Coordinate measurement eyeglasses, coordinate measurement methods, devices, apparatuses, and storage media thereof

Abstract

The application relates to the technical field of coordinate detection, in particular to a coordinate measurement glasses, a coordinate measurement method, a device, equipment and a storage medium thereof. The method comprises the following steps: real-time receiving state information associated with an execution end; judging whether to generate an enabling instruction based on the state information; sending the enabling instruction to the execution end after the enabling instruction is generated; real-time receiving a feedback signal associated with the execution end; comparing the feedback signal with preset feedback information; real-time receiving a distance information group when the feedback signal matches the preset feedback information; generating an eyebox coordinate based on the distance information group; real-time receiving a continuous state information group associated with the execution end; judging whether to generate a disabling instruction based on the continuous state information group; and sending the disabling instruction to the execution end after the disabling instruction is generated. The application has the effect of automatically measuring an eyebox coordinate.

Description

Technical Field

[0001] This application relates to the technical field of coordinate measurement, and in particular to coordinate measuring glasses, coordinate measuring methods, devices, equipment and their storage media. Background Technology

[0002] With societal development, products in the field of in-vehicle head-up displays (HUDs) have gradually come into the public eye. An in-vehicle HUD projects information such as vehicle speed, fuel level or battery level, and navigation onto the windshield through refraction. Drivers can see the road ahead while simultaneously viewing information like speed, navigation, fuel level, or battery level without looking down or turning their heads, thus improving driving safety.

[0003] During the development of an in-vehicle head-up display (HUD) system, developers need to pre-measure the coordinates of the driver's head-up camera. The existing method involves developers using a laser measuring ruler to measure the distances between the driver's head-up camera and surrounding objects, then manually inputting this distance information into the software to calculate the head-up camera's coordinates, thus completing the positioning of the head-up camera. However, using a laser measuring ruler requires multiple manual measurements and data entry into the software, reducing development efficiency. The inventor believes an improvement is needed. Summary of the Invention

[0004] To improve the efficiency of measuring eyebox coordinates, this application provides coordinate measuring glasses, coordinate measuring method, apparatus, device and storage medium thereof.

[0005] The purpose of this application is to provide a coordinate measurement method with the function of real-time coordinate information measurement to improve development efficiency.

[0006] The above-mentioned objective of this application is achieved through the following technical solution: A coordinate measurement method, comprising: Receive status information associated with the execution end in real time; Based on the status information, determine whether to generate an activation command; Once the activation command is generated, it is sent to the execution end. Receive feedback signals associated with the execution end in real time; The feedback signal is compared with preset feedback information; When the feedback signal matches the preset feedback information, the distance information group is received in real time; Based on the distance information set, generate the eye box coordinates; Receives continuous status information groups associated with the execution end in real time; Based on the continuous state information group, determine whether to generate a deactivation command; Once the deactivation command is generated, it is sent to the execution end.

[0007] In the above scheme, the activation command is first determined based on the status information related to the execution end. This ensures that the execution end is only activated when it is in use, allowing it to receive distance information sets under these conditions. This avoids excessive invalid data caused by the execution end receiving distance information sets when it is idle. Simultaneously, the execution end receives distance information sets, replacing the manual measurement of eye box coordinates using a laser ruler, which improves both the efficiency and accuracy of eye box coordinate measurement. Secondly, the activation command is triggered automatically by acquiring the execution end's status information, eliminating the need for manual activation and improving ease of operation. Furthermore, after activation, continuous status information sets from the execution end are received in real time to determine whether the execution end is being used, i.e., whether it remains in use or has switched from use to idle. When a deactivation command is determined based on the continuous status information sets, it is sent to the execution end. The execution end then responds to the deactivation command and stops receiving distance information sets, reducing the generation of invalid data related to distance information sets.

[0008] Optionally, the step of determining whether to generate an activation command based on the status information includes: The state information is parsed to obtain image information and force information associated with the target object; the target object is the driver's seat. Based on the image information, the initial contour features of the image are obtained; The initial contour features are compared with the preset initial pupil contour features: When the initial contour feature matches the preset pupil initial contour feature, based on the force information, it is determined whether to generate an enable command; When the force information matches the preset force information, an activation command is generated.

[0009] By adopting the above technical solution, image information is received to record whether the user is wearing the execution device, and force information associated with the target object is received to record whether the user is located at the target object's position when wearing the execution device. The status information is parsed while simultaneously acquiring image and force information, eliminating the need for multiple status information parsing steps, saving information acquisition steps and improving method execution efficiency. Force data is used to record the pressure values ​​experienced by the target object. When the initial contour features match the preset pupil initial contour features and the force data matches the preset force information, it indicates that the user is both wearing the execution device and located at the target object's position, proving that the user is using the execution device. An activation command is generated to turn on the execution device, realizing the function of automatically activating the execution device.

[0010] Optionally, the step of determining whether to generate a deactivation instruction based on the continuous state information group includes: The continuous state information group is parsed to obtain a first continuous image group and a second continuous image group; the image data contained in the first continuous image group and the image data contained in the second continuous image group are different; Extract the time information of the images in the first continuous image group, sort the first continuous image group according to the chronological order of the time information, and determine the first initial time and the first final time; set the image associated with the first initial time as the first initial image, and set the image associated with the first final time as the first final image; the time interval between the first initial image and the first final image is preset to a certain duration; Extract the contour features of the first initial image and mark the contour features as the first initial contour features; extract the contour features of the first final image and mark the contour features as the first final contour features. The first initial contour feature is compared with the first final contour feature: When the first initial contour feature does not match the first final contour feature, the time information of the images in the second continuous image group is extracted, and the second continuous image group is sorted according to the order of the time information to determine the second initial time and the second final time; the image associated with the second initial time is set as the second initial image, and the image associated with the second final time is set as the second final image; the time interval between the second initial image and the second final image is preset to a certain duration. Extract the contour features of the second initial image and label the contour features as the second initial contour features; extract the contour features of the second final image and label the contour features as the second final contour features. The second initial contour feature is compared with the second final contour feature: When the second initial contour feature does not match the second final contour feature, a deactivation command is generated.

