Verification method and device based on vehicle-mounted environment and electronic equipment

Abstract

The embodiment of the invention relates to the technical field of vehicles, and provides a verification method and device based on a vehicle-mounted environment and electronic equipment. The method comprises the following steps: acquiring a first image containing a target user and a second image containing a collection code based on a vehicle entering a target area; determining the sight direction of the target user based on the first image; determining a first position of the collection code based on the second image; and verifying the target user based on the matching relationship between the sight direction of the target user and the first position of the collection code. According to the method, payment verification can be automatically completed, manual operation of a driver is not needed, operation steps can be simplified, payment efficiency can be improved, it can be guaranteed that the driver is not distracted in the driving process, and driving safety is improved.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of vehicles, and particularly relates to a verification method and device based on a vehicle-mounted environment and an electronic device. BACKGROUND

[0002] When a vehicle passes a toll gate of a parking lot, the vehicle needs to be parked and a toll payment operation is performed. The existing toll payment method usually requires the driver to use a mobile phone or the like to perform code scanning payment. Specifically, the driver needs to perform the following operation steps in sequence: parking, taking out the mobile phone, opening the mobile phone payment application, scanning the toll payment two-dimensional code, inputting the payment password, waiting for the password verification to be completed, and driving away. SUMMARY

[0003] The current toll payment verification method requires the driver to perform multiple operation steps, which is cumbersome and inefficient, and may also affect the smoothness of traffic flow. Moreover, since the payment and driving operations are cross-operated, safety problems are also likely to be caused.

[0004] To solve the above technical problems, the present disclosure provides a verification method and device based on a vehicle-mounted environment and an electronic device, which can automatically complete the toll payment verification without the driver manually performing the above steps.

[0005] In a first aspect, the present disclosure provides a verification method based on a vehicle-mounted environment, the method comprising: based on a vehicle entering a target area, acquiring a first image containing a target user and a second image containing a payment code; determining a line-of-sight direction of the target user based on the first image; determining a first position of the payment code based on the second image; and verifying the target user based on a matching relationship between the line-of-sight direction of the target user and the first position of the payment code.

[0006] In a second aspect, the present disclosure provides a verification device based on a vehicle-mounted environment, the device comprising: a signal acquisition component comprising a first camera and a second camera; the first camera is configured to acquire a first image containing a target user based on a vehicle entering a target area; the second camera is configured to acquire a second image containing a payment code based on the vehicle entering the target area; and one or more processors configured to run instructions stored in a memory to determine a line-of-sight direction of the target user based on the first image; determine a first position of the payment code based on the second image; and verify the target user based on a matching relationship between the line-of-sight direction of the target user and the first position of the payment code.

[0007] In a third aspect, the present disclosure provides a computer-readable storage medium storing a computer program for executing the verification method based on a vehicle-mounted environment provided in the first aspect.

[0008] In a fourth aspect, the electronic device is provided. The electronic device includes a processor, and a memory storing processor-executable instructions. The processor is configured to read the executable instructions from the memory and execute the executable instructions to implement the vehicle environment-based verification method according to the first aspect.

[0009] According to the vehicle environment-based verification method provided by the present disclosure, when a vehicle enters a target area such as a toll area of a parking lot, a first image containing a target user and a second image containing a collection code are collected respectively, and the line-of-sight direction of the target user is determined based on the first image, and the first position of the collection code is determined based on the second image. Thereafter, the verification of the fixation object of the target user is performed, specifically, whether the target user is fixating on the collection code is determined based on the matching relationship between the line-of-sight direction of the target user and the first position of the collection code. If the target user is fixating on the collection code, the target user is verified, and then the account corresponding to the target user is automatically used to pay the toll after the verification is passed. In this way, the driver can complete the toll without operating the mobile phone, which can simplify the operation steps, improve the toll efficiency, and ensure that the driver does not distract during driving, thereby improving the driving safety. In addition, the present disclosure performs two rounds of verification before the toll, which are the verification of the fixation object and the verification of the target user, respectively. In this way, the safety of the toll operation can be ensured. BRIEF DESCRIPTION OF DRAWINGS

[0010] The above and other objects, features and advantages of the present disclosure will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings in which:

[0011] Figure 1 is a structural block diagram of a vehicle environment-based verification system provided by an exemplary embodiment of the present disclosure;

[0012] Figure 2 is a flowchart of a vehicle environment-based verification method provided by an exemplary embodiment of the present disclosure;

[0013] Figure 3 is a flowchart of a vehicle environment-based verification method provided by another exemplary embodiment of the present disclosure;

[0014] Figure 4 is a flowchart of a vehicle environment-based verification method provided by still another exemplary embodiment of the present disclosure;

[0015] Figure 5 is a schematic diagram of a target vector range provided by an exemplary embodiment of the present disclosure;

[0016] Figure 6 is a schematic diagram of a target vector range provided by another example embodiment of the present disclosure;

[0017] Figure 7 is a schematic diagram of a matching relationship between a line-of-sight direction and a first position provided by an example embodiment of the present disclosure;

[0018] Figure 8 is a flowchart of a verification method based on a vehicle-mounted environment provided by a fourth example embodiment of the present disclosure;

[0019] Figure 9 is a schematic diagram of a line-of-sight depth and a target distance provided by an example embodiment of the present disclosure;

[0020] Figure 10 is a flowchart of a verification method based on a vehicle-mounted environment provided by a fifth example embodiment of the present disclosure;

[0021] Figure 11 is a flowchart of a verification method based on a vehicle-mounted environment provided by a sixth example embodiment of the present disclosure;

[0022] Figure 12 is a flowchart of a verification method based on a vehicle-mounted environment provided by a seventh example embodiment of the present disclosure;

[0023] Figure 13 is a schematic diagram of a verification device based on a vehicle-mounted environment provided by an example embodiment of the present disclosure;

[0024] Figure 14 is a schematic diagram of an electronic device provided by an example embodiment of the present disclosure. DETAILED DESCRIPTION

[0025] Hereinafter, example embodiments according to the present disclosure will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, and not all embodiments of the present disclosure. It should be understood that the present disclosure is not limited to the example embodiments described herein.

[0026] It should be noted that: unless otherwise specifically stated, the relative arrangement, numerical expressions and values of the components and steps set forth in these embodiments do not limit the scope of the present disclosure.

[0027] Summary

[0028] When a vehicle passes a toll gate of a parking lot, the vehicle needs to stop and perform a toll payment operation. The existing toll payment method usually requires the driver to use a mobile phone or the like to perform a code scanning payment. Specifically, the driver needs to perform the following operation steps in sequence: stopping, taking out the mobile phone, opening a mobile payment application, scanning a toll payment code, inputting a payment password, waiting for the password verification to be completed, and driving away. This series of operation steps is tedious and inefficient, not only consuming the time and energy of the driver, but also possibly causing traffic accidents due to the driver operating the mobile phone during driving, affecting road safety and traffic flow.

