Driver self-service physical examination anti-cheating method, device and equipment and medium

Abstract

The invention discloses a driver self-service physical examination anti-cheating method, device and equipment and a medium, and relates to the technical field of face recognition, and the method comprises the steps: carrying out the real-time monitoring of a to-be-detected target region, so as to obtain a first target image; performing head position detection and head confidence detection on the first target image to obtain target head information, and judging whether alarm information is triggered or not based on the target head information; acquiring a second target image when the physical examination person performs visual function detection, determining a forehead center position by using the second target image, and determining an expected eye position according to the forehead center position; the expected eye position comprises a left eye position and a right eye position estimated according to the center position of the forehead; whether a first abnormal condition is met or not is judged based on the expected eye position and the actual visual bucket position, if the first abnormal condition is not met, whether a second abnormal condition is met or not is judged based on the offset between the forehead center position and the visual bucket center position, and if the second abnormal condition is met, alarm information is triggered.

Description

Technical Field

[0001] This application relates to the field of face recognition technology, and particularly to a method, device, equipment and medium for preventing cheating in driver self-service physical examination. Background Technique

[0002] In the modern traffic management system, driver physical examination is an important link to ensure road traffic safety. With the continuous progress of technology, driver self-service physical examination equipment has emerged. However, during the physical examination process, common cheating methods emerge in an endless stream. For replacing people to cheat, for example, in the height detection link, if the driver's height is insufficient, a person with a qualified height may be replaced to measure the height; for replacing eyes to cheat, for example, the visual acuity of both the left and right eyes is required to reach the standard of 4.9. If the physical examinee fails to meet the standard in the left eye and meets the standard in the right eye, when detecting the left eye, the physical examinee may try to use the right eye to observe the visual target.

[0003] Existing anti-cheating technologies have many deficiencies in dealing with the above cheating problems. Traditional non-contact identity verification mostly uses face comparison methods. However, in actual applications, especially in short-distance scenarios such as when the physical examinee is in the observation barrel area of the visual function detector, due to reasons such as large changes in the physical examinee's posture or being close to the device, most of the face will be blocked, resulting in inaccurate face comparison and difficulty in effectively solving the problem of replacing people to cheat in complex situations such as head occlusion and multiple people overlapping; at the same time, the detection of replacing eyes to cheat in existing technologies is not yet mature; therefore, existing anti-cheating technologies cannot meet the growing demand for efficient and accurate anti-cheating. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a method, device, equipment and medium for preventing cheating in driver self-service physical examination, which can detect cheating behaviors that occur during driver physical examination efficiently and at low cost, ensure the reliability of driver physical examination results, and meet the demand for efficient and accurate anti-cheating. The specific solutions are as follows:

[0005] In the first aspect, this application provides a method for preventing cheating in driver self-service physical examination, including:

[0006] Real-time monitoring of the area to be detected to obtain a first target image;

[0007] Performing head position detection and head confidence detection on the first target image to obtain target head information, and judging whether to trigger an alarm message based on the target head information; the head confidence detection is used to detect the probability of containing a human head in the head position area;

[0008] Obtain a second target image of the person undergoing vision function detection, determine the center position of the forehead using the second target image, and determine the expected eye positions based on the center position of the forehead; the expected eye positions include the estimated left eye position and right eye position based on the center position of the forehead.

[0009] Based on the comparison between the expected eye positions and the actual vision bucket positions, determine whether the first abnormal condition is met. If the first abnormal condition is not met, then based on the offset between the center position of the forehead and the center position of the vision bucket, determine whether the second abnormal condition is met. If the second abnormal condition is met, trigger an alarm message; the actual vision bucket positions include the left vision bucket position and the right vision bucket position equipped on the vision function detection device for performing vision function detection.

[0010] Optionally, before performing head position detection and head confidence detection on the first target image to obtain target head information, it further includes:

[0011] Perform image preprocessing operations on the first target image; the image preprocessing operations include noise removal operations and normalization processing.

[0012] Perform feature extraction operations on the first target image after image preprocessing based on a preset network, and perform feature fusion operations on the image after feature extraction operations to obtain the first target image after target processing, so as to perform head position detection and head confidence detection using the first target image after target processing.