[0011] By adopting the above technical solution, a first continuous image group is received to confirm whether the user is continuously wearing the execution terminal, and a second continuous image group is received to confirm whether the user is using the execution terminal normally. Simultaneously receiving the first and second continuous image groups allows the processing terminal to acquire the necessary information all at once, improving operational efficiency. The first initial image is used in conjunction with the second initial image, and the second initial image is used in conjunction with the second final image to determine whether there are changes in the state of the execution terminal at the first initial time and at the first final time. The time interval between the first initial image and the first final image is preset to accurately determine whether the first final image has changed relative to the first initial image within a certain period. Therefore, in the above solution, it is possible to determine whether the user is wearing the execution terminal, and simultaneously determine whether the visual field image of the execution terminal is in a usage state. When the first final contour feature changes compared to the first initial contour feature, and the second final contour feature changes compared to the second initial contour feature, it is determined that the execution terminal is in an unused state, and thus a deactivation command is generated to deactivate the execution terminal.

[0012] Optionally, while performing the step of receiving the distance information group in real time, and before performing the step of generating the eyebox coordinates, the coordinate measurement method further includes: Real-time reception of second image information; Associate the second image information with the distance information group; The second image information is compared with the preset field-of-view image information to determine whether the second image information is a valid field-of-view image; When the second image information matches the preset field of view image information, the distance information group associated with the second image information is marked as valid data, and eye box coordinate information is generated.

[0013] By adopting the above technical solution, the second image information is received to determine whether the user's eye box orientation meets the preset orientation after the user wears the actuator and sits in the driver's seat, thus avoiding the generation of a large amount of invalid coordinate data when the user looks in other directions while wearing the actuator and sitting in the driver's seat. The second image information is associated with a distance information group. When the second image information matches the preset field of view image information, it proves that the distance information group associated with the second image information is valid data and eye box coordinates can be generated based on the distance information group, realizing the function of automatically judging whether the distance information group is valid data and the function of automatically generating eye box coordinates. Eye box coordinate information generated based on invalid data will also result in invalid results during the development process, so it is necessary to filter out valid data to improve development efficiency.

[0014] Optionally, the step of comparing the second image information with preset field-of-view image information to determine whether the second image information is a valid field-of-view image includes: Extract the contour features from the second image information and label the contour features as the third contour features; The third contour feature is compared with the preset visual contour feature: When the third contour feature matches the preset field of view contour feature, the second image information is determined to be a valid field of view image; When the third contour feature does not match the preset field of view contour feature, the second image information is determined to be an invalid field of view image.

[0015] By employing the above technical solution, the third contour feature of the second image information is extracted, enabling the processing end to focus on contour features during comparison and improving comparison efficiency. When the third contour feature matches the preset field-of-view contour feature, it proves that the second image information is a valid field-of-view image, and further proves that the distance information group associated with the second image information is valid data. When the third contour feature does not match the preset field-of-view contour feature, it proves that the second image information is an invalid field-of-view image, and further proves that the distance information group associated with the second image information is invalid data. This achieves the function of automatically filtering valid data and improves the accuracy of the data.

[0016] The second objective of this application is to provide a coordinate measuring device.

[0017] The above-mentioned objective 2 of this application is achieved through the following technical solution: A coordinate measuring device, comprising: Status information receiving module: Receives status information associated with the execution end in real time; Enable Information Judgment Module: Based on the status information, determine whether to generate an enable command; Enable command sending module: After the enable command is generated, the enable command is sent to the execution end; Feedback signal receiving module: Receives feedback signals associated with the execution end in real time; Feedback signal comparison module: compares the feedback signal with preset feedback information; Distance information group receiving module: When the feedback signal matches the preset feedback information, it receives the distance information group in real time; Eye box coordinate generation module: Generates eye box coordinates based on the distance information group; Continuous Status Information Group Receiving Module: Receives continuous status information groups associated with the execution end in real time; Deactivation instruction determination module: Based on the continuous status information group, determine whether to generate a deactivation instruction; Deactivation command sending module: After generating the deactivation command, the module sends the deactivation command to the execution end.

[0018] The third objective of this application is to provide a computer device.

[0019] The third objective of this invention is achieved through the following technical solution: A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the steps of the coordinate measurement method as described in any of the above embodiments.

[0020] The fourth objective of this application is to provide a computer-readable storage medium.

[0021] The fourth objective of this invention is achieved through the following technical solution: A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the coordinate measurement method as described in any of the above embodiments.

[0022] The fifth objective of this application is to provide a coordinate measuring glasses that can measure eyebox coordinates in real time to improve development efficiency.

[0023] The fifth objective of this invention is achieved through the following technical solution: A coordinate measuring glasses includes a housing, a frame, a distance measuring device, and an adjustment assembly. The housing is mounted on a connecting portion of the frame, the adjustment assembly is mounted inside the housing, and the distance measuring device is mounted on the adjustment assembly. The distance measuring device is located inside the housing, and the top of the housing has an opening for the distance measuring device to enter and exit the housing. The adjustment assembly is used to drive the distance measuring device to move relative to the connecting portion. The coordinate measuring glasses also include an image acquisition unit and a computer device as described above. The image acquisition unit is mounted on the frame and located on the side of the lens of the frame. The image acquisition unit is connected to the computer device, and the adjustment assembly is also connected to the computer device.

[0024] By adopting the above technical solution, compared to a laser measuring ruler, the distance measuring device, located at the connection point of the coordinate measuring glasses, can measure a more accurate set of distance information for the eye box, improving data accuracy. When the developer uses the coordinate measuring glasses, the computer generates an activation command and sends it to the adjustment component and the distance measuring device. The adjustment component responds to the activation command and drives the distance measuring device through the opening into the housing. The distance measuring device responds to the activation command and measures the distance information set, achieving automatic activation. When the developer stops using the coordinate measuring glasses, the computer generates a deactivation command and sends it to the adjustment component and the distance measuring device. The adjustment component responds to the deactivation command and drives the distance measuring device to reset at the connection point of the eyeglass frame. The distance measuring device responds to the deactivation command and stops measuring the distance information set, achieving automatic deactivation. After the distance measuring device is activated, it sends a feedback signal to the computer. The computer responds to the feedback signal and controls the start of the distance measuring device and the image acquisition unit. Based on the distance information set of the distance measuring device and the second image information from the image acquisition unit, the computer determines whether to generate eye box coordinates, achieving automatic determination of whether to generate eye box coordinates, thus improving the accuracy of measuring eye box coordinates.

