Image detection method and device, readable storage medium and vehicle

Abstract

The present disclosure relates to an image detection method, device, readable storage medium and vehicle. The method comprises: acquiring a to-be-detected image; determining related information of a target image in the to-be-detected image, wherein the target image is an image capable of being projected onto a windshield of a vehicle by a projection device for display; and determining whether the to-be-detected image is an abnormal image according to the related information of the target image. In this way, the reliability of the detection of the to-be-detected image is improved. Furthermore, according to the detection result of the to-be-detected image, it is determined whether to project the image onto the windshield of the vehicle for display, so that it can be ensured that the image projected on the windshield of the vehicle does not affect the driving of the driver, thereby improving the driving safety.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of vehicles, in particular to an image detection method and device, readable storage medium and vehicle. BACKGROUND

[0002] A head-up display (HUD) is a display device that projects an image into the field of view of the driver in front, which mainly uses the principle of optical reflection to project and display vehicle driving related information (such as vehicle speed, navigation route, remaining fuel quantity, etc.) in the form of a two-dimensional image on the windshield of the vehicle. When the driver looks forward through the windshield, a virtual image can be seen on the windshield.

[0003] Compared with the traditional vehicle driver who needs to look down to check the instrument panel and the central control screen, the driver does not need to look down when checking the vehicle driving related information, avoiding the driver's line of sight switching back and forth between the image and the road surface, reducing the crisis reaction time and improving the driving safety. SUMMARY

[0004] The purpose of the present disclosure is to provide an image detection method, device, readable storage medium and vehicle to improve driving safety.

[0005] To achieve the above purpose, the first aspect of the present disclosure provides an image detection method, comprising:

[0006] obtaining a to-be-detected image;

[0007] determining related information of a target image in the to-be-detected image, wherein the target image is an image that can be projected and displayed on the windshield of the vehicle by a projection device;

[0008] determining whether the to-be-detected image is an abnormal image according to the related information of the target image.

[0009] Optionally, the related information of the target image comprises at least one of the following:

[0010] a first proportion of the target image in a non-drawing area of the to-be-detected image, a second proportion of the target image in the to-be-detected image, and a matching result of each sub-image in the target image and interface design template information corresponding to the sub-image.

[0011] Optionally, the target image is an image composed of non-black pixel points.

[0012] In the case where the related information comprises the first proportion, the determining of the related information of the target image in the to-be-detected image comprises:

[0013] selecting M first pixel points in a non-drawing area of the image to be detected, wherein the M first pixel points are uniformly distributed;

[0014] If there is a non-black pixel point in the M first pixel points, determining a first proportion P1 of the target image in the non-drawing area of the image to be detected.

[0015] Optionally, in the case that there is no non-black pixel point in the M first pixel points, the related information further comprises the second proportion, the determination of the related information of the target image in the image to be detected further comprises:

[0016] selecting N second pixel points in a drawing area of the image to be detected, wherein the N second pixel points are uniformly distributed;

[0017] determining the number n of non-black pixel points in the N second pixel points;

[0018] determining a second proportion P2 of the target image in the image to be detected by the following formula: P2 = n / (M+N)*100%.

[0019] Optionally, in the case that the related information comprises the matching result of each sub-image in the target image and the interface design template information corresponding to the sub-image, the determination of the related information of the target image in the image to be detected comprises:

[0020] segmenting the image to be detected according to user interface layout information of the projection device to obtain a plurality of sub-images;

[0021] obtaining interface design template information corresponding to each of the plurality of sub-images;

[0022] for each sub-image, determining a matching result of the sub-image and the interface design template information corresponding to the sub-image according to the sub-image and the interface design template information corresponding to the sub-image.

[0023] Optionally, the obtaining of the interface design template information corresponding to each of the plurality of sub-images comprises:

[0024] obtaining a plurality of interface design template libraries of a plurality of display areas in a user interface of the projection device, wherein each of the interface design template libraries comprises a plurality of interface design template information;

[0025] for each sub-image, determining an interface design template library of a display area corresponding to the sub-image, and determining the plurality of interface design template information included in the interface design template library as the interface design template information corresponding to the sub-image;

[0026] The interface design template library of the display area is generated in the following manner:

[0027] According to the user interface layout information of the projection device, the user interface of the projection device is segmented to obtain a plurality of display areas;

[0028] For each display area, a plurality of interface design templates corresponding to the display area are determined, a hash algorithm is used to respectively generate hash values corresponding to the plurality of interface design templates, and the interface design template library of the display area is generated according to the hash values corresponding to the plurality of interface design templates.

[0029] Optionally, in the case where the related information includes the second proportion and the matching result of each sub-image in the target image and the interface design template information corresponding to the sub-image, the determining, according to the related information of the target image, whether the to-be-detected image is an abnormal image, includes:

[0030] When the second proportion and the matching result of the sub-image and the interface design template information corresponding to the sub-image do not satisfy a preset qualified condition, it is determined that the to-be-detected image is an abnormal image.

[0031] The preset qualified condition includes that the second proportion is less than or equal to a preset value, and the matching result of each sub-image and the interface design template information corresponding to the sub-image is a first result, wherein the first result indicates that there is an interface design template matching the sub-image in the display area.

[0032] The second aspect of the present disclosure provides an image detection device, comprising:

[0033] A first acquisition module is configured to acquire a to-be-detected image.

[0034] A first determination module is configured to determine related information of a target image in the to-be-detected image, wherein the target image is an image that can be projected onto a vehicle windshield by a projection device for display.

[0035] A second determination module is configured to determine whether the to-be-detected image is an abnormal image according to the related information of the target image.

[0036] Optionally, the related information of the target image includes at least one of the following:

[0037] The first proportion of the target image in a non-drawing area of the to-be-detected image, the second proportion of the target image in the to-be-detected image, and the matching result of each sub-image in the target image and the interface design template information corresponding to the sub-image.

[0038] Optionally, the target image is an image composed of non-black pixel points.

[0039] In a case where the related information includes the first proportion, the first determining module includes:

[0040] A first selecting submodule is configured to select M first pixel points in a non-drawing area of the to-be-detected image, wherein the M first pixel points are uniformly distributed.

[0041] A first determining submodule is configured to determine a first proportion P1 of the target image in the non-drawing area of the to-be-detected image if there is a non-black pixel point in the M first pixel points.

