Spatial distance measurement method and apparatus
Patent Information
- Application Number
- PCT/CN2025/138114
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2025-03-26
- Filing Date
- 2025-11-27
- Publication Date
- 2026-10-01
Smart Images
Figure CN2025138114_01102026_PF_FP_ABST
Abstract
Description
A method and apparatus for measuring spatial distance Technical Field
[0001] This invention relates to the field of computer technology, and in particular to a method and apparatus for measuring spatial distance. Background Technology
[0002] In today's era of rapid technological advancement, spatial distance measurement technology plays a crucial role in numerous fields, with applications spanning architecture, surveying, industrial automation, smart homes, virtual reality, augmented reality, and aerospace, among others. However, traditional spatial distance measurement methods suffer from several limitations, such as measurement accuracy being greatly affected by the environment, complex measurement processes, low efficiency, and difficulty in implementation under specific conditions.
[0003] Traditional methods for measuring spatial distance mainly include laser ranging, total station surveying, and GPS surveying. Laser ranging technology uses the round-trip time of a laser pulse to calculate distance, featuring high accuracy and fast measurement, but its measurement range is limited and it is relatively sensitive to environmental conditions. Total station surveying, through electronic distance and angle measurement functions, can simultaneously measure horizontal distance, vertical distance, and elevation difference, making it suitable for medium- to long-distance topographic mapping and engineering surveying.
[0004] However, traditional spatial distance measurement methods have many drawbacks in terms of measurement accuracy, environmental adaptability, operational complexity, and measurement efficiency. These drawbacks limit their application in certain complex environments or scenarios requiring high precision, resulting in significant limitations. Summary of the Invention
[0005] This invention provides a spatial distance measurement method and apparatus to solve the problems of low measurement accuracy, poor environmental adaptability, high operational complexity, and low measurement efficiency in the prior art.
[0006] In a first aspect, the present invention provides a spatial distance measurement method, specifically comprising the following steps:
[0007] Step S1: Acquire multiple consecutive frames of images using the device's camera;
[0008] Step S2: Perform feature detection on each frame of the continuous multi-frame images to form feature points in the continuous multi-frame images, and extract the feature point information to form a descriptor for each feature point;
[0009] Step S3: Based on the descriptor of each feature point, compare the feature points pairwise to form matching feature point pairs;
[0010] Step S4: Based on the matched feature point pairs, the device's acceleration information, and angular velocity information, estimate the motion trajectory of the device between consecutive frames to form the motion trajectory estimate of the device;
[0011] Step S5: Based on the feature points and the motion trajectory estimation of the device, form a planar hypothesis;
[0012] Step S6: Based on the aforementioned planar assumption, obtain two virtual anchor points through the device screen, perform coordinate transformation on the two virtual anchor points to form the real coordinates of the two virtual anchor points, and calculate the distance between the two virtual anchor points.
[0013] In this application, a descriptor represents a set of vectors that can characterize the local features of the image surrounding the feature point, including the position, orientation, scale of the feature point, and texture information of the surrounding image.
[0014] Preferably, in step S2, feature detection is performed using the FAST (Features from Accelerated Segment Test) algorithm, and feature points are extracted using the BRIEF (Binary Robust Independent Elementary Features) algorithm.
[0015] Preferably, in step S2, feature detection and feature extraction are performed using the ORB (Oriented FAST and Rotated BRIEF) algorithm.
[0016] Preferably, in step S3, the distance between feature point descriptors is calculated using a brute-force match algorithm, and feature point pairs whose distance is less than a first threshold (in this application, the "first threshold" changes depending on the specific application requirements) are considered as matched feature point pairs.
[0017] More preferably, the distance includes, but is not limited to, one of the following: Euclidean distance, Manhattan distance, Chebyshev distance, Minkowski distance, Mahalanobis distance, and Hamming distance.
[0018] Preferably, in step S4, the motion trajectory of the device between consecutive frames is estimated using ARCore.
[0019] Preferably, in step S5, a planar hypothesis is formed based on the feature points and the estimated motion trajectory of the device, specifically including the following steps:
[0020] Step S501: Select the feature point set used to form the plane hypothesis by using the Random Sample Consensus (RANSAC) algorithm;
[0021] Step S502: Based on the set of feature points, form the parameters of the plane hypothesis ax+by+cz+d=0;
[0022] Step S503: Optimize the parameters of the plane assumption until the number of points in the plane assumption is maximized, and then output the optimized plane assumption parameters.