[0025] In summary, this application includes at least one of the following beneficial technical effects: 1. Compared to manually measuring the distance between the eye box and surrounding objects using a laser measuring ruler, this method receives distance information groups in real time and automatically generates eye box coordinates based on these groups, thus achieving the function of automatically measuring eye box coordinates and improving the efficiency of measuring eye box coordinates. 2. Receiving the first continuous image group can more accurately record the process of the user from wearing the actuator to removing the actuator over a period of time, and receiving the second continuous image group can more accurately record the change process of the user's field of vision over a period of time, thus improving the accuracy of the data; 3. When the third contour feature matches the preset visual field contour feature, it proves that the second image information is a valid visual field image, and further proves that the distance information group associated with the second image information is valid data, thus realizing the function of automatically determining whether the distance information group is valid data. When the third contour feature does not match the preset visual field contour feature, it proves that the second image information is an invalid visual field image, and further proves that the distance information group associated with the second image information is invalid data, thus realizing the function of automatically detecting valid data and improving the accuracy of the data. Attached Figure Description

[0026] Figure 1 This is a schematic diagram of the overall structure of the coordinate measuring glasses according to an embodiment of this application; Figure 2 This is a cross-sectional structural diagram of the housing in the coordinate measuring glasses according to an embodiment of this application; Figure 3 yes Figure 2 A magnified view of part A in the middle; Figure 4 This is a flowchart illustrating a coordinate measurement method according to an embodiment of this application; Figure 5 This is a schematic diagram of the specific process of step S2 of a coordinate measurement method according to an embodiment of this application; Figure 6 This is a structural block diagram of a coordinate measuring device according to an embodiment of this application; Figure 7 This is a structural block diagram of the computer device in the embodiments of this application.

[0027] In the diagram, 1 is the eyeglass frame; 11 is the connecting part; 2 is the ranging device; 3 is the adjusting component; 31 is the driving component; 32 is the housing; 321 is the opening; 322 is the baffle; 33 is the lead screw; 34 is the guide rod; 35 is the push rod; 36 is the spring; 37 is the connecting block; 4 is the image acquisition unit; 41 is the first camera; 42 is the second camera; 10 is the status information receiving module; 20 is the activation information judgment module; 30 is the activation command sending module; 40 is the feedback signal receiving module; 50 is the feedback signal comparison module; 60 is the distance information group receiving module; 70 is the eye box coordinate generation module; 80 is the continuous status information group receiving module; 90 is the deactivation command judgment module; and 100 is the deactivation command sending module. Detailed Implementation

[0028] The following is in conjunction with the appendix Figure 1 -Appendix Figure 7 This application will be described in further detail below.

[0029] This application discloses a coordinate measuring glasses, which is applied in the development of vehicle head-up display systems. During the development process, developers wear coordinate measuring glasses to measure distance information associated with the eye box, and then convert the distance information into eye box coordinates through a calculation formula.

[0030] Reference Figure 1 and Figure 2 The coordinate detection glasses include a frame 1, a distance measuring device 2, an adjustment assembly 3, and a computer device. The frame 1 includes a connecting part 11 located between two lenses. The adjustment assembly 3 is mounted on the connecting part 11 of the frame 1, and the distance measuring device 2 is mounted on the adjustment assembly 3. The adjustment assembly 3 and the distance measuring device 2 are connected to the computer device, thus enabling the computer device to control their operation. Specifically, the adjustment assembly 3 drives the distance measuring device 2 to move up and down relative to the connecting part 11. Because the distance measuring device 2 is mounted on the adjustment assembly 3 so that it is positioned on the connecting part 11, it is closer to the center of the glasses case. Compared to manual distance measurement using a laser measuring ruler, the distance information measured by the distance measuring device 2 is more accurate.

[0031] When the user wears the coordinate measuring glasses, the computer equipment control adjustment component 3 drives the distance measuring device 2 to rise relative to the connecting part 11. When the user stops using the coordinate measuring glasses, the computer equipment control adjustment component 3 drives the distance measuring device 2 to fall relative to the connecting part 11. This setting of the distance measuring device 2 makes it easier to retract the distance measuring device 2 when it is not in use. The adjustment component 3 protects the distance measuring device 2 from wear and tear, thus improving the service life of the distance measuring device 2.

[0032] See Figure 2 and Figure 3 A housing 32 is provided on the connecting part 11, and an opening 321 is provided on the top of the housing 32. The adjusting component 3 and the ranging device 2 are both mounted on the connecting part 11 through the housing 32. The adjusting component 3 is used to drive the ranging device 2 to move in a direction toward or away from the opening 321. The adjusting component 3 includes a driving member 31, a lead screw 33, a push rod 35, and a connecting block 37. The driving member 31 is installed on the bottom inner side of the housing 32. The length direction of the lead screw 33 is the same as the moving direction of the ranging device 2. One end of the lead screw 33 is coaxially fixedly connected to the output end of the driving member 31, and the other end of the lead screw 33 is rotatably engaged with the housing 32. One end of the connecting block 37 has a threaded hole, and the connecting block 37 is sleeved on the lead screw 33 through the threaded hole, and the connecting block 37 is threadedly engaged with the lead screw 33 through the threaded hole. In this embodiment, the adjusting component 3 also includes a guide rod 34, which is located to the side of the lead screw 33, and the length direction of the guide rod 34 is consistent with the length direction of the lead screw 33. The two ends of the guide rod 34 are fixedly connected to the top and bottom of the housing 32, respectively. The connecting block 37 has a guide hole, and the connecting block 37 is sleeved on the guide rod 34 through the guide hole, and the connecting block 37 can slide relative to the guide rod 34.

[0033] When the drive unit 31 drives the lead screw 33 to rotate, under the guidance of the guide rod 34, the lead screw 33 drives the connecting block 37 to move towards or away from the opening 321, making the lifting and lowering of the connecting block 37 more stable. The length direction of the push rod 35 is consistent with the length direction of the lead screw 33. One end of the push rod 35 is fixedly connected to the top of the connecting block 37, and the other end of the push rod 35 is fixedly connected to the side wall of the ranging device 2. In order to improve the connection stability between the ranging device 2 and the connecting block 37, the number of push rods 35 is set to two, and the two push rods 35 are located on both sides of the ranging device 2.

[0034] The driving component 31 drives the lead screw 33 to rotate, and the lead screw 33 drives the connecting block 37 to move along the opening 321 toward or away from the housing 32. The connecting block 37 drives the push rod 35 to rise and fall, and the push rod 35 drives the ranging device 2 to pass through or retract into the opening 321, so as to realize the function of the driving component 31 driving the ranging device 2 to extend out of the housing 32 or retract into the housing 32.