[0042] Optionally, in a case where there is no non-black pixel point in the M first pixel points and the related information further includes the second proportion, the first determining module further includes:

[0043] A second selecting submodule is configured to select N second pixel points in a drawing area of the to-be-detected image, wherein the N second pixel points are uniformly distributed.

[0044] A second determining submodule is configured to determine a number n of non-black pixel points in the N second pixel points.

[0045] A third determining submodule is configured to determine a second proportion P2 of the target image in the to-be-detected image by using the following formula: P2 = n / (M+N)*100%.

[0046] Optionally, in a case where the related information includes a matching result of each sub-image in the target image and interface design template information corresponding to the sub-image, the first determining module includes:

[0047] A segmenting submodule is configured to segment the to-be-detected image according to user interface layout information of a projection device to obtain a plurality of sub-images.

[0048] An obtaining submodule is configured to obtain interface design template information corresponding to each of the plurality of sub-images.

[0049] A sixth determining submodule is configured to, for each sub-image, determine, according to the sub-image and the interface design template information corresponding to the sub-image, a matching result of the sub-image and the interface design template information corresponding to the sub-image.

[0050] Optionally, the obtaining submodule is configured to:

[0051] obtain a plurality of interface design template libraries of a plurality of display areas in a user interface of a projection device, wherein each of the interface design template libraries includes a plurality of interface design template information.

[0052] For each sub-image, a display area interface design template library corresponding to the sub-image is determined, and a plurality of interface design template information included in the display area interface design template library is determined as the interface design template information corresponding to the sub-image.

[0053] The display area interface design template library is generated by the following method:

[0054] According to the user interface layout information of the projection device, the user interface of the projection device is segmented to obtain a plurality of display areas.

[0055] For each display area, a plurality of interface design templates corresponding to the display area are determined, a hash algorithm is used to respectively generate hash values corresponding to the plurality of interface design templates, and a display area interface design template library is generated according to the hash values corresponding to the plurality of interface design templates.

[0056] Optionally, in the case where the related information includes the second proportion and the matching result of each sub-image in the target image and the interface design template information corresponding to the sub-image, the second determination module includes:

[0057] A seventh determination sub-module is configured to determine the to-be-detected image as an abnormal image when the second proportion and the matching result of the sub-image and the interface design template information corresponding to the sub-image do not satisfy a preset qualified condition.

[0058] The preset qualified condition includes that the second proportion is less than or equal to a preset value, and the matching result of each sub-image and the interface design template information corresponding to the sub-image is a first result, wherein the first result indicates that there is an interface design template matching the sub-image in the display area.

[0059] The third aspect of the present disclosure provides a non-transitory computer readable storage medium having a computer program stored thereon, wherein the program is executed by a processor to implement the steps of the method of the first aspect of the present disclosure.

[0060] The fourth aspect of the present disclosure provides a vehicle, comprising:

[0061] A projection device is configured to project the to-be-detected image onto the windshield of the vehicle.

[0062] A memory having a computer program stored thereon.

[0063] A processor is configured to execute the computer program in the memory to implement the steps of the method of the first aspect of the present disclosure.

[0064] According to the technical scheme, the related information of the target image in the to-be-detected image is determined, the target image is an image capable of being projected onto the windshield of the vehicle by the projection device for display, whether the to-be-detected image is an abnormal image is determined according to the related information of the target image, and thus, whether the to-be-detected image is an abnormal image is determined according to the related information of the image capable of being projected onto the windshield of the vehicle by the projection device for display, and the reliability of detection of the to-be-detected image is improved. Moreover, whether the image is projected onto the windshield of the vehicle for display is determined according to the detection result of the to-be-detected image, and it can be ensured that the image projected on the windshield of the vehicle does not affect the driving of the driver, and thus the driving safety is improved.

[0065] Other features and advantages of the present disclosure will be described in detail in the following detailed description section. BRIEF DESCRIPTION OF DRAWINGS

[0066] The accompanying drawings are included to provide a further understanding of the present disclosure and constitute a part of the specification, and are used together with the following detailed description to explain the present disclosure, but do not constitute a limitation of the present disclosure. In the drawings:

[0067] Figure 1 is a flowchart of an image detection method according to an exemplary embodiment.

[0068] Figure 2 is a schematic diagram of a to-be-detected image according to an exemplary embodiment.

[0069] Figure 3 is a flowchart of a method for determining related information of a target image in a to-be-detected image according to an exemplary embodiment.

[0070] Figure 4 is a schematic diagram of a to-be-detected image according to an exemplary embodiment.

[0071] Figure 5 is a schematic diagram of a user interface according to an exemplary embodiment.

[0072] Figure 6 is a block diagram of an image detection device according to an exemplary embodiment.

[0073] Figure 7 is a block diagram of a vehicle according to an exemplary embodiment.

[0074] Figure 8 is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0075] The specific embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit this disclosure.

[0076] It should be noted that all actions involving the acquisition of signals, information, or data (e.g., images to be detected, interface design template information, interface design template libraries, etc.) in this disclosure are carried out in compliance with the relevant data protection laws and regulations of the country where the device is located, and with the authorization granted by the owner of the relevant device.

[0077] As mentioned in the background section, projecting vehicle-related information onto the windshield using projection equipment can effectively prevent traffic accidents caused by drivers frequently looking down at the dashboard and center console screen. However, the vehicle-related information displayed on the windshield may, to some extent, obstruct the driver's view of the road ahead. In other words, if the area displaying this information is large, the driver may not be able to clearly see the road ahead. Alternatively, if the content actually displayed in a certain area of ​​the windshield does not match the interface layout, the driver may see incorrect information, leading to a traffic accident. Therefore, if the image projected onto the windshield is abnormal, it will affect the driver's safe driving.

[0078] In view of this, the present disclosure provides an image detection method, apparatus, readable storage medium, and vehicle to ensure that the image projected on the vehicle windshield does not affect the driver's driving, thereby improving driving safety.

[0079] Figure 1 This is a flowchart illustrating an image detection method according to an exemplary embodiment. This method can be applied to electronic devices with processing capabilities, such as in-vehicle processors or controllers, or it can also be applied to servers that remotely communicate with vehicles. Figure 1 As shown, the method may include the following steps.

[0080] In step S11, the image to be detected is acquired.

