CN117392101A - Method and device for evaluating atlas, terminal equipment and computer storage medium - Google Patents

Method and device for evaluating atlas, terminal equipment and computer storage medium Download PDF

Info

Publication number
CN117392101A
CN117392101A CN202311442518.6A CN202311442518A CN117392101A CN 117392101 A CN117392101 A CN 117392101A CN 202311442518 A CN202311442518 A CN 202311442518A CN 117392101 A CN117392101 A CN 117392101A
Authority
CN
China
Prior art keywords
target
atlas
determining
map set
projections
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202311442518.6A
Other languages
Chinese (zh)
Inventor
黄国书
张向军
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Goertek Techology Co Ltd
Original Assignee
Goertek Techology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Goertek Techology Co Ltd filed Critical Goertek Techology Co Ltd
Priority to CN202311442518.6A priority Critical patent/CN117392101A/en
Publication of CN117392101A publication Critical patent/CN117392101A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/0002Inspection of images, e.g. flaw detection
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00Three dimensional [3D] modelling, e.g. data description of 3D objects
    • G06T17/05Geographic models
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T19/00Manipulating 3D models or images for computer graphics
    • G06T19/003Navigation within 3D models or images
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/70Determining position or orientation of objects or cameras
    • G06T7/73Determining position or orientation of objects or cameras using feature-based methods
    • G06T7/74Determining position or orientation of objects or cameras using feature-based methods involving reference images or patches
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/30Subject of image; Context of image processing
    • G06T2207/30168Image quality inspection
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02TCLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00Road transport of goods or passengers
    • Y02T10/10Internal combustion engine [ICE] based vehicles
    • Y02T10/40Engine management systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Geometry (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Remote Sensing (AREA)
  • Computer Graphics (AREA)
  • Quality & Reliability (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Computer Hardware Design (AREA)
  • General Engineering & Computer Science (AREA)
  • Navigation (AREA)

Abstract

The application discloses an evaluation method, an evaluation device, terminal equipment and a computer storage medium of a map set, and relates to the technical field of virtual reality, wherein the evaluation method of the map set comprises the following steps: acquiring a target map set established by virtual reality head-mounted equipment, and determining initial pose coordinates of the virtual reality head-mounted equipment according to the target map set; generating a target map set dividing region based on the initial pose coordinates and the target map set, and determining a plurality of map points contained in the target map set dividing region; determining target projections of each of a plurality of map points on an equatorial plane within the target map set partition area, and determining the number of projections in the equatorial plane according to each of the target projections; and determining a map set evaluation result corresponding to the target map set based on the projection quantity. By adopting the method and the device, the technical effect that the terminal equipment can evaluate the atlas established by the VR headset is achieved.

Description

Method and device for evaluating atlas, terminal equipment and computer storage medium
Technical Field
The present disclosure relates to the field of virtual reality technologies, and in particular, to a method and apparatus for evaluating a atlas, a terminal device, and a computer readable storage medium.
Background
In some off-line conferences or brands requiring use of the vehicle, the SLAM (Simultaneous localization and mapping, synchronous positioning and mapping) algorithm, which is mainly formed by the vehicle party to arrange the vehicle requirements to E along with the continuous development of virtual reality technology, becomes the main algorithm for tracking VR headsets.
Because the quality of the atlas established by the VR headset in the operation process is difficult to control, and the quality of the atlas cannot be detected by the SLAM algorithm in the related technology in the operation process, the SLAM algorithm is easy to occur the condition that the tracking of the VR headset cannot be accurately completed because of the lower quality of the atlas.
Therefore, how to make the SLAM algorithm detect the quality of the atlas is also a technical problem that needs to be solved in industry.
Disclosure of Invention
The main purpose of the application is to provide a method, a device, a terminal device and a computer readable storage medium for evaluating a map set, which aim to evaluate the map set established by VR head-mounted equipment, further determine the quality of the map set and guarantee the tracking accuracy of the VR head-mounted equipment.