[0023] The feature point set represents the set of feature points that best embody the plane hypothesis.
[0024] Wherein, the interior point means that for a feature point, the straight-line distance between it and the plane hypothesis is calculated, and if the distance is less than the distance threshold, then the feature point is the interior point of the plane hypothesis.
[0025] Preferably, in step S6, the coordinate system transformation specifically includes: multiplying the virtual anchor point coordinates in the device screen coordinate system with the camera's extrinsic parameter matrix to obtain the virtual anchor point coordinates (i.e., the real coordinates) in the world coordinate system.
[0026] Preferably, step S6 specifically includes:
[0027] Step S601: Obtain two virtual anchor points through the device screen, and after coordinate system transformation, their coordinates are respectively... , ;
[0028] Step S602: Calculate the Euclidean distance between the two virtual anchor points.
[0029] The distance d is calculated as follows:
[0030] ;
[0031] Distance d is the actual distance of the area the user wants to measure.
[0032] Secondly, the present invention also provides a spatial distance measuring device, specifically comprising the following modules:
[0033] An image acquisition module is used to acquire multiple consecutive frames of images through the device's camera; wherein, the device is an external device or integrated into the device.
[0034] The feature point and descriptor generation module is used to perform feature detection on each frame of the continuous multi-frame images, form feature points in the continuous multi-frame images, and extract the feature point information to form a descriptor for each feature point;
[0035] The feature point pair matching module is used to compare the feature points pairwise according to the descriptor of each feature point to form a matching feature point pair;
[0036] The motion trajectory estimation module is used to estimate the motion trajectory of the device between consecutive frames based on the matched feature point pairs, the device's acceleration information and angular velocity information, to form the motion trajectory estimate of the device;
[0037] A plane hypothesis generation module is used to form a plane hypothesis based on the feature points and the motion trajectory estimation of the device;
[0038] The distance measurement module is used to combine the plane assumption, acquire two virtual anchor points through the device screen, perform coordinate transformation on the two virtual anchor points to form the real coordinates of the two virtual anchor points, and calculate the distance between the two virtual anchor points.
[0039] Preferably, in the feature point and descriptor generation module, feature detection is performed using the FAST algorithm, and feature point extraction is performed using the BRIEF algorithm.
[0040] Preferably, in the feature point and descriptor generation module, feature detection and feature extraction are performed using the ORB algorithm.
[0041] Preferably, in the feature point pair matching module, the distance between feature point descriptors is calculated using a brute-force matching algorithm, and feature point pairs with a distance less than a first threshold are considered as matched feature point pairs.
[0042] More preferably, the distance includes, but is not limited to, one of the following: Euclidean distance, Manhattan distance, Chebyshev distance, Minkowski distance, Mahalanobis distance, and Hamming distance.
[0043] Preferably, in the motion trajectory estimation module, ARCore is used to estimate the motion trajectory of the device between consecutive frames.
[0044] Preferably, the planar hypothesis generation module specifically includes the following sub-modules:
[0045] The first submodule for generating the plane hypothesis is used to select the set of feature points for forming the plane hypothesis through a random sampling consensus algorithm.
[0046] The second submodule for generating the plane hypothesis is used to form the parameters of the plane hypothesis ax+by+cz+d=0 based on the set of feature points.
[0047] The third submodule for generating the plane hypothesis is used to optimize the parameters of the plane hypothesis until the number of points in the plane hypothesis is maximized, and then outputs the optimized plane hypothesis parameters.
[0048] The feature point set represents the set of feature points that best embody the plane hypothesis.
[0049] Wherein, the interior point means that for a feature point, the straight-line distance between it and the plane hypothesis is calculated, and if the distance is less than the distance threshold, then the feature point is the interior point of the plane hypothesis.
[0050] Preferably, the coordinate system transformation in the distance measurement module specifically includes: multiplying the virtual anchor point coordinates in the device screen coordinate system with the camera's extrinsic parameter matrix to obtain the virtual anchor point coordinates (i.e., the real coordinates) in the world coordinate system.
