AR augmented reality interaction method and system using microcomputer host

Abstract

The present application relates to the field of image processing technology, and specifically to an AR augmented reality interaction method and system using a microcomputer host, the method comprising: using a microcomputer host to collect images in real time during the AR interaction process; filtering and adjusting the images by analyzing the regional interference to which the images are subjected during the real-time interaction process; and using the filtered images for augmented reality interaction. The present application aims to dynamically optimize and adjust the filtering process of the real-time collected images, and effectively improve the stability of the augmented reality interaction.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to an AR augmented reality interaction method and system using a microcomputer host. Background Art

[0002] With the continuous improvement of the performance of microcomputer hosts, their processor computing speed has increased and their graphics processing capabilities have been enhanced, providing stronger computing support for augmented reality interaction. The microcomputer host needs to cooperate with various sensors such as cameras, depth sensors, inertial measurement units, etc. to perceive the real environment information in real time, accurately determine the user's position and posture, as well as the position and shape of surrounding objects, so as to ensure the precise integration of virtual information and the real world. Although the performance of microcomputer hosts continues to improve, there is still a certain gap compared to traditional large computers. At present, the naturalness and comfort of augmented reality interaction still have room for improvement. For example, the accuracy and stability of gesture recognition still need to be continuously optimized to avoid misoperation.

[0003] In the field of augmented reality interaction methods, the comparative document CN117311506A proposes a model, that is, to collect information through the local wearable device and control device, and transmit it to the remote wearable device and control device for interactive analysis, so as to achieve local and remote augmented reality interaction. However, in this interaction process, the accuracy of data collection and information processing has a direct impact on the accuracy of augmented reality interaction, and in the current augmented reality interaction process, there is still a large deviation problem in the information collection and processing link based on the microcomputer host, which to a certain extent restricts the effect and application expansion of augmented reality interaction.

[0004] In the process of augmented reality interaction using a microcomputer host, the existing technology needs to coordinate various sensors such as cameras, depth sensors, inertial measurement units, etc. to perceive the real environment information in real time and accurately determine the user's position and posture; however, in the process of data collection and analysis, there are deviations in data collection quality due to scene changes, which leads to large errors in interaction. Summary of the invention

[0005] In order to solve the above technical problems, the present application provides an AR augmented reality interaction method and system using a microcomputer host, and the technical solutions adopted are as follows:

[0006] In a first aspect, an embodiment of the present application provides an AR augmented reality interaction method using a microcomputer host, the method comprising the following steps:

[0007] Step 1: Use a microcomputer host to collect images in real time during the AR interaction process;

[0008] Step 2: Filter and adjust the image by analyzing the regional interference of the image during the real-time interaction process; specifically:

[0009] S1, projecting the grayscale image in the horizontal direction and the vertical direction respectively to obtain two projection sequences after the grayscale values ​​are superimposed; obtaining the characteristics of each peak in the projection sequence; dividing the projection sequence into a number of sub-intervals; analyzing the average level of the difference between the characteristics of all peaks in each sub-interval as the interval peak feature of each sub-interval;

[0010] S2, based on the peak position discrete characteristics and peak width characteristics of all sub-intervals in the projection sequence, and combined with the interval peak characteristics of all sub-intervals, determining the contrast division coefficient in the projection direction corresponding to the projection sequence;

[0011] S3, using the contrast division coefficient to divide the image into regions in the horizontal direction and the vertical direction respectively, to obtain a plurality of divided regions in the image; using the normalized value of the mean of the similarity between each divided region and all its adjacent regions as the adjustment coefficient of each region, adjusting the side length of the adaptive filtering window of the region, to obtain a filtered image;

[0012] Step 3: Use the filtered image for augmented reality interaction.

[0013] Preferably, in step S1, the characteristics of each peak include at least the peak value, peak width and peak position of the corresponding peak.

[0014] Preferably, in step S1, the sub-intervals are further obtained by evenly dividing the value range in the projection sequence according to a preset number of sub-intervals.

[0015] Preferably, when analyzing the interval peak characteristics of each sub-interval in step S1, the mean and maximum values ​​of the peak values ​​of all peaks in each sub-interval may be further considered.