In order to achieve the above object, the present application provides a method for evaluating a atlas, the method for evaluating a atlas comprising the steps of:
Acquiring a target map set established by virtual reality head-mounted equipment, and determining initial pose coordinates of the virtual reality head-mounted equipment according to the target map set;
generating a target map set dividing region based on the initial pose coordinates and the target map set, and determining a plurality of map points contained in the target map set dividing region;
determining target projections of each of a plurality of map points on an equatorial plane within the target map set partition area, and determining the number of projections in the equatorial plane according to each of the target projections;
and determining a map set evaluation result corresponding to the target map set based on the projection quantity.
Further, the step of generating a target atlas division area based on the initial pose coordinates and the target atlas includes:
determining the initial pose coordinates as a target space center, and determining a first pole and a second pole based on the target space center;
and generating an equatorial plane based on the target space center, the first pole and the second pole, and generating a target atlas division region based on the equatorial plane and a preset region division rule.
Further, the step of generating a target map set division region based on the equatorial plane and a preset region division rule includes:
Acquiring a preset region division rule, and determining a target pitch according to the region division rule;
determining a plurality of target regions based on the target pitch, the equatorial plane, the first pole, and the second pole;
and generating a target atlas division area according to the target areas.
Further, the step of determining the atlas evaluation result corresponding to the target atlas based on the projection number includes:
acquiring a preset azimuth dividing rule, and determining a plurality of azimuth areas contained in the equatorial plane based on the azimuth dividing rule;
and determining the target projection quantity corresponding to each of the azimuth areas based on the projection quantity, and determining a map set evaluation result corresponding to the target map set according to each target projection quantity.
Further, the step of determining the atlas evaluation result corresponding to the objective atlas according to the objective projection quantity includes:
acquiring a preset projection quantity threshold, and comparing the projection quantity of each target with the projection quantity threshold to obtain a plurality of comparison results;
judging whether a plurality of comparison results contain abnormal comparison results or not, wherein the abnormal comparison results are that the number of the target projections is smaller than the threshold value of the number of projections;
If the comparison results contain the abnormal comparison results, determining that the atlas evaluation result corresponding to the target atlas is the target atlas to be optimized;
and if the comparison results do not contain the abnormal comparison results, determining that the atlas evaluation result corresponding to the target atlas is the target atlas and optimization is not needed.
Further, after the step of determining that the atlas evaluation result corresponding to the target atlas is that the target atlas needs to be optimized, the method further includes:
determining a target azimuth angle area in a plurality of azimuth angle areas based on the abnormal comparison result, and determining a point location optimization area in a plurality of target areas in the target map set division area according to the target azimuth angle area;
generating optimization prompt information according to the point position optimization region, and outputting the optimization prompt information to the virtual reality headset so that the virtual reality headset can acquire target map points in the point position optimization region;
and optimizing the target map set based on the target map points to obtain an optimized map set.
Further, the step of determining initial pose coordinates of the virtual reality headset according to the target atlas includes:
reading each image characteristic point contained in the target map set, and determining a characteristic description value corresponding to each image characteristic point;
and determining initial pose coordinates of the virtual reality headset based on each characteristic description value.
In addition, to achieve the above object, the present application further provides an apparatus for evaluating a atlas, the apparatus including:
the pose calculation module is used for acquiring a target atlas established by the virtual reality head-mounted equipment and determining initial pose coordinates of the virtual reality head-mounted equipment according to the target atlas;
the region generation module is used for generating a target map set dividing region based on the initial pose coordinates and the target map set and determining a plurality of map points contained in the target map set dividing region;
a number calculation module, configured to determine target projections of each of the map points on an equatorial plane within the target map set division area, and determine a number of projections in the equatorial plane according to each of the target projections;
And the result generation module is used for determining a map set evaluation result corresponding to the target map set based on the projection quantity.
In addition, to achieve the above object, the present application further provides a terminal device, including: the method comprises the steps of realizing the method for evaluating the atlas by the processor when the computer program is executed by the processor.
In addition, in order to achieve the above object, the present application further provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the map set evaluation method as described above.