[0029] To solve this problem, there are mainly two existing solutions. One solution is a traditional manual payment operation, which, although does not require the driver to be distracted by operating the mobile phone during driving, is also tedious and inefficient. The other solution is that a vehicle-mounted camera scans a payment code to trigger a payment process and use the driver's account to pay the toll. Although this solution is simple to operate, it does not consider the payment willingness of the driver, which may easily lead to mistaken payment and thus is less secure.

[0030] Embodiments of the present disclosure provide a new solution that can solve the problems caused by the driver's mobile phone code scanning payment method and does not introduce new problems as in the above two solutions. Specifically, embodiments of the present disclosure provide a verification method based on a vehicle-mounted environment, which can capture a first image containing a target user and a second image containing a payment code when a vehicle enters a target area such as a toll area of a parking lot, determine a line of sight direction of the target user based on the first image, and determine a first position of the payment code based on the second image. Thereafter, the target user's gaze object is verified, specifically, whether the target user is gazing at the payment code is determined based on the matching relationship between the line of sight direction of the target user and the first position of the payment code. If the target user is gazing at the payment code, the target user is verified, and then the toll is automatically paid using the account corresponding to the target user after the verification is passed. In this way, the driver can complete the payment without operating the mobile phone, which not only simplifies the operation steps and improves the payment efficiency, but also ensures that the driver does not be distracted during driving and improves the driving safety. In addition, the present disclosure performs two rounds of verification before the payment, which are the verification of the gaze object and the verification of the target user, which can ensure the safety of the payment operation.

[0031] Exemplary system

[0032] Figure 1 FIG. 1 is a structural block diagram of a verification system based on a vehicle-mounted environment provided by an exemplary embodiment of the present disclosure.

[0033] As shown in FIG. 1, the verification system based on a vehicle-mounted environment includes a vehicle-mounted camera 10, a vehicle-mounted processor 20, a vehicle-mounted storage 30, a vehicle-mounted communication interface 40, and a vehicle-mounted power supply 50. Figure 1As shown, in one embodiment, the in-vehicle environment-based verification system can include a collection system 10 and a payment verification system 20, and the payment verification system 20 and the collection system 10 perform data transmission.

[0034] The collection system 10 can include at least one sensor for collecting a first image containing a target user and a second image containing a payment code. The sensor can be an image sensor, such as a camera, an infrared sensor, etc. The collection system 10 can perform data transmission with the payment verification system 20, for example, the collection system 10 sends the collected first image and second image to the payment verification system 20.

[0035] In some implementations, the image sensor can be multiple, such as two image sensors, respectively arranged in the vehicle and outside the vehicle. In this way, the image sensor arranged in the vehicle can be used to collect the first image containing the target user, and the image sensor arranged outside the vehicle can be used to collect the second image containing the payment code.

[0036] The payment verification system 20 can determine the line-of-sight direction of the target user based on the first image collected by the collection system 10, determine the first position of the payment code based on the second image collected by the collection system 10, and determine whether the target user is gazing at the payment code based on the matching relationship between the line-of-sight direction of the target user and the first position of the payment code. If the target user is gazing at the payment code, the target user is verified, and then the payment is automatically made using the account corresponding to the target user after the verification is passed.

[0037] The payment verification system 20 can include a processor and a memory, and the processor is configured to execute instructions stored in the memory to implement the in-vehicle environment-based verification method. The processor can be one or more general-purpose processors, such as a CPU, or a special-purpose processor, such as an ASIC, an FPGA, etc. The memory is configured to store instructions and data executable by the processor, such as line-of-sight direction data of the target user, position data of the payment code, etc.

[0038] In one implementation, the payment verification system 20 can include one or more processors 201. The processor 201 can include a general-purpose processor, such as a central processing unit (CPU), a graphics processing unit (GPU), etc., or an acceleration computing unit designed for deep learning tasks, autonomous driving tasks, etc., such as a neural processing unit (NPU), etc.

[0039] In an implementation manner, the payment verification system 20 can further include one or more memories 202, which can store program instructions executable by the processor 201. The processor 201 can load and execute the program instructions in the memory 202 to implement the functions of the payment verification system 20.

[0040] In addition, the memory 202 can also be used to cache or store intermediate data or result data generated by the processor 201 during operation, as well as to store system files, application files, data files, etc. For example, the memory 202 can store the first image and the second image collected by the collection system 10.

[0041] For example, the memory 202 can include volatile memory such as dynamic random access memory (DRAM), static random access memory (SRAM), etc., and can also include non-volatile memory such as read-only memory (ROM), flash memory, etc.

[0042] Exemplary method

[0043] Figure 2 FIG. 1 is a flowchart of a vehicle environment-based verification method according to an example embodiment of the present disclosure. The embodiment can be applied to an electronic device such as a server, a terminal, etc. Figure 2 As shown in FIG. 1, the method includes the following steps:

[0044] In step 100, based on the vehicle entering a target area, a first image containing a target user and a second image containing a payment code are acquired.

[0045] In step 100, the vehicle can monitor in real time whether it enters the target area by sensing the environment outside the vehicle through the image sensor in the collection system 10 described above, or by acquiring the current positioning information and performing position matching with the high-precision map, etc. If the vehicle enters the target area, for example, the payment area of the parking lot, the first image containing the target user and the second image containing the payment code are collected by the image sensor of the collection system 10 described above. The target user can be the driver of the vehicle, and the first image contains the head features and facial features of the target user, which can be used to analyze the line-of-sight direction of the target user. The payment code can be a two-dimensional code for payment, and the second image can be used to determine the specific position information of the payment code.

[0046] Step 200, determining a line-of-sight direction of the target user based on the first image.

[0047] In step 200, a user feature in the first image is extracted, and then the line-of-sight direction of the target user is determined based on the user feature. Specifically, the head pose, the eyeball pose, the pupil offset, the eye texture, and the like of the target user can be determined according to the first image, and then the direction that the target user is gazing at, i.e., the line-of-sight direction of the target user, is determined according to one or more of the above features.

[0048] In one example, the line-of-sight direction corresponding to the left eye (hereinafter referred to as the left eye line-of-sight direction) and the line-of-sight direction corresponding to the right eye (hereinafter referred to as the right eye line-of-sight direction) can be determined based on the eyeball pose, the eye texture, and the like of the left and right eyes, respectively. At this time, the left eye line-of-sight direction or the right eye line-of-sight direction can be taken as the line-of-sight direction of the target user; or the left eye line-of-sight direction and the right eye line-of-sight direction can be comprehensively analyzed to obtain the line-of-sight direction of the target user by taking the mean value or the like.