[0013] Optionally, performing head position detection and head confidence detection on the first target image to obtain target head information includes:

[0014] Perform head position detection and head confidence detection on the first target image to obtain the initial head information in the first target image; the initial head information includes the head position and the head position confidence.

[0015] Remove redundant head information from the initial head information based on the head position confidence to obtain the target head information in the first target image.

[0016] Optionally, the driver self-service physical examination anti-cheating method further includes:

[0017] Determine the target physical examination person information corresponding to the physical examination person, and compare the target physical examination person information with the expected physical examination person information obtained in advance;

[0018] If the target physical examination person information is consistent with the expected physical examination person information, no alarm message is triggered. If the target physical examination person information is inconsistent with the expected physical examination person information, an alarm message is triggered.

[0019] Optionally, determining whether to trigger an alarm message based on the target header information includes:

[0020] Determining the examinee corresponding to the target header information;

[0021] Judging whether the examinee has changed within a preset time period and whether the number of examinees included in the target header information exceeds one;

[0022] If the examinee corresponding to the target header information has changed and / or the number of examinees included in the target header information exceeds one, an alarm message is triggered. If the examinee corresponding to the target header information has not changed and the number of examinees included in the target header information is only one, no alarm message is triggered.

[0023] Optionally, the first abnormal condition is that the overlap degree between the area corresponding to the left eye position in the expected eye position and the area corresponding to the left viewing barrel position in the actual viewing barrel position is lower than a preset overlap threshold, and / or the overlap degree between the area corresponding to the right eye position in the expected eye position and the area corresponding to the right viewing barrel position in the actual viewing barrel position is lower than a preset overlap threshold.

[0024] Optionally, determining whether the second abnormal condition is met based on the offset between the forehead center position and the viewing barrel center position includes:

[0025] Determining the offset between the forehead center position and the viewing barrel center position;

[0026] If the offset exceeds a preset offset threshold, it is confirmed that the second abnormal condition is met. If the offset does not exceed the preset offset threshold, it is confirmed that the second abnormal condition is not met.

[0027] In a second aspect, the present application provides a driver self-service physical examination anti-cheating device, including:

[0028] An area monitoring module for performing real-time monitoring on a to-be-detected target area to obtain a first target image;

[0029] A first alarm judgment module for performing head position detection and head confidence detection on the first target image to obtain target head information, and determining whether to trigger an alarm message based on the target head information; the head confidence detection is used to detect the probability of including a human head in the head position area;

[0030] A position determination module for obtaining a second target image when the examinee performs visual function detection, determining the forehead center position using the second target image, and determining the expected eye position according to the forehead center position; the expected eye position includes the left eye position and the right eye position estimated according to the forehead center position;

[0031] A second alarm determination module, configured to determine whether a first abnormal condition is met based on the expected eye position and the actual view barrel position. If the first abnormal condition is not met, it is determined whether a second abnormal condition is met based on the offset between the center position of the forehead and the center position of the view barrel. If the second abnormal condition is met, an alarm message is triggered; the actual view barrel position includes the left view barrel position and the right view barrel position equipped with the vision function detection device for performing vision function detection.

[0032] In a third aspect, the present application provides an electronic device, including:

[0033] A memory, configured to store a computer program;

[0034] A processor, configured to execute the computer program to implement the foregoing driver self-service physical examination anti-cheating method.

[0035] In a fourth aspect, the present application provides a computer-readable storage medium, configured to store a computer program, wherein the computer program, when executed by a processor, implements the foregoing driver self-service physical examination anti-cheating method.