[0016] Preferably, in step S2, the method for acquiring the peak position discrete feature is:

[0017] For each subinterval, all peaks in the projection sequence are sorted in ascending order, and the difference means of all adjacent peak positions are calculated based on the sorting results, and the difference means are used as the peak position discrete feature of each subinterval.

[0018] Preferably, in step S2, the peak width feature is determined by the mean peak width of all peaks in the corresponding subinterval.

[0019] Preferably, in step S2, the method for determining the contrast division coefficient in the projection direction corresponding to the projection sequence is:

[0020] The peak width feature of each sub-interval is reversely fused with the peak position discrete feature;

[0021] Perform forward fusion of the interval peak features of each sub-interval with the result of reverse fusion;

[0022] The forward fusion results of all subintervals in the projection sequence are accumulated to obtain the contrast division coefficient in the projection direction corresponding to the projection sequence.

[0023] Preferably, in step S3, the length of each region into which the image is uniformly divided in the horizontal and vertical directions is equal to the contrast division coefficient in the corresponding projection direction.

[0024] Preferably, in step S3, the method for adjusting the side length of the adaptive filtering window of the region is:

[0025] The side length of the adaptive filtering window for each region divided in the image is recorded as ; ; In the formula, round is the rounding function, and Represent the contrast division coefficients in the horizontal and vertical directions respectively, Represents the adjustment coefficient of the area.

[0026] In a second aspect, the embodiment of the present application further provides an AR augmented reality interaction system using a microcomputer host, including:

[0027] The interactive image acquisition module is used to use the microcomputer host to collect images in the AR interaction process in real time;

[0028] The interactive image processing module is used to filter and adjust the image by analyzing the regional interference of the image during the real-time interaction process;

[0029] The interactive display module is used to perform augmented reality interaction using the filtered images.

[0030] This application has at least the following beneficial effects:

[0031] When this application uses a microcomputer host to realize AR augmented reality interaction, it is considered that the actual scene data collection is in dynamic change, and the scene offset at different angles is extremely complex. When collecting and analyzing data, it is easy to cause deviations in the quality of data collection due to scene changes, which in turn causes large errors at the interaction level. To this end, this application uses a variety of sensors such as cameras, depth sensors, and inertial measurement units to perceive real-world environment information in real time when using a microcomputer host to carry out augmented reality interaction. According to the regional interference deviation image characteristics generated by the dynamic changes of the collected image, combined with the AR augmented reality shooting angle and scene changes, the horizontal and vertical interference differences are analyzed, and the range of the interval affected by different interferences is accurately divided, so as to implement targeted interference impact processing adjustments. Its advantage is that it can dynamically optimize and adjust the filtering processing of real-time collected images in combination with the regional interference characteristics caused by the dynamic changes of AR augmented reality interaction, effectively improve the stability of augmented reality interaction, and the adaptability and reliability of augmented reality interaction applications in complex scenes, provide users with a more accurate and smooth augmented reality interaction experience, and promote the effective application and expansion of AR technology in multiple fields. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0033] Figure 1 A flowchart of the AR augmented reality interaction method using a microcomputer host provided in this application;

[0034] Figure 2 A flow chart of the process of filtering and adjusting an image provided in this application. DETAILED DESCRIPTION

[0035] In order to further explain the technical means and effects adopted by this application to achieve the predetermined invention purpose, the following, in combination with the accompanying drawings and preferred embodiments, describes in detail the specific implementation methods, structures, features and effects of the AR augmented reality interaction method and system using a microcomputer host proposed in this application. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0036] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0037] The specific scheme of the AR augmented reality interaction method and system using a microcomputer host provided by the present application is described in detail below with reference to the accompanying drawings.

[0038] An embodiment of the present application provides an AR augmented reality interaction method and system using a microcomputer host.

[0039] Specifically, the following AR augmented reality interaction method using a microcomputer host is provided, please refer to Figure 1 , the method comprises the following steps:

[0040] Step 1: Use a microcomputer host to collect images during AR interaction in real time.