[0049] Step 300, determining a first position of the collection code based on the second image.

[0050] In step 300, the second image is detected by using an image target detection technology. Specifically, first, it is detected by using an image target detection method whether the second image contains the collection code. If not, the second image is re-acquired; if yes, the first position of the collection code based on the second image is determined. In one example, first, the pixel coordinates of the collection code in the second image are determined, then the depth information corresponding to each pixel coordinate is determined, and finally, the first position of the collection code is determined according to the pixel coordinates and the corresponding depth information. In another example, in addition to the depth information, the Perspective-n-Point (PnP) technology, the structured light technology, and the like can also be used to determine the first position of the collection code.

[0051] Step 400, verifying the target user based on the matching relationship between the line-of-sight direction of the target user and the first position of the collection code.

[0052] In step 400, after determining the line-of-sight direction of the target user and the first position where the collection code is located, the payment demand of the target user can be verified first. Specifically, whether the line-of-sight direction of the target user matches the first position where the collection code is located can be determined by judging whether the line-of-sight direction of the target user is directed to the first position where the collection code is located. If it is determined that the two match, it is considered that the target user is gazing at the collection code, and at this time it can be considered that the target user has a payment demand, otherwise it can be considered that the target user does not have a payment demand. After determining that the target user has a payment demand, the target user can be further verified to improve the safety and accuracy of the payment operation. For example, the payment verification system 20 can ask the target user whether to agree to pay through voice prompts, display payment information on the central control screen, and the like, and verify the target user based on the feedback information of the target user.

[0053] From the above technical solutions, it can be seen that the method provided by the embodiments of the present disclosure can respectively collect the first image containing the target user and the second image containing the collection code when the vehicle enters the target area, automatically analyze the matching relationship between the line-of-sight direction of the target user and the position of the collection code, and verify the target user based on this. If the verification is passed, the payment operation is automatically performed. In this way, the driver does not need to manually operate the mobile phone for the payment process, so the payment process can be simplified and the payment efficiency can be improved, and the driver can avoid distracted operation of the mobile phone during driving, thereby improving road safety and traffic flow. At the same time, since the payment operation is performed after the target user is verified, the safety and accuracy of the payment operation can also be ensured.

[0054] Figure 3 is a flowchart of a verification method based on a vehicle-mounted environment provided by another exemplary embodiment of the present disclosure.

[0055] As shown in Figure 3 the above Figure 2 based on the embodiment shown in the above embodiment, step 400 can include the following steps:

[0056] Step 410, based on the first position of the collection code and the second position of the target user, determining the target direction between the target user and the collection code.

[0057] In step 410, based on the respective positions of the collection code and the target user (referred to as the first position and the second position respectively), the direction of the target user pointing to the collection code is determined as the target direction. The second position of the target user can be the position of the eye of the target user, so that the target direction is the direction of the eye of the target user pointing to the collection code, that is, the line-of-sight direction when the target user gazes at the collection code.

[0058] Exemplarily, if the coordinate of the first position of the collection code is p_qr_dms, and the coordinate of the second position where the target user is located is p_eye_dms, the target direction between the target user and the collection code can be expressed in the form of a vector, specifically, v_target = p_qr_dms - p_eye_dms.

[0059] In step 420, based on the line-of-sight direction of the target user and the target direction, a matching relationship between the line-of-sight direction of the target user and the first position of the collection code is determined.

[0060] In step 420, it can be understood that the target direction is the line-of-sight direction when the target user gazes at the collection code, and therefore, the smaller the included angle between the line-of-sight direction of the target user and the target direction, the higher the possibility that the target user gazes at the collection code. Based on this, whether the matching relationship between the line-of-sight direction of the target user and the first position of the collection code is matched can be determined according to the line-of-sight direction of the target user and the target direction, and the smaller the included angle between the line-of-sight direction and the target direction, the higher the matching degree between the line-of-sight direction of the target user and the first position of the collection code.

[0061] Exemplarily, if the line-of-sight direction of the target user is g_dms, and the target direction between the target user and the collection code is v_target = p_qr_dms - p_eye_dms, before calculating the included angle, the target direction can be first unitized, and the unitized target direction is v_target1 = v_target / ||v_target||. In this way, the included angle between the line-of-sight direction and the unitized target direction is the included angle between g_dms and v_target1, denoted as theta. In this way, the smaller theta is, the higher the possibility that the target user gazes at the collection code, and the higher the matching degree between the line-of-sight direction of the target user and the first position of the collection code.

[0062] wherein an angle threshold value can be set in advance, and if theta is less than the angle threshold value, it can be considered that the target user is gazing at the collection code, and at this time, it is determined that the matching relationship between the line-of-sight direction of the target user and the first position of the collection code is matched, otherwise it is determined to be not matched. It can be understood that the larger the angle threshold value, the looser the determination of the matching relationship, that is, the lower the matching degree requirement between the line-of-sight direction of the target user and the first position of the collection code, and therefore the lower the false negative rate; on the contrary, the smaller the angle threshold value, the stricter the determination of the matching relationship, that is, the higher the matching degree requirement between the line-of-sight direction of the target user and the first position of the collection code, and therefore the lower the false positive rate. Therefore, the strictness of the matching can be flexibly adjusted according to actual needs, for example, the angle threshold value can be set to 5°, or the angle threshold value can be set to 10°.

[0063] In one implementation, the cosine form of the angle can be used to perform a matching relationship determination operation. For example, the cosine of the angle theta between g_dms and v_target can be expressed as cos_theta = dot(g_dms, v_target). Wherein, dot is the dot product operation of the vector. If cos_theta is equal to 1, it means that theta is 0°, so the target user is looking at the payment code. Based on this concept, a cosine threshold can be set in advance. If cos_theta is greater than the cosine threshold, it can be considered that the target user is looking at the payment code. At this time, the matching relationship between the target user's line of sight and the first position of the payment code is determined to be a match, otherwise it is determined to be a mismatch. The setting method of the cosine threshold is similar to the setting method of the aforementioned angle threshold, and will not be repeated here.

[0064] It is understandable that the matching relationship can also be determined using the sine, tangent, and other forms of the included angle. For details, please refer to the aforementioned cosine form of the included angle, which will not be repeated here.

[0065] Step 430: Based on the matching relationship being a match, verify the target user.

[0066] In step 430, after determining the matching relationship between the target user's line of sight and the first position of the payment code, if the two match, that is, the target user is looking at the payment code, it can be assumed that the target user has a payment intention, and thus the target user is further verified. For example, the target user's willingness to pay can be verified, and if the verification passes, the target user is considered to have the willingness to pay. Among them, verification methods may include voice verification, expression verification, etc. In this way, the target user can complete the verification by uttering a specific voice or making a specific expression based on the instructions of the payment verification system. In one example, the target user can pre-select the verification method. If the target user does not select, the default verification method can also be used.

