Method for identifying second vehicle with visual identification and automatic vehicle driving method

Abstract

The invention relates to a method for identifying a second vehicle with a visual identifier, a vehicle automatic driving method, a vehicle identification system, electronic equipment and a computer readable medium. The method comprises the steps that the imaging device shoots an image; the processor judges whether the visual identification exists in the image or not, and if the visual identification exists, it is determined that the second vehicle exists in the field of view. According to the method, only the visual identifier in the image needs to be identified, and the vehicle does not need to be identified by extracting texture features in the image in the prior art, so that the vehicle identification rate can be improved, and the calculation power required by identification is reduced.

Description

Technical Field

[0001] The present invention relates to the field of computer information processing, and in particular to a method for identifying a second vehicle with a visual identifier, a vehicle automatic driving method, a vehicle identification system, an electronic device and a computer-readable medium. Background Art

[0002] After years of development, cars have become more and more technologically advanced, and high-tech technologies such as assisted driving or autonomous driving are getting closer and closer to us.

[0003] In the process of assisted driving or automatic driving, the car uses computer vision to identify the vehicle. The common practice is to take a picture of the vehicle to obtain an image and identify the vehicle by extracting the texture features in the image. Texture features describe the local patterns that recur in the image and their arrangement rules. Commonly used texture feature extraction methods are generally divided into four categories: 1. Statistical methods, such as gray-level co-occurrence matrix, gray-level travel statistics, gray-level difference statistics, local gray-level statistics, semivariogram, autocorrelation function, etc.; 2. Model-based methods, such as synchronous autoregressive model, Markov model, Gibbs model, sliding average model, complex network model, etc.; 3. Structure-based methods, such as syntactic texture analysis, mathematical morphology, Laws texture measurement, feature filter, etc.; 4. Signal processing-based methods, such as Radon transform, discrete cosine transform, local Fourier transform, Gabor transform, binary wavelet transform, tree wavelet decomposition, etc.

[0004] The common problem with the above methods is that they require large amounts of calculations and high computing power. In addition, when a partial image of a vehicle is captured, the vehicle may not be recognized because sufficient texture features cannot be extracted from the image, resulting in a low vehicle recognition rate.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the invention and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the invention

[0006] In view of this, the present invention provides a method for identifying a second vehicle with a visual identification, a vehicle automatic driving method (including assisted driving), a vehicle identification system, an electronic device and a computer-readable medium, which can improve the recognition rate of the vehicle and reduce the computing power requirements for recognition.

[0007] Other features and advantages of the present invention will become apparent from the following detailed description, or may be learned in part by practice of the present invention.

[0008] According to one aspect of the present invention, a method for identifying a second vehicle with a visual identification is proposed, the method comprising: an imaging device captures an image; a processor determines whether the visual identification exists in the image, and if the visual identification exists, determines that the second vehicle exists within the field of view.

[0009] In an exemplary embodiment of the present invention, the visual logo is displayed in the following ways: placing, pasting, or installing an identification object on the body of a vehicle to display the visual logo; or painting the visual logo on the body of a vehicle; or installing a display device for displaying the visual logo on the body of the vehicle; or using the vehicle's onboard lamps or body decorations or vehicle license plates or onboard display devices to display the visual logo.

[0010] In an exemplary embodiment of the present invention, a vehicle interaction information mapping rule is pre-stored in the processor, and the vehicle interaction information mapping rule is used to indicate a mapping relationship between visual identification and vehicle interaction information. The method also includes: determining the vehicle interaction information based on the acquired visual identification and the vehicle interaction information mapping rule.

[0011] In an exemplary embodiment of the present invention, the vehicle interaction information mapping rule can be used to indicate the mapping relationship between the arrangement of visual identification and vehicle interaction information, and determining the vehicle interaction information based on the acquired visual identification and the vehicle interaction information mapping rule includes: determining the vehicle interaction information based on the arrangement of visual identification and the vehicle interaction information mapping rule.

[0012] In an exemplary embodiment of the present invention, vehicle interaction information mapping rules are pre-stored in the processor, and the vehicle interaction information mapping rules are used to indicate the mapping relationship between visual identification and vehicle interaction information. The method also includes: determining the vehicle interaction information that needs to be transmitted; searching for a visual identification that has a mapping relationship with the vehicle interaction information that needs to be transmitted from the vehicle interaction information mapping rules; and displaying the found visual identification on the body of the vehicle.

[0013] In an exemplary embodiment of the present invention, the vehicle interaction information mapping rule is used to indicate the mapping relationship between the arrangement of visual identifiers and the vehicle interaction information, and the visual identifier having a mapping relationship with the vehicle interaction information to be transmitted is searched from the vehicle interaction information mapping rule; and the found visual identifier is displayed on the body of the vehicle, including: searching from the vehicle interaction information mapping rule for the arrangement of visual identifiers having a mapping relationship with the vehicle interaction information to be transmitted; and displaying the visual identifier on the body of the vehicle in the found arrangement.

[0014] In an exemplary embodiment of the present invention, the imaging device is arranged on a first vehicle, and the method further includes: determining at least one of the following based on the visual identification: the driving state of the second vehicle, the vehicle size parameters of the second vehicle, the model of the second vehicle, and the relative position between the first vehicle and the second vehicle.

[0015] In an exemplary embodiment of the present invention, the processor pre-stores a mapping relationship between the size of a visual identifier in an image and the distance, the relative position includes the vehicle distance, and determining the relative position between the first vehicle and the second vehicle based on the visual identifier includes: determining the size of the visual identifier in the image; searching the mapping relationship to obtain a distance that has a mapping relationship with the size of the visual identifier in the image; and determining the distance found to be the vehicle distance between the first vehicle and the second vehicle. In a specific embodiment, the processor pre-stores a mapping relationship between the size of multiple points on one or more visual identifiers in an image and the vehicle distance, the relative position includes the vehicle distance, and determining the relative position between the first vehicle and the second vehicle based on the visual identifier includes: determining the size of multiple points on the one or more visual identifiers in the image; searching the mapping relationship to obtain a distance that has a mapping relationship with the size of multiple points on the one or more visual identifiers in the image; and determining the distance found to be the vehicle distance between the first vehicle and the second vehicle.

[0016] According to one aspect of the present invention, a vehicle automatic driving method is proposed, comprising: step one, using the above method to identify a second vehicle; step two, determining a driving strategy for a first vehicle based on the identification result.

[0017] According to one aspect of the present invention, a vehicle identification system is provided, comprising: an imaging device and a first terminal arranged in a first vehicle, wherein the first terminal comprises a processor, and the imaging device and the processor are used to implement the method described above.