[0041] The camera in the microcomputer host is used to collect image information of the actual AR interactive scene in real time, and the collected images are transmitted to the interactive image processing module of the microcomputer host.

[0042] Step 2: Filter and adjust the image by analyzing the regional interference to which the image is subjected during the real-time interaction process.

[0043] In AR interactive scenarios, the scene changes are extremely complex due to the subject movement, and the shooting environment will produce varying degrees of noise interference in the shooting process. The traditional image preprocessing process mainly optimizes and adjusts the overall noise interference of the captured image, and processes images in different scenarios by setting the initial parameters of the filter.

[0044] However, due to regional differences in environmental changes and interference effects, this traditional method can easily lead to low image processing accuracy, which in turn results in poor virtual and real display effects based on the collected information.

[0045] Based on the above analysis, in order to effectively deal with the impact of frequent scene changes on data processing during AR augmented reality interaction, this application adopts a processing strategy of implementing regional comparison of image interference impact features during real-time image data acquisition. Considering that under frequent scene changes, the changes in actual scenes may cause significant differences in the interference impacts on different areas, interference processing adjustments are made to different areas in a targeted manner.

[0046] In this application, the process flow chart of filtering and adjusting the image is as shown in the attached figure. Figure 2 As shown, specifically:

[0047] S1, projecting the grayscale image of the image in the horizontal direction and the vertical direction respectively to obtain two projection sequences after the grayscale values ​​are superimposed; obtaining the characteristics of each peak in the projection sequence; dividing the projection sequence into a number of sub-intervals; analyzing the average level of the difference between the characteristics of all peaks in each sub-interval as the interval peak feature of each sub-interval.

[0048] In the actual interaction process, the images collected by the camera will be interfered by many factors. Under different viewing angles and scene conditions, the interference experienced by each area is significantly different. In local areas, abnormal brightness changes may occur, that is, the pixel values ​​in some areas form peaks compared to other locations in the area. From the perspective of the range of the interference area and the distribution characteristics of the pixel value, there are two typical situations: one is that the interference area is small but the pixel value changes are concentrated, which is manifested as a sharp increase or decrease in the pixel value in a small local area; the other is that the interference area is large and the pixel value changes are dispersed, and the pixel value fluctuates widely in a larger area. In addition, the shape and size of the pixel value change area affected by noise are variable, which may be a regular geometric shape or an irregular shape.

[0049] In view of the above situation, the present application first converts the collected image into a grayscale image, projects the grayscale image horizontally and vertically, and obtains two projection sequences after the grayscale values ​​are superimposed. The purpose of constructing the projection sequence is to combine the regional difference characteristics shown by the interference when collecting the image, and analyze the pixel distribution comparison differences in different directions, so as to accurately analyze the scattered characteristics of the regional interference effects in the image.

[0050] Furthermore, under the influence of regional interference, the fluctuation of its pixel value has a fast or narrow range of prominent change peak characteristics. Accordingly, each projection sequence is used as the input of the peak recognition method to obtain all peaks and their characteristics in each projection sequence.

[0051] In this embodiment, the characteristics of each peak include the peak value, peak width and peak position of the corresponding peak.

[0052] In other embodiments of the present application, the difference between adjacent peak values ​​of each peak may be further considered, and the difference between adjacent peak values ​​may reflect the fluctuation of the data.

[0053] As a specific implementation, the peak recognition method may adopt the findpeak function in MATLAB and the automatic multi-scale peak detection method. Both methods are well-known technologies and will not be described in detail.

[0054] Considering the regional extreme value characteristics of pixels in the image under the influence of interference, each projection sequence is divided into subintervals. In this embodiment, the value range interval is determined according to the minimum and maximum values ​​of all elements in the projection sequence, and the value range interval is evenly divided according to a preset number of subintervals to obtain a plurality of subintervals.

[0055] In other embodiments of the present application, the division of each projection sequence into sub-intervals may also be performed based on the value range intervals of the peak values ​​of all peaks.

[0056] As a specific implementation of this embodiment, the preset number of sub-intervals is 10, and in other implementations, it can be set by the implementer.