[0035] When the computer device sends an enable or disable command to the drive unit 31, and the drive unit 31 responds to the enable command and drives the ranging device 2 to rise, the detection end of the ranging device 2 protrudes through the opening 321, and the computer device controls the ranging device 2 to start ranging operation. When the drive unit 31 responds to the disable command and drives the ranging device 2 to descend, the ranging device 2 retracts into the housing 32 through the opening 321, and the computer device controls the ranging device 2 to stop working. When the ranging device 2 is idle inside the housing 32, the housing 32 can protect the ranging device 2.

[0036] Reference Figure 2 and Figure 3 A baffle 322 is horizontally arranged inside the housing 32, with an inlet / outlet for the ranging device 2 and two push rods 35 to pass through and exit the baffle 322. One of the push rods 35 is fitted with a spring 36, one end of which is fixedly connected to the baffle 322, and the other end is fixedly connected to the connecting block 37. When the spring 36 is in its natural state, the ranging device 2 is located inside the housing 32. When the lead screw 33 drives the connecting block 37 to rise, the connecting block 37 gradually compresses the spring 36. The thrust of the spring 36 on the connecting block 37 gradually increases with the rising height of the connecting block 37, while the rising speed of the connecting block 37 gradually decreases with the thrust of the spring 36. The spring 36 acts as a buffer between the baffle 322 and the connecting block 37. When the lead screw 33 drives the connecting block 37 to descend, the connecting block 37 gradually relaxes the spring 36, the thrust of the spring 36 on the connecting block 37 gradually decreases, and the descending speed of the connecting block 37 gradually slows down. The spring 36 plays the role of adjusting the reset speed of the ranging device 2, so that the reset of the ranging device 2 is more stable.

[0037] Reference Figure 1 The coordinate measuring glasses also include an image acquisition unit 4. In this embodiment, the image acquisition unit 4 includes a second camera 42 and two first cameras 41, with the two first cameras 41 respectively mounted above the two lenses. The second camera 42 is mounted on the side of the housing 32 facing away from the connecting part 11. When the user wears the coordinate measuring glasses, the two first cameras 41 are used to capture images near the user's eye box area; the second camera 42 is used to capture the field of vision image seen by the user. Both the first cameras 41 and the second cameras 42 are connected to a computer device to transmit the images captured by the first cameras 41 and the second cameras 42 to the computer device.

[0038] When the user wears coordinate measuring glasses and sits in the driver's seat, based on the image information captured by the first camera 41 and the force information from the force sensor in the driver's seat, the computer device generates an activation command and sends it to the drive unit 31. The drive unit 31 responds to the activation command and drives the lead screw 33 to rotate, which in turn drives the connecting block 37 to rise. The connecting block 37 pushes the push rod 35 to rise and compresses the spring 36. The push rod 35 pushes the ranging device 2 to rise and causes the ranging device 2 to pass through the opening 321 of the housing 32. At this time, the computer device activates the ranging device 2 through the activation command, realizing the function of automatic activation.

[0039] After the ranging device 2 is activated, it begins measuring the distance information of the user's eye box from surrounding objects in multiple directions. Simultaneously, the second camera 42 begins capturing second image information of the user. The ranging device 2 sends the distance information sets to the computer device, and the second camera 42 sends the second image information to the computer device. The computer device determines whether to generate eye box coordinate information based on the distance information sets and the second image information.

[0040] When the computer device generates a disable command, it sends the disable command to the drive unit 31. The drive unit 31 responds to the disable command and drives the lead screw 33 to reverse. The lead screw 33 drives the connecting block 37 to descend. The connecting block 37 drives the push rod 35 to descend and releases the spring 36. The push rod 35 drives the ranging device 2 to descend and causes the ranging device 2 to retract into the housing 32 through the opening 321. The computer device disables the ranging device 2 through the disable command, realizing the function of automatic disable.

[0041] This application also discloses a coordinate measurement method, which is based on the following preprocessing steps: An image database and a distance information database are established. The image database is used to store image information, a first continuous image group, a second continuous image group, second image information, and preset images. The distance information database is used for distance information groups. An image information storage area is established to store image information acquired by the detection end, the first continuous image group, the second continuous image group, second image information, initial contour features obtained by parsing the image information, first initial contour features and first final contour features obtained by parsing the first continuous image group, second initial contour features and second final contour features obtained by parsing the second continuous image group, and third field-of-view contour features obtained by parsing the second image information. A distance information storage area is established to store distance information in the distance information groups acquired by the detection end.

[0042] Reference Figure 1 Coordinate measurement methods include: S1. Receive status information associated with the execution end in real time. The execution end is the coordinate detection glasses in the above embodiment.

[0043] In this embodiment, the status information includes image information and force information associated with the target object, which refers to the driver's seat. The image information is obtained by the first camera 41 capturing images of the area corresponding to the user's eye box position. The force information is obtained by a pressure sensor inside the driver's seat sending a signal to the actuator. The status information of the actuator is used to record whether the user is wearing the actuator and whether the user is sitting in the driver's seat while wearing the actuator. When the first camera 41 captures an image, it sends it to a computer device. The image is associated with the signal sent to the computer device by the pressure sensor, and then the image and signal are stored together in the computer storage medium.

[0044] S2. Based on the status information, determine whether to generate an enable command.

[0045] Specifically, step S2 includes: S21. Parse the state information to obtain image information and force information associated with the target object.

[0046] The status information is broken down into multiple sub-information segments based on its format type. When the sub-information's format type is image, it is considered image information; when its format type is data type, it is considered force information. Image and force information are acquired simultaneously to reduce the number of times the status information is parsed and improve the method's execution efficiency.

[0047] S22. Based on image information, obtain the initial contour features of the image.

[0048] The initial contour features are extracted from image information. In this embodiment, the following method is used to extract the initial contour features from the image information: (1) Use the weighted average method to process the image information into grayscale, the specific formula is: Gray(i,j) = 0.299*R(i,j) + 0.578*G(i,j) + 0.114*B(i,j), where i and j represent the number of pixels in the length direction and the number of pixels in the width direction of the image, respectively. The three functions R(), G(), and B() process the three primary colors of the image to obtain a grayscale image. (2) The grayscale image is binarized using the cv2.threshold() function in Python to obtain a binarized image; (3) Use the Sobel operator to calculate the initial contour features of the binarized image.

[0049] S23. Compare the initial contour features with the preset pupil initial contour features.