[0051] Preferably, the distance measurement module specifically includes the following sub-modules:
[0052] The first submodule for distance measurement is used to acquire two virtual anchor points through the device screen. After coordinate system transformation, their coordinates are respectively... , ;
[0053] The second submodule for distance measurement is used to calculate the Euclidean distance between two virtual anchor points.
[0054] The distance d is calculated as follows:
[0055] ;
[0056] Distance d is the actual distance of the area the user wants to measure.
[0057] Thirdly, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a spatial distance measurement method as described in any one of the first aspects of this application.
[0058] Fourthly, the present invention also provides an electronic device, the electronic device comprising: a memory storing a computer program; and a processor communicatively connected to the memory, which executes a spatial distance measurement method as described in any one of the first aspects of this application when the computer program is invoked.
[0059] Compared with the prior art, the present invention has the following obvious and prominent substantive features and significant advantages:
[0060] This invention provides a spatial distance measurement method and apparatus, solving the problems of low measurement accuracy, poor environmental adaptability, high operational complexity, and low measurement efficiency in existing technologies. By generating a plane assumption and combining it with the plane assumption to construct virtual anchor points, the distance between two virtual anchor points is calculated. This improves the accuracy and environmental adaptability of spatial distance measurement while also increasing measurement efficiency and reducing operational complexity. Attached Figure Description
[0061] The accompanying drawings, which constitute a part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings:
[0062] Figure 1 is a flowchart of a spatial distance measurement method according to a preferred embodiment of the present invention.
[0063] Figure 2 is a schematic diagram of a spatial distance measuring device according to a preferred embodiment of the present invention. Detailed Implementation
[0064] This invention provides a method and apparatus for measuring spatial distance. To make the objectives, technical solutions, and effects of this invention clearer and more explicit, the invention will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only for explaining the invention and are not intended to limit the invention.
[0065] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be used interchangeably where appropriate. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products, or apparatuses. Example
[0066] As shown in Figure 1, the spatial distance measurement method described in this embodiment specifically includes the following steps:
[0067] Step S1: Acquire multiple consecutive frames of images through the camera of a device (such as a mobile phone, tablet, VR glasses, or other devices with cameras).
[0068] Augmented Reality (AR) technology uses optoelectronic display technology, interactive technology, multiple sensor technologies, and computer graphics and multimedia technologies to integrate a computer-generated virtual environment with the user's surrounding real environment, allowing the user to perceive and believe that the virtual environment is a component of their real environment. Augmented Reality is characterized by its integration of virtual and real elements, real-time interaction, and 3D registration.
[0069] Step S2: Perform feature detection on each frame of the continuous multi-frame images to form feature points in the continuous multi-frame images, and extract the feature point information to form a descriptor for each feature point.
[0070] In the specific implementation process, the FAST algorithm can be used to detect features in each frame of the image, forming feature points in the consecutive frames. The BRIEF algorithm is then used to extract information from these feature points, forming a descriptor that includes information such as the location, method, scale, and texture of the surrounding image. However, both the FAST and BRIEF algorithms lack scale invariance and rotation invariance. To avoid this deficiency, the ORB algorithm can be used for feature detection and extraction, resulting in a descriptor with scale and rotation invariance. Such a descriptor can better handle feature matching problems caused by translation, rotation, and scaling of images.
[0071] Among them, scale-invariant representation algorithms or feature descriptors can maintain the consistency of feature expression and the accuracy of recognition / matching when the scale (spatial resolution or physical size) of the target object changes linearly or nonlinearly; rotation-invariant representation algorithms or feature descriptors are invariant to any rotation transformation of the target object in the image plane, that is, the feature expression and matching results are not affected by the rotation angle of the target.
[0072] Step S3: Based on the descriptor of each feature point, compare each feature point pairwise to form a matching feature point pair. In the specific implementation, the distance between feature point descriptors is calculated using a brute-force matching algorithm (one of Euclidean distance, Manhattan distance, Chebyshev distance, Minkowski distance, Mahalanobis distance, and Hamming distance can be used for distance calculation), and feature point pairs whose distance is less than a first threshold are considered as matching feature point pairs.
[0073] Step S4: Based on the matched feature point pairs, the device's acceleration information, and angular velocity information, estimate the motion trajectory of the device between consecutive frames to form the motion trajectory estimate of the device; wherein, ARCore is used to estimate the motion trajectory of the device between consecutive frames.