[0057] According to the peak characteristics in each sub-interval in the projection sequence, the interval peak characteristics of each sub-interval are determined, and the purpose is to make the area division processing and allocation more accurate for the sub-intervals affected by regional interference differences. In this embodiment, the average level of the difference between the characteristics of all peaks in each sub-interval is used as the interval peak characteristic of each sub-interval.

[0058] In other embodiments of the present application, when calculating the interval peak feature of each sub-interval, the mean and maximum value of the peak values ​​of all peaks in each sub-interval may be further considered.

[0059] As an implementation method, The peak characteristics of the sub-intervals For example, the relationship is:

[0060]

[0061] In the formula, represents the interval peak characteristics of the x-th subinterval; represents the mean of the peak values ​​of all peaks in the x-th subinterval, represents the maximum value of the peaks of all the peaks in the projected sequence; Indicates The number of peaks in each subinterval; represents the difference in features between the i-th peak and the j-th peak in the x-th subinterval, where the feature difference can be calculated using Manhattan distance or Euclidean distance.

[0062] It should be understood that the larger the calculated interval peak feature is, the more likely it is that the divided sub-interval is affected by regional interference, resulting in drastic changes in pixels within the region and greater differences in changes in interference effects.

[0063] S2, based on the peak position discrete characteristics and peak width characteristics of all sub-intervals in the projection sequence, and combined with the interval peak characteristics of all sub-intervals, determine the contrast division coefficient in the projection direction corresponding to the projection sequence.

[0064] After the captured image is projected vertically and horizontally, a comprehensive comparative analysis of the interference impact range is carried out based on the projection results in each direction and the impact characteristics of regional interference. The accurate division range of the interference impact is determined based on the comparative analysis results.

[0065] Specifically, in this embodiment, for each sub-interval, the peak positions of all peaks in the projection sequence are sorted in ascending order, and the difference mean of all adjacent peak positions is calculated based on the sorting results, and the difference mean is used as the peak position discrete feature of each sub-interval. The larger the discrete characteristics of the peak position, the more discrete it is affected by regional interference differences.

[0066] In other embodiments of the present application, the difference variances of all adjacent peak positions can be calculated based on the sorting results, and the difference variances and difference means are forward fused to obtain the peak position discrete features of the corresponding sub-interval. The peak position discrete features obtained using this method can be used to evaluate whether the distribution between all peaks in the sub-interval has regular characteristics. The more regular the peak distribution, the less significant its discrete features.

[0067] Specifically, in an implementation manner of this embodiment, the difference between each adjacent peak position is the absolute value of the difference between the adjacent peak positions.

[0068] Furthermore, the mean peak width of all peaks in each subinterval is calculated and the mean peak width is used as the peak width characteristic of the corresponding subinterval. , the larger the peak width feature, the greater the range of influence of the regional influence change difference of the image caused by the regional interference difference.

[0069] In other embodiments of the present application, the peak width variance of all peaks in each subinterval is calculated, and the peak width mean and the peak width variance are reversely fused to obtain the peak width feature of the corresponding subinterval. The peak width feature obtained using this method can be used to evaluate whether all peak widths in the subinterval have regular distribution characteristics. The more regular the peak width distribution, the more significant its peak width feature.

[0070] In this embodiment, the peak width features of each sub-interval are reversely fused with the peak position discrete features; the interval peak features of each sub-interval are forward fused with the result of the reverse fusion; the results of the forward fusion of all sub-intervals in the projection sequence are accumulated to obtain the contrast division coefficient of the projection sequence corresponding to the projection direction.

[0071] It can be understood that fusion can be divided into forward fusion and reverse fusion. Forward fusion is a fusion method such as addition and multiplication between data, and reverse fusion is a fusion method such as subtraction and division between data. The specific forward fusion and reverse fusion methods are determined by the implementer according to actual conditions, and this application does not impose any special restrictions.