According to the method, the device, the terminal equipment and the computer readable storage medium for evaluating the atlas, the target atlas established by the virtual reality head-mounted equipment is obtained, and initial pose coordinates of the virtual reality head-mounted equipment are determined according to the target atlas; generating a target map set dividing region based on the initial pose coordinates and the target map set, and determining a plurality of map points contained in the target map set dividing region; determining target projections of each of a plurality of map points on an equatorial plane within the target map set partition area, and determining the number of projections in the equatorial plane according to each of the target projections; and determining a map set evaluation result corresponding to the target map set based on the projection quantity.
In this embodiment, the terminal device first reads the virtual reality headset to obtain a target map set established by the virtual reality headset, determines initial pose coordinates of the virtual reality headset based on the target map set, then constructs a target map set dividing region based on the initial pose coordinates and the target map set, identifies a plurality of map points in the target map set dividing region, then detects an equatorial plane in the target map set dividing region to determine target projections formed by the map points on the equatorial plane, determines the projection number contained in the equatorial plane according to each target projection, and finally generates a map set evaluation result corresponding to the target map set based on each projection number, and outputs the map set evaluation result to the virtual reality headset.
Therefore, the initial pose coordinates of the VR headset are determined based on the target atlas established by the VR headset, the target atlas dividing area is obtained based on the initial pose coordinates and the target atlas, and then the atlas evaluation result corresponding to the target atlas is generated based on the projection quantity of target projections generated by respective projections of a plurality of map points in the target atlas dividing area, so that the technical problem that tracking of the VR headset cannot be accurately completed due to low atlas quality in the SLAM algorithm is solved, the technical effect that the terminal equipment can evaluate the atlas established by the VR headset is achieved, the quality of the atlas can be determined, and the accuracy of tracking of the VR headset is further guaranteed.
Drawings
Fig. 1 is a schematic structural diagram of a terminal device of a hardware running environment according to an embodiment of the present application;
FIG. 2 is a flowchart of a first embodiment of an evaluation method for a atlas of the present application;
FIG. 3 is a schematic view of a scenario involved in an embodiment of a method for evaluating a atlas of the present application;
FIG. 4 is a schematic view of a target atlas partitioning area according to an embodiment of an evaluation method of an atlas of the present application;
FIG. 5 is a schematic view of azimuth areas according to an embodiment of the method for evaluating a atlas of the present application;
FIG. 6 is a flow chart of a preferred embodiment of the method for evaluating a atlas of the present application;
fig. 7 is a schematic diagram of functional modules related to an embodiment of an evaluation apparatus for a atlas of the present application.
The realization, functional characteristics and advantages of the present application will be further described with reference to the embodiments, referring to the attached drawings.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a terminal device of a hardware running environment according to an embodiment of the present application.
It should be noted that, the terminal device in the embodiment of the present application may be a terminal device that executes the evaluation method of the atlas of the present application, and the terminal device may specifically be a terminal device configured on a VR headset with a plurality of image capturing devices, and integrated with a mobile terminal, a data storage control terminal, a PC, and the like of a SLAM algorithm.
As shown in fig. 1, the terminal device may include: a processor 1001, such as a central processing unit (Central Processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, a memory 1005. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a WIreless interface (e.g., a WIreless-FIdelity (WI-FI) interface). The Memory 1005 may be a high-speed random access Memory (Random Access Memory, RAM) Memory or a stable nonvolatile Memory (NVM), such as a disk Memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
It will be appreciated by those skilled in the art that the structure shown in fig. 1 does not constitute a limitation of the terminal device, and may include more or less components than illustrated, or may combine certain components, or may be arranged in different components.
As shown in fig. 1, an operating system, a data storage module, a network communication module, a user interface module, and an evaluation program of a map set may be included in the memory 1005 as one storage medium.
In the terminal device shown in fig. 1, the network interface 1004 is mainly used for data communication with other devices; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the terminal device of the present application may be provided in the terminal device, and the terminal device calls, through the processor 1001, the evaluation program of the atlas stored in the memory 1005, and executes each embodiment of the atlas evaluation method provided in the embodiment of the present application.