[0074] ARCore is an augmented reality platform developed by Google, designed to deliver high-precision virtual-real fusion interactive experiences through mobile devices such as smartphones and tablets. As the core AR technology framework of the Android ecosystem, ARCore combines computer vision, sensor fusion, and machine learning algorithms, empowering developers to build immersive AR applications.
[0075] Step S5: Based on the feature points and the motion trajectory estimation of the device, form a planar hypothesis.
[0076] Specifically, step S5 includes the following steps:
[0077] Step S501: The feature point set used to form the planar hypothesis is selected through the Random Sampling Consensus (RANSAC) algorithm (the feature point set represents the set of feature points that best reflect the planar hypothesis). Furthermore, before using the RANSAC algorithm, a simple judgment can be made regarding whether the planar hypothesis can be formed, i.e., whether the relative positional relationships of the feature points remain unchanged. For example, in several consecutive frames of images, if the relative positional relationships between some feature points remain unchanged, and the coordinates of these feature points in three-dimensional space exhibit certain coplanar characteristics, then it can be inferred that a planar hypothesis exists. This judgment provides the basis for subsequent planar hypothesis fitting, performs a preliminary judgment on whether a planar hypothesis exists, and eliminates cases where the planar hypothesis does not exist.
[0078] Step S502: Based on the set of feature points, form the parameters of the plane hypothesis ax+by+cz+d=0.
[0079] Step S503: Optimize the parameters of the plane hypothesis until the number of interior points of the plane hypothesis (an interior point is a feature point whose straight-line distance to the plane hypothesis is calculated; if the distance is less than a distance threshold, the feature point is an interior point of the plane hypothesis) is the largest. Output the optimized plane hypothesis parameters. Through continuous iteration, the plane hypothesis with the largest number of interior points is finally selected as the final plane hypothesis, making the final generated plane hypothesis more accurate and reliable.
[0080] Step S6: Based on the aforementioned planar assumption, obtain two virtual anchor points through the device screen, perform coordinate transformation on the two virtual anchor points to form the real coordinates of the two virtual anchor points, and calculate the distance between the two virtual anchor points.
[0081] There are several ways to obtain virtual anchor points through the device screen. For example, users can manually select two points as virtual anchor points on the screen of a mobile phone or tablet to complete the subsequent spatial distance measurement. Alternatively, users can use wearable devices with display devices (such as AR glasses) to generate eye movement signals based on their eye movements, thereby generating virtual anchor points and displaying them on the user's wearable device screen.
[0082] Specifically, the coordinate system transformation includes multiplying the virtual anchor point coordinates (two-dimensional coordinates) in the device screen coordinate system with the camera's extrinsic parameter matrix (which contains the camera's position and attitude information in the world coordinate system) to obtain the virtual anchor point coordinates (three-dimensional coordinates) in the world coordinate system, i.e., the real coordinates.
[0083] Optionally, step S6 specifically includes:
[0084] Step S601: Obtain two virtual anchor points through the device screen, and after coordinate system transformation, their coordinates are respectively... , ;
[0085] Step S602: Calculate the Euclidean distance d between the two virtual anchor points, as shown below:
[0086] ;
[0087] Distance d is the actual distance of the area the user wants to measure.
[0088] In this application, the role of the planar assumption in the measurement of spatial distance is mainly reflected in the following aspects:
[0089] 1. Determine the placement plane of the virtual anchor point
[0090] After a user generates a touch point by touching the screen, the virtual anchor point needs to be placed on a suitable plane. Plane assumptions provide the basis for placing the virtual anchor point. By generating plane assumptions through feature points, the existence of possible plane assumptions in the 3D environment is determined. Thus, when the user constructs the virtual anchor point, it can be accurately placed on these planes, ensuring that the virtual anchor point has actual physical meaning and corresponds to the planes in the real-world scene.
[0091] 2. Ensure the accuracy of spatial distance measurements.
[0092] Spatial distance measurements are based on the true coordinates of virtual anchor points within the 3D environment. Planar assumptions help ensure the accuracy of these coordinates. Without planar assumptions, the placement of virtual anchor points will be off, leading to significant errors between the measured spatial distance and the actual distance. By using planar assumptions, ARCore can place virtual anchor points on a more accurate plane, resulting in a smaller error between the calculated spatial distance between two virtual anchor points and the actual distance or height of the area the user wants to measure.