[0072] In other embodiments of the present application, the peak width feature of each sub-interval may be forward fused with the interval peak feature first, and then the result of the forward fusion of each sub-interval may be reversely fused with the peak position discrete feature, and the reverse fusion results of all sub-intervals in the projection sequence may be accumulated to obtain the contrast division coefficient in the projection direction corresponding to the projection sequence. The difference between the fusion and the present embodiment is that before the result of the forward fusion of each sub-interval is reversely fused with the peak position discrete feature, some other operations may be performed on the result of the forward fusion or the peak position discrete feature, such as normalization, multiplication by a coefficient, etc., so that the implementer can change the influence of each value on the final result according to the actual situation, thereby achieving the final division effect.

[0073] As an implementation method of this embodiment, the comparison division coefficient is calculated , the specific calculation relationship is as follows:

[0074]

[0075] In the formula, Indicates the contrast division coefficient; round[] is the rounding function; represents the number of subintervals; represents the normalized value of the interval peak feature of the x-th subinterval; and They respectively represent the peak position discrete characteristics and peak width characteristics in the comparison interval corresponding to the x-th subinterval.

[0076] It should be understood that the larger the calculated contrast division coefficient is, the larger the range of influence of the regional interference is in the projection direction corresponding to the projection sequence, and the regional interference difference is significant.

[0077] S3, using contrast division coefficients to divide the image into regions in the horizontal and vertical directions respectively, to obtain a number of divided regions in the image; using the normalized value of the mean similarity between each divided region and all its adjacent regions as the adjustment coefficient of each region, adjusting the side length of the adaptive filtering window of the region, to obtain a filtered image.

[0078] Based on the above analysis results, a comparative analysis is performed on the regional interference difference characteristics of the horizontal and vertical projection results, and the contrast division coefficient in each projection direction is obtained. Based on the contrast division coefficient, the captured image is divided into regions in the horizontal and vertical directions. In this embodiment, the length of each region evenly divided in the horizontal and vertical directions is equal to the contrast division coefficient in its corresponding projection direction.

[0079] In other embodiments of the present application, the number of regions evenly divided in the horizontal direction and the vertical direction is the contrast division coefficient in the corresponding projection direction.

[0080] Furthermore, the captured images are divided into multiple areas in two directions. The purpose is to analyze the horizontal and vertical interference differences in combination with the shooting angle and scene changes in the AR augmented reality process, and then accurately divide the interval ranges with different interference influence differences, and make targeted adjustments to the interference processing.

[0081] Specifically, the mean SAD value between each area divided in the image and all its adjacent areas is calculated respectively, and the normalized value of the mean SAD value is used as the adjustment coefficient of each area divided. The calculation method of the SAD value is a well-known technique and will not be described in detail.

[0082] Furthermore, the divided image is used as the input of the adaptive filtering algorithm, and the side length of the adaptive filtering window of each area divided in the image is The method of determining is: ; In the formula, round is the rounding function, and Represent the contrast division coefficients in the horizontal and vertical directions respectively, In this embodiment, the adaptive filtering window calculated is a square with a side length of .

[0083] It should be understood that different areas are analyzed and corresponding adjustment coefficients are obtained, and then the size of the filter window is adjusted; its purpose is: when the comparison between adjacent areas shows that the interference impact on the area is significantly different within the divided interference range, it means that the interference impact range after division is wider. At this time, a relatively large filter window is set according to the corresponding adjustment coefficient to effectively reduce the interference impact; on the contrary, if the comparison between adjacent areas shows that the interference impact on the area is slightly different within the established interference range, that is, the interference impact range after division is narrower, then a relatively small filter window is configured according to the corresponding adjustment coefficient, so as to fully retain the image detail features; after the above further division and adjustment, the impact of regional interference differences caused by changing shooting angles and scene changes on the filtering process can be reduced.

[0084] In addition, in other embodiments of the present application, the adaptive filtering window of each region may be set to be a rectangle, that is, the length and width of the adaptive filtering window are respectively recorded as and : , .

[0085] By determining the side length of the adaptive filtering window of each area divided in the image, an adaptive filtering algorithm is used to perform noise reduction and enhancement processing to obtain a filtered image. The filtering process of the image by the adaptive filtering algorithm is a well-known technology and will not be described in detail.

[0086] Step 3: Use the filtered image for augmented reality interaction.