[0081] First, it should be understood that the image can be detected before it is projected onto the vehicle's windshield, after it is projected onto the windshield, or at the same time as it is projected onto the windshield. This disclosure does not specifically limit the detection in any particular way.

[0082] In the present disclosure, the image to be detected can be an image output by a projection device, which can be a head-up display (HUD), an augmented reality head-up display (AR-HUD), a combiner head-up display (C-HUD), a windshield head-up display (W-HUD), or the like, and the present disclosure does not make specific limitations thereon.

[0083] In a possible embodiment, the specific implementation of obtaining the image to be detected is as follows: obtaining the image to be detected from the projection device in the case where the projection device does not have an abnormality.

[0084] In this embodiment, the projection device outputting the image to be detected is monitored before the image to be detected is obtained, to determine whether the projection device has an abnormality, and in the case where the projection device does not have an abnormality, the image to be detected is obtained from the projection device in response to receiving an image detection request input by a user. For example, in the case where the projection device does not have an abnormality, the image to be detected can be obtained from the projection device by using a shared memory or a data encoding transmission technology, or the like.

[0085] In this embodiment, considering that the image output by the projection device is usually abnormal when the projection device has an abnormality, in order to avoid the invalid workload caused by detecting the abnormal image output by the abnormal projection device, the image to be detected output by the abnormal projection device can be directly determined as an abnormal image in this embodiment, so that the detection workload is effectively reduced. In addition, by monitoring whether the projection device has an abnormality, the image to be detected output by the projection device can be quickly identified as an abnormal image in the case where the projection device has an abnormality. The abnormality of the projection device can include that the projection device does not output the image to be detected at a preset frequency, or that the communication function of the projection device is abnormal, or the like.

[0086] In addition, in the case where the projection device has an abnormality, at least one of the following operations can be performed: controlling the self-checking system to perform self-checking on the projection device, restarting the projection device, outputting abnormal prompt information, or the like.

[0087] In step S12, related information of a target image in the image to be detected is determined. The target image is an image that can be projected onto the windshield of the vehicle by the projection device for display.

[0088] In step S13, whether the image to be detected is an abnormal image is determined according to the related information of the target image.

[0089] By adopting the technical scheme, the related information of the target image in the to-be-detected image is determined, the target image is an image capable of being projected onto the vehicle windshield by the projection device for display, and whether the to-be-detected image is an abnormal image is determined according to the related information of the target image. In this way, according to the related information of the image capable of being projected onto the vehicle windshield by the projection device for display, whether the to-be-detected image is an abnormal image is determined, and the reliability of detection of the to-be-detected image is improved. Moreover, whether the image is projected onto the vehicle windshield for display is determined according to the detection result of the to-be-detected image, so that it can be ensured that the image projected on the vehicle windshield does not affect the driving of the driver, and the driving safety is further improved.

[0090] In order to enable a person skilled in the art to better understand the image detection method provided by the present disclosure, the image detection method is described in detail below with one complete embodiment.

[0091] In the present disclosure, the related information of the target image refers to related information capable of representing that the target image will interfere with the safe driving of the driver when the target image is projected onto the vehicle windshield for display. In actual application, it is considered that when the area of the vehicle driving related information displayed on the windshield is large, or when the actual display content in a certain area of the windshield is inconsistent with the interface layout information, a traffic accident may occur. Therefore, the related information of the target image in step S12 can include at least one of the following: a first proportion of the target image in the non-drawing area of the to-be-detected image, a second proportion of the target image in the to-be-detected image, and a matching result of each sub-image in the target image and the interface design template information corresponding to the sub-image.

[0092] It should be understood that the principle of the heads-up display (HUD) projection is that the light emitting device projects an image, and a black image (an image composed of black pixels) is not light-emitting in the HUD light emitting device, that is, it is not projected, so the black image cannot be projected onto the windshield in the HUD, and therefore the black color can be considered as a safe color, and non-black color is a non-safe color affecting the safe driving of the driver. Therefore, in the present disclosure, the target image can be an image composed of non-black pixels.

[0093] For example, in the first embodiment, the related information of the target image includes a first proportion of the target image in the non-drawing region of the to-be-detected image. It should be understood that the user interface layout information of the projection device can be defined in the design stage of the projection device, and the user interface layout information includes a region pre-defined for displaying the vehicle driving related information, and each display region in the region corresponds to the vehicle driving related information displayed, and the like. Therefore, the user interface can be divided into a drawing region and a non-drawing region according to the user interface layout information of the projection device. The drawing region is a region in the user interface for displaying the vehicle driving related information, and the non-drawing region is a region in the user interface without displaying the vehicle driving related information, that is, normally, the target image is displayed in the drawing region, and the target image does not appear in the non-drawing region.

[0094] In theory, when the image is not abnormal, there is no non-black pixel point in the non-drawing region, and therefore, in this embodiment, whether the to-be-detected image is abnormal can be determined according to whether there is a non-black pixel point in the non-drawing region. For example, the specific implementation of the step S12 can be that M first pixel points are selected in the non-drawing region of the to-be-detected image, and the M first pixel points are uniformly distributed; if there is a non-black pixel point in the M first pixel points, it is determined that the first proportion P1 of the target image in the non-drawing region of the to-be-detected image is determined.

[0095] In the present disclosure, in order to ensure that the M first pixel points selected can reflect the distribution of the pixel points in the non-drawing region of the to-be-detected image, the M first pixel points are uniformly distributed in the non-drawing region of the to-be-detected image.

[0096] The ratio of the number of non-black pixel points in the M first pixel points to M is taken as the first proportion P1, and when the first proportion P1 is not 0, it indicates that there is a non-black pixel point in the non-drawing region, and when the first proportion P1 is 0, it indicates that there is no non-black pixel point in the non-drawing region. That is, when the first proportion P1 is not 0, it is determined that the to-be-detected image is an abnormal image, so that the rapid inspection of the to-be-detected image can be realized, and the image abnormality can be fed back.

[0097] For example, Figure 2 is a schematic diagram of a to-be-detected image according to an example embodiment. As Figure 2 shown, the vehicle driving related information can include an icon indicating whether there is a camera on the current road, a current speed limit value, an icon indicating whether to wear a seat belt, a navigation path, an adaptive cruise icon, a remaining distance of the route, and a predicted driving time. In Figure 2 , the rectangular points in the to-be-detected image represent the M first pixel points selected.