[0018] In an exemplary embodiment of the present invention, the second vehicle is provided with a second terminal, and the second terminal is used to send vehicle interaction information to the first terminal and / or receive vehicle interaction information sent by the first terminal.

[0019] According to one aspect of the present invention, an electronic device is provided, which includes: one or more processors; a storage device for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the method described above.

[0020] According to one aspect of the present invention, a computer-readable medium is provided, on which a computer program is stored. When the program is executed by a processor, the method described above is implemented.

[0021] According to the present invention, the first vehicle recognizes the captured image, and if the image is recognized to contain a visual logo, the area where the visual logo is located is determined to be the body of the second vehicle, and the second vehicle is identified by identifying the visual logo displayed on the second vehicle. Furthermore, since only the visual logo in the image needs to be identified, and there is no need to identify the vehicle by extracting texture features in the image as in the related art, the vehicle recognition rate can be improved and the computing power required for recognition can be reduced.

[0022] In addition, the technical solution of the present invention also brings many other advantages, which will be described in detail in the specific implementation manner.

[0023] It is to be understood that the foregoing general description and the following detailed description are exemplary only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings of the embodiments will be briefly introduced below. Obviously, the drawings in the following description only relate to some embodiments of the present invention, but are not intended to limit the present invention.

[0025] Figure 1 The present invention is a flowchart showing a method for identifying a second vehicle with a visual identification according to an exemplary embodiment.

[0026] Figure 2 It is a diagram of a vehicle hitting an overturned truck.

[0027] Figure 3-1 , 3-2 They are schematic diagrams of body sides of vehicles of different types according to an exemplary embodiment.

[0028] Figure 4-1 , 4-2 They are schematic diagrams showing visual identification on the body sides of vehicles of different models according to an exemplary embodiment.

[0029] Figure 5-1 , 5-2 is a schematic diagram showing different arrangements of visual identifiers according to an exemplary embodiment.

[0030] Figure 6-1 , 6-2 It is a schematic diagram showing only a portion of the side surface of a vehicle body according to an exemplary embodiment.

[0031] Figure 7-1 , 7-2 It is a schematic diagram showing an arrangement of visual identifiers extracted from an image according to an exemplary embodiment.

[0032] Figure 8 is a schematic diagram showing vehicle dimensions and visual identification dimensions according to an exemplary embodiment.

[0033] Fig. 9 The diagram is a schematic diagram showing a driving direction of a vehicle according to an exemplary embodiment.

[0034] Fig.10 It is a block diagram of an electronic device according to an exemplary embodiment.

[0035] Fig.11 It is a block diagram of a computer-readable medium according to an exemplary embodiment. DETAILED DESCRIPTION

[0036] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that the present invention will be comprehensive and complete and fully convey the concepts of the example embodiments to those skilled in the art. The same reference numerals in the figures represent the same or similar parts, and thus their repeated description will be omitted.

[0037] In addition, the described features, structures or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present invention. However, those skilled in the art will appreciate that the technical solution of the present invention can be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known methods, devices, implementations or operations are not shown or described in detail to avoid blurring various aspects of the present invention.

[0038] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0039] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0040] These terms are used to distinguish one component from another component. Therefore, the first component discussed below can be referred to as the second component without departing from the teachings of the inventive concept. As used herein, the term "and / or" includes any one of the associated listed items and all combinations of one or more.

[0041] Those skilled in the art will appreciate that the drawings are merely schematic diagrams of example embodiments, and the modules or processes in the drawings are not necessarily necessary for implementing the present invention, and therefore cannot be used to limit the protection scope of the present invention.

[0042] Figure 1 : is a flow chart showing a method for identifying a second vehicle with a visual identification according to an exemplary embodiment, the method comprising the following steps:

[0043] S101: An imaging device captures an image.

[0044] S102: The processor determines whether there is a visual identifier in the image, and if there is a visual identifier, determines that there is a second vehicle in the field of view.

[0045] S101 is executed by an imaging device installed in the first vehicle, S102 is executed by a processor installed in the terminal of the first vehicle, and the visual identification is displayed on the body of the second vehicle. In the present invention, "body" has a broad meaning, including not only the car skin, but also wheels, chassis, lighting, etc.

[0046] In the present invention, the "first" and "second" in "first vehicle" and "second vehicle" do not have a sequential order, but are only used to distinguish different vehicles.

[0047] For example, a visual mark is displayed on the body of car A. During the process of automatic driving (or assisted driving), the imaging device installed on the body of car B takes pictures of the surrounding environment. The captured image is recognized. If the image is recognized to contain the visual mark, it is determined that there is a vehicle within the field of view, and the image area where the visual mark is located is determined to be an image of the vehicle body. Car B recognizes the vehicle by recognizing the visual mark displayed on the body of car A. In this example, car B is the first vehicle and car A is the second vehicle.

[0048] For another example, a visual mark is displayed on the body of car B. During the process of automatic driving (or assisted driving, the automatic driving mentioned later includes assisted driving unless otherwise specified), the imaging device installed on the body of car A takes pictures of the surrounding environment. The captured image is recognized. If the image is recognized to contain the visual mark, it is determined that there is a vehicle in the field of view, and the image area where the visual mark is located is determined to be the image of the vehicle body. Car A recognizes the vehicle by recognizing the visual mark displayed on the body of car B. In this example, car A is the first vehicle and car B is the second vehicle.

[0049] As an optional implementation, the visual logo is displayed in the following ways: placing, pasting, or installing a logo object on the body of the vehicle to display the visual logo, or painting the visual logo on the body of the vehicle; or installing a display device for displaying the visual logo on the body of the vehicle; or using the vehicle's onboard lamps or body decorations or vehicle license plates or onboard display devices to display the visual logo. The visual logo can also be a code, graphic, dot matrix, barcode, QR code, etc.

[0050] The visual identification can be dynamic or static. For example, a display device or a vehicle-mounted lamp can display multiple different static visual identifications or dynamic visual identifications by changing the characteristics of the light emitted.

[0051] Image recognition is based on the main features of the image. There are some parts on the body of the vehicle that are relatively easy to identify during the image recognition process, such as lights, wheels, license plates, body decorations, etc. These parts have a lot of feature data, obvious visual features, and a large visual distinction. And there are some parts that are relatively difficult to identify during the image recognition process, such as the car skin. This part has less feature data, unclear visual features, a large area, and a small visual distinction. In the present invention, the part of the vehicle that does not have significant visual features refers to the part other than the lights, wheels, license plates, and body decorations. In other words, the part of the vehicle that does not have significant visual features refers to the car skin.