[0093] 3. Auxiliary coordinate system transformation
[0094] The plane assumption also plays a supporting role in coordinate system transformation. The plane assumption provides information about planes in the 3D environment, allowing ARCore to more accurately estimate the camera's position and pose, thereby optimizing the transformation from screen coordinates to world coordinates. For example, when generating the plane assumption using the RANSAC algorithm, the resulting plane parameters can serve as additional constraints to improve the estimation accuracy of the camera's extrinsic parameters, thus enhancing the accuracy of coordinate system transformation. Example
[0095] As shown in Figure 2, the spatial distance measuring device described in this embodiment specifically includes the following modules:
[0096] An image acquisition module is used to acquire multiple consecutive frames of images through the device's camera; wherein, the device is an external device or integrated into the device.
[0097] The feature point and descriptor generation module is used to perform feature detection on each frame of the continuous multi-frame images, form feature points in the continuous multi-frame images, and extract the feature point information to form a descriptor for each feature point;
[0098] Feature detection can be performed using the FAST algorithm, feature point extraction can be performed using the BRIEF algorithm, or feature detection and extraction can be performed using the ORB algorithm.
[0099] The feature point pair matching module is used to compare the feature points pairwise according to the descriptor of each feature point to form a matching feature point pair;
[0100] Optionally, the distance between feature point descriptors is calculated using a brute-force matching algorithm, and feature point pairs with a distance less than a first threshold are considered as matched feature point pairs; wherein, the distance includes, but is not limited to, one of Euclidean distance, Manhattan distance, Chebyshev distance, Minkowski distance, Mahalanobis distance, and Hamming distance.
[0101] The motion trajectory estimation module is used to estimate the motion trajectory of the device between consecutive frames based on the matched feature point pairs, the device's acceleration information, and angular velocity information, thereby forming a motion trajectory estimate of the device; wherein, ARCore is used to estimate the motion trajectory of the device between consecutive frames.
[0102] The planar hypothesis generation module is used to form a planar hypothesis based on the feature points and the motion trajectory estimation of the device.
[0103] The planar hypothesis generation module specifically includes a first planar hypothesis generation submodule, a second planar hypothesis generation submodule, and a third planar hypothesis generation submodule.
[0104] The first submodule for generating the plane hypothesis is used to select the set of feature points for forming the plane hypothesis through a random sampling consensus algorithm.
[0105] The second submodule for generating the plane hypothesis is used to form the parameters of the plane hypothesis ax+by+cz+d=0 based on the set of feature points.
[0106] The third submodule for generating the plane hypothesis is used to optimize the parameters of the plane hypothesis until the number of points in the plane hypothesis is maximized, and then outputs the optimized plane hypothesis parameters.
[0107] Wherein, the feature point set represents the set of feature points that best embody the plane hypothesis; the interior point represents the feature point whose straight-line distance from the plane hypothesis is calculated, and if the distance is less than a distance threshold, then the feature point is an interior point of the plane hypothesis.
[0108] The distance measurement module is used to combine the plane assumption, acquire two virtual anchor points through the device screen, perform coordinate transformation on the two virtual anchor points to form the real coordinates of the two virtual anchor points, and calculate the distance between the two virtual anchor points.
[0109] Specifically, the coordinate system transformation includes multiplying the virtual anchor point coordinates in the device screen coordinate system with the camera's extrinsic parameter matrix to obtain the virtual anchor point coordinates in the world coordinate system, i.e., the real coordinates.
[0110] Specifically, the distance measurement module includes a first distance measurement submodule and a second distance measurement submodule.
[0111] The first submodule for distance measurement is used to acquire two virtual anchor points through the device screen. After coordinate system transformation, their coordinates are respectively... , .
[0112] The second submodule for distance measurement is used to calculate the Euclidean distance between two virtual anchor points.
[0113] The distance d is calculated as follows:
[0114] ;
[0115] Distance d is the actual distance of the area the user wants to measure.
[0116] The specific embodiments of the present invention have been described in detail above, but they are merely examples, and the present invention is not limited to the specific embodiments described above. For those skilled in the art, any equivalent modifications and substitutions to the present invention are also within the scope of the present invention. Therefore, all equivalent transformations and modifications made without departing from the spirit and scope of the present invention should be covered within the scope of the present invention.