[0050] When the image information includes both the user's eyelid image and pupil image, the initial contour feature also includes the pupil feature. Therefore, the initial contour feature is compared with a preset initial pupil contour feature, and the similarity between the two is calculated. This similarity is then compared with a similarity threshold. If the similarity is higher than the threshold, the initial contour feature is considered a match with the preset initial pupil contour feature, thus confirming that the initial contour feature includes the pupil feature. The similarity threshold can be set according to the specific circumstances.

[0051] In this embodiment, the similarity threshold is set to 60%. A perceptual hash algorithm is used to proportionally reduce the initial contour feature to 64 pixels. The average grayscale value of all pixels in the initial contour feature is calculated. The grayscale value of each pixel is compared to the average grayscale value. When the grayscale value of a pixel is greater than the average grayscale value, the associated number for that pixel is 1; when the grayscale value of a pixel is less than the average grayscale value, the associated number is 0. The associated numbers of the 64 pixels are combined and compared with the 64-bit number of the preset pupil initial contour feature to obtain the similarity. When the corresponding numbers in the two sets of 64-bit numbers are the same, the number of identical numbers divided by 64 is the similarity. When the similarity is higher than the 60% threshold, it is determined that the initial contour feature contains the pupil contour feature, and thus it is determined that the image information contains pupil information.

[0052] It should be noted that since the images corresponding to the pupils of different drivers are different, in this embodiment, the similarity threshold is set to 60%, that is, when pupil information is detected, it can be determined that the user has worn the execution terminal, thus improving the applicability of the method.

[0053] S24-1. If the initial contour features do not match the preset pupil initial contour features, then return to step S21.

[0054] S24-2. When the initial contour features match the preset pupil initial contour features, determine whether to generate an enable command based on the force information.

[0055] When the image information is determined to contain pupil information, it is also necessary to determine whether the user is in the driver's seat to improve the accuracy of determining whether the actuator is in use. That is, the conditions for activating the actuator are met when the user is wearing the actuator and sitting in the driver's seat.

[0056] In this embodiment, the system determines whether a user is sitting in the driver's seat by judging the force information of the driver's seat. This force information is represented by force data, which indicates the specific force borne by the driver's seat. When the force data is higher than a preset force value, it is determined that the user is in the driver's seat. For example, if the preset force data is 50 kg and the measured force data is 60 kg, the measured force data is obviously greater than the preset force data, thus confirming that the user is in the driver's seat. When it is determined that the image information contains pupil information and the user is in the driver's seat, it proves that the execution terminal is in use.

[0057] S25-1. When the force data matches the preset force information, determine to generate an activation command.

[0058] S25-2. If the force data does not match the preset force information, return to step S21.

[0059] S3. After generating the enable command, send the enable command to the execution end.

[0060] When the execution end receives the enable command, it responds to the enable command and executes the corresponding action, thus completing the enable process.

[0061] S4. Receive feedback signals associated with the execution end in real time.

[0062] Feedback signals are signals sent from the execution end to the processing end in response to an enable or disable command, indicating whether the corresponding action of the enable or disable command has been completed.

[0063] S5. Compare the feedback signal with the preset feedback information.

[0064] The preset feedback information is the signal returned by the execution end after responding to the enable command and completing the corresponding action. When the feedback signal matches the preset feedback signal, it is determined that the execution end has completed the corresponding action of the enable command, and thus the execution end is determined to be enabled. When the feedback signal does not match the preset feedback signal, it indicates that the execution end has not completed the corresponding action of the enable command due to some initial reason, and thus the execution end is determined to be disabled.

[0065] S6. When the feedback signal matches the preset feedback information, receive the distance information group in real time.

[0066] The distance information group is a combination of multiple distance data between the eye box inside the vehicle and surrounding objects. This distance data is used as the basis for generating the coordinates of the eye box.

[0067] S7. Generate eyebox coordinates based on distance information groups.

[0068] S8. Receive continuous status information groups associated with the execution end in real time.

[0069] When the feedback signal matches the preset feedback information, step S8 is executed. That is, step S8 can be executed synchronously with the step of receiving the real-time distance information group. The continuous status information group includes a first continuous image group and a second continuous image group. The image data contained in the first continuous image group and the image data contained in the second continuous image group are different.

[0070] Simultaneously with receiving distance information sets, the first camera 41 acquires a first continuous image set within a preset time period. When the user is continuously wearing coordinate detection glasses, this first continuous image set includes images containing pupil features; if the user initially wears the coordinate detection glasses but removes them within the preset time period, the first continuous image set includes images containing pupil features and images without pupil features. Similarly, simultaneously with receiving distance information sets, the second camera 42 acquires a second continuous image set within a preset time period. When the user is continuously wearing coordinate detection glasses and sitting in the driver's seat, this second continuous image set includes images containing features of the forward field of view; if the user initially wears the coordinate detection glasses and sits in the driver's seat (at which point the execution device is in use), but removes the coordinate detection glasses within the preset time period (i.e., the execution device's state changes), then the second continuous image set includes images containing features of the forward field of view and images without such features. Thus, the combination of the first and second continuous image sets is used to determine whether the user has been continuously using the execution device within the preset time period.

[0071] The first and second consecutive image groups are received synchronously, thus representing changes in pupil image and visual field image respectively within the same time period. The first camera 41 and the second camera 42 transmit the captured first and second consecutive image groups to the computer device in real time. The computer device then associates the first and second consecutive image groups based on their reception time and stores them together in the database. This allows for subsequent determination of whether the user is using the execution terminal by combining the first and second consecutive image groups.

[0072] Specifically, the images in the first continuous image group are pupil images detected by the first camera 41 and associated with the user's eye box. For example, if the reception of the first continuous image group begins at 10:00:00 and ends at 10:00:10, then the first continuous image group records the changes in the pupil images within those 10 seconds. The images in the second continuous image group are visual field images detected by the detection end. For example, if the reception of the second continuous image group begins at 10:00:00 and ends at 10:00:10, then the second continuous image group records the changes in the visual field images within those 10 seconds.

[0073] S9. Based on the continuous status information group, determine whether to generate a shutdown instruction.

[0074] Step S9 includes: S91. Parse the continuous state information group to obtain the first continuous image group and the second continuous image group.

[0075] S92. Extract the time information of the images in the first continuous image group, sort the first continuous image group according to the chronological order of the time information, and determine the first initial time and the first final time. Set the image associated with the first initial time as the first initial image, and set the image associated with the first final time as the first final image; the time interval between the first initial image and the first final image is preset to a certain duration.