[0067] As can be seen from the above technical solutions, the method provided by the embodiment of the present disclosure first determines the target direction between the target user and the payment code, and then determines the matching relationship between the target user's line of sight direction and the first position where the payment code is located based on the angle between the target user's line of sight direction and the target direction. In this way, if there is a match, it can be considered that the target user is looking at the payment code, and therefore it can be considered that the target user has a payment demand, and then the target user is verified; if there is no match, it can be considered that the target user is not looking at the payment code, and therefore it can be considered that the target user has no payment demand. In this way, it can be ensured that the payment operation is completed under the premise that the target user has a payment demand, and under the premise of simplifying the payment operation steps, it can effectively avoid erroneous deductions, thereby ensuring the security of the payment operation.

[0068] Figure 4is a flowchart of a verification method based on a vehicle-mounted environment provided by another example embodiment of the present disclosure.

[0069] As shown in Figure 4 , on the basis of the above-mentioned Figure 3 , step 410 can include the following steps:

[0070] Step 411, determining a target vector range based on the first direction vectors corresponding to the target directions.

[0071] In step 411, considering that the first position where the payment code is located occupies a certain area, when the target user gazes at different position points in the area, the directions of the line of sight also have slight differences. That is, the target directions from the second position where the target user is located to different position points in the area occupied by the payment code are also different. Based on this, a target vector range can be determined based on the first direction vectors corresponding to a plurality of different target directions. The target vector range can include the first direction vectors corresponding to the target directions of the target user gazing at any position in the area occupied by the payment code.

[0072] The method for determining the target vector range will be introduced below in combination with Figure 5 and Figure 6 .

[0073] Figure 5 is a schematic diagram of a target vector range provided by an example embodiment of the present disclosure.

[0074] Exemplarily, a plurality of reference points can be determined based on the payment code, such as Figure 5 , in which the four corner points A, B, C and D of the payment code are determined as the reference points. Thereafter, the target directions between the second position S where the target user is located and the position points where each reference point is located are determined respectively. In this way, the first direction vectors corresponding to each target direction can be obtained respectively, such as Figure 5 , in which the target direction from the S point to the A point can correspond to the first direction vector SA, and the first direction vectors SB, SC and SD can be obtained in the same way. The directions defined by the four first direction vectors enclose a conical area, and the range corresponding to the conical area is the target vector range.

[0075] It should be noted that, in order to avoid missing judgment, the four corner points in Figure 5 may be expanded respectively along the diagonal direction of the payment code to obtain A1, B1, C1 and D1 Figure 5 (not shown in Figure 5 ), and A1, B1, C1 and D1 are taken as new reference points. Among them, the distance of the expansion can be adjusted according to the actual application requirements.

[0076] Figure 6 is a schematic diagram of a target vector range provided by another example embodiment of the present disclosure.

[0077] Exemplarily, for the convenience of calculation, only one reference point can be determined based on the payment code, such as Figure 6 The center point O of the collection code is taken as the reference point in the above example. Thereafter, the target direction from the second position S of the target user to the position point where the reference point O is located and the corresponding first direction vector SO are determined. Then, a conical region is formed with the direction defined by the first direction vector SO as the axis, and the corresponding range of the conical region is the target vector range. The conical region can be a circular cone as shown in Figure 6 , or a pyramid, and the vertex angle corresponding to the S point can be adjusted according to actual application requirements.

[0078] In step 412, it is determined that the matching relationship between the line-of-sight direction of the target user and the first position of the collection code is matched if the second direction vector corresponding to the line-of-sight direction of the target user falls within the target vector range, and otherwise, it is determined that the matching relationship is not matched.

[0079] In step 412, after the target vector range is determined, it can be judged whether the second direction vector corresponding to the line-of-sight direction of the target user falls within the target vector range, and then the matching relationship between the line-of-sight direction of the target user and the first position of the collection code is determined to be matched or not matched according to the judgment result.

[0080] Figure 7 is a schematic diagram of the matching relationship between the line-of-sight direction and the first position provided by an example embodiment of the present disclosure.

[0081] As shown in (1) of Figure 7 , the line-of-sight direction g1_dms of the target user S1 falls within the target vector range, so it can be considered that the target user S1 is gazing at the collection code, and it is determined that the matching relationship between the line-of-sight direction of the target user S1 and the first position of the collection code is matched. As shown in (2) of Figure 7 , the line-of-sight direction g2_dms of the target user S2 falls outside the target vector range, so it can be considered that the target user S2 is not gazing at the collection code, and it is determined that the matching relationship between the line-of-sight direction of the target user S2 and the first position of the collection code is not matched.

[0082] As can be seen from the above technical solutions, the method provided by the embodiments of the present disclosure first determines a target vector range based on the first direction vector corresponding to the target direction, and then judges whether the second direction vector corresponding to the line-of-sight direction of the target user falls within the target vector range. If it falls within the range, it can be considered that the target user is gazing at a certain position in the collection code occupying area, and the matching relationship between the line-of-sight direction of the target user and the first position of the collection code is matched. In this way, the accuracy of the judgment of the matching relationship between the line-of-sight direction of the target user and the first position can be further improved, so as to ensure that the payment operation is completed on the premise that the target user has a payment demand, thereby avoiding mistaken deduction of payment and ensuring the safety of the payment operation.

[0083] Figure 8 is a flowchart of the verification method based on the vehicle-mounted environment provided by the fourth exemplary embodiment of the present disclosure.

[0084] As shown in Figure 8 the above Figure 2 embodiments, step 400 can include the following steps:

[0085] Step 440, based on the matching relationship between the line-of-sight direction of the target user and the first position where the collection code is located, the line-of-sight depth of the target user is determined according to the intersection of the left eye line-of-sight direction and the right eye line-of-sight direction in the line-of-sight direction.

[0086] In step 440, if the matching relationship between the line-of-sight direction of the target user and the first position where the collection code is located is matching, that is, the line-of-sight direction of the target user points to the first position where the collection code is located, the line-of-sight depth of the target user can be further determined, and then it is judged whether the target user gazes at the collection code according to the line-of-sight depth.

[0087] Wherein, the line-of-sight depth of the target user can be determined based on the left eye line-of-sight direction and the right eye line-of-sight direction.

[0088] Figure 9 is a schematic diagram of the line-of-sight depth and the target distance provided by an exemplary embodiment of the present disclosure.