[0036] In this application, the first target image is obtained by performing real-time monitoring on the target area to be detected; the head position detection and head confidence detection are performed on the first target image to obtain the target head information, and whether to trigger an alarm message is judged based on the target head information; the head confidence detection is used to detect the probability of containing a human head in the head position area; the second target image of the physical examinee during visual function detection is obtained, the center position of the forehead is determined by using the second target image, and the expected eye positions are determined according to the center position of the forehead; the expected eye positions include the left eye position and the right eye position estimated according to the center position of the forehead; whether the first abnormal condition is satisfied is judged based on the expected eye positions and the actual visual bucket positions, if the first abnormal condition is not satisfied, whether the second abnormal condition is satisfied is judged based on the offset between the center position of the forehead and the center position of the visual bucket, and if the second abnormal condition is satisfied, an alarm message is triggered; the actual visual bucket positions include the left visual bucket position and the right visual bucket position equipped for visual function detection by the visual function detection device. As can be seen from the above, in this application, the head position detection and head confidence detection are first performed on the first target image obtained by real-time monitoring of the target area to be detected to obtain the target head information, and whether to trigger an alarm message is judged based on the target head information to detect whether there is a problem of substituting people for cheating; further, when the physical examinee performs visual function detection, the second target image obtained by monitoring is obtained, the center position of the forehead is obtained according to the second target image, and then the expected eye positions are obtained, and then whether the first abnormal condition is satisfied is judged based on the expected eye positions and the actual visual bucket positions, and whether the second abnormal condition is satisfied is judged based on the offset between the center position of the forehead and the center position of the visual bucket, and whether to trigger an alarm message is determined according to the judgment of the first abnormal condition and the second abnormal condition to detect whether there is a problem of substituting eyes for cheating. In this way, through the above-mentioned detection of substituting people for cheating and substituting eyes for cheating, the cheating behavior during the driver's physical examination can be efficiently detected, the reliability of the driver's physical examination results can be ensured, and the anti-cheating requirements of high efficiency and accuracy can be met. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0038] Figure 1 It is a flowchart of a method for preventing cheating in driver self-service physical examination disclosed in the present application;

[0039] Figure 2 It is a schematic diagram of a head detection method disclosed in the present application;

[0040] Figure 3 Schematic diagram of a visual function detector disclosed in this application;

[0041] Figure 4 Schematic diagram of the structure of a cheating prevention device for self-service driver physical examination disclosed in this application;

[0042] Figure 5 Schematic diagram of the structure of an electronic device disclosed in this application. Specific embodiments

[0043] Next, the technical solutions in the embodiments of this application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of this application.

[0044] Traditional non-contact identity verification mostly uses face comparison methods. However, in actual applications, especially in close-range scenarios such as when the physical examination personnel are in the observation barrel area of the visual function detector, due to reasons such as large changes in the posture of the physical examination personnel or being close to the device, most of the face will be blocked, resulting in inaccurate face comparison and difficulty in effectively solving the problem of substituting people for cheating in complex situations such as head occlusion and multiple people overlapping. At the same time, the detection of eye substitution cheating in the prior art is not yet mature. Therefore, the existing anti-cheating technologies cannot meet the growing demand for efficient and accurate anti-cheating. For this reason, this application provides a method for preventing cheating in self-service driver physical examination, which can efficiently and low-cost detect cheating behaviors during driver physical examination, ensure the reliability of driver physical examination results, and meet the requirements of efficient and accurate anti-cheating.

[0045] See Figure 1 As shown, an embodiment of the present invention discloses a method for preventing cheating in self-service driver physical examination, including:

[0046] Step S11: Real-time monitor the target area to be detected to obtain a first target image.

[0047] In this embodiment, during the physical examination of the physical examination personnel, for the target area to be detected, the target area to be detected is monitored and recorded in real time through a camera device, and a first target image is obtained to judge whether a cheating behavior occurs based on the first target image. If a cheating behavior is detected, an alarm message is triggered.

[0048] Step S12: Detect the head position and head confidence of the first target image to obtain target head information, and judge whether to trigger an alarm message based on the target head information; the head confidence detection is used to detect the probability of containing a human head in the head position area.

[0049] In order to overcome the deficiencies of detecting cheating behavior through traditional face comparison techniques, in this embodiment, the target head information can be obtained by performing head position detection and head confidence detection on the first target image, and whether to trigger an alarm message can be determined based on the target head information, so as to detect whether cheating behavior occurs based on the head detection method.