[0076] The time interval between the first initial image and the first final image can be set according to actual conditions. It should be noted that during this time period of the first consecutive image group, there may be instances where the execution terminal switches from an active state to a disabled state and then back to an active state within a short period. Therefore, a preset duration is set for the time interval between the first initial image and the first final image. The preset duration can be set according to actual conditions, for example, to 10 seconds, 20 seconds, or 30 seconds. In this embodiment, the preset time interval is set to 10 seconds, which can filter out most instances where the execution terminal switches from an active state to a disabled state and then back to an active state within a short period of time in the first consecutive image group, thereby further improving the applicability of the method.

[0077] Since the user is wearing the device throughout the acquisition of the first consecutive image group, the first initial image best represents the state of the device when it is worn. The first final image represents the final state of the device during the first consecutive image group. When the first initial image matches the first final image, it is determined that the device has been worn during this period. When the first initial image does not match the first final image, it is determined that the device has switched from being worn to not being worn during this period.

[0078] S93. Extract the contour features of the first initial image and mark the contour features as the first initial contour features. Extract the contour features of the first final image and mark the contour features as the first final contour features.

[0079] The first initial contour feature is the pupil-related contour feature extracted from the first initial image, and the first final contour feature is the contour feature extracted from the first final image. In this embodiment, the method for extracting contour features is as follows: the first initial image is processed into a grayscale image using a weighted average method, then the grayscale image is binarized using the cv2.threshold() function in Python to obtain a binarized image, and finally the Sobel operator is used to calculate the pupil image contour features on the binarized image.

[0080] S94. Compare the first initial contour feature with the first final contour feature.

[0081] The first initial contour feature is compared with the first final contour feature to calculate the similarity between them. This similarity is then compared to a similarity threshold. If the similarity is lower than the threshold, the first initial contour feature and the first final contour feature are determined to be mismatched. The similarity threshold can be set according to the actual situation.

[0082] In this embodiment, the similarity threshold is set to 80%. The first initial contour feature and the first final contour feature are proportionally reduced using a perceptual hash algorithm. The average grayscale value of all pixels in the first initial contour feature and the first final contour feature is calculated respectively. The grayscale values ​​of all pixels in the first initial contour feature are compared with the average grayscale value of the first initial contour feature to obtain a set of 64-bit numbers. The grayscale values ​​of all pixels in the first final contour feature are compared with the average grayscale value of the first final contour feature to obtain another set of 64-bit numbers. The similarity is obtained by comparing the two sets of 64-bit numbers. When the similarity is lower than 80% of the threshold, it is determined that the first initial contour feature and the first final contour feature do not match, and thus it is determined that the execution end switches from the wearing state to the non-wearing state.

[0083] S95-1. When the first initial contour feature matches the first final contour feature, return to step S91.

[0084] S95-2. When the first initial contour feature does not match the first final contour feature, extract the time information of the images in the second continuous image group, sort the second continuous image group according to the order of the time information, and determine the second initial time and the second final time.

[0085] When the first initial image matches the first final image, it is determined that the execution terminal is in the wearing state during this period. When the first initial image does not match the first final image, it is determined that the execution terminal switches from the wearing state to the non-wearing state during this period.

[0086] Specifically, the image associated with the second initial time is designated as the second initial image, and the image associated with the second final time is designated as the second final image; the time interval between the second initial image and the second final image is preset. The time interval between the second initial image and the second final image can be set according to the actual situation.

[0087] The second final image is the image associated with the last moment of a preset time period in the second consecutive image group.

[0088] S96. Extract the contour features of the second initial image and mark the contour features as the second initial contour features. Extract the contour features of the second final image and mark the contour features as the second final contour features.

[0089] The second initial contour feature is the contour feature of the eyebox field of view in the second initial image, and the second final contour feature is the contour feature of the second final image. The method for extracting contour features is as follows: use the weighted average method to process the second initial image into grayscale to obtain a grayscale image, then use the threshold() function to binarize the grayscale image to obtain a binarized image, and finally use the Sobel operator to calculate the contour features of the eyebox field of view image on the binarized image.

[0090] S97. Compare the second initial contour features with the second final contour features.

[0091] The second initial contour feature is compared with the second final contour feature to calculate the similarity between them. This similarity is then compared to a similarity threshold. If the similarity is lower than the threshold, the second initial contour feature and the second final contour feature are determined to be mismatched. The similarity threshold can be set according to the actual situation.

[0092] S98. When the second initial contour feature does not match the second final contour feature, a deactivation command is generated.

[0093] When the second initial image matches the second final image, it is determined that the user has been wearing coordinate detection glasses during this period, and the process returns to step S91; when the second initial image does not match the second final image, it proves that the user has taken off the coordinate detection glasses during the preset time period.

[0094] When the second initial contour feature does not match the second final contour feature, it indicates that the user has removed the coordinate detection glasses within a preset time period, and therefore it is necessary to determine and generate a deactivation command.

[0095] It should be noted that steps S91-S98 help avoid the situation where a user briefly removes and then puts the coordinate detection glasses back on, which could lead to the erroneous generation of a stop command, thereby further improving the applicability of the method and the accuracy of the detection.

[0096] S10. Send the deactivation command to the execution end. When the execution end receives the deactivation command, it stops receiving distance information groups.

[0097] Since users wearing coordinate measurement glasses and sitting in the driver's seat may be looking in other directions, in this application, the preset orientation is for the user to look towards the front of the vehicle (i.e., towards the windshield). When a user wearing coordinate measurement glasses and sitting in the driver's seat, but not looking towards the front of the vehicle, although distance information groups can still be received, there are a few cases of generating invalid distance information group data. Therefore, in order to minimize the generation of invalid distance information group data and further improve the effectiveness and accuracy of eye box coordinate detection, in some possible embodiments, while step S6 is being performed and before step S7, this coordinate measurement method further includes: A1. Receive second image information in real time.

[0098] The second image information contains the field of view that the user can see when wearing coordinate detection glasses. The second image information and the distance information group are received synchronously.

[0099] A2. Associate the second image information with the distance information group.

[0100] Since the distance information group and the second image information are received synchronously, the second image information obtained at each moment corresponds one-to-one with the distance information group received at each moment in time. Therefore, the second image information and the distance information group are associated.

[0101] A3. Compare the second image information with the preset field-of-view image information to determine whether the second image information is a valid field-of-view image.