[0098] After the first pixel points are selected, color information of each first pixel point is sampled, and it is determined whether there is a pixel point with non-black color in the first pixel point according to the color information. Since the first pixel points are all located in the non-drawing area, if the layout of the to-be-detected image is consistent with the layout represented by the user interface layout information, there will be no pixel point with non-black color in the first pixel point, that is, the first proportion P1 is 0. If there is a pixel point with non-black color in the first pixel point, that is, the first proportion P1 is not 0, it indicates that the layout of the to-be-detected image output by the projection device is inconsistent with the layout represented by the user interface layout information, that is, it is determined that the to-be-detected image is an abnormal image.

[0099] In addition, considering that the larger the area of the target image in the to-be-detected image is, the larger the image area displayed on the vehicle windshield by the projection is, and correspondingly, the smaller the area of the front road condition that the driver can observe is, which is more likely to cause traffic accidents. Therefore, in the present disclosure, in the second embodiment, the to-be-detected image can also be detected according to the second proportion of the target image in the to-be-detected image.

[0100] In one possible manner in this embodiment, the related information of the target image includes the second proportion of the target image in the to-be-detected image. For example, first, L third pixel points are selected in the to-be-detected image, and the L third pixel points are uniformly distributed in the drawing area and the non-drawing area in the to-be-detected image. Then, the number m of non-black pixel points in the L third pixel points is determined. Finally, the second proportion of the target image in the to-be-detected image is determined by the formula P2=(m / L)*100%, and whether the to-be-detected image is an abnormal image is detected according to the second proportion.

[0101] When the image to be detected is detected in this way, there can be a case that non-black pixel points exist in the non-drawing area and the second proportion is less than the preset value, that is, in this way, an abnormal image can be detected as a normal image, thereby causing the accuracy of image detection to be low. Therefore, in another possible way in this embodiment, in a case that it is determined that no non-black pixel points exist in the non-drawing area, the second proportion of the target image in the image to be detected can be further determined. That is, in a case that no non-black pixel points exist in the M first pixel points and the related information further includes the second proportion, whether the image to be detected is an abnormal image can be determined according to the second proportion. Correspondingly, the specific implementation of the step S12 can be that: N second pixel points are selected in the drawing area of the image to be detected, wherein the N second pixel points are uniformly distributed; the number n of non-black pixel points in the N second pixel points is determined; and the second proportion P2 of the target image in the image to be detected is determined by the following formula: P2 = n / (M+N)*100%. Wherein, whether non-black pixel points exist in the non-drawing area can be determined in the manner described in the first embodiment, which will not be described here.

[0102] For example, first, in a case that no non-black pixel points exist in the M first pixel points, that is, the first proportion P1 is 0, N second pixel points are selected in the drawing area of the image to be detected, and the color of each second pixel point is determined. Similarly, in order to improve the accuracy of the determined second proportion of the target image in the image to be detected, in one way, the selected N second pixel points are uniformly distributed in the drawing area of the image to be detected. For example, as shown in FIG. 2, the circle dots represent the N second pixel points selected in the image to be detected. Figure 2

[0103] Next, the number n of non-black pixel points in the N second pixel points is determined. Since the selected N second pixel points are uniformly distributed in the drawing area of the image to be detected, non-black pixel points exist in the second pixel points.

[0104] Finally, the second proportion P2 of the target image in the image to be detected is determined by the formula: P2 = n / (M+N)*100%.

[0105] By using the above technical solution, without traversing all pixel points in the image to be detected, the second proportion of the target image in the image to be detected can be quickly determined, thereby improving the efficiency of image detection.

[0106] ​In addition, the second proportion P2 of the target image in the image to be detected can also be determined in the following manner: first, the image to be detected is binarized to generate a binary image. In the binarization process, the gray value of each pixel point with a color other than black is set to 1, and the gray value of each pixel point with a color of black is set to 0. Thus, the gray value of each pixel point in the generated binary image is either 0 or 1. Then, the ratio of the area with a gray value of 1 to the entire image area in the binary image is determined. For example, the ratio of the number of pixel points with a gray value of 1 to the number of all pixel points in the binary image is determined, and the ratio is determined as the second proportion of the target image in the image to be detected.

[0107] In this manner, all pixel points in the image to be detected need to be analyzed to generate a binary image, and the number of pixel points with a gray value of 1 and the number of all pixel points in the binary image need to be determined, that is, all pixel points in the image to be detected need to be traversed, which is a large amount of analysis work, but the accuracy of the determined second proportion is high. It should be understood that in actual applications, different manners can be selected to determine the second proportion of the target image in the image to be detected according to requirements, and the present disclosure does not make specific limitations in this regard.

[0108] After the second proportion of the target image in the image to be detected is determined in any of the above manners, it can be determined whether the image to be detected is an abnormal image according to the second proportion. For example, the specific implementation of step S13 can be that when the second proportion is less than or equal to a preset value, the image to be detected is determined to be a normal image, and when the second proportion is greater than the preset value, the image to be detected is determined to be an abnormal image.

[0109] In the present disclosure, when the image to be detected is determined to be an abnormal image, the abnormal level of the image to be detected can also be divided according to the size of the second proportion. The greater the second proportion, the higher the abnormal level of the image to be detected, that is, the greater the abnormal degree of the image to be detected.

[0110] For example, the preset value is 30%, when the second proportion is greater than 30% and less than or equal to 50%, the abnormal level of the image to be detected is determined to be a first level, when the second proportion is greater than 50% and less than or equal to 80%, the abnormal level of the image to be detected is determined to be a second level, and when the second proportion is greater than 80%, the abnormal level of the image to be detected is determined to be a third level. The abnormal degree of the first level is less than the abnormal degree of the second level, and the abnormal degree of the second level is less than the abnormal degree of the third level. For example, the abnormal degree of the first level can be general abnormality, the abnormal degree of the second level can be serious abnormality, and the abnormal degree of the third level can be fatal abnormality.

[0111] In addition, in a case where it is determined that the image to be detected is an abnormal image, the projection device can also be prohibited from projecting the image output by the projection device onto the vehicle windshield for display, so as to improve driving safety.