[0050] See Figure 2 As shown, first, an image preprocessing operation can be performed on the first target image. For example, noise removal and normalization operations can be performed on the first target image. Through size transformation and normalization, the noise in the image can be removed and the image can be normalized to ensure that the image input meets the requirements of the network, laying a foundation for subsequent head detection. Then, based on a preset network, a feature extraction operation is performed on the first target image after the image preprocessing operation. For example, the CSPDarknet53 (Cross Stage Partial Darknet53, a neural network architecture widely used in fields such as object detection) network is used to extract features from the image after the image preprocessing operation. Among them, the CSPDarknet53 network can quickly and accurately extract important features in the image through its efficient structure and has strong advantages in the recognition of the head area. Further, a feature fusion operation is performed on the image after the feature extraction operation to obtain the first target image after target processing, so as to perform head position detection and head confidence detection using the first target image after target processing. Among them, target processing includes image preprocessing operation, feature extraction operation, and feature fusion operation. For example, the PANet (Path Aggregation Network) can be used for the feature fusion operation. The PANet can effectively fuse image features from different scales, thereby enhancing the multi-scale recognition ability of the network and further improving the head detection accuracy for different poses and distances.

[0051] Further, head position detection and head confidence detection are performed on the first target image after the above target processing to achieve head detection. Specifically, first, head position detection and head confidence detection are performed on the first target image after target processing to obtain the initial head information in the image. Among them, the initial head information includes the head position and the head position confidence. Then, based on the head position confidence, redundant head information is removed from the initial head information to obtain the target head information in the image, so as to perform a post-processing operation on the first target image after target processing. For example, through post-processing steps such as non-maximum suppression (NMS, i.e., Non-Maximum Suppression), redundant head information can be removed to accurately obtain the head information of each person.

[0052] After obtaining the target header information, determine whether to trigger an alarm message based on the target header information. Specifically, first determine the examinee corresponding to the target header information; then determine whether the examinee has changed within a preset time period and whether the number of examinees included in the target header information exceeds one; if the examinee corresponding to the target header information has changed, and / or the number of examinees included in the target header information exceeds one, then trigger an alarm message, if the examinee corresponding to the target header information has not changed and the number of examinees included in the target header information is only one, then do not trigger an alarm message.

[0053] It can be understood that within the preset time period, the system continuously monitors the situation of the examinee. If it is detected that the examinee has changed, it is very likely that there is a situation of someone replacing another person for cheating. For example, during the physical examination, originally Zhang San was having the physical examination, but it was detected that the examinee corresponding to the head information became Li Si. This situation triggers an alarm message so that the staff can intervene and investigate in a timely manner. At the same time, if the number of examinees included in the target header information exceeds one, it also indicates that there is an abnormal situation in the detection area. It may be that multiple people are trying to participate in the physical examination at the same time or there is an act of assisting in cheating, which will also trigger an alarm. Only when the examinee corresponding to the target header information has not changed and the number is only one, is it determined to be a normal situation and no alarm message is triggered to ensure that the physical examination process can proceed smoothly and orderly.

[0054] It should be noted that when the examinee starts the physical examination, the identity of the examinee can be verified first. Specifically, first determine the target examinee information corresponding to the examinee and compare the target examinee information with the expected examinee information obtained in advance; if the target examinee information is consistent with the expected examinee information, then do not trigger an alarm message, if the target examinee information is inconsistent with the expected examinee information, then trigger an alarm message. For example, when the self-service physical examination starts, the examinee is required to swipe the ID card, and the system performs a 1:1 face comparison on the examinee and the ID card photo to ensure that it is the examinee himself / herself having the physical examination.

[0055] Step S13: Obtain a second target image when the examinee performs visual function detection, use the second target image to determine the center position of the forehead, and determine the expected eye positions according to the center position of the forehead; the expected eye positions include the left eye position and the right eye position estimated according to the center position of the forehead.

[0056] In this embodiment, after it is determined that there is no behavior of someone replacing another person for cheating, continue to monitor to determine whether there is a behavior of replacing eyes for cheating during the physical examination process.

[0057] It should be noted that a visual function detection device can be used to perform visual function detection, such as Figure 3The visual function detector shown, where 01 is a camera for real-time monitoring of the target area to be detected to obtain a second target image; 02 is the visual function detector observation barrel, that is, the visual barrel, including a left visual barrel and a right visual barrel. When detecting eyesight, the examinee needs to align each eye with a visual barrel. When detecting the left eye, there is no visual target in the right visual barrel. When detecting the right eye, there is no visual target in the left visual barrel. The visual target in the visual barrel can only be seen by the examinee. A visual function detection system is encapsulated in the visual function detector for performing visual function detection operations.

