the method described above may be performed.

[0088] In an embodiment of the present invention, a non-transitory computer-readable storage medium is further provided, on which a computer program is stored. The program can be executed by a processor of an electronic device to perform the defogging method of any of the above embodiments. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0089] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0090] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, apparatus, or computer program products. Thus, embodiments of the present invention may take the form of a fully hardware embodiment, a fully software embodiment, or an embodiment combining software and hardware. Furthermore, embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0091] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the process in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0092] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0093] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0094] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they become aware of the basic creative concepts. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0095] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or terminal device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or terminal device that includes the element.

[0096] The above is a detailed introduction to the electronic device and storage medium for the defogging method provided by the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A demisting method, characterized in that: The method comprises: In response to identifying that the user's hand motion trajectory matches a preset hand motion trajectory, acquiring and analyzing a target image, the target image being an image of a vehicle window and / or windshield; In response to the target image including a first water mist trace, determining whether fog is generated in the vehicle according to the first water mist trace and the hand movement trajectory; In response to determining that fog is generated in the vehicle, turning on a defogger mode; The determining whether fog is generated in the vehicle according to the first water mist trace and the hand movement trajectory includes: Obtaining a center line of the first water mist trace, and using the center line as a trajectory corresponding to the first water mist trace; determining whether the trajectory corresponding to the first water mist mark matches the hand movement trajectory; If the trajectory corresponding to the first water mist mark matches the hand movement trajectory, it is determined that fog is generated in the vehicle.

2. The method according to claim 1, wherein the user's hand movement trajectory is obtained through image recognition technology.

3. The method according to claim 2, wherein identifying the user's hand movement trajectory by image recognition technology comprises: Acquire and analyze user videos, and use image recognition technology to acquire multiple consecutive images containing human hands from the user videos; Based on the multiple consecutive images, a user's hand movement trajectory is generated.

4. The method according to claim 1, wherein the step of starting the defog mode comprises: Obtaining edge clarity of the first water mist trace; Determining a defogging intensity based on the edge definition; wherein the defogging intensity is positively correlated with the edge definition; Turn on the defog mode according to the defog intensity.

5. According to the method of claim 4, obtaining the edge clarity of the first water mist trace includes the following steps: identifying the first water mist trace from the target image, obtaining the edge strength of the first water mist trace, and obtaining the edge clarity of the first water mist trace based on the edge strength.

6. The method according to claim 1, after turning on the defogging mode, further comprising: determining whether the first water mist trace is eliminated; In response to determining that the first water mist trace has been eliminated for a preset time period, the defog mode is turned off.

7. The method according to claim 6, after turning off the defogging mode, further comprising: acquiring and analyzing an image, and in response to the image including a second water mist trace, determining whether the second water mist trace matches the first water mist trace; In response to determining that the second water mist trace matches the first water mist trace, the demisting mode is turned on.

8. An electronic device, characterized in that: include: one or more processors; and one or more computer-readable storage media having instructions stored thereon; When the instructions are executed by the one or more processors, the processors are enabled to perform the defogging method according to any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that A computer program is stored thereon, and when the program is executed by a processor, the defogging method according to any one of claims 1 to 7 is implemented.

Images