[0112] According to the technical solution, the second proportion of the target image in the image to be detected is used to detect whether the image to be detected is an abnormal image, and then, according to the detection result of the image to be detected, it is determined whether the image is projected onto the vehicle windshield for display, so as to ensure that the image projected onto the vehicle windshield does not affect the driving of the driver, and thus improve driving safety.

[0113] In actual application, in addition to the size of the image displayed on the vehicle windshield affecting driving safety, whether the layout of the image displayed on the vehicle windshield is consistent with the layout of the user interface of the projection device also affects driving safety. Therefore, the layout of the image to be detected can also be detected to determine whether the image to be detected is an abnormal image, that is, in a third embodiment, the related information of the target image includes the matching result of each sub-image in the target image and the interface design template information corresponding to the sub-image.

[0114] Figure 3 FIG. 1 is a flowchart of a method for determining related information of a target image in an image to be detected according to an example embodiment. As shown in FIG. 1, the method for determining the related information of the target image in the image to be detected can include the following steps. Figure 3

[0115] In step S121, the image to be detected is segmented according to the user interface layout information of the projection device to obtain a plurality of sub-images.

[0116] As described above, the user interface layout information of the projection device includes the content displayed in each region of the image, for example, the icon in region a1 of the image is used to indicate whether there is a camera on the current road, the region a2 of the image is used to display the current speed limit value, and so on. Therefore, the image to be detected can be segmented according to the user interface layout information of the projection device to obtain a plurality of sub-images. For example, Figure 4 FIG. 2 is a schematic diagram of segmenting an image to be detected to obtain sub-images according to an example embodiment. In FIG. 2, each rectangular box is denoted as a sub-image. Figure 4

[0117] In step S122, the interface design template information corresponding to each of the plurality of sub-images is obtained.

[0118] The interface design template information is pre-set. Obtaining the interface design template information corresponding to each of the plurality of sub-images includes the following steps:

[0119] ​​(1) obtaining a plurality of display area interface design template libraries in the user interface of the projection device, wherein each interface design template library includes a plurality of interface design template information.

[0120] In the present disclosure, the user interface includes a plurality of display areas, each display area has an interface design module library, and the interface design module library includes a plurality of interface design template information.

[0121] It is worth noting that for a projection device, the display area of the user interface of the projection device and the interface design template library of each display area are usually fixed. Therefore, in the present disclosure, the interface design template library can be pre-generated, and the interface design template library is obtained and used when image detection is needed. Alternatively, the interface design template library is generated in the process of detecting the image, for example, the interface design template library is generated when the image to be detected is obtained. The present disclosure does not make specific limitations on this.

[0122] The generation method of the interface design template library of the display area is described below.

[0123] First, the user interface layout information of the projection device is obtained, and the user interface of the projection device is segmented according to the user interface layout information to obtain a plurality of display areas.

[0124] In one possible way, according to the user interface layout information, the user interface can be segmented into dynamic display areas, static display areas, and image-free display areas. The plurality of display areas obtained above include dynamic display areas, static display areas, and image-free display areas. Among them, the dynamic display area is used to display the real-time changing environmental information of the vehicle during driving, such as the image of the lane line, the image of the vehicle in front, the image of the pedestrian in front, etc. The static display area is used to display the information displayed in the vehicle instrument panel and / or center screen, such as the icon indicating whether there is a camera on the current road, the current speed limit value, the icon indicating whether the safety belt is fastened, the navigation path icon, the adaptive cruise control icon, the remaining distance of the route and the estimated driving time. No image is displayed in the image-free display area.

[0125] For example, Figure 5 is a schematic diagram of segmenting a user interface according to an exemplary embodiment. In Figure 5 , the first area represents the dynamic display area obtained by segmenting the user interface, the second area represents the static display area obtained by segmenting the user interface, and the third area represents the image-free display area obtained by segmenting the user interface. Among them, the third area is all areas in the user interface except the first area and the second area.

[0126] However, considering that no image is displayed in the image-free display area, i.e., there is no any interface design template information in the interface design template library of the image-free display area, it is not necessary to construct the interface design template library of the image-free display area. In addition, the image displayed in the dynamic display area is closely related to the driving environment of the vehicle, and the image is an irregular image, and the template of the image cannot be provided in the design stage of the projection device, and therefore, it is also not necessary to construct the interface design template library of the dynamic display area.

[0127] Therefore, in another possible manner, the user interface layout information includes vehicle driving related information corresponding to each display position in the static display area, and according to the vehicle driving related information corresponding to each display position, the static display area can be further divided into a plurality of display areas displaying vehicle driving related information, and the display area described above is a display area displaying vehicle driving related information. For example, the static display area can be divided according to the vehicle driving related information displayed in the static display area, for example, the area for displaying an icon indicating whether there is a camera on the current road is divided into a display area, the area displaying the current speed limit value is divided into a display area, and the like.

[0128] Then, for each display area, a plurality of interface design templates corresponding to the display area are determined, a hash algorithm is used to respectively generate hash values corresponding to the plurality of interface design templates, and an interface design template library of the display area is generated according to the hash values corresponding to the plurality of interface design templates.

[0129] Each of the plurality of interface design templates corresponding to each display area is designed in the design stage of the projection device. For example, for the area displaying the current speed limit value, a plurality of images are designed in advance, and the speed limit value included in each image is different. These images are called interface design templates.

[0130] In the above manner, the interface design template library of each display area can be generated, and the hash value corresponding to each interface design template included in the interface design template library is the interface design template information.

[0131] (2) For each sub-image, the interface design template library of the display area corresponding to the sub-image is determined, and a plurality of interface design template information included in the interface design template library is determined as the interface design template information corresponding to the sub-image.

[0132] In the present disclosure, according to the user interface layout information of the projection device, the display area corresponding to each sub-image is determined. For example, for the projection device shown in FIG. 1, the user interface layout information includes the information of the display area 101, the display area 102, the display area 103, the display area 104, the display area 105, the display area 106, the display area 107, the display area 108, the display area 109, and the display area 110. Figure 4The sub-image of the current speed limit value is displayed according to the vehicle travel related information corresponding to each display area included in the layout information, the display area for displaying the current speed limit value is determined, the interface design template library of the display area is determined as the interface design template library of the display area corresponding to the sub-image, and the plurality of interface design template information included in the interface design template library is determined as the interface design template information corresponding to the sub-image.