[0052] In one embodiment of the present invention, the visual logo can be displayed on a part of the vehicle with significant visual features, for example, the visual logo can be displayed on a part with significant visual features such as a lamp, a wheel, a license plate, or a body decoration. Specifically, a logo object is placed, pasted, or installed on a part of the vehicle with significant visual features to display the visual logo, or a visual logo is painted on a part of the vehicle with significant visual features; or the visual logo is displayed using a vehicle-mounted lamp, a body decoration, a vehicle license plate, or a vehicle-mounted display device.

[0053] In another embodiment provided by the present invention, the visual identification can be displayed on a portion of the vehicle that does not have significant visual features, such as displaying the visual identification on the skin of the vehicle (for example, placing, pasting, or installing an identification object on the skin of the vehicle to display the visual identification, or painting the visual identification on the skin of the vehicle; or installing a display device for displaying the visual identification on the skin of the vehicle). In this embodiment, even if the vehicle's headlights, wheels, license plates, and body decorations that have significant visual features are not photographed, and only the skin is photographed, the vehicle can still be quickly identified by recognizing the visual identification under low computing power. In the prior art, if the vehicle's headlights, wheels, license plates, and body decorations that have significant visual features are not photographed, the process of identifying the vehicle by identifying the skin requires very high computing power, and the vehicle cannot be identified under low computing power.

[0054] A visual logo is displayed on the body of vehicle A. During the process of autonomous driving of vehicle B, an imaging device installed on the body of vehicle B takes pictures of the surrounding environment. The imaging device may be a camera. The imaging device may be installed on the top of vehicle B, and the imaging device and vehicle B remain relatively stationary during driving. In this way, if the distance between the imaging device and vehicle A can be calculated, the distance between vehicle A and vehicle B can be obtained through simple calculation.

[0055] Car B recognizes the captured image. If it recognizes that the image contains a visual logo, it determines that there is a vehicle in the field of view, and determines that the image area where the visual logo is located is the body image of the vehicle. Car A is identified by identifying the visual logo displayed on the body of Car A. In addition, since only the visual logo in the image needs to be identified, and there is no need to identify the vehicle by extracting texture features in the image as in the related art, the vehicle recognition rate can be improved and the computing power required for recognition can be reduced. After Car B recognizes Car A, it can take corresponding measures, such as braking, overtaking, decelerating, accelerating, and exchanging information with Car A, thereby improving the safety and flexibility of autonomous driving.

[0056] In the vehicle recognition methods currently used by autonomous vehicles, when the entire vehicle image cannot be captured, all texture features cannot be extracted, resulting in the inability to recognize the vehicle even with high computing power, which poses a danger to autonomous driving. For example, according to a news report, a truck overturned on the road, and the autonomous vehicle could not recognize the truck and collided with it. Figure 2 The method for identifying a second vehicle with a visual identification provided by the present invention can solve this problem.

[0057] The method for identifying a second vehicle with a visual identification provided by the present invention can identify the vehicle based on the visual identification even if the entire vehicle image cannot be captured, as long as the visual identification displayed on the vehicle body is captured. The vehicle can be identified even when only part of the vehicle body is captured, thereby improving the accuracy of vehicle identification and thus improving the safety of autonomous driving.

[0058] In the method for identifying a second vehicle with a visual mark provided by the present invention, the visual mark can be displayed on any part of the vehicle body, for example, the front, side, rear, bottom, and top of the vehicle body are all displayed with the visual mark. Then, even if only a part of the vehicle body can be photographed, it can be identified as a vehicle based on the visual mark of the part, thereby greatly improving the recognition rate. For example, the front, side, rear, bottom, and top of vehicle A are all displayed with the visual mark. When vehicle A is in the following situation: Figure 2 When the vehicle rolls over as shown, vehicle B captures an image and identifies the visual signs in the image, thereby knowing that the image contains a vehicle. In this way, vehicle B can identify the vehicle even when only the bottom of vehicle A is captured, thereby applying the brakes to avoid colliding with vehicle A.

[0059] As an optional implementation, the visual logo displayed on different parts of the vehicle body can be different, so that it is possible to determine which part of the vehicle is photographed by identifying the visual logo. For example, a circular visual logo is displayed on the front of the vehicle body of vehicle A, a triangular visual logo is displayed on the side of the vehicle body, and a square visual logo is displayed on the bottom of the vehicle body. If a square visual logo is identified from the image taken by vehicle B, then it can be determined that the bottom of the vehicle body of vehicle A is photographed; if a triangular visual logo is identified from the image taken by vehicle B, then it can be determined that the side of the vehicle body of vehicle A is photographed. In addition to identifying vehicles, different visual logos can also map corresponding vehicle interaction information. The vehicle interaction information can include information related to the vehicle where the visual logo is located, such as vehicle size parameters, vehicle model, and vehicle driving status, and can also include information related to the visual logo or the arrangement of visual logos, such as the position parameters of the visual logo on the vehicle, the parameters of the visual logo, and the relative position between multiple visual logos.

[0060] As an optional implementation, other information may also be determined based on the visual identification, such as vehicle size parameters, vehicle model, vehicle driving status, relative position of the vehicle, etc. Vehicle size parameters refer to the length, width, and height of the vehicle. Vehicle driving status refers to left turn, right turn, left lane merge, right lane merge, braking, emergency braking, speed, acceleration, etc. of the vehicle.

[0061] A method for determining the vehicle model, vehicle size parameters, and vehicle driving status based on visual identification is as follows:

[0062] The vehicle interaction information mapped by the visual identification may include one or more of the vehicle size parameters, vehicle model, vehicle driving status and other information. After the visual identification is identified, one or more of the vehicle size parameters, vehicle model, vehicle driving status and other information may be determined based on the corresponding vehicle interaction information.

[0063] Another method to determine the vehicle model and vehicle size parameters based on visual identification is as follows:

[0064] A mapping relationship table is preset, and the mapping relationship table stores the mapping relationship between the arrangement of visual identifications and vehicle models.

[0065] Figure 3-1 , Figure 3-2 The side views of different vehicle models are shown respectively.

[0066] Figure 4-1 , Figure 4-2 The visual logo is displayed on the side of the vehicle body of different models.

[0067] Figure 5-1 , Figure 5-2 They are shown respectively Figure 4-1 , Figure 4-2 Schematic diagram of the visual identity arrangement in .

[0068] Figure 5-1 The arrangement shown is similar to Figure 3-1 There is a mapping relationship between the vehicle models shown; Figure 5-2 The arrangement shown is similar to Figure 3-2 There is a mapping relationship between the vehicle models shown.