[0058] Step S14: Determine whether the first abnormal condition is satisfied based on the expected eye position and the actual visual barrel position. If the first abnormal condition is not satisfied, then determine whether the second abnormal condition is satisfied based on the offset between the forehead center position and the visual barrel center position. If the second abnormal condition is satisfied, trigger an alarm message; the actual visual barrel position includes the left visual barrel position and the right visual barrel position equipped with the visual function detection device for performing visual function detection.

[0059] In this embodiment, the first abnormal condition is that the overlap degree between the area corresponding to the left eye position in the expected eye position and the area corresponding to the left visual barrel position in the actual visual barrel position is lower than a preset overlap threshold, and / or the overlap degree between the area corresponding to the right eye position in the expected eye position and the area corresponding to the right visual barrel position in the actual visual barrel position is lower than a preset overlap threshold.

[0060] The above determination of whether the second abnormal condition is satisfied based on the offset between the forehead center position and the visual barrel center position may include: determining the offset between the forehead center position and the visual barrel center position; if the offset exceeds a preset offset threshold, it is confirmed that the second abnormal condition is satisfied. If the offset does not exceed the preset offset threshold, it is confirmed that the second abnormal condition is not satisfied.

[0061] It can be understood that after obtaining the second target image of the examinee during visual function detection, first use image analysis technology to determine the forehead center position of the examinee. This process can use algorithms for identifying and locating facial features in the image. By analyzing pixel features, shapes, and other information in the forehead area, the center coordinates of the forehead can be accurately found. Based on the forehead center position, according to the proportional relationship of the human facial structure and the common distribution law of eye positions, the approximate positions of the left and right eyes are estimated, that is, the expected eye positions are determined. For example, 80% of the detected forehead center position area is used as the approximate range where the eyes are located, and the positions of the left and right eyes are estimated within the above approximate range; then compare the overlap degree between the expected eye position and the actual visual barrel position. If the overlap degree between the area corresponding to the left eye position and the area corresponding to the left visual barrel position is too low, or the overlap degree between the area corresponding to the right eye position and the area corresponding to the right visual barrel position is too low, it may indicate that the examinee did not correctly align the eyes with the corresponding visual barrel, and there is a suspicion of cheating by changing eyes.

[0062] If the first abnormal condition is not met, the real-time image monitored by the camera can be further analyzed by a visual algorithm and the offset between the center of the forehead and the center of the visual barrel can be calculated to determine whether the second abnormal condition is met. Under normal circumstances, the examinee's head and the visual barrel should maintain a relatively stable positional relationship, and the offset between the center of the forehead and the center of the visual barrel is within a certain range. Once the offset exceeds the preset offset threshold, it means that the examinee's head position has a large abnormality, and it is likely that an eye-changing operation is being performed. At this time, an alarm message will be triggered to effectively prevent the examinee from cheating by changing eyes to obtain false vision test results, and ensure the accuracy and fairness of the vision test. For example, under normal circumstances, the offset of the center of the examinee's forehead relative to the center of the visual barrel should be less than 20%. If the offset exceeds 20%, it is determined that the examinee's head position is abnormal and an eye-changing operation may have occurred.

[0063] As can be seen from the above, this embodiment can detect and determine in real time whether the head of the examinee is missing or there are multiple examinees' heads in the designated physical examination area through the head detection method. If an abnormal phenomenon is detected, an alarm is triggered and the staff is notified in time to conduct further verification to ensure the accuracy and security of the identity verification process. At the same time, this embodiment combines the head detection method and proposes an eye change detection method based on head position offset. By analyzing the offset between the center position of the forehead and the center position of the visual barrel, it is determined whether the examinee has eye change behavior. This method does not require additional hardware and can reuse existing equipment. In this way, the head detection method and the eye change detection method are combined, and various possible abnormal situations are comprehensively analyzed in one detection process, thereby realizing multi-dimensional protection against cheating behaviors during the driver's physical examination. At the same time, compared with the face comparison technology that relies on complete facial features, the head detection method supplemented by the present embodiment can continue to work effectively when the face is partially blocked; it also strengthens the anti-cheating detection means of visual barrel type equipment. Through the above-mentioned head detection method and eye change detection method, cheating behaviors occurring during the physical examination of the examinee can be efficiently detected, thereby ensuring the reliability of the physical examination results of the examinee and meeting the efficient and accurate anti-cheating needs. On the other hand, only the video acquisition device provided by the visual function detection equipment is required, and no additional hardware support is required, which significantly reduces the system implementation cost and improves the intelligence level of the vision detection equipment.