[0102] The preset field-of-view image information is pre-set by staff and stored in a database. This preset field-of-view image information is an image containing the features of the field of view in front of the vehicle. The preset field-of-view image information is used to compare with second image information. When the second image information matches the preset field-of-view image information, the second image information is determined to be a valid field-of-view image, and therefore the distance information group associated with the second image information is determined to be valid data. When the second image information does not match the preset field-of-view image information, the second image information is determined to be an invalid field-of-view image, and the distance information group associated with the second image information is determined to be invalid data.

[0103] Specifically, the A3 steps include: A31. Extract the contour features of the second image information and mark these contour features as the third contour features.

[0104] The third contour feature is the visual field contour feature of the second image information. The method for extracting the contour feature is as follows: the second initial image is processed into a grayscale image using a weighted average method, and then the grayscale image is binarized using the cv2.threshold() function in Python to obtain a binarized image. Finally, the Sobel operator is used to calculate the visual field contour feature of the second image information on the binarized image.

[0105] A32. Compare the third contour feature with the preset vision contour feature.

[0106] Specifically, a preset visual field contour feature is used for comparison with a third contour feature. The third contour feature is compared with the preset visual field contour feature, and the similarity between the two is calculated. This similarity is then compared to a similarity threshold. If the similarity is higher than the threshold, the third contour feature is considered a match; if the similarity is lower than the threshold, the two are considered mismatched. The similarity threshold can be set according to actual conditions.

[0107] A33. When the third contour feature matches the preset field of view contour feature, the second image information is determined to be a valid field of view image.

[0108] When the third contour feature matches the preset visual field contour feature, the second image information is determined to be the visual field image when the user is using the execution terminal normally, and thus the second image information is determined to be a valid visual field image.

[0109] A34. When the third contour feature does not match the preset visual field contour feature, the second image information is determined to be an invalid visual field image.

[0110] When the third contour feature does not match the preset visual field contour feature, the second image information is determined to be an abnormal visual field image when the user uses the execution terminal, and thus the second image information is determined to be an invalid visual field image.

[0111] A4. When the second image information matches the preset field of view image information, the distance information group associated with the second image information is determined to be valid data, and the eye box coordinate information is generated.

[0112] When the second image information matches the preset field-of-view image information, the distance information group is determined to be valid data, and then eyebox coordinate information is generated based on the distance information group. When the second image information does not match the preset field-of-view image information, the distance information group associated with the second image information is determined to be invalid data, eyebox coordinates will not be generated, and the process returns to step S6.

[0113] The implementation principle of this application embodiment is as follows: When the user puts on the coordinate measuring glasses and sits in the driver's seat, the computer device receives image information and force information. It compares the image information with preset image information. When the image information matches the preset image information, it compares the force information with preset force information. When the force information matches the preset force information, the computer device generates an activation command and sends the activation command to the drive unit 31 and the ranging device 2. The drive unit 31 responds to the activation command and drives the ranging device 2 to rise through the opening 321 to the outside of the housing 32. The ranging device 2 responds to the activation command and begins to measure the distance information group. At the same time, the second camera 42 captures the second image information. The ranging device 2 sends the measured distance information group to the computer device. The second camera 42 sends the second image information to the computer device and compares the second image information with a preset field of view image. When the second image information matches the preset field of view image, the computer device generates eye box coordinate information based on the distance information group.

[0114] When the ranging device 2 starts ranging, the first camera 41 and the second camera 42 respectively capture the first continuous image group and the second continuous image group. The first initial image and the first final image are extracted from the first continuous image group, and the second initial image and the second final image are extracted from the second continuous image group. The first initial image and the first final image are compared. When the first final image changes relative to the first initial image, the second initial image and the second final image are compared. When the second final image changes relative to the second initial image, the computer device generates a stop command and sends the stop command to the drive unit 31 and the ranging device 2. The drive unit 31 responds to the stop command and drives the ranging device 2 to retract into the housing 32 through the opening 321. The ranging device 2 responds to the stop command and stops measuring the distance information group.

[0115] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0116] This application also discloses a coordinate measuring device, which corresponds one-to-one with the coordinate measuring methods described in the above embodiments. (Refer to...) Figure 6 The coordinate measuring device includes a status information receiving module 10, an activation information judgment module 20, an activation command sending module 30, a feedback signal receiving module 40, a feedback signal comparison module 50, a distance information group receiving module 60, an eyebox coordinate generation module 70, a continuous status information group receiving module 80, a deactivation command judgment module 90, and a deactivation command sending module 100. Detailed descriptions of each functional module are as follows: Status information receiving module 10: Receives status information associated with the execution end in real time.

[0117] Enable Information Judgment Module 20: Based on the status information, determine whether to generate an enable command.

[0118] Enable command sending module 30: After generating the enable command, it sends the enable command to the execution end.

[0119] Feedback signal receiving module 40: Receives feedback signals associated with the execution end in real time.

[0120] Feedback signal comparison module 50: compares the feedback signal with preset feedback information.

[0121] Distance information group receiving module 60: When the feedback signal matches the preset feedback information, it receives the distance information group in real time.

[0122] Eye box coordinate generation module 70: Generates eye box coordinates based on the distance information group.

[0123] Continuous Status Information Group Receiving Module 80: Receives continuous status information groups associated with the execution end in real time.

[0124] Deactivation instruction determination module 90: Based on the continuous status information group, determine whether to generate a deactivation instruction.

[0125] Deactivation instruction sending module 100: After generating the deactivation instruction, it sends the deactivation instruction to the execution end.

[0126] Specific limitations regarding the coordinate measuring device can be found in the limitations of the coordinate measuring method above, and will not be repeated here. Each module in the aforementioned coordinate measuring device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in hardware or independently of the processor in a computer device, or stored in software in the memory of a computer device, so that the processor can call and execute the operations corresponding to each module.

[0127] This application also discloses a computer device, including a memory, a processor, and a computer device stored in the memory and capable of running on the processor. When the processor executes the computer device, it performs the following steps: S1. Receive status information associated with the execution end in real time.

[0128] S2. Based on the status information, determine whether to generate an enable command.

[0129] S3. After the activation command is generated, the activation command is sent to the execution end.

[0130] S4. Receive feedback signals associated with the execution end in real time.

[0131] S5. Compare the feedback signal with the preset feedback information.

[0132] S6. When the feedback signal matches the preset feedback information, the distance information group is received in real time.

[0133] S7. Based on the distance information group, generate the eye box coordinates.

[0134] S8. Receive continuous status information groups associated with the execution end in real time.