[0089] As shown in Figure 9 exemplarily, the left eye line-of-sight direction of the target user is denoted as gl_dms, and the right eye line-of-sight direction is denoted as gr_dms. The straight line where the left eye line-of-sight direction is located and the straight line where the right eye line-of-sight direction is located intersect at point P. At this time, the line-of-sight depth of the target user can be determined based on the distance d1 between the intersection point P and the second position of the target user (such as the position where the eyes of the target user are located).

[0090] Wherein, the distance between the intersection point P and the left eye of the target user or the distance between the intersection point P and the right eye of the target user can be taken as the aforementioned distance d1; the distances between the intersection point S and the left eye and the right eye of the target user can also be comprehensively analyzed, and the aforementioned distance d1 can be obtained by taking the mean value or the like. As Figure 9 shown in the figure, the left eye of the target user is denoted as eye1, and the right eye is denoted as eye2. Then the distance d1-1 between the intersection point P and the left eye eye1, and the distance d1-2 between the intersection point P and the right eye eye2 can be obtained, and the mean value of d1-1 and d1-2 is taken as the target distance d1.

[0091] Step 450, based on the first position of the collection code and the second position of the target user, the target distance between the collection code and the target user is determined.

[0092] In step 450, the distance between the first location where the collection code is located and the second location where the target user is located is taken as the target distance d2 between the collection code and the target user. Here, the point in the collection code closest to the second location can be determined, and the distance between the point and the second location is taken as the target distance between the collection code and the target user; or the center point (such as point O in the foregoing Figure 6 ) of the collection code and the second location can be taken as the target distance between the collection code and the target user; or several points in the collection code can be determined, such as the four corner points in the foregoing Figure 5 , and the average of the distances between the four corner points and the target user is taken as the target distance.

[0093] Here, the distance between the collection code and the left eye of the target user or the distance between the collection code and the right eye of the target user can be taken as the foregoing target distance d2; or the distances between the collection code and the left eye and the right eye of the target user can be comprehensively analyzed, and the foregoing target distance d2 can be obtained by taking the average, etc.

[0094] As in the foregoing Figure 9 , the center point of the collection code is denoted as O, and the left eye of the target user is denoted as eye1 and the right eye of the target user is denoted as eye2. Then the distance d2-1 between the center point O and eye1 and the distance d2-2 between the center point O and eye2 can be obtained, and the average of d2-1 and d2-2 is taken as the target distance d2.

[0095] In step 460, the target user is verified based on matching the depth of the line of sight of the target user with the target distance.

[0096] In step 460, it is determined whether the depth of the line of sight of the target user matches the target distance. If the depth of the line of sight of the target user matches the target distance, it is considered that the target user gazes at the collection code, and the target user has a payment demand, so the target user is further verified, and then the account of the target user is used to perform a deduction operation after the verification is passed. If the depth of the line of sight of the target user does not match the target distance, it is considered that although the direction of the line of sight of the target user points to the collection code, the target user does not gaze at the collection code, and the target user does not have a payment demand, so the target user is not verified and the account of the target user is not used to perform a deduction operation.

[0097] Exemplarily, it can be determined whether the depth of the line of sight of the target user matches the target distance according to the foregoing distance d1 and the target distance d2. If the difference between the distance d1 and the target distance d2 is within a preset range, it is considered that the depth of the line of sight of the target user matches the target distance, otherwise it is considered that the depth of the line of sight of the target user does not match the target distance.

[0098] As in the foregoing Figure 9 , the distance d1 is less than the target distance d2, and the difference between the distance d1 and the target distance d2 is not within a preset range Figure 9If the distance d1 = the target distance d2 (as shown in FIG. 6), it is determined that the line-of-sight depth of the target user matches the target distance. At this time, the line-of-sight direction of the target user points to the payment code, and the line-of-sight landing point of the target user is on the payment code, that is, the target user is gazing at the payment code. Therefore, the target user is verified to perform the subsequent payment deduction operation.

[0099] Similarly, if the distance d1 = the target distance d2 (as shown in FIG. 6), it is determined that the line-of-sight depth of the target user matches the target distance. At this time, the line-of-sight direction of the target user points to the payment code, and the line-of-sight landing point of the target user is on the payment code, that is, the target user is gazing at the payment code. Therefore, the target user is verified to perform the subsequent payment deduction operation. Figure 9

[0100] From the above technical solutions, it can be seen that the method provided by the embodiments of the present disclosure further determines the line-of-sight depth of the target user and the target distance between the payment code and the target user after determining that the line-of-sight direction of the target user matches the first position of the payment code, and determines whether the line-of-sight depth matches the target distance. By comparing the line-of-sight depth with the target distance, it can be determined whether the target user is truly gazing at the payment code or only the line-of-sight direction points to the payment code, so as to improve the accuracy of the judgment of the payment demand of the target user.

[0101] Figure 10 FIG. 7 is a flowchart of a verification method based on a vehicle-mounted environment provided by a fifth exemplary embodiment of the present disclosure.

[0102] As shown in FIG. 7, on the basis of the above-mentioned embodiments, the following steps can be further included before step 400: Figure 10 Figure 2 As shown in FIG. 7, on the basis of the above-mentioned embodiments, the following steps can be further included before step 400:

[0103] Step 500: converting the second direction vector corresponding to the line-of-sight direction and the first coordinate corresponding to the first position to the same coordinate system based on the relative external parameters between the first camera and the second camera.

[0104] ​​In step 500, the first camera is a camera for capturing a first image containing the target user, and thus the direction vector corresponding to the line-of-sight direction of the target user (i.e., the second direction vector) is a direction vector in the coordinate system corresponding to the first camera. Similarly, the second camera is a camera for capturing a second image containing the payment code, and thus the coordinate (i.e., the first coordinate) corresponding to the first position of the payment code is a coordinate in the coordinate system corresponding to the second camera. Based on this, in order to facilitate the matching relationship between the line-of-sight direction of the target user and the first position of the payment code, the second direction vector corresponding to the line-of-sight direction and the first coordinate corresponding to the first position of the payment code can be converted to the same coordinate system. For example, the first coordinate can be converted from the coordinate system corresponding to the second camera to the coordinate system corresponding to the first camera based on the relative extrinsic parameters between the first camera and the second camera, or the second direction vector can be converted from the coordinate system corresponding to the first camera to the coordinate system corresponding to the second camera, and in addition, the first coordinate and the second direction vector can be converted to other coordinate systems, such as the vehicle body coordinate system, the world coordinate system, etc.

[0105] Exemplarily, the second direction vector can be kept unchanged, and based on the relative extrinsic parameters from the second camera to the first camera, a transformation matrix T_main_to_dms of the coordinate system corresponding to the second camera to the coordinate system corresponding to the first camera is determined, and then based on the transformation matrix, the first coordinate p_qr_main is converted from the coordinate system corresponding to the second camera to the coordinate system corresponding to the first camera, that is, a first mapping coordinate p_qr_dms of the first coordinate in the coordinate system corresponding to the first camera is obtained. In this way, in the subsequent steps, the first mapping coordinate can be used instead of the first coordinate to participate in the operation. For example, the target direction between the target user and the payment code is calculated based on the aforementioned formula v_target = p_qr_dms - p_eye_dms by using p_qr_dms.