[0064] See also Figure 4 As shown, the embodiment of the present application also discloses a driver self-service physical examination anti-cheating device, including:

[0065] The area monitoring module 11 is used to monitor the target area to be detected in real time to obtain a first target image;

[0066] The first alarm determination module 12 is configured to perform head position detection and head confidence detection on the first target image to obtain target head information, and determine whether to trigger an alarm message based on the target head information; the head confidence detection is used to detect the probability of including a human head within the head position area.

[0067] The position determination module 13 is configured to obtain a second target image when the physical examinee performs visual function detection, determine the center position of the forehead using the second target image, and determine the expected eye positions based on the center position of the forehead; the expected eye positions include the left eye position and the right eye position estimated according to the center position of the forehead.

[0068] The second alarm determination module 14 is configured to determine whether the first abnormal condition is satisfied based on the expected eye positions and the actual visual bucket positions. If the first abnormal condition is not satisfied, it is determined whether the second abnormal condition is satisfied based on the offset between the center position of the forehead and the center position of the visual bucket. If the second abnormal condition is satisfied, an alarm message is triggered; the actual visual bucket positions include the left visual bucket position and the right visual bucket position equipped for visual function detection by the visual function detection device.

[0069] As can be seen from the above, the present application first performs head position detection and head confidence detection on the first target image obtained by real-time monitoring of the target area to be detected to obtain target head information, and determines whether to trigger an alarm message based on the target head information to detect whether there is a problem of substitution cheating. Further, when the physical examinee performs visual function detection, a second target image obtained by monitoring is acquired, the center position of the forehead is obtained from the second target image, and then the expected eye positions are obtained. Then, it is determined whether the first abnormal condition is satisfied based on the expected eye positions and the actual visual bucket positions, and it is determined whether the second abnormal condition is satisfied based on the offset between the center position of the forehead and the center position of the visual bucket. Whether to trigger an alarm message is determined according to the judgment of the first abnormal condition and the second abnormal condition to detect whether there is a problem of eye substitution cheating. In this way, through the above-mentioned substitution cheating detection and eye substitution cheating detection, cheating behaviors during the driver's physical examination can be efficiently detected, ensuring the reliability of the driver's physical examination results and meeting the requirements of efficient and accurate anti-cheating.

[0070] In some specific embodiments, the first alarm determination module 12 further includes:

[0071] A preprocessing unit configured to perform image preprocessing operations on the first target image; the image preprocessing operations include noise removal operations and normalization processing.

[0072] An image acquisition unit is configured to perform feature extraction operations on a first target image after image preprocessing based on a preset network, and perform feature fusion operations on the image after the feature extraction operations to obtain the first target image after target processing, so as to use the first target image after target processing for head position detection and head confidence detection.

[0073] In some specific embodiments, the first alarm determination module 12 includes:

[0074] A first information acquisition unit is configured to perform head position detection and head confidence detection on the first target image to obtain initial head information in the first target image; the initial head information includes a head position and a head position confidence.

[0075] A second information acquisition unit is configured to remove redundant head information from the initial head information based on the head position confidence to obtain target head information in the first target image.

[0076] In some specific embodiments, the driver self-service physical examination anti-cheating device includes:

[0077] An information comparison unit is configured to determine target examinee information corresponding to the examinee, and compare the target examinee information with expected examinee information obtained in advance.

[0078] A first alarm unit is configured to not trigger an alarm message if the target examinee information is consistent with the expected examinee information, and trigger an alarm message if the target examinee information is inconsistent with the expected examinee information.

[0079] In some specific embodiments, the first alarm determination module 12 includes:

[0080] A person determination unit is configured to determine the examinee corresponding to the target head information.

[0081] A first determination unit is configured to determine whether the examinee changes and whether the number of examinees included in the target head information exceeds one within a preset time period.