Based on the terminal equipment, the overall conception of the evaluation method of the atlas is provided.
Because the quality of the atlas established by the VR headset in the operation process is difficult to control, and the quality of the atlas cannot be detected by the SLAM algorithm in the related technology in the operation process, the SLAM algorithm is easy to occur the condition that the tracking of the VR headset cannot be accurately completed because of the lower quality of the atlas.
In view of the above phenomena, the present application proposes a method for evaluating a atlas, the method for evaluating a atlas comprising the steps of: acquiring a target map set established by virtual reality head-mounted equipment, and determining initial pose coordinates of the virtual reality head-mounted equipment according to the target map set; generating a target map set dividing region based on the initial pose coordinates and the target map set, and determining a plurality of map points contained in the target map set dividing region; determining target projections of each of a plurality of map points on an equatorial plane within the target map set partition area, and determining the number of projections in the equatorial plane according to each of the target projections; and determining a map set evaluation result corresponding to the target map set based on the projection quantity.
Therefore, the initial pose coordinates of the VR headset are determined based on the target atlas established by the VR headset, the target atlas dividing area is obtained based on the initial pose coordinates and the target atlas, and then the atlas evaluation result corresponding to the target atlas is generated based on the projection quantity of target projections generated by respective projections of a plurality of map points in the target atlas dividing area, so that the technical problem that tracking of the VR headset cannot be accurately completed due to low atlas quality in the SLAM algorithm is solved, the technical effect that the terminal equipment can evaluate the atlas established by the VR headset is achieved, the quality of the atlas can be determined, and the accuracy of tracking of the VR headset is further guaranteed.
Based on the overall conception of the terminal device and the evaluation method of the atlas of the application, various embodiments of the evaluation method of the atlas of the application are further provided.
Referring to fig. 2, fig. 2 is a flowchart of a first embodiment of an evaluation method of a atlas of the present application.
It should be understood that while a logical order is illustrated in the flowchart, in some cases the evaluation method of the atlas of the present application may of course perform the steps illustrated or described in a different order than that which is illustrated herein.
As shown in fig. 2, in this embodiment, the evaluation method of the atlas of the present application may include the steps of:
step S10: acquiring a target map set established by virtual reality head-mounted equipment, and determining initial pose coordinates of the virtual reality head-mounted equipment according to the target map set;
in this embodiment, the terminal device first reads the virtual reality headset to obtain a target map set established by the virtual reality headset, and then detects the virtual reality headset according to the target map set to determine initial pose coordinates of the virtual reality headset.
For example, the terminal device first reads the VR headset to obtain a target map set established by the VR headset, the terminal device further inputs the target map set to a SLAM module configured by the terminal device, the SLAM module invokes a SLAM algorithm to calculate based on the target map set according to a preset normal SLAM tracking policy to determine pose coordinates of the VR headset in the target map set, and the SLAM module further determines the pose coordinates of the VR headset in the target map set as initial pose coordinates of the VR headset.
In this embodiment and another embodiment, please refer to fig. 3, fig. 3 is a schematic view of a scenario involved in an embodiment of an evaluation method of a map set of the present application, as shown in fig. 3, when a user wears a VR headset to move in a space in fig. 3, a plurality of vision sensors configured by the VR headset may be called to shoot the surroundings so as to capture a target image including a surrounding environment, the VR headset further builds an initial map set based on the target image, and simultaneously, the VR headset starts a Local Mapping thread and a Loop cloning thread configured by the VR headset in a running process, so that each key frame image is generated by the Local Mapping thread and the Loop cloning thread, and the VR headset further adds each key frame image into the initial map set to build the target map set.
Further, in a possible embodiment, the step of determining the initial pose coordinates of the virtual reality headset according to the target atlas in the step S10 may specifically include:
step S101: reading each image characteristic point contained in the target map set, and determining a characteristic description value corresponding to each image characteristic point;
In this embodiment, after acquiring a target atlas established by the virtual reality headset device, the terminal device reads the target atlas to acquire a plurality of image feature points contained in the target atlas, and determines feature description values corresponding to the plurality of image feature points contained in the target atlas.