[0087] In the interactive image processing module of the microcomputer host, the user's position and posture information in the real environment is calculated in real time based on the data collected by the depth sensor and IMU, and integrated with the virtual environment; using spatial computing technology, the correct display position and direction of virtual objects in the real scene are determined to achieve seamless integration of virtual and reality.

[0088] Furthermore, the generated virtual content is fused with the image after filtering in step 2 to generate a final fused image. Then, the fused image data and interactive feedback information are transmitted back to the head-mounted display device through a wireless transmission link. The head-mounted display device presents the virtual and real fusion scene to the user through the display screen in the interactive display module based on the received fused image data.

[0089] Based on the same inventive concept as the above method, an embodiment of the present application also provides an AR augmented reality interactive system using a microcomputer host, including an interactive image acquisition module, an interactive image processing module and an interactive display module.

[0090] The interactive image acquisition module is used to use the microcomputer host to collect images in the AR interaction process in real time;

[0091] The interactive image processing module is used to filter and adjust the image by analyzing the regional interference of the image during the real-time interaction process;

[0092] The interactive display module is used to perform augmented reality interaction using the filtered images.

[0093] In addition, the device for realizing AR augmented reality interaction using a microcomputer host in the present application includes at least: a microcomputer host, a head-mounted display device, a camera, a depth sensor, an inertial measurement unit, an interactive controller, and a data transmission device. Specifically, the selection and connection of the devices in this embodiment are as follows:

[0094] (1) Equipment selection and preparation

[0095] Microcomputer host: GMKNucBox5 mini host is used, equipped with Intel Core i51240U processor, multiple USB3.2, HDMI2.0 and other interfaces, strong computing and graphics processing capabilities, and can cope with augmented reality interaction tasks.

[0096] Head-mounted display device: MetaQuest Pro AR glasses are used, with a single-eye resolution of 2560x1440 and a refresh rate of 120Hz. They are connected to the mini host via HDMI to ensure clear and smooth fusion images.

[0097] Camera: OccpitalBridge RGBD camera with 1920x1080 resolution and 60fps frame rate is used. It is connected to the mini host via USB to provide visual data input for collecting images and videos.

[0098] Depth sensor: Use STMicroelectronics VL53L5CX ToF depth sensor with a measurement range of 4 meters, an accuracy of ±3 cm, and an I2C interface to connect to the host to enhance environmental perception.

[0099] Inertial measurement unit: MPU6050IMU module, including high-precision gyroscope, SPI interface communicates with mini host, and provides device motion status information.

[0100] Interactive controller: Xiaomi Mi Controller handle, with multi-modal interaction function, paired with the mini host via Bluetooth or USB, to enable users to interact with the virtual environment in a variety of ways and receive feedback.

[0101] Data transmission device: Intel WiFi 6 EAX 210 network card, installed in the mini host, supports WiFi 6E technology, and ensures high-speed and stable data transmission between local and remote ends.

[0102] (2) Connection and configuration

[0103] Connect the AR glasses and the GMKNucBox5 mini host: firmly connect them through the HDMI interface and ensure normal power supply to achieve stable operation and clear integrated picture display.

[0104] Connect the RGBD camera: plug its USB interface into the mini host, install drivers such as OccpitalBridgeSDK, complete the calibration and initialization settings to capture high-quality images and depth information; connect the ToF depth sensor to the host via I2C and configure it according to the instructions.

[0105] Connect the IMU module: connect it to the mini host through the SPI interface, install the driver and calibrate it accurately so that it can accurately measure attitude angle, acceleration and other information.

[0106] Configure the interactive handle: After completing the Bluetooth pairing or USB connection with the mini host, install the handle driver and related interactive software, and configure functions such as gesture recognition, voice control, touch operation projection, etc. in detail to accurately identify operations and send instructions to the host.

[0107] Install the WiFi6E wireless network card: Install and configure it correctly, set the SSID, password and other network parameters to ensure a stable and high-speed wireless connection between local and remote devices and ensure data transmission.