[0082] A second alarm unit is configured to trigger an alarm message if the examinee corresponding to the target head information changes and / or the number of examinees included in the target head information exceeds one, and not trigger an alarm message if the examinee corresponding to the target head information does not change and the number of examinees included in the target head information is only one.

[0083] In some specific embodiments, the first abnormal condition is that the degree of overlap between the area corresponding to the left eye position in the expected eye position and the area corresponding to the left viewing barrel position in the actual viewing barrel position is lower than a preset overlap threshold, and / or the degree of overlap between the area corresponding to the right eye position in the expected eye position and the area corresponding to the right viewing barrel position in the actual viewing barrel position is lower than a preset overlap threshold.

[0084] In some specific embodiments, the second warning determination module 14 includes:

[0085] An offset determination unit for determining the offset between the forehead center position and the viewing barrel center position;

[0086] A second determination unit for confirming that the second abnormal condition is met if the offset exceeds a preset offset threshold, and confirming that the second abnormal condition is not met if the offset does not exceed the preset offset threshold.

[0087] Furthermore, an embodiment of the present application also discloses an electronic device, Figure 5 It is a structural diagram of an electronic device 20 shown according to an exemplary embodiment, and the content in the figure cannot be considered as any limitation on the scope of use of the present application.

[0088] Figure 5 This is a schematic structural diagram of an electronic device 20 provided by an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. Among them, the memory 22 is used to store a computer program, and the computer program is loaded and executed by the processor 21 to implement the relevant steps in the driver self-examination anti-cheating method disclosed in any of the foregoing embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0089] In this embodiment, the power supply 23 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows is any communication protocol applicable to the technical solution of the present application, and no specific limitation is imposed on it here; the input / output interface 25 is used to obtain external input data or output data to the outside, and its specific interface type can be selected according to specific application needs, and no specific limitation is made here.

[0090] In addition, as a carrier for resource storage, the memory 22 may be a read-only memory, a random access memory, a disk, or an optical disc, etc., and the resources stored thereon may include an operating system 221, a computer program 222, etc., and the storage method may be temporary storage or permanent storage.

[0091] Among them, the operating system 221 is used to manage and control each hardware device and computer program 222 on the electronic device 20, and it can be Windows Server, Netware, Unix, Linux, etc. In addition to the computer program that can be used to complete the driver self-service physical examination anti-cheating method executed by the electronic device 20 disclosed in any of the foregoing embodiments, the computer program 222 may further include computer programs that can be used to complete other specific tasks.

[0092] Furthermore, the present application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the driver self-service physical examination anti-cheating method disclosed above is implemented. For the specific steps of this method, reference can be made to the corresponding content disclosed in the foregoing embodiments, and details will not be repeated here.

[0093] In this specification, the various embodiments are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. For the same or similar parts between the various embodiments, reference can be made to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and reference can be made to the method part for the relevant parts.

[0094] Those skilled in the art can further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in this article can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the components and steps of each example have been generally described according to their functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0095] The steps of the method or algorithm described in combination with the embodiments disclosed in this article can be directly implemented by hardware, a software module executed by a processor, or a combination of the two. The software module can be placed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, register, hard disk, removable disk, CD-ROM, or any other form of storage medium well-known in the technical field.

[0096] Finally, it should also be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising said element.

[0097] The technical solutions provided in this application have been introduced in detail above. Specific examples are used in this text to elaborate on the principles and implementation manners of this application. The descriptions of the above embodiments are only used to help understand the method and its core idea of this application. At the same time, for those of ordinary skill in the art, according to the idea of this application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to this application.

Claims

1. A driver self-service physical examination anti-cheating method, characterized in that: include: Performing real-time monitoring on the target area to be detected to obtain a first target image; Performing head position detection and head confidence detection on the first target image to obtain target head information, and determining whether to trigger alarm information based on the target head information; The head confidence detection is used to detect the probability of containing a human head in the head position area; Acquire a second target image when the examinee is undergoing visual function testing, determine the center position of the forehead using the second target image, and determine the expected eye position based on the center position of the forehead; the expected eye position includes the left eye position and the right eye position estimated based on the center position of the forehead; Based on the expected eye position and the actual visual barrel position, it is judged whether the first abnormal condition is met. If the first abnormal condition is not met, it is judged whether the second abnormal condition is met based on the offset between the center position of the forehead and the center position of the visual barrel. If the second abnormal condition is met, an alarm message is triggered; the actual visual barrel position includes the left visual barrel position and the right visual barrel position equipped by the visual function detection device for visual function detection.