[0133] Return Figure 3 In step S123, for each sub-image, the matching result of the sub-image and the interface design template information corresponding to the sub-image is determined according to the sub-image and the interface design template information corresponding to the sub-image.

[0134] In the present disclosure, determining the matching result of the sub-image and the interface design template information corresponding to the sub-image is to determine whether there is interface design template information matching the sub-image in the interface design template information corresponding to the sub-image.

[0135] For example, the specific implementation of step S123 can be:

[0136] The hash value corresponding to the sub-image is generated by using a hash algorithm, the Hamming distance between the hash value corresponding to the sub-image and the hash value corresponding to each interface design template included in the interface design template library is calculated to obtain a plurality of Hamming distances, if there is a Hamming distance less than or equal to a preset threshold in the plurality of Hamming distances, the matching result of the sub-image and the interface design template information corresponding to the sub-image is determined as a first result, and the first result is used to represent that there is an interface design template matching the sub-image in the display area, and if each Hamming distance is greater than the preset threshold, the matching result of the sub-image and the interface design template information corresponding to the sub-image is determined as a second result, and the second result is used to represent that there is no interface design template matching the sub-image in the display area.

[0137] In the present disclosure, assuming that the number of interface design templates corresponding to the display area is K, the interface design template library of the display area includes K hash values, the Hamming distance between the hash value corresponding to the sub-image and each hash value included in the interface design template library of the display area is calculated, and K Hamming distances are obtained. The number of bits of the hash value corresponding to the sub-image is the same as the number of bits of the hash value corresponding to each interface design template.

[0138] If there is a Hamming distance less than or equal to the preset threshold in the K Hamming distances, it is considered that there is an interface design template matching the sub-image in the plurality of interface design templates corresponding to the display area of the sub-image, that is, the content displayed by the sub-image is consistent with the content displayed by the display area defined in the user interface layout information of the projection device. If each Hamming distance in the K Hamming distances is greater than the preset threshold, it is determined that the content displayed by the sub-image is inconsistent with the content displayed by the display area defined in the user interface layout information of the projection device, which represents that the to-be-detected image is an abnormal image.

[0139] It should be understood that the above only describes the manner of determining whether there is an interface design template matching the sub-image in the display area with one sub-image as an example. In actual application, it is necessary to determine whether there is an interface design template matching the sub-image in the display area corresponding to each sub-image according to the above manner.

[0140] Correspondingly, in this embodiment, the specific implementation of step S13 of determining whether the to-be-detected image is an abnormal image according to the related information of the target image is that if there is a sub-image with the matching result of the second result, it is determined that the to-be-detected image is an abnormal image.

[0141] As described above, if the matching result of the sub-image and the interface design template information corresponding to the sub-image is the second result, it indicates that the content displayed by the sub-image is inconsistent with the content displayed by the display area defined in the user interface layout information of the projection device. Therefore, if there is at least one sub-image with the matching result of the second result in the plurality of sub-images, it is determined that the to-be-detected image is an abnormal image.

[0142] In the fourth embodiment, the related information of the target image includes a second proportion of the target image in the to-be-detected image and a matching result of each sub-image in the target image and the interface design template information corresponding to the sub-image, wherein the second proportion and the matching result of each sub-image and the interface design template information corresponding to the sub-image can be determined in the above manner, and the present disclosure will not be repeated here.

[0143] In this embodiment, the specific implementation of step S13 of determining whether the to-be-detected image is an abnormal image according to the related information of the target image can be that when the second proportion and the matching result of the sub-image and the interface design template information corresponding to the sub-image do not satisfy the preset qualified condition, it is determined that the to-be-detected image is an abnormal image. The qualified condition includes that the second proportion is less than or equal to a preset value, and the matching result of each sub-image and the interface design template information corresponding to the sub-image is the first result, wherein the first result represents that there is an interface design template matching the sub-image in the display area.

[0144] In the present disclosure, when the matching result of the second proportion and the interface design template information corresponding to the sub-image meets the above eligibility condition, the to-be-detected image is determined as a normal image, otherwise, the to-be-detected image is determined as an abnormal image.

[0145] In addition, if the to-be-detected image is determined as an abnormal image, the abnormal level of the to-be-detected image can be further determined according to the matching result of the second proportion and the interface design template information corresponding to the sub-image. In an embodiment, the abnormal level of the to-be-detected image is determined according to the matching result of the second proportion and the interface design template information corresponding to the sub-image in the case that the to-be-detected image is an abnormal image. It should be understood that the projection device abnormality can also cause the to-be-detected image to be abnormal, and therefore, in another embodiment, the abnormal level of the to-be-detected image can be determined based on the second proportion, the matching result of the interface design template information corresponding to the sub-image, and whether the projection device is abnormal.

[0146] For example, Table 1 shows the correspondence between the matching result of the second proportion and the interface design template information corresponding to the sub-image, whether the projection device is abnormal, and the abnormal level of the to-be-detected image, and the abnormal degree represented by the abnormal level is also shown in Table 1.

[0147] Table 1

[0148]

[0149] Therefore, when the to-be-detected image is determined as an abnormal image, the abnormal level of the to-be-detected image can be further determined, which improves the flexibility of image detection.

[0150] In addition, after the abnormal level of the to-be-detected image is determined, a corresponding operation can be performed, for example, alarm information can be output to prompt the driver that the image output by the projection device is abnormal, or the projection device can be disabled, that is, the projection device is not enabled to project and display vehicle driving related information on the vehicle windshield, and the like.

[0151] Based on the same inventive concept, the present disclosure also provides an image detection device. Figure 6 is a block diagram of an image detection device according to an exemplary embodiment. As Figure 6 shown, the image detection device 500 includes:

[0152] A first acquisition module 501 is configured to acquire a to-be-detected image.

[0153] A first determination module 502 is configured to determine the related information of a target image in the to-be-detected image, wherein the target image is an image that can be projected onto a vehicle windshield by a projection device for display.

[0154] The second determining module 503 is configured to determine whether the to-be-detected image is an abnormal image according to the related information of the target image.

[0155] Optionally, the related information of the target image comprises at least one of the following:

[0156] a first proportion of the target image in a non-drawing region of the to-be-detected image, a second proportion of the target image in the to-be-detected image, and a matching result of each sub-image in the target image and interface design template information corresponding to the sub-image.