[0108] The various embodiments in the present application are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0109] It should be noted that, unless otherwise specified and limited, terms such as "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a circuit structure, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such article or device. In the absence of further restrictions, an element defined by the sentence "including one..." does not exclude the existence of other identical elements in the article or device including the element. In addition, the term "and\or" used herein includes any and all combinations of one or more related listed items.

[0110] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention herein. The present application is intended to cover any variations, uses or adaptations of the present application, which follow the general principles of the present application and include common knowledge or customary technical means in the art that are not invented by the present application.

[0111] It should be understood that the present application is not limited to the exact construction that has been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof.

Claims

1. An AR augmented reality interaction method using a microcomputer host, characterized in that: The method comprises the following steps: Step 1: Use a microcomputer host to collect images in real time during the AR interaction process; Step 2: Filter and adjust the image by analyzing the regional interference of the image during the real-time interaction process; specifically: S1, projecting the grayscale image in the horizontal direction and the vertical direction respectively to obtain two projection sequences after the grayscale values ​​are superimposed; obtaining the characteristics of each peak in the projection sequence; dividing the projection sequence into a number of sub-intervals; analyzing the average level of the difference between the characteristics of all peaks in each sub-interval as the interval peak feature of each sub-interval; S2, reversely fuse the peak width feature of each sub-interval with the peak position discrete feature; forwardly fuse the interval peak feature of each sub-interval with the result of reverse fusion; accumulate the results of forward fusion of all sub-intervals in the projection sequence to obtain the contrast division coefficient of the projection sequence corresponding to the projection direction; S3, using the contrast division coefficient to divide the image into regions in the horizontal direction and the vertical direction respectively, to obtain a plurality of divided regions in the image; using the normalized value of the similarity mean between each divided region and all its adjacent regions as the adjustment coefficient of each region, and combining the contrast division coefficients in the horizontal direction and the vertical direction to adjust the side length of the adaptive filtering window of the region, to obtain a filtered image; Step 3: Use the filtered image for augmented reality interaction.

2. The AR augmented reality interaction method using a microcomputer host as claimed in claim 1, characterized in that: In step S1, the characteristics of each peak include at least the peak value, peak width and peak position of the corresponding peak.

3. The AR augmented reality interaction method using a microcomputer host as claimed in claim 1, characterized in that: In step S1, the sub-intervals are further obtained by evenly dividing the value range in the projection sequence according to a preset number of sub-intervals.

4. The AR augmented reality interaction method using a microcomputer host as claimed in claim 2, characterized in that: When analyzing the interval peak characteristics of each subinterval in step S1, the mean and maximum values ​​of the peak values ​​of all peaks in each subinterval may be further considered.

5. The AR augmented reality interaction method using a microcomputer host as claimed in claim 2, characterized in that: In step S2, the method for acquiring the peak position discrete feature is: For each subinterval, all peaks in the projection sequence are sorted in ascending order, and the difference means of all adjacent peak positions are calculated based on the sorting results, and the difference means are used as the peak position discrete feature of each subinterval.

6. The AR augmented reality interaction method using a microcomputer host as claimed in claim 2, characterized in that: In step S2, the peak width feature is determined by the mean peak width of all peaks in the corresponding subinterval.

7. The AR augmented reality interaction method using a microcomputer host as claimed in claim 1, characterized in that: In step S3, the length of each region into which the image is evenly divided in the horizontal and vertical directions is equal to the contrast division coefficient in the corresponding projection direction.

8. The AR augmented reality interaction method using a microcomputer host as claimed in claim 1, characterized in that: In step S3, the method for adjusting the side length of the adaptive filtering window of the region is: The side length of the adaptive filtering window for each region divided in the image is recorded as ; ; In the formula, round is the rounding function, and Represent the contrast division coefficients in the horizontal and vertical directions respectively, Represents the adjustment coefficient of the area.

9. Using an AR augmented reality interactive system of a microcomputer host to implement the method according to any one of claims 1 to 8, characterized in that: include: The interactive image acquisition module is used to use the microcomputer host to collect images in the AR interaction process in real time; The interactive image processing module is used to filter and adjust the image by analyzing the regional interference of the image during the real-time interaction process; The interactive display module is used to perform augmented reality interaction using the filtered images.

Images