2. The driver self-service physical examination anti-cheating method according to claim 1 is characterized in that: Before performing head position detection and head confidence detection on the first target image to obtain target head information, the method further includes: Performing an image preprocessing operation on the first target image; the image preprocessing operation includes a noise removal operation and a standardization operation; A feature extraction operation is performed on the first target image after image preprocessing based on a preset network, and a feature fusion operation is performed on the image after the feature extraction operation to obtain a first target image after target processing, so as to use the first target image after target processing to perform head position detection and head confidence detection.

3. The driver self-service physical examination anti-cheating method according to claim 1 is characterized in that: The performing head position detection and head confidence detection on the first target image to obtain target head information includes: Performing head position detection and head confidence detection on the first target image to obtain initial head information in the first target image; the initial head information includes the head position and the head position confidence; Redundant head information is removed from the initial head information based on the head position confidence level to obtain target head information in the first target image.

4. The driver self-service physical examination anti-cheating method according to claim 1, characterized in that: Also includes: Determine the target examinee information corresponding to the examinee, and compare the target examinee information with the expected examinee information obtained in advance; If the target physical examinee information is consistent with the expected physical examinee information, no alarm information is triggered; if the target physical examinee information is inconsistent with the expected physical examinee information, an alarm information is triggered.

5. The driver self-service physical examination anti-cheating method according to claim 1 is characterized in that: The determining whether to trigger the alarm information based on the target header information includes: Determine the physical examinee corresponding to the target header information; Determine whether the examinee has changed within a preset time period and whether the number of examinees included in the target header information exceeds one; If the person being examined corresponding to the target header information changes, and / or the number of persons being examined contained in the target header information exceeds one, an alarm message is triggered; if the person being examined corresponding to the target header information does not change, and the number of persons being examined contained in the target header information is only one, no alarm message is triggered.

6. The driver self-service physical examination anti-cheating method according to any one of claims 1 to 5, characterized in that: The first abnormal condition is that the overlap between the area corresponding to the left eye position in the expected eye position and the area corresponding to the left visual barrel position in the actual visual barrel position is lower than a preset overlap threshold, and / or the overlap between the area corresponding to the right eye position in the expected eye position and the area corresponding to the right visual barrel position in the actual visual barrel position is lower than a preset overlap threshold.

7. The driver self-service physical examination anti-cheating method according to any one of claims 1 to 5, characterized in that: The determining whether the second abnormal condition is met based on the offset between the center position of the forehead and the center position of the visual barrel includes: Determining the offset between the center position of the forehead and the center position of the visual barrel; If the offset exceeds the preset offset threshold, it is determined that the second abnormal condition is met; if the offset does not exceed the preset offset threshold, it is determined that the second abnormal condition is not met.

8. A driver self-service physical examination anti-cheating device, characterized in that: include: A region monitoring module, used for real-time monitoring of the target region to be detected to obtain a first target image; a first alarm determination module, configured to perform head position detection and head confidence detection on the first target image to obtain target head information, and determine whether to trigger alarm information based on the target head information; The head confidence detection is used to detect the probability of containing a human head in the head position area; A position determination module, used to obtain a second target image when the examinee is undergoing visual function testing, determine the center position of the forehead using the second target image, and determine the expected eye position based on the center position of the forehead; the expected eye position includes the left eye position and the right eye position estimated based on the center position of the forehead; The second alarm judgment module is used to judge whether the first abnormal condition is met based on the expected eye position and the actual visual barrel position. If the first abnormal condition is not met, whether the second abnormal condition is met is judged based on the offset between the center position of the forehead and the center position of the visual barrel. If the second abnormal condition is met, an alarm message is triggered; the actual visual barrel position includes the left visual barrel position and the right visual barrel position equipped by the visual function detection device for visual function detection.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, used to execute the computer program to implement the driver's self-service physical examination anti-cheating method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Used to store a computer program, which, when executed by a processor, implements the driver's self-service physical examination anti-cheating method as described in any one of claims 1 to 7.

Images