[0135] S9. Based on the continuous state information group, determine whether to generate a deactivation command.

[0136] S10. After the deactivation instruction is generated, the deactivation instruction is sent to the execution end.

[0137] The processor can also execute any of the coordinate measurement methods described in the above embodiments.

[0138] This computer device is a server; its internal structure diagram can be found by referring to [reference needed]. Figure 7 The computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and the database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The computer's database stores continuous image group information, preset image information, and image information storage areas. The network interface is used for communication with external terminals via a network connection. When executed by the processor, the computer program implements a coordinate measurement method.

[0139] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, performs the following steps: S1. Receive status information associated with the execution end in real time.

[0140] S2. Based on the status information, determine whether to generate an enable command.

[0141] S3. After the activation command is generated, the activation command is sent to the execution end.

[0142] S4. Receive feedback signals associated with the execution end in real time.

[0143] S5. Compare the feedback signal with the preset feedback information.

[0144] S6. When the feedback signal matches the preset feedback information, the distance information group is received in real time.

[0145] S7. Based on the distance information group, generate the eye box coordinates.

[0146] S8. Receive continuous status information groups associated with the execution end in real time.

[0147] S9. Based on the continuous state information group, determine whether to generate a deactivation command.

[0148] S10. After the deactivation instruction is generated, the deactivation instruction is sent to the execution end.

[0149] When the computer program is executed by the processor, it can also implement any of the coordinate measurement methods described in the above embodiments.

[0150] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), Synchlink, DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0151] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A coordinate measurement method, characterized in that, include: The system receives real-time status information associated with the execution end, including image information and force information associated with the driver's seat. Based on the status information, determine whether to generate an activation command; Once the activation command is generated, it is sent to the execution end. Receive feedback signals associated with the execution end in real time; The feedback signal is compared with preset feedback information; When the feedback signal matches the preset feedback information, the distance information group is received in real time; The system receives second image information in real time, compares the second image information with preset field-of-view image information, and filters out the distance information group corresponding to the effective field of view. Based on the effective distance information group, generate eyebox coordinates; The system receives a continuous status information group associated with the execution end in real time. The continuous status information group includes a first continuous image group and a second continuous image group. The system parses the continuous status information group and extracts the first initial image and the first final image of the first continuous image group, as well as the second initial image and the second final image of the second continuous image group. The system compares the contour features of the first and last images within a preset time period. When the contour features of the two sets of images do not match, a deactivation command is generated. Based on the continuous state information group, determine whether to generate a deactivation command; Once the deactivation command is generated, it is sent to the execution end.

2. The coordinate measurement method according to claim 1, characterized in that, The step of determining whether to generate an activation command based on the status information includes: Based on the image information, the initial contour features of the image are obtained; The initial contour features are compared with the preset initial pupil contour features: When the initial contour feature matches the preset pupil initial contour feature, based on the force information, it is determined whether to generate an enable command; When the force information matches the preset force information, an activation command is generated.

3. The coordinate measurement method according to claim 1, characterized in that, The step of determining whether to generate a deactivation instruction based on the continuous state information group includes: The continuous state information group is parsed to obtain a first continuous image group and a second continuous image group; the image data contained in the first continuous image group and the image data contained in the second continuous image group are different; Extract the time information of the images in the first continuous image group, sort the first continuous image group according to the chronological order of the time information, and determine the first initial time and the first final time; set the image associated with the first initial time as the first initial image, and set the image associated with the first final time as the first final image; the time interval between the first initial image and the first final image is preset to a certain duration; Extract the contour features of the first initial image and mark the contour features as the first initial contour features; extract the contour features of the first final image and mark the contour features as the first final contour features. The first initial contour feature is compared with the first final contour feature: When the first initial contour feature does not match the first final contour feature, the time information of the images in the second continuous image group is extracted, and the second continuous image group is sorted according to the order of the time information to determine the second initial time and the second final time; the image associated with the second initial time is set as the second initial image, and the image associated with the second final time is set as the second final image; the time interval between the second initial image and the second final image is preset to a certain duration. Extract the contour features of the second initial image and label the contour features as the second initial contour features; extract the contour features of the second final image and label the contour features as the second final contour features. The second initial contour feature is compared with the second final contour feature: When the second initial contour feature does not match the second final contour feature, a deactivation command is generated.

4. The coordinate measurement method according to claim 1, characterized in that, While the step of receiving the distance information group in real time is being performed, and before the step of generating the eyebox coordinates, the coordinate measurement method further includes: Real-time reception of second image information; Associate the second image information with the distance information group; The second image information is compared with the preset field-of-view image information to determine whether the second image information is a valid field-of-view image; When the second image information matches the preset field of view image information, the distance information group associated with the second image information is marked as valid data, and eye box coordinate information is determined to be generated.

5. The coordinate measurement method according to claim 4, characterized in that, The step of comparing the second image information with preset field-of-view image information to determine whether the second image information is a valid field-of-view image includes: Extract the contour features from the second image information and label the contour features as the third contour features; The third contour feature is compared with the preset visual contour feature: When the third contour feature matches the preset field of view contour feature, the second image information is determined to be a valid field of view image; When the third contour feature does not match the preset field of view contour feature, the second image information is determined to be an invalid field of view image.

6. A coordinate measuring device, characterized in that, include: Status information receiving module (10): receives status information associated with the execution end in real time, including image information and force information associated with the driver's seat; Enable Information Judgment Module (20): Based on the status information, determine whether to generate an enable command; Enable command sending module (30): After the enable command is generated, the enable command is sent to the execution end; Feedback signal receiving module (40): receives feedback signals associated with the execution end in real time; Feedback signal comparison module (50): compares the feedback signal with preset feedback information; Distance information group receiving module (60): When the feedback signal matches the preset feedback information, it receives the distance information group in real time; Effective data filtering module (110): receives second image information in real time, compares the second image information with preset field of view image information, and filters out the distance information group corresponding to the effective field of view; Eye box coordinate generation module (70): Generates eye box coordinates based on the distance information group; Continuous status information group receiving module (80): receives continuous status information groups associated with the execution end in real time, the continuous status information groups including a first continuous image group and a second continuous image group; Disabling instruction judgment module (90): Based on the continuous state information group, determine whether to generate a disabling instruction; Disable instruction sending module (100): After generating the disable instruction, the disable instruction is sent to the execution end.

7. A computer device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the coordinate measurement method as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the coordinate measurement method as described in any one of claims 1-5.

Images