[0069] Vehicle B captures an image, identifies multiple visual identifiers in the image, and matches the arrangement of the identified multiple visual identifiers with the arrangement of visual identifiers pre-stored in the database. If the match is successful, the corresponding vehicle model is searched from the mapping relationship table. For example, if the arrangement of the identified multiple visual identifiers matches Figure 5-1 If the arrangement shown is matched successfully, it means that the vehicle model in the image is Figure 3-1 If the arrangement of multiple visual signs identified is different from Figure 5-2 If the arrangement shown matches successfully, it means that the vehicle model in the image is Figure 3-2 Model shown.

[0070] It should be noted that in this solution, when photographing a vehicle, part of the vehicle body may be photographed (for example, only part of the front of the vehicle body is photographed, or only part of the side of the vehicle body is photographed, or only part of the back of the vehicle body is photographed, or only part of the bottom of the vehicle body is photographed, or only part of the top of the vehicle body is photographed), which does not affect the identification of the vehicle model. The following describes the process of identifying the vehicle model by taking only part of the side of the vehicle body as an example.

[0071] The image captured by vehicle B may only capture a portion of the side of vehicle A, so that some visual signs on the side of vehicle A are not captured (e.g. Figure 6-1 , 6-2 , the part in the dotted box is the part that is photographed, and the visual signs outside the dotted box are not photographed), or, although car B captures all the visual signs on the side of car A, due to the problem of low computing power, only some of the visual signs are recognized, but these do not affect the matching result of matching the arrangement of multiple recognized visual signs with the arrangement of visual signs pre-stored in the database. Because the matching process does not require all visual signs to participate in the matching. For example, car B takes an image of car A and only captures part of the side body of car A (such as Figure 6-1 The part in the dotted box), identify the visual logo in the image, and obtain the arrangement of the visual logo as follows Figure 7-1 As shown, Figure 7-1 The visual identity shown is arranged in a similar way to Figure 5-1 , Figure 5-2 The arrangement of the visual identification shown is matched respectively, wherein Figure 5-1 The arrangement of the visual identity shown matches successfully with Figure 5-2 The arrangement of the visual signs shown in the figure fails to match. This means that the model of vehicle A is the same as Figure 5-1 The arrangement of the visual identification shown has a mapping relationship between the vehicle models, namely Figure 3-1 For another example, when car B takes an image of car A, only part of the side body of car A is captured (e.g. Figure 6-2 The part in the dotted box), identify the visual logo in the image, and obtain the arrangement of the visual logo as follows Figure 7-2 As shown, Figure 7-2 The visual identity shown is arranged in a similar way to Figure 5-1 , Figure 5-2 The arrangement of the visual identification shown is matched respectively, wherein Figure 5-2 The arrangement of the visual identity shown matches successfully with Figure 5-1 The arrangement of the visual signs shown in the figure fails to match. This means that the model of vehicle A is the same as Figure 5-2The arrangement of the visual identification shown has a mapping relationship between the vehicle models, namely Figure 3-2 It should be noted that, for the sake of clarity, the size of the visual logo shown in the drawings is larger, and in fact, the size of the visual logo can be smaller, which is more beautiful and achieves the same effect.

[0072] As an optional implementation, the association between the model and the length, width, and height of the vehicle can be pre-stored. After the model is determined according to the arrangement of the recognized visual identifiers, the length, width, and height data associated with the model can be queried to know the length, width, and height of the vehicle.

[0073] As another optional implementation, the association between the vehicle model and the length, width, and height of the vehicle does not need to be pre-stored. After the vehicle model is determined based on the arrangement of the identified visual markers, the length, width, and height of the vehicle are determined based on the size and / or area of ​​the visual markers in the image. The size and / or area of ​​the visual markers are known, and the length, width, and height of the vehicle are calculated based on the actual size of the visual markers, the number of pixels occupied by the visual markers in the image, and the number of pixels occupied by the vehicle body in the image. For example Figure 8 As shown, pd / pD=d / D...Formula (1), where pd represents the number of pixels occupied by a visual marker in the image, pD represents the number of pixels occupied by the vehicle body width in the image, d represents the actual size of the visual marker, and D represents the actual body width of the vehicle. Wherein, pd can be obtained from the captured image, pD can be determined by the two visual markers that are farthest apart in the horizontal direction, d is known, and the actual body width D can be calculated according to Formula (1).

[0074] As an optional implementation, the relative positions of the imaging devices of vehicle A and vehicle B can be determined based on the visual identification, and the relative positions include angles and distances.

[0075] As mentioned above, the imaging device and vehicle B remain relatively stationary during driving, and the relative position between the imaging device and vehicle B is known. Thus, if the position of vehicle A relative to the imaging device can be calculated, the position of vehicle A relative to vehicle B can be obtained through simple calculation.

[0076] In the embodiment provided by the present invention, the vehicle distance can be calculated with one image. In an exemplary embodiment of the present invention, a processor disposed in the first vehicle pre-stores a mapping relationship between the size of the visual identifier in the image and the distance, an imaging device disposed in the first vehicle captures the image, and the processor determines whether there is a visual identifier in the captured image, and if there is a visual identifier, it is determined that there is a second vehicle in the field of view, and the vehicle distance between the first vehicle and the second vehicle is determined based on the visual identifier. The specific steps for the processor to determine the vehicle distance include: determining the size of the visual identifier in the image; searching for a mapping relationship to obtain a distance that has a mapping relationship with the size of the visual identifier in the image; and determining the distance found to be the vehicle distance between the first vehicle and the second vehicle.

[0077] In a specific embodiment, a processor disposed on the first vehicle pre-stores a mapping relationship between the size of multiple points on one or more visual identifiers in an image and the vehicle distance. An imaging device disposed on the first vehicle captures an image, and the processor determines whether there is a visual identifier in the captured image. If there is a visual identifier, it is determined that a second vehicle exists within the field of view, and the vehicle distance between the first vehicle and the second vehicle is determined based on the visual identifier. The specific steps for the processor to determine the vehicle distance include: determining the size of multiple points on one or more visual identifiers in an image; searching for a mapping relationship to obtain a distance that has a mapping relationship with the size of multiple points on one or more visual identifiers in an image; and determining the distance found as the vehicle distance between the first vehicle and the second vehicle.

[0078] As an optional embodiment, the sizes of the visual signs displayed on different vehicles are the same and known.

[0079] The size / area of ​​the visual marker in the image is negatively correlated with the vehicle distance. The larger the vehicle distance, the smaller the size / area of ​​the visual marker in the image. In this solution, the vehicle is located according to the visual marker, and then the vehicle distance is calculated according to the size / area of ​​the visual marker in the image.