Step S102: determining initial pose coordinates of the virtual reality headset based on each of the feature description values;
in this embodiment, the terminal device performs nonlinear optimization calculation on the obtained feature description values, so as to obtain initial pose coordinates of the virtual reality headset device.
For example, after acquiring a target atlas established by the VR headset, the SLAM module continues to read the target atlas, identifies a plurality of image feature points contained in the target atlas through an ORB algorithm configured by the SLAM module, determines feature description values corresponding to the image feature points through the target atlas, and then invokes a preset PNP algorithm to perform nonlinear optimization solution on the feature description values, so as to calculate pose coordinates of the VR headset in the target atlas, and the SLAM module further determines the pose coordinates of the VR headset in the target atlas as initial pose sitting of the VR headset.
Step S20: generating a target map set dividing region based on the initial pose coordinates and the target map set, and determining a plurality of map points contained in the target map set dividing region;
in this embodiment, the terminal device uses the determined initial pose coordinate as a target space center, and constructs a target map set dividing region based on the target space center and the obtained target map set, and at the same time, the terminal device identifies the target map set dividing region to determine a plurality of map points contained in the target map set dividing region.
For example, after calculating the initial pose coordinates of the VR headset, the SLAM module directly uses the initial pose coordinates as a target space center, and further uses the target space center as a reference, establishes a circular space, and determines the circular space as a target map set dividing area, and at the same time, the SLAM module identifies the target map set dividing area, so as to identify a plurality of map points contained in the target map set dividing area through the ORB algorithm described above.
Further, in a possible embodiment, the step of generating the target atlas division area "in the step S20 based on the initial pose coordinate and the target atlas may specifically include:
Step S201: determining the initial pose coordinates as a target space center, and determining a first pole and a second pole based on the target space center;
in this embodiment, the terminal device first uses the initial pose coordinates as the target space center, and determines a north pole directly above the target space center and a south pole directly below the target space center.
Step S202: generating an equatorial plane based on the target space center, the first pole and the second pole, and generating a target atlas division region based on the equatorial plane and a preset region division rule;
in this embodiment, the terminal device further generates an equatorial plane with the center of the target space as a midpoint and perpendicular to a meridian line connecting the north pole and the south pole based on the north pole and the south pole, and further generates a spherical space based on the equatorial plane, the north pole and the south pole.
For example, referring to fig. 4, fig. 4 is a schematic diagram of a target map set dividing region related to an embodiment of an evaluation method of a map set of the present application, the SLAM module first uses an initial pose coordinate of a VR headset as a target space center, the SLAM module thereby determines an upper space boundary above the VR headset based on the obtained target map set, the SLAM module further determines a north pole that is above the target space center and intersects the upper space boundary, and simultaneously, the SLAM module determines a lower space boundary below the VR headset based on the obtained target map set, the SLAM module further determines south poles that intersect the lower space center, and then determines all space boundaries around the VR headset based on the target map set, the SLAM module further establishes a plane that is perpendicular to 90 ° and intersects all space boundaries around the VR headset based on the obtained north poles and south poles, and generates a spherical map set based on the obtained north poles and the north poles, and the spherical map set, and generates a spherical map region dividing region based on the spherical map set dividing rule 4.
Further, in a possible embodiment, the step of generating the target atlas division area "in the step S202 based on the equatorial plane and the preset area division rule may specifically include:
step S2021: acquiring a preset region division rule, and determining a target pitch according to the region division rule;
in this embodiment, the terminal device first obtains a region division rule preset by a technician, and determines the target pitch based on the region division rule.
Step S2022: determining a plurality of target regions based on the target pitch, the equatorial plane, the first pole, and the second pole;
in this embodiment, the terminal device generates a spherical space based on the equatorial plane, the north pole and the south pole, and at the same time, the terminal device performs a score change on the spherical space in order from the equatorial plane to the north pole and from the equatorial plane to the south pole with reference to the equatorial plane, so as to generate a plurality of target regions.