[0106] As can be seen from the above technical solutions, the method provided by the embodiments of the present disclosure can perform coordinate system conversion based on the relative extrinsic parameters between the first camera and the second camera, unify the second direction vector corresponding to the line-of-sight direction and the first coordinate corresponding to the first position of the payment code to the same coordinate system, and perform matching judgment of the line-of-sight direction and the first position in the same coordinate system.

[0107] Figure 11 is a flowchart of the verification method based on a vehicle-mounted environment provided by the sixth exemplary embodiment of the present disclosure.

[0108] As Figure 11 indicated above Figure 2 on the basis of the embodiments

[0109] At step 470, after the payment information is presented to the target user, response information corresponding to the payment information is obtained, the response information including voice information issued by the target user and / or a third image containing the target user.

[0110] At step 470, after it is determined that the line-of-sight direction of the target user matches the first position where the collection code is located, i.e., it is confirmed that the target user gazes at the collection code, it is considered that the target user has a payment demand. Therefore, the payment verification system 20 can access the collection code corresponding collection system by scanning the collection code, and then the collection system calculates the payment amount based on the license plate number image captured by the camera in the target area, generates and presents the payment information to the target user based on the payment amount. In this way, the target user can respond based on the payment information to indicate whether to agree to pay.

[0111] In one example, the response information is voice information issued by the target user. Specifically, after viewing the payment information, the target user can express the payment intention through voice reply. For example, the target user can issue a voice instruction of "agree to pay". The signal acquisition component 10 can be provided with a microphone, and the microphone can be used to collect the "agree to pay" voice instruction issued by the user and transmit it to the payment verification system 20.

[0112] In another example, the response information is a third image containing the target user. Specifically, the target user moves the line of sight away from the collection code and gazes at the payment information, and after viewing the payment information, the target user can make corresponding expressions or actions according to the payment intention, and the first camera collects the third image containing the target user, i.e., the payment intention of the target user can be determined by analyzing the third image.

[0113] In addition, in an implementation, based on the quick payment setting of the target user, the third image can also not be collected, but the first image collected previously can be used as the third image. In this way, after it is determined that the line-of-sight direction of the target user matches the first position where the collection code is located, the payment intention of the target user can be immediately analyzed based on the first image. That is, the first image is used to determine both the line-of-sight direction of the target user and the payment intention. In this way, the steps of collecting and analyzing the third image can be omitted, and therefore the payment efficiency can be improved.

[0114] At step 480, the target user is verified based on the response information, and the verification result is used to pay by using the account corresponding to the target user.

[0115] In step 480, the target user is verified based on the response information, and after obtaining the verification result, a payment operation can be performed based on the verification result. Specifically, if the verification is passed, the payment can be automatically made using the account corresponding to the target user. For example, the payment verification system can bind the account corresponding to the target user in advance, so that after the verification is passed, the account can be used to make the payment, for example, deducting the fee corresponding to the aforementioned payment information from the account.

[0116] In one example, if the response information is voice information issued by the target user, the microphone of the signal collection component 10 transmits the voice information to the payment verification system 20, and the payment verification system 20 can extract semantic features from the voice information based on voice recognition technology, and then determine the payment intention of the target user. In addition, the voiceprint feature in the voice information can also be extracted through voiceprint recognition technology, and compared with the pre-stored voiceprint feature. If the comparison is consistent, it is considered that the identity verification of the target user is passed.

[0117] In another example, if the response information includes a third image of the target user, the first camera transmits the third image to the payment verification system 20, and the payment verification system 20 can determine the biological features and / or action features of the target user based on the third image, and then verify the target user based on the biological features and / or action features of the target user.

[0118] Specifically, at least one of the biological features and the action features of the target user is first extracted from the third image. The biological features refer to the unique physiological identification of the target user, including the facial features, iris features, etc. of the target user. The action features refer to the behavior actions of the target user, including the facial actions, head actions or body actions of the target user, such as blinking, nodding and shrugging, etc.

[0119] Then, the target user is verified based on at least one of the biological features and the action features of the target user. The biological features can be used to verify the identity of the target user, to ensure the security of the payment operation. For example, the facial features of the target user can be compared with the pre-stored facial features, and if the comparison is consistent, it is considered that the identity verification of the target user is passed. The action features can be used to verify the payment intention of the target user, to ensure that the payment behavior is voluntary. For example, if the action features of the target user include nodding, it can be considered that the target user agrees to pay, and the payment intention verification is passed; if the action features of the target user include shaking the head, it can be considered that the target user does not agree to pay, and the payment intention verification is not passed.

[0120] According to the technical solution, after determining that the line-of-sight direction of the target user matches the first position where the payment code is located, it is considered that the target user has a payment demand, and then the identity of the target user is verified through the biometric feature or the voiceprint feature, and the payment willingness of the target user is verified through the action feature or the semantic feature, so that the security of the payment operation can be improved.

[0121] Figure 12 is a flowchart of the verification method based on the vehicle-mounted environment provided by the seventh exemplary embodiment of the present disclosure.

[0122] As shown in Figure 12 , on the basis of the above Figure 2 embodiment, before step 100, the following steps can also be included:

[0123] Step 600: Collect an image of the environment outside the vehicle, and determine that the vehicle has entered the target area based on the target object in the target area included in the image of the environment outside the vehicle.

[0124] In step 600, considering that there are usually specific markers in the target area, such as boundary markers, specific buildings, or specific objects, etc., these markers can be used as target objects, and whether the vehicle has entered the target area can be determined according to whether these target objects exist in the environment outside the vehicle.

[0125] In one example, the railing can be used as the target object, and the aforementioned second camera or other cameras can be used to collect the image of the environment outside the vehicle in real time. In this way, if the collected image of the environment outside the vehicle includes the railing, it can be considered that the vehicle has entered the target area, and then the first image and the second image are collected, and the subsequent steps of determining whether the target user gazes at the payment code based on the first image and the second image are performed.

[0126] In one example, the shape, color, texture, and other information of the target object can be pre-stored in the vehicle or pre-stored in a storage space accessible by the aforementioned verification system based on the vehicle-mounted environment, so that the verification system can compare the information of the target object with the information of the object in the image of the environment outside the vehicle in real time, and then identify the target object from the image of the environment outside the vehicle.

[0127] Step 700: Collect a vehicle motion state feature, and determine that the vehicle has entered the target area based on the matching between the vehicle motion state feature and the preset motion state feature corresponding to the target area.