[0157] Optionally, the target image is an image composed of non-black pixel points.

[0158] In a case where the related information comprises the first proportion, the first determining module 502 comprises:

[0159] A first selecting sub-module, configured to select M first pixel points in a non-drawing region of the to-be-detected image, wherein the M first pixel points are uniformly distributed.

[0160] A first determining sub-module, configured to determine the first proportion P1 of the target image in the non-drawing region of the to-be-detected image if there is a non-black pixel point in the M first pixel points.

[0161] Optionally, in a case where there is no non-black pixel point in the M first pixel points and the related information further comprises the second proportion, the first determining module 502 further comprises:

[0162] A second selecting sub-module, configured to select N second pixel points in a drawing region of the to-be-detected image, wherein the N second pixel points are uniformly distributed.

[0163] A second determining sub-module, configured to determine a number n of non-black pixel points in the N second pixel points.

[0164] A third determining sub-module, configured to determine the second proportion P2 of the target image in the to-be-detected image by the following formula: P2=n / (M+N)*100%.

[0165] Optionally, in a case where the related information comprises the matching result of each sub-image in the target image and interface design template information corresponding to the sub-image, the first determining module 502 comprises:

[0166] A segmenting sub-module, configured to segment the to-be-detected image according to user interface layout information of a projection device to obtain a plurality of sub-images.

[0167] The acquisition sub-module is configured to acquire interface design template information corresponding to each of the plurality of sub-images.

[0168] The sixth determination sub-module is configured to, for each sub-image, determine a matching result of the sub-image and interface design template information corresponding to the sub-image according to the sub-image and the interface design template information corresponding to the sub-image.

[0169] Optionally, the acquisition sub-module is configured to:

[0170] The acquisition sub-module is configured to acquire a plurality of display region interface design template libraries in a user interface of a projection device, wherein each of the display region interface design template libraries includes a plurality of interface design template information.

[0171] The acquisition sub-module is configured to, for each sub-image, determine a display region interface design template library corresponding to the sub-image, and determine the plurality of interface design template information included in the display region interface design template library as interface design template information corresponding to the sub-image.

[0172] The display region interface design template library is generated by:

[0173] The acquisition sub-module is configured to segment the user interface of the projection device according to user interface layout information of the projection device to obtain a plurality of display regions.

[0174] The acquisition sub-module is configured to, for each display region, determine a plurality of interface design templates corresponding to the display region, respectively generate a hash value corresponding to each of the plurality of interface design templates by using a hash algorithm, and generate the display region interface design template library according to the hash values corresponding to the plurality of interface design templates.

[0175] Optionally, in a case where the related information includes the second proportion and a matching result of each sub-image in the target image and interface design template information corresponding to the sub-image, the second determination module includes:

[0176] The seventh determination sub-module is configured to determine the to-be-detected image as an abnormal image when the second proportion and the matching result of the sub-image and the interface design template information corresponding to the sub-image do not satisfy a preset qualified condition.

[0177] The preset qualified condition includes that the second proportion is less than or equal to a preset value, and the matching result of each sub-image and the interface design template information corresponding to the sub-image is a first result, wherein the first result indicates that there is an interface design template matching the sub-image in the display region.

[0178] As to the apparatus in the above embodiments, the specific manners in which various modules perform operations have been described in details in the embodiments of the method, and thus will not be described in details here.

[0179] Figure 7 is a block diagram of a vehicle according to an exemplary embodiment. As shown, the vehicle 600 can include a processor 601, a memory 602, and a projection device 603. The vehicle 600 can also include one or more of a multimedia component 604, an input / output (I / O) interface 605, and a communication component 606. Figure 7

[0180] The projection device 603 can be a head-up display (HUD), an augmented reality head-up display (AR-HUD), a combiner head-up display (C-HUD), a windshield head-up display (M-HUD), or the like.

[0181] ​The processor 601 is configured to control overall operations of the vehicle 600 to complete all or part of the steps of the image detection method described above. The memory 602 is configured to store various types of data to support the operations of the vehicle 600, which can include, for example, instructions for any application or method operating on the vehicle 600, and application-related data, such as contact data, sent and received messages, pictures, audio, video, and the like. The memory 602 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The multimedia component 604 can include a screen and an audio component. The screen can be, for example, a touch screen, and the audio component is configured to output and / or input audio signals. For example, the audio component can include a microphone configured to receive external audio signals. The received audio signals can be further stored in the memory 602 or transmitted through the communication component 606. The audio component also includes at least one speaker configured to output audio signals. The I / O interface 605 provides an interface between the processor 601 and other interface modules, which can be a keyboard, a mouse, a button, and the like. The buttons can be virtual buttons or physical buttons. The communication component 606 is configured to perform wired or wireless communication between the vehicle 600 and other devices. The wireless communication, such as Wi-Fi, Bluetooth, near field communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, and the like, or a combination of one or more of them, is not limited herein. Therefore, the corresponding communication component 606 can include a Wi-Fi module, a Bluetooth module, an NFC module, and the like.

[0182] In an example embodiment, the vehicle 600 can be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors, or other electronic elements for executing the above-mentioned image detection method.

[0183] In another example embodiment, a computer-readable storage medium including program instructions is also provided, which when executed by a processor, implement the steps of the above-mentioned image detection method. For example, the computer-readable storage medium can be the above-mentioned memory 602 including program instructions, which can be executed by the processor 601 of the vehicle 600 to complete the above-mentioned image detection method.

[0184] Figure 8 is a block diagram of an electronic device according to an example embodiment. For example, the electronic device 700 can be provided as a server. Referring to Figure 8 , the electronic device 700 includes a processor 722, the number of which can be one or more, and a memory 732 for storing computer programs executable by the processor 722. The computer programs stored in the memory 732 can include one or more modules each corresponding to a set of instructions. In addition, the processor 722 can be configured to execute the computer programs to perform the above-mentioned image detection method.

[0185] In addition, the electronic device 700 can also include a power supply component 726, which can be configured to perform power management of the electronic device 700, and a communication component 750, which can be configured to implement communication of the electronic device 700, such as wired or wireless communication. In addition, the electronic device 700 can also include an input / output (I / O) interface 758. The electronic device 700 can operate based on an operating system stored in the memory 732, such as Windows Server TM , Mac OSX TM , Unix TM , Linux TM , etc.