Step S2023: generating a target atlas division area according to a plurality of target areas;
in this embodiment, the terminal device integrates the plurality of target areas to generate the target atlas division area.
For example, after generating the equatorial plane, the SLAM module reads the terminal device to obtain a region division rule preset by a technician and determines that the target pitch is 30 ° according to the region division rule, then constructs a spherical space based on the north pole, south pole and equatorial plane obtained, and divides the spherical space from the equatorial plane to the north pole and south pole directions respectively at intervals of 30 ° based on the equatorial plane to obtain a target region R1 (0 ° -30 °), a target region R2 (30 ° -60 °), a target region R3 (60 ° -90 °), a target region R4 (90 ° -120 °), a target region R5 (120 ° -150 °) and a target region R6 (150 °), and the SLAM module further integrates a plurality of target regions R1 to R6 to generate a target map set division region as shown in fig. 4.
Step S30: determining target projections of each of a plurality of map points on an equatorial plane within the target map set partition area, and determining the number of projections in the equatorial plane according to each of the target projections;
in this embodiment, the terminal device identifies an equatorial plane in the dividing region of the target map set to determine target projections formed on the equatorial plane by target vectors formed between each of the plurality of feature points and the center of the target space, and further determines the number of projections in the equatorial plane according to each of the target projections.
Illustratively, for example, after identifying a plurality of map points, the SLAM module connects the plurality of map points with a target space center, respectively, to form a plurality of target vectors, and projects the plurality of target vectors to an equatorial plane within a target map set partition, the SLAM module in turn detects the equatorial plane to determine a target projection of each of the plurality of target vectors formed on the equatorial plane, and the SLAM module in turn determines a number of projections within the equatorial plane based on each of the target projections.
Step S40: determining a map set evaluation result corresponding to the target map set based on the projection quantity;
in this embodiment, the terminal device divides a plurality of azimuth areas in the equatorial plane, determines the target projection numbers corresponding to the azimuth areas based on the azimuth areas and the projection numbers, further determines the atlas evaluation result corresponding to the target atlas based on the target projection numbers, inputs the atlas evaluation result to the virtual reality headset, and the virtual reality headset displays the atlas evaluation result to a user wearing the virtual reality headset through a display device configured by the virtual reality headset, so that the user can save the target atlas or optimize the target atlas based on the atlas evaluation result.
Step S401: acquiring a preset azimuth dividing rule, and determining a plurality of azimuth areas contained in the equatorial plane based on the azimuth dividing rule;
in this embodiment, after determining the number of projections included in the equatorial plane, the terminal device obtains an azimuth dividing rule preset by a technician, and divides the equatorial plane based on the azimuth dividing rule, so as to divide a plurality of azimuth areas in the equatorial plane.
Step S402: determining the target projection quantity corresponding to each of a plurality of azimuth areas based on the projection quantity, and determining a map set evaluation result corresponding to the target map set according to each target projection quantity;
in this embodiment, the terminal device determines the number of target projections corresponding to each of the plurality of azimuth areas based on the number of projections and the position information of each of the plurality of target projections, and further determines a map set evaluation result corresponding to the target map set based on each of the number of target projections.
For example, referring to fig. 5, fig. 5 is a schematic view of an azimuth area related to an embodiment of an evaluation method of an atlas of the present application, after determining the number of projections included in an equatorial plane, a SLAM module reads a terminal device to obtain a preset two-team azimuth dividing rule of a technician, and divides the equatorial plane based on the azimuth dividing rule to divide an azimuth area 1, an azimuth area 2, an azimuth area 3 and an azimuth area 4 shown in fig. 5 on the equatorial plane, and then, based on the number of projections and position information corresponding to each of a plurality of target projections, the SLAM module determines the number of target projections corresponding to each of the azimuth area 1, the azimuth area 2, the azimuth area 3 and the azimuth area 4, and determines an atlas evaluation result corresponding to the target atlas based on each of the number of target projections.