[0128] In step 700, considering that there are usually special motion state features when the vehicle enters the target area, such as deceleration when passing through the toll gate, etc., these motion state features can be used as the preset motion state features corresponding to the target area, and whether the vehicle has entered the target area can be determined according to whether these preset motion state features exist.

[0129] In one example, deceleration can be used as a pre-set behavioral state characteristic, and CAN signals can be received in real time via a CAN bus. The vehicle's current motion state characteristics can then be determined based on the CAN signals. If the vehicle's current motion state characteristics indicate deceleration, the vehicle can be considered to have entered the target area. The first and second images can then be captured, and the subsequent gaze direction determination step can be performed based on the first and second images to determine whether the target user is looking at the payment code.

[0130] As can be seen from the above technical solutions, the method provided by the embodiments of the present disclosure can determine whether a vehicle has entered a target area by collecting and analyzing images of the vehicle's external environment and / or the vehicle's motion characteristics. This eliminates the need to continuously collect the first and second images, only after confirming that the vehicle has entered the target area. This reduces unnecessary image collection and analysis.

[0131] In some examples, only one of step 600 and step 700 may be included before step 100, and the specific implementation method and technical effect are not repeated here.

[0132] Exemplary apparatus

[0133] The above describes the in-vehicle environment-based verification method provided by the embodiments of the present disclosure. It is understood that the in-vehicle environment-based verification system may include corresponding hardware and software for implementing the hardware functions in order to implement the various functions of the in-vehicle environment-based verification method.

[0134] Those skilled in the art should easily realize that, in combination with the steps of a verification method based on an in-vehicle environment described in each embodiment of the present disclosure, each embodiment of the present disclosure can be implemented in the form of hardware, or in a combination of software-driven hardware. Whether a function is executed in hardware or software-driven hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this disclosure.

[0135] Figure 13 It is a structural diagram of a verification device based on a vehicle environment provided by an exemplary embodiment of the present disclosure.

[0136] like Figure 13 As shown, in one embodiment, the vehicle-mounted environment-based verification device 1300 includes: a signal acquisition component 1310 and one or more processors 1320 .

[0137] The signal collection component 1310 includes a first camera 1311 and a second camera 1312. The first camera 1311 is configured to acquire a first image containing a target user based on the vehicle entering a target area. The second camera 1312 is configured to acquire a second image containing a payment code based on the vehicle entering the target area.

[0138] The one or more processors 1320 are configured to execute instructions stored in the memory to determine a line-of-sight direction of the target user based on the first image, determine a first position of the payment code based on the second image, and verify the target user based on a matching relationship between the line-of-sight direction of the target user and the first position of the payment code.

[0139] In an example embodiment, the processor 1320 is configured to execute instructions stored in the memory to determine a target direction between the target user and the payment code based on the first position of the payment code and a second position of the target user, wherein the target direction is a line-of-sight direction when the target user gazes at the payment code, determine the matching relationship between the line-of-sight direction of the target user and the first position of the payment code based on the line-of-sight direction of the target user and the target direction, and verify the target user based on the matching relationship being a match.

[0140] In an example embodiment, the processor 1320 is configured to execute instructions stored in the memory to determine a target vector range based on a first direction vector corresponding to the target direction, and determine the matching relationship between the line-of-sight direction of the target user and the first position of the payment code as a match based on a second direction vector corresponding to the line-of-sight direction of the target user falling within the target vector range, or as a mismatch otherwise.

[0141] In an example embodiment, the processor 1320 is configured to execute instructions stored in the memory to determine a line-of-sight depth of the target user based on the matching relationship between the line-of-sight direction of the target user and the first position of the payment code being a match, and determine a target distance between the payment code and the target user based on the first position of the payment code and the second position of the target user, and verify the target user based on the line-of-sight depth of the target user matching the target distance.

[0142] In an example embodiment, the processor 1320 is configured to execute instructions stored in the memory to convert a second direction vector corresponding to the line-of-sight direction and a first coordinate corresponding to the first position to a same coordinate system based on a relative extrinsic parameter between a first camera and a second camera, wherein the first camera and the second camera are cameras used to acquire the first image and the second image, respectively.

[0143] In an example embodiment, the signal collection component 1310 is configured to obtain response information corresponding to the payment information after the payment information is presented to the target user, wherein the response information includes voice information issued by the target user and / or a third image containing the target user, the microphone 1313 in the signal collection component is configured to obtain the voice information issued by the target user, and the first camera 1311 is configured to obtain the third image containing the target user; the processor 1320 is configured to execute instructions stored in the memory to perform the following operation: verifying the target user based on the response information, wherein the verification result is used for payment using the account corresponding to the target user.

[0144] In an example embodiment, the second camera 1312 is configured to collect an out-of-vehicle environment image; the processor 1320 is configured to execute instructions stored in the memory to perform the following operation: determining that the vehicle enters the target area based on the target object in the target area contained in the out-of-vehicle environment image.

[0145] In an example embodiment, the vehicle environment-based verification device 1300 includes a CAN (Controller Area Network) bus interface configured to collect vehicle motion state features; the processor 1320 is configured to execute instructions stored in the memory to perform the following operation: determining that the vehicle enters the target area based on the vehicle motion state features matching the preset motion state features corresponding to the target area.

[0146] Exemplary electronic device

[0147] Figure 14 is a structural diagram of an electronic device provided by an example embodiment of the present disclosure. As shown in Figure 14 The electronic device 1400 includes at least one processor 1410 and a memory 1420.

[0148] The processor 1410 can be a central processing unit (CPU) or other form of processing unit having data processing and / or instruction execution capabilities, and can control other components in the electronic device 1400 to perform desired functions.

[0149] The memory 1420 can include one or more computer program products that can include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory, for example, can include random access memory (RAM), cache memory, and / or the like. The non-volatile memory, for example, can include read only memory (ROM), hard disk drives, solid state drives, and / or the like. The computer-readable storage media can store one or more computer program instructions implementing the vehicle environment-based verification method and / or other desired function(s) of various embodiments of the present disclosure described above, which the processor 1410 can execute.

[0150] In one example, the electronic device 1400 can further include an input device 1430 and an output device 1440, which are interconnected through a bus system and / or other forms of connection mechanisms (not shown).

[0151] The input device 1430 can further include, for example, a keyboard, a mouse, and / or the like.

[0152] The output device 1440 can output various information to the outside, which can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and / or the like.

[0153] Of course, in order to simplify, Figure 14 Only some of the components of the electronic device 1400 related to the present disclosure are shown in FIG. 14, and components such as a bus, an input / output interface, and / or the like are omitted. In addition to this, the electronic device 1400 can further include any other appropriate components according to a specific application.