[0186] In another exemplary embodiment, a computer readable storage medium including program instructions is also provided, which when executed by a processor, implement the steps of the image detection method described above. For example, the non-transitory computer readable storage medium can be the memory 732 described above including program instructions executable by the processor 722 of the electronic device 700 to complete the image detection method described above.

[0187] In another exemplary embodiment, a computer program product is also provided, which contains a computer program executable by a programmable apparatus, the computer program having code portions for performing the image detection method described above when executed by the programmable apparatus.

[0188] The preferred embodiments of the present disclosure are described in detail above with reference to the accompanying drawings, but the present disclosure is not limited to the specific details in the above-described embodiments. Various simple modifications can be made to the technical solutions of the present disclosure within the scope of the technical concepts of the present disclosure, and all these simple modifications shall fall within the protection scope of the present disclosure.

[0189] It should be further noted that each of the various technical features described in the above specific embodiments can be combined in any suitable manner, provided that there is no contradiction. In order to avoid unnecessary repetition, the present disclosure will not make further descriptions on various possible combinations.

[0190] In addition, any combination of the various different embodiments of the present disclosure can also be made, as long as it does not deviate from the idea of the present disclosure, it should also be considered as disclosed by the present disclosure.

Claims

1. An image detection method characterized by, The method comprises: acquiring a to-be-detected image; determining related information of a target image in the to-be-detected image, wherein the target image is an image capable of being projected onto a vehicle windshield by a projection device for display, and a user interface is divided into a drawing area and a non-drawing area according to user interface layout information of the projection device; determining whether the to-be-detected image is an abnormal image according to the related information of the target image; the target image is an image composed of non-black pixel points; in a case where the related information comprises a first proportion of the target image in the non-drawing area of the to-be-detected image, the determining of the related information of the target image in the to-be-detected image comprises: selecting M first pixel points in the non-drawing area of the to-be-detected image, wherein the M first pixel points are uniformly distributed; if there is a non-black pixel point in the M first pixel points, determining the first proportion P1 of the target image in the non-drawing area of the to-be-detected image; the determining of whether the to-be-detected image is an abnormal image according to the related information of the target image comprises: if the first proportion P1 is not 0, determining that the to-be-detected image is an abnormal image.

2. The method of claim 1, wherein the related information of the target image comprises at least one of the following: a second proportion of the target image in the to-be-detected image and a matching result of each sub-image in the target image and interface design template information corresponding to the sub-image.

3. The method of claim 2, wherein in a case where there is no non-black pixel point in the M first pixel points and the related information further comprises the second proportion, the determining of the related information of the target image in the to-be-detected image further comprises: selecting N second pixel points in the drawing area of the to-be-detected image, wherein the N second pixel points are uniformly distributed; determining the number n of non-black pixel points in the N second pixel points.

4. The method of claim 2, wherein in a case where the related information comprises the matching result of each sub-image in the target image and interface design template information corresponding to the sub-image, the determining of the related information of the target image in the to-be-detected image comprises: segmenting the to-be-detected image according to user interface layout information of the projection device to obtain a plurality of sub-images; The second proportion P2 of the target image in the image to be detected is determined by the following formula, . acquiring interface design template information corresponding to each of the plurality of sub-images; for each sub-image, determining a matching result of the sub-image and interface design template information corresponding to the sub-image according to the sub-image and the interface design template information corresponding to the sub-image. the acquiring of the interface design template information corresponding to each of the plurality of sub-images comprises: acquiring a plurality of interface design template libraries of a plurality of display areas in a user interface of the projection device, wherein each of the interface design template libraries comprises a plurality of interface design template information; ​ 5. The method of claim 4, wherein, ​ ​ For each sub-image, determine an interface design template library of a display area corresponding to the sub-image, and determine a plurality of interface design template information included in the interface design template library as interface design template information corresponding to the sub-image; The interface design template library of the display area is generated by the following method: According to the user interface layout information of the projection device, the user interface of the projection device is segmented to obtain a plurality of display areas; For each display area, determine a plurality of interface design templates corresponding to the display area, respectively generate hash values corresponding to the plurality of interface design templates by using a hash algorithm, and generate the interface design template library of the display area according to the hash values corresponding to the plurality of interface design templates.

6. The method of claim 2, wherein, In a case where the related information includes the second proportion and a matching result of each sub-image in the target image and the interface design template information corresponding to the sub-image, the determining, according to the related information of the target image, whether the to-be-detected image is an abnormal image comprises: In a case where the second proportion and the matching result of the sub-image and the interface design template information corresponding to the sub-image do not satisfy a preset qualified condition, determining that the to-be-detected image is an abnormal image; The preset qualified condition includes that the second proportion is less than or equal to a preset value, and the matching result of each sub-image and the interface design template information corresponding to the sub-image is a first result, wherein the first result indicates that there is an interface design template matching the sub-image in the display area.

7. An image detection apparatus characterized by comprising: Comprise: A first acquisition module is configured to acquire a to-be-detected image; A first determination module is configured to determine related information of a target image in the to-be-detected image, wherein the target image is an image that can be projected onto a vehicle windshield by a projection device for display, and according to user interface layout information of the projection device, the user interface is divided into a drawing area and a non-drawing area; A second determination module is configured to determine, according to the related information of the target image, whether the to-be-detected image is an abnormal image; The target image is an image composed of non-black pixel points; In a case where the related information includes a first proportion of the target image in the non-drawing area of the to-be-detected image, the first determination module comprises: A first selection sub-module is configured to select M first pixel points in the non-drawing area of the to-be-detected image, wherein the M first pixel points are uniformly distributed; A first determination sub-module is configured to determine the first proportion P1 of the target image in the non-drawing area of the to-be-detected image if there is a non-black pixel point in the M first pixel points; The determining, according to the related information of the target image, whether the to-be-detected image is an abnormal image comprises: If the first proportion P1 is not 0, it is determined that the to-be-detected image is an abnormal image.

8. A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the steps of the method of any one of claims 1-6.

9. A vehicle characterized by comprising: Comprise: A projection device is configured to project the to-be-detected image onto a vehicle windshield; a memory having stored thereon a computer program; a processor configured to execute the computer program in the memory to implement the steps of the method of any one of claims 1-6.

Images