[0080] The camera installed on vehicle B captures the surrounding environment to obtain an RGB color image, which is processed according to preset steps. Specifically, the RGB color image is converted into a grayscale image and an HSV (hue, saturation, brightness) color image. The RGB color image is binarized according to the grayscale image and the HSV color image, and the binarized image is filtered and denoised, and then a closing operation is performed to obtain multiple closed blocks with smooth contours. The closed blocks are visual identifiers.

[0081] As mentioned above, the arrangement of visual identifiers is pre-stored in the database, and the arrangement of multiple identified visual identifiers is matched with the arrangement of visual identifiers pre-stored in the database, and the model of vehicle A is determined based on the matching result. During the matching process, a problem may arise: due to the shooting angle of the imaging device of vehicle B (for example, the body of vehicle A is not facing the imaging device of vehicle B), after the arrangement of visual identifiers is identified from the image captured by the imaging device of vehicle B, it cannot be successfully matched with any arrangement pre-stored in the database. In order to solve this problem, image correction is performed before matching. The correction process is described in detail below.

[0082] The correction process involves two images. One is an image taken of vehicle B, which is obtained by processing the image according to the preset steps described above and contains closed blocks. It is called the image to be corrected. The other is an image pre-stored in the database, which is called the reference image. The reference image contains a visual marker, and the reference image is obtained by taking a camera facing the visual marker.

[0083] A plurality of points are determined in the reference image as first correction identification points. A first coordinate system is established, and the coordinates of each first correction identification point in the first coordinate system are determined.

[0084] A number of points are determined in the image to be corrected as second correction identification points. A second coordinate system is established based on preset rules. The preset rules may be the relationship between pixels and coordinate positions. The preset rules may, for example, specify the relationship between the image to be corrected and the coordinate positions of different image resolutions. The image resolution refers to the amount of information stored in the image, which is how many pixels there are per inch of the image. The unit of resolution is PPI (Pixels Per Inch), which is usually called pixels per inch. After the second coordinate system is established, the coordinates of each second correction identification point in the second coordinate system are determined. As an optional implementation, multiple second correction identification points in the image to be corrected are obtained by image recognition. The positions of the multiple second correction identification points in the image to be corrected are determined. Specifically, the pixel numbers of the multiple second correction identification points in the image to be corrected are obtained, and the positions in the image to be corrected are determined according to the pixel numbers. The pixel numbers may be in the form of a horizontal axis number combined with a vertical axis number. It is worth mentioning that the second correction identification point may occupy multiple pixel positions in the image to be corrected according to different image resolutions. In this case, the central pixel point may be determined based on the multiple pixel points as the position of the second correction identification point. The coordinates of the plurality of second correction identification points in the second coordinate system are generated based on the plurality of positions. More specifically, the image resolution of the image to be corrected can be first obtained, and then the positions of the plurality of second correction identification points in the image to be corrected can be obtained by image recognition, and then the coordinates of the plurality of second correction identification points in the second coordinate system can be determined according to a preset rule.

[0085] It should be noted that the number of the first correction identification points and the second correction identification points are the same and have a one-to-one correspondence. For example, there are m first correction identification points, namely, the first correction identification point d1, the first correction identification point d2, ..., the first correction identification point dm. There are also m second correction identification points, namely, the second correction identification point d1′, the second correction identification point d2′, ..., the second correction identification point dm′. The first correction identification point d1 has a corresponding relationship with the second correction identification point d1′; the first correction identification point d2 has a corresponding relationship with the second correction identification point d2′; ...; the first correction identification point dm has a corresponding relationship with the second correction identification point dm′.

[0086] There is no unique way to select the first correction identification point and the second correction identification point, and different selection methods may have a certain impact on the accuracy of image correction. A preferred selection method is to select the first correction identification point according to the shape of the visual identifier contained in the reference image. For example, assuming that the shape of the visual identifier contained in the reference image is a triangle, the three vertices of the visual identifier can be used as the first correction identification point; for another example, if the shape of the visual identifier contained in the reference image is a quadrilateral, the four vertices of the visual identifier can be used as the first correction identification point. The second correction identification point is selected according to the shape of the closed block contained in the image to be corrected. For example, assuming that the shape of the closed block is a triangle, the three vertices of the closed block can be used as the second correction identification points; for another example, if the shape of the closed block is a quadrilateral, the four vertices of the closed block can be used as the second correction identification points.

[0087] Select m groups of correction identification points, each group of correction identification points includes a first correction identification point and a second correction identification point, for example, the first group of correction identification points includes a first correction identification point d1 and a second correction identification point d1′; the second group of correction identification points includes a first correction identification point d2 and a second correction identification point d2′; ...; the mth group of correction identification points includes a first correction identification point dm and a second correction identification point dm′. Compare the coordinates of the first correction identification point in each group of correction identification points in the first coordinate system with the coordinates of the second correction identification point in the second coordinate system, and establish a coordinate mapping relationship between the first coordinate system and the second coordinate system.

[0088] According to the coordinate mapping relationship between the first coordinate system and the second coordinate system, and the coordinates of each pixel in the image to be corrected in the second coordinate system, the coordinates of each pixel in the image to be corrected in the first coordinate system are calculated. For example, for any pixel si′ (1≤i≤n) among the pixel s1′, the pixel s2′, the pixel s3′, ..., the pixel sn′ in the image to be corrected, the coordinates of the pixel si′ in the second coordinate system are (x1′, y1′), and according to the coordinate mapping relationship between the first coordinate system and the second coordinate system, the coordinates of the pixel si′ in the first coordinate system are determined (xi, yi). The corrected image is generated according to the coordinates of each pixel in the image to be corrected in the first coordinate system.

[0089] As mentioned above, the arrangement of the identified multiple visual identifiers is matched with the arrangement of the visual identifiers pre-stored in the database, so as to determine the model of the vehicle A according to the matching result. In an optional implementation, the image to be corrected is first corrected to obtain a corrected image, the arrangement of the multiple visual identifiers in the corrected image is determined, and the arrangement of the multiple visual identifiers in the corrected image is matched with the arrangement of the visual identifiers pre-stored in the database, so as to determine the model of the vehicle A according to the matching result. By correcting the image first and then matching it, the problem of low matching success rate caused by shooting angle problems is solved.

[0090] The preset mapping table stores the relationship between the pixel value of the visual mark in the image and the distance. "Distance" refers to the distance between the visual mark of car A and the imaging device of car B. The distance between car A and car B can be simply converted from the above "distance".