Claims
1. A method for measuring spatial distance, characterized in that, Specifically, the steps include the following: Step S1: Acquire multiple consecutive frames of images using the device's camera; Step S2: Perform feature detection on each frame of the continuous multi-frame images to form feature points in the continuous multi-frame images, and extract the feature point information to form a descriptor for each feature point; Step S3: Based on the descriptor of each feature point, compare the feature points pairwise to form matching feature point pairs; Step S4: Based on the matched feature point pairs, the device's acceleration information, and angular velocity information, estimate the motion trajectory of the device between consecutive frames to form the motion trajectory estimate of the device; Step S5: Based on the feature points and the motion trajectory estimation of the device, form a planar hypothesis; Step S6: Based on the aforementioned planar assumption, obtain two virtual anchor points through the device screen, perform coordinate transformation on the two virtual anchor points to form the real coordinates of the two virtual anchor points, and calculate the distance between the two virtual anchor points.
2. The spatial distance measurement method according to claim 1, characterized in that, In step S2, feature detection is performed using the FAST algorithm, and feature points are extracted using the BRIEF algorithm.
3. The spatial distance measurement method according to claim 1, characterized in that, Feature detection and feature extraction are performed using the ORB algorithm.
4. The spatial distance measurement method according to claim 1, characterized in that, In step S3, the distance between feature point descriptors is calculated using a brute-force matching algorithm, and feature point pairs with a distance less than a first threshold are considered as matched feature point pairs.
5. The spatial distance measurement method according to claim 4, characterized in that, The distance mentioned includes one of the following: Euclidean distance, Manhattan distance, Chebyshev distance, Minkowski distance, Mahalanobis distance, and Hamming distance.
6. The spatial distance measurement method according to claim 1, characterized in that, In step S4, the motion trajectory of the device between consecutive frames is estimated using ARCore.
7. The spatial distance measurement method according to claim 1, characterized in that, In step S5, a planar hypothesis is formed based on the feature points and the estimated motion trajectory of the device, specifically including the following steps: Step S501: Select the feature point set used to form the plane hypothesis through the random sampling consensus algorithm; Step S502: Based on the set of feature points, form the parameters for the plane hypothesis ax+by+cz+d=0; Step S503: Optimize the parameters of the plane assumption until the number of points in the plane assumption is maximized, and then output the optimized plane assumption parameters. Wherein, the feature point set represents the set of feature points that best embody the plane hypothesis; the interior point represents the feature point whose straight-line distance from the plane hypothesis is calculated, and if the distance is less than a distance threshold, then the feature point is an interior point of the plane hypothesis.
8. The spatial distance measurement method according to claim 1, characterized in that, In step S6, the coordinate transformation specifically includes: multiplying the virtual anchor point coordinates in the device screen coordinate system with the camera's extrinsic parameter matrix to form the virtual anchor point coordinates in the world coordinate system.
9. A spatial distance measurement method according to claim 1, characterized in that, Step S6 specifically includes: Step S601: Obtain two virtual anchor points through the device screen, and after coordinate system transformation, their coordinates are respectively... 、 ； Step S602: Calculate the Euclidean distance between the two virtual anchor points; The distance d is calculated as follows: ； Distance d is the actual distance of the area the user wants to measure.
10. A spatial distance measuring device, characterized in that, Specifically, it includes the following modules: An image acquisition module is used to acquire multiple consecutive frames of images through the device's camera; wherein, the device is an external device or integrated into the device. The feature point and descriptor generation module is used to perform feature detection on each frame of the continuous multi-frame images, form feature points in the continuous multi-frame images, and extract the feature point information to form a descriptor for each feature point; The feature point pair matching module is used to compare the feature points pairwise according to the descriptor of each feature point to form a matching feature point pair; The motion trajectory estimation module is used to estimate the motion trajectory of the device between consecutive frames based on the matched feature point pairs, the device's acceleration information and angular velocity information, to form the motion trajectory estimate of the device; A plane hypothesis generation module is used to form a plane hypothesis based on the feature points and the motion trajectory estimation of the device; The distance measurement module is used to combine the plane assumption, acquire two virtual anchor points through the device screen, perform coordinate transformation on the two virtual anchor points to form the real coordinates of the two virtual anchor points, and calculate the distance between the two virtual anchor points.