[0154] Exemplary computer program product and computer readable storage medium

[0155] In addition to the above-described method and device, embodiments of the present disclosure can be a computer program product including computer program instructions that, when executed by a processor, cause the processor to perform steps of the bandwidth control method according to various embodiments of the present disclosure described in the above "Exemplary Method" section of the specification.

[0156] The computer program product can be written in any combination of one or more programming languages, including an object-oriented programming language such as Java, C++, and / or the like, and conventional procedural programming languages, such as the "C" programming language, or similar programming languages. The program code can execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device or entirely on the remote cloud device or server.

[0157] Furthermore, an embodiment of the present disclosure can also be a computer readable storage medium having stored thereon a computer program instructing, which, when executed by a processor, causes the processor to perform the steps of the bandwidth control method according to various embodiments of the present disclosure described in the above "Exemplary Methods" section of the specification.

[0158] The computer readable storage medium can take the form of one or more combinations of any type of readable media. The readable media can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or apparatus, or any suitable combination of the above. More specific examples (a non-exhaustive list) of the readable storage medium include an electrical connection having one or more wires, a portable disc, 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 disc read-only memory (CD-ROM), an optical memory, a magnetic memory, or any suitable combination of the above.

[0159] The above describes the basic principles of the present disclosure in combination with specific embodiments, but it should be noted that the advantages, benefits, effects and the like mentioned in the present disclosure are only examples and are not limiting, and these advantages, benefits, effects and the like cannot be considered as necessary for each embodiment of the present disclosure. In addition, the above specific details are only for the purpose of example and for the purpose of understanding, and are not limiting, and the above details do not limit the present disclosure to be necessarily implemented with the above specific details.

[0160] The block diagrams of the devices, apparatuses, equipment, systems involved in the present disclosure are only illustrative examples and are not intended to require or imply that the connections, arrangements, configurations must be as shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, equipment, systems can be connected, arranged, configured in any manner. Words such as "include", "contain", "have", and the like are open-ended words, mean "including but not limited to", and can be used interchangeably. The words "or" and "and" used herein mean the word "and / or", and can be used interchangeably unless the context clearly indicates otherwise. The word "such as" used herein means the phrase "such as but not limited to", and can be used interchangeably.

[0161] It should also be noted that in the apparatuses, equipment and methods of the present disclosure, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be considered as equivalent solutions of the present disclosure.

[0162] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein can be applied to other aspects without departing from the scope of the disclosure. Thus, the present disclosure is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0163] The above description has been presented to enable any person skilled in the art to make or use the disclosure. Furthermore, the purpose of the above description is not intended to limit the embodiments of the present disclosure to the form disclosed herein. Although various example aspects and embodiments have been discussed above, those of ordinary skill in the art will appreciate a variety of modifications, alternatives, permutations, additions, and sub-combinations, which fall within the scope of the disclosed aspects.

Claims

1. A verification method based on an in-vehicle environment, comprising: Based on the vehicle entering the target area, obtaining a first image containing a target user and a second image containing a payment code; determining a sight direction of the target user based on the first image; determining a first position of the payment code based on the second image; The target user is verified based on a matching relationship between the sight line direction of the target user and the first position of the payment code.

2. The verification method based on the vehicle environment according to claim 1, wherein: The verifying the target user based on the matching relationship between the sight line direction of the target user and the first position of the payment code includes: determining a target direction between the target user and the payment code based on the first position of the payment code and the second position of the target user, wherein the target direction is a line of sight of the target user when looking at the payment code; Determining a matching relationship between the target user's sight line direction and the first position of the payment code based on the target user's sight line direction and the target direction; Based on the matching relationship being a match, the target user is verified.

3. The vehicle-based verification method according to claim 2, wherein: The determining, based on the sight line direction of the target user and the target direction, a matching relationship between the sight line direction of the target user and the first position of the payment code includes: determining a target vector range based on a first direction vector corresponding to the target direction; Based on the second direction vector corresponding to the sight line direction of the target user falling within the target vector range, the matching relationship between the sight line direction of the target user and the first position of the payment code is determined to be a match; otherwise, the matching relationship is determined to be a mismatch.

4. The vehicle-mounted environment verification method according to any one of claims 1 to 3, wherein: The verifying the target user based on the matching relationship between the sight line direction of the target user and the first position of the payment code includes: Based on the matching relationship between the target user's sight line direction and the first position of the payment code being a match, determining the sight line depth of the target user according to the intersection of the left eye sight line direction and the right eye sight line direction in the sight line direction; determining a target distance between the payment code and the target user based on the first position of the payment code and the second position of the target user; The target user is verified based on a match between the sight depth of the target user and the target distance.

5. The vehicle-mounted environment verification method according to any one of claims 1 to 3, wherein: Before verifying the target user based on the matching relationship between the target user's sight line direction and the first position of the payment code, the method further includes: Based on the relative external parameters between the first camera and the second camera, the second direction vector corresponding to the line of sight and the first coordinate corresponding to the first position are converted into the same coordinate system, wherein the first camera and the second camera are cameras for capturing the first image and the second image, respectively.

6. The verification method based on the vehicle environment according to claim 1, wherein: The verifying the target user includes: After presenting the payment information to the target user, obtaining response information corresponding to the payment information, wherein the response information includes a voice message sent by the target user and / or a third image containing the target user; Based on the response information, the target user is verified, wherein the verification result is used to pay using an account corresponding to the target user.

7. The vehicle-based verification method according to claim 1, wherein: Before acquiring the first image containing the target user and the second image containing the payment code based on the vehicle entering the target area, the method further includes: Acquire an image of the vehicle's exterior environment, and determine that the vehicle has entered the target area based on the image of the vehicle's exterior environment containing the target object in the target area; and / or, The vehicle motion state feature is collected, and based on a match between the vehicle motion state feature and a preset motion state feature corresponding to the target area, it is determined that the vehicle has entered the target area.

8. A verification device based on a vehicle-mounted environment, comprising: A signal acquisition component, comprising a first camera and a second camera; The first camera is configured to acquire a first image containing a target user based on the vehicle entering the target area; The second camera is configured to obtain a second image including a payment code based on the vehicle entering the target area; One or more processors configured to execute instructions stored in a memory to determine a gaze direction of the target user based on the first image; determining a first position of the payment code based on the second image; The target user is verified based on a matching relationship between the sight line direction of the target user and the first position of the payment code.

9. An electronic device comprising: One or more processors, and a memory; the memory stores computer instructions; the computer instructions, when executed by the processor, cause the processor to perform the method according to any one of claims 1 to 7. 10 . A computer-readable storage medium having computer program instructions stored thereon, wherein when the computer program instructions are executed by a processor, the processor is caused to perform the method according to claim 1 .

Images