[0091] One image can calculate the distance between vehicles, and two images can calculate the speed V of vehicle A relative to vehicle B. AB , and the speed V of vehicle A relative to the ground A At time t1, vehicle B takes an image and obtains image P1. From image P1, a visual identifier is obtained, thereby determining that the image area where the visual identifier is located is the body image of vehicle A. Based on image P1, the vehicle distance s1 at time t1 can be calculated. At time t2, vehicle B takes an image and obtains image P2. From image P2, a visual identifier is obtained, thereby determining that the image area where the visual identifier is located is the body image of vehicle A. Based on image P2, the vehicle distance s2 at time t2 can be calculated. The speed V of vehicle A relative to vehicle B AB =(s2-s1) / (t2-t1), V AB It can be positive or negative. If the speed of car A is greater than that of car B, then V AB is a positive number; if the speed of car A is less than that of car B, then V AB is a negative number. A 、V Bdenote the speeds of car A and car B respectively, then the speed of car A is V A =V B +V AB , so we get the speed V of car A A It should be noted that the speed of car A V A It is the average speed of car A in the time interval between t1 and t2. Since the time interval between t1 and t2 is very small, the instantaneous speed in the time interval between t1 and t2 can be approximately equal to the average speed in the time interval.

[0092] Three images can be used to calculate the acceleration a of car A relative to car B AB , and the acceleration a of car A relative to the ground. At time t1, car B captures an image to obtain image P1, and obtains the visual identifier from image P1, thereby determining that the image area where the visual identifier is located is the body image of car A. Based on image P1, the vehicle distance s1 at time t1 can be calculated. At time t2, car B captures an image to obtain image P2, and obtains the visual identifier from image P2, thereby determining that the image area where the visual identifier is located is the body image of car A. Based on image P2, the vehicle distance s2 at time t2 can be calculated. At time t3, car B captures an image to obtain image P3, and obtains the visual identifier from image P3, thereby determining that the image area where the visual identifier is located is the body image of car A. Based on image P3, the vehicle distance s3 at time t3 can be calculated. Using the method described in the previous paragraph, the average speed V of car A in the time interval between time t1 and time t2 can be calculated. A1 , which can be regarded as the instantaneous speed at (t2+t1) / 2; the average speed of car A in the time interval between t2 and t3 is V A2 , the average speed can be regarded as the instantaneous speed at (t3+t2) / 2, and a is used to represent the average acceleration of vehicle A in the time interval between t1 and t3, a=(V A2 -V A1 ) / Δt, Δt is the time interval between (t3+t2) / 2 and (t2+t1) / 2, Δt=(t3+t2) / 2-(t2+t1) / 2=(t3-t1) / 2. From this, we can calculate the average acceleration a of car A in the time interval between t1 and t3. The average acceleration a of car A in the time interval between t1 and t3 relative to car B AB The calculation method is: Using the method described in the previous paragraph, the time interval between time t1 and time t2 of vehicle A relative to the average speed V of vehicle B can be calculated. AB1 The time interval between time t2 and time t3 of vehicle A relative to the average speed V of vehicle B AB2 , use a ABrepresents the average acceleration of car A relative to car B during the time interval from t1 to t3, a AB =(V AB2 -V AB1 ) / Δt, Δt is the time interval between (t3+t2) / 2 and (t2+t1) / 2, Δt=(t3+t2) / 2-(t2+t1) / 2=(t3-t1) / 2. From this, we can calculate the average acceleration a of vehicle A in the time interval between t1 and t3 relative to vehicle B. AB .

[0093] As an optional implementation, if the driving direction of vehicle A is not parallel to the driving direction of vehicle B (for example Fig. 9 As shown in the figure, vehicle B photographs vehicle A, and after extracting the visual identifiers in the image, n (n≥1) visual identifiers are obtained. Since the different visual identifiers displayed on the body of vehicle A are at different distances from the imaging device of vehicle B, the sizes of the visual identifiers in the image are different, and the size of the visual identifier in the image is negatively correlated with the distance of the visual identifier from vehicle B, that is, the visual identifier with a smaller distance from the imaging device of vehicle B is larger in size in the image; the visual identifier with a larger distance from the imaging device of vehicle B is smaller in size in the image.

[0094] Determine the sizes of the n visual identifiers, and select the visual identifier with the largest size. Assuming that visual identifier m (1≤m≤n) is the visual identifier with the largest size, then determine visual identifier m as the visual identifier closest to vehicle B. According to the method described above, calculate the distance between the imaging device of vehicle B and vehicle A based on the size of visual identifier m. As an optional implementation, when the computing power is low, only the distance between visual identifier m and vehicle B can be calculated, and the distances between the remaining n-1 visual identifiers and the imaging device of vehicle B are no longer calculated, and the distance between visual identifier m and vehicle B is used as the distance between the two vehicles. As another optional implementation, when the computing power is high, the distances between multiple visual identifiers or even all n visual identifiers and vehicle B can also be calculated. The orientation of vehicle A relative to vehicle B can be calculated based on the distances between multiple visual identifiers or all n visual identifiers and vehicle B.

[0095] As an optional implementation, the vehicle displays a visual identifier corresponding to the vehicle interaction information on a display device, and transmits the vehicle's speed, acceleration and other driving status information to other vehicles. Vehicle B can learn the driving status information of vehicle A based on the visual identifier by photographing the content displayed on the display device and identifying the visual identifier displayed on the display device.

[0096] As an optional implementation, the visual identification can be dynamic, and the vehicle transmits the information of the vehicle to other vehicles through the visual identification, thereby playing the role of broadcasting. For example, vehicle A transmits the driving status information of the vehicle to other vehicles through the change of the characteristics (color, shape, frequency, etc.) of the light emitted by the display device. The mapping relationship between the characteristics of the light emitted by the display device and the driving status information is pre-stored in vehicle B. Vehicle B takes a picture of the content displayed by the display device, identifies the characteristics of the light emitted by the display device, and can understand the driving status information of vehicle A based on the characteristics of the light emitted by the display device.

[0097] The vehicle can determine the vehicle interaction information through the visual identification displayed on the other vehicle, and the vehicle interaction information is transmitted to the vehicle by the other vehicle through the visual identification. The vehicle can also transmit the vehicle interaction information to the other vehicle through the visual identification displayed on its own body.

[0098] The vehicle's processor pre-stores a vehicle interaction information mapping rule, which is used to indicate the mapping relationship between the visual identifier and the vehicle interaction information. After the vehicle obtains the visual identifier displayed on the other vehicle, it searches for the vehicle interaction information that has a mapping relationship with the other vehicle's visual identifier from the vehicle interaction information mapping rule, so that the vehicle knows the vehicle interaction information that the other vehicle wants to transmit. When the vehicle needs to transmit vehicle interaction information to the other vehicle, the vehicle first determines the vehicle interaction information that needs to be transmitted, then searches for the visual identifier that has a mapping relationship with the vehicle interaction information that needs to be transmitted from the vehicle interaction information mapping rule, and then displays the found visual identifier on the body of the vehicle.

[0099] As an optional implementation, the vehicle interaction information mapping rule is used to indicate the mapping relationship between the arrangement of visual identifiers and the vehicle interaction information, and the arrangement of visual identifiers that has a mapping relationship with the vehicle interaction information that needs to be transmitted is searched from the vehicle interaction information mapping rule. Different vehicle interaction information can be transmitted in different arrangement methods. For example, when three visual identifiers are arranged in the form of three vertices of a triangle, one type of vehicle interaction information can be transmitted; and when three visual identifiers are arranged in the form of three points on a line segment, another type of vehicle interaction information can be transmitted. The vehicle interaction information can be determined based on the arrangement of the acquired visual identifiers and the vehicle interaction information mapping rule. The arrangement of visual identifiers that has a mapping relationship with the vehicle interaction information that needs to be transmitted can be searched from the vehicle interaction information mapping rule; and the visual identifier can be displayed on the body of the vehicle in the found arrangement method.

[0100] During the process of autonomous driving, the imaging device installed on the body of car B takes pictures of the surrounding environment. The captured image is identified. If the image contains a visual identifier, the image area where the visual identifier is located is determined to be the image of the body of car A. Car B identifies car A by identifying the visual identifier displayed on the body of car A. The processor of car B stores vehicle interaction information mapping rules. Car B determines vehicle interaction information based on the acquired visual identifier and vehicle interaction information mapping rules. The vehicle interaction information is the information that car A wants to transmit to car B. Car B can also transmit vehicle interaction information to car A in the same way, so that the vehicle can both publish vehicle interaction information to other vehicles and receive vehicle interaction information published by other vehicles, achieving a technical effect of two-way interaction.

[0101] It should be noted that there is no necessary precedence relationship between determining the vehicle interaction information based on the acquired visual identification and the vehicle interaction information mapping rules and determining the presence of the second vehicle within the field of view in the above step S102. As an optional implementation, it is possible to first determine the presence of the second vehicle within the field of view, and then determine the vehicle interaction information based on the acquired visual identification and the vehicle interaction information mapping rules; as another optional implementation, it is possible to first determine the vehicle interaction information based on the acquired visual identification and the vehicle interaction information mapping rules, and then determine the presence of the second vehicle within the field of view; as yet another optional implementation, it is possible to determine the presence of the second vehicle within the field of view while determining the vehicle interaction information based on the acquired visual identification and the vehicle interaction information mapping rules.

[0102] The inventors consider that if vehicles transmit information through a server, once the network is interrupted or attacked, vehicles cannot transmit information, which may easily lead to large-scale traffic accidents. In the present invention, whether a vehicle transmits its own information to other vehicles or vehicles exchange information with each other, there is no need to use a server, but visual identification is used to directly interact through a terminal set on the vehicle, thereby avoiding the above problem.

[0103] The present invention also provides a vehicle automatic driving method, which includes two steps: step one, using the above method to identify the second vehicle through visual identification; step two, determining the driving strategy of the first vehicle based on the identification result.

[0104] After vehicle B recognizes vehicle A based on the visual signs displayed on vehicle A, it can determine its own driving strategy based on the recognition results and take corresponding measures, such as braking, overtaking, decelerating, accelerating, and exchanging information with vehicle A, thereby improving the safety and flexibility of autonomous driving.

[0105] The present invention also provides a vehicle identification system, including: a terminal, and an imaging device connected to the terminal. An imaging device and a terminal are provided on a vehicle, and the terminal includes a processor. For example, an imaging device and a terminal are provided on vehicle B, and during the automatic driving process of vehicle B, the surrounding environment is photographed by an imaging device installed on the body of vehicle B. The imaging device can be a camera. The imaging device can be installed on the top of vehicle B, and the imaging device and vehicle B remain relatively still during driving. A processor is provided in the terminal, and the function of the processor includes recognizing an image. If the processor of the terminal recognizes a visual identification from the image taken by the imaging device, the processor determines that there is a vehicle within the field of view of the imaging device (of course, the premise is that a visual identification is displayed on the body of the identified vehicle).

[0106] The vehicle identification system may also include visual identification, that is, in addition to an imaging device and a terminal, a set of visual identification may be displayed on the vehicle. The specific display method is as described above and will not be repeated here. For example, if an imaging device and a terminal are installed on vehicle B, and a visual identification is also displayed on the body of vehicle B, then vehicle B can not only identify other vehicles through the visual identification, but also be identified by other vehicles through the visual identification displayed on its own body.

[0107] In the case where both vehicles are provided with the vehicle identification system provided by the present invention, the two vehicles can exchange information. For example, the body of vehicle A displays a visual identification. During the process of automatic driving of vehicle B, the imaging device installed on the body of vehicle B takes pictures of the surrounding environment. The processor set in the terminal of vehicle B recognizes the image obtained by the shooting. If the image is identified to contain a visual identification, it is determined that there is a vehicle within the field of view of the imaging device of vehicle B, so that vehicle A is identified. After vehicle B recognizes vehicle A, the driving state of vehicle A can be obtained (the specific method is as described above), and when necessary, vehicle B can exchange information with vehicle A. For example, vehicle B calculates that the speed of vehicle A is small, and vehicle B wants to overtake, then the terminal set in vehicle B uses the visual identification to send vehicle interaction information to the terminal set in vehicle A. After the terminal set in vehicle A receives the vehicle interaction information, it can be known that vehicle B wants to overtake. This achieves the effect that vehicle B can exchange information with vehicle A. Similarly, vehicle A can also recognize vehicle B and send information to vehicle B using the visual identification, thereby achieving the effect of two-way interaction.

[0108] In this solution, when car B recognizes car A, if it wants to change its own driving status, such as braking, overtaking, decelerating, accelerating, etc., it can interact with car A to let the surrounding vehicles know the next driving operation of the car, thereby improving driving safety and flexibility.

[0109] Those skilled in the art will appreciate that all or part of the steps for implementing the above embodiments are implemented as a computer program executed by a CPU. When the computer program is executed by the CPU, the above functions defined by the above method provided by the present invention are performed. The program may be stored in a computer-readable storage medium, which may be a read-only memory, a disk, or an optical disk, etc.

[0110] In addition, it should be noted that the above-mentioned figures are only schematic illustrations of the processes included in the method according to an exemplary embodiment of the present invention, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0111] Fig.10 It is a block diagram of an electronic device according to an exemplary embodiment.

[0112] Refer to the following Fig.10 The electronic device 1000 according to this embodiment of the present invention will be described. Fig.10 The electronic device 1000 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0113] like Fig.10 As shown, the electronic device 1000 is in the form of a general computing device. The components of the electronic device 1000 may include but are not limited to: at least one processing unit 1010, at least one storage unit 1020, a bus 1030 connecting different system components (including the storage unit 1020 and the processing unit 1010), etc.

[0114] The storage unit stores program codes, and the program codes can be executed by the processing unit 1010, so that the processing unit 1010 executes the steps described in this specification according to one or several exemplary embodiments of the present invention.

[0115] The storage unit 1020 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 10201 and / or a cache memory unit 10202 , and may further include a read-only memory unit (ROM) 10203 .

[0116] The storage unit 1020 may also include a program / utility 10204 having a set (at least one) of program modules 10205, such program modules 10205 including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include the implementation of a network environment.

[0117] Bus 1030 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0118] The electronic device 1000 may also communicate with one or more external devices 1000' (e.g., keyboards, pointing devices, Bluetooth devices, etc.) to enable a user to communicate with the electronic device 1000, and / or any device (e.g., routers, modems, etc.) that the electronic device 1000 can communicate with one or more other computing devices. Such communication may be performed via an input / output (I / O) interface 1050. In addition, the electronic device 1000 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 1060. The network adapter 1060 may communicate with other modules of the electronic device 1000 via the bus 1030. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 1000, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0119] Through the above description of the implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by combining software with necessary hardware. Fig.11 As shown, the technical solution according to the embodiment of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes a number of instructions to enable a computing device (which can be a personal computer, or a network device, etc.) to execute the above method according to the embodiment of the present invention.

[0120] The software product may be any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, a system, device or component of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0121] The computer readable storage medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by an instruction execution system, an apparatus, or a device or used in combination with it. The program code contained on the readable storage medium may be transmitted with any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

[0122] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on the remote computing device. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0123] The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by a device, the computer-readable medium realizes the following functions: photographing the second vehicle to obtain an image, wherein a visual marker is set on the body of the second vehicle; obtaining the visual marker from the image, and determining that the area where the visual marker is located is the body of the second vehicle.

[0124] Those skilled in the art will appreciate that the above modules can be distributed in the device according to the description of the embodiment, or can be changed accordingly and only used in one or more devices different from the embodiment. The modules of the above embodiments can be combined into one module, or further divided into multiple sub-modules.

[0125] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the exemplary embodiments described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the embodiment of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a mobile terminal, or a network device, etc.) to execute the method according to the embodiment of the present invention.

[0126] The exemplary embodiments of the present invention are specifically shown and described above. It should be understood that the present invention is not limited to the detailed structure, configuration or implementation method described herein; on the contrary, the present invention is intended to cover various modifications and equivalent configurations included in the spirit and scope of the appended claims.

Claims

1. A method for identifying a second vehicle with a visual identifier, characterized in that: The method comprises: The imaging device captures an image; The processor determines whether the visual identifier exists in the image, and if so, determines that the second vehicle exists within the field of view.

2. The method according to claim 1, characterized in that The visual identity is displayed through: Placing, affixing, or mounting identification objects on the body of a vehicle to display visual identification; or painting visual identification on the body of the vehicle; or Mounting a display device on the body of the vehicle for displaying the visual identification; or Use the vehicle's onboard lighting, body decoration, vehicle license plate or onboard display device to display visual identification.

3. The method according to claim 1, characterized in that The processor pre-stores a vehicle interaction information mapping rule, wherein the vehicle interaction information mapping rule is used to indicate a mapping relationship between a visual identifier and vehicle interaction information. The method further includes: The vehicle interaction information is determined according to the acquired visual identification and the vehicle interaction information mapping rule.

4. The method according to claim 1, characterized in that: The processor pre-stores a vehicle interaction information mapping rule, wherein the vehicle interaction information mapping rule is used to indicate a mapping relationship between a visual identifier and vehicle interaction information. The method further includes: Determine the vehicle interaction information that needs to be transmitted; Searching the vehicle interaction information mapping rule for a visual identifier having a mapping relationship with the vehicle interaction information to be transmitted; Display the found visual identification on the body of the vehicle.

5. The method according to claim 4, characterized in that The vehicle interaction information mapping rule is used to indicate the mapping relationship between the arrangement of visual identification and vehicle interaction information. Searching the vehicle interaction information mapping rule for a visual identifier having a mapping relationship with the vehicle interaction information to be transmitted; Display the found visual signs on the body of the vehicle, including: Searching for an arrangement of visual identifiers having a mapping relationship with the vehicle interaction information to be transmitted from the vehicle interaction information mapping rule; Display visual identifiers on the body of the vehicle in the found arrangement.

6. The method according to any one of claims 1 to 5, characterized in that The imaging device is disposed on the first vehicle, and the method further comprises: At least one of the following is determined based on the visual identification: a driving state of the second vehicle, a vehicle size parameter of the second vehicle, a model of the second vehicle, and a relative position between the first vehicle and the second vehicle.

7. The method according to claim 6, characterized in that The processor pre-stores a mapping relationship between the size of multiple points on one or more visual markers in the image and the vehicle distance, wherein the relative position includes the vehicle distance, Determining the relative position between the first vehicle and the second vehicle according to the visual identifier includes: Determine the size of multiple points on the one or more visual identifiers in the image; find a mapping relationship to obtain a distance that has a mapping relationship with the size of multiple points on the one or more visual identifiers in the image; and determine the found distance as the vehicle distance between the first vehicle and the second vehicle.

8. A method for automatic vehicle driving, characterized in that: include: Step 1: Identify the second vehicle using the method described in any one of claims 1 to 7; Step 2: Determine the driving strategy of the first vehicle according to the recognition result.

9. A vehicle identification system, characterized in that: include: An imaging device and a first terminal are arranged in a first vehicle, wherein the first terminal includes a processor, and the imaging device and the processor are used to implement the method as described in any one of claims 1-7.

10. The system according to claim 9, characterized in that The second vehicle is provided with a second terminal, and the second terminal is used to send vehicle interaction information to the first terminal and / or receive vehicle interaction information sent by the first terminal.

11. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

12. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images