Further, in a possible embodiment, the step of determining the atlas evaluation result corresponding to the target atlas according to the number of target projections in the step S402 may specifically include:
step S4021: acquiring a preset projection quantity threshold, and comparing the projection quantity of each target with the projection quantity threshold to obtain a plurality of comparison results;
in this embodiment, the terminal device obtains a projection number threshold preset by a technician while obtaining a plurality of target projection numbers, and compares the plurality of target projection numbers with the projection number threshold respectively, so as to obtain a plurality of comparison results.
Step S4022: judging whether a plurality of comparison results contain abnormal comparison results or not, wherein the abnormal comparison results are that the number of the target projections is smaller than the threshold value of the number of projections;
in this embodiment, the terminal device reads each obtained comparison result, and determines whether the plurality of comparison results include an abnormal comparison result in which the number of target projections is smaller than the threshold of the number of projections.
Step S4023: if the comparison results contain the abnormal comparison results, determining that the atlas evaluation result corresponding to the target atlas is the target atlas to be optimized;
In this embodiment, if the terminal device determines that the plurality of comparison results include the abnormal comparison result, it determines that the map points included in the target atlas are fewer, and then the terminal device determines that the atlas evaluation result is the target atlas and needs to be optimized.
Step S4024: if the comparison results do not contain the abnormal comparison results, determining that the atlas evaluation result corresponding to the target atlas is the target atlas and does not need to be optimized;
in this embodiment, if the terminal device determines that the plurality of comparison results do not include the abnormal comparison result, it determines that the number of map points included in the target atlas is sufficient, and the quality of map points included in the target atlas is higher, so that the terminal device determines that the atlas evaluation result corresponding to the target atlas is the target atlas and does not need to be optimized.
For example, the SLAM module obtains the target projection numbers corresponding to the azimuth areas 1 to 4, and simultaneously reads the terminal device to obtain the projection number threshold preset by the technician, and then compares the target projection numbers corresponding to the azimuth areas 1 to 4 with the projection number threshold to determine the size relationship between the target projection numbers and the projection number threshold, so as to generate 4 comparison results, and then sequentially reads the 4 comparison results, and judges whether the 4 comparison results comprise an abnormal comparison result that the target projection numbers are smaller than the projection number threshold, and then, if the SLAM module determines that the 4 comparison results comprise the abnormal comparison result, the SLAM determines that the map points contained in the target map set are insufficient, and further determines that the map set evaluation result corresponding to the target map set is the target map set to be optimized; if the SLAM module determines that the 4 comparison results do not contain the abnormal comparison results, the SLAM determines that the number of map points contained in the target atlas is enough, and further determines that the atlas evaluation result corresponding to the target atlas is the target atlas and does not need to be optimized; finally, the SLAM inputs the generated atlas evaluation result to the VR head-mounted device, and the VR head-mounted device displays the atlas evaluation result to a user wearing the VR head-mounted device based on a display module configured by the VR head-mounted device, so that the user can save or optimize the target atlas based on the atlas evaluation result.
In this embodiment, the terminal device first reads the virtual reality headset to obtain a target atlas established by the virtual reality headset, the terminal device further detects the virtual reality headset according to the target atlas to determine initial pose coordinates of the virtual reality headset, then the terminal device uses the determined initial pose coordinates as a target space center, and constructs and obtains a target atlas division area based on the target space center and the obtained target atlas, meanwhile, the terminal device identifies the target atlas division area to determine a plurality of map points contained in the target atlas division area, then the terminal device identifies an equatorial plane in the target atlas division area to determine target projections formed by target vectors formed between the feature points and the target space center on the equatorial plane, the terminal device further determines the projection number in the equatorial plane according to each target projection, finally the terminal device divides a plurality of azimuth areas in the equatorial plane, determines the number of target projections corresponding to the azimuth areas based on the target space center and the projection number, and the terminal device can be arranged on the basis of the virtual atlas to display the virtual atlas by the user's head according to an optimized evaluation result, and the user can display the target atlas by the user's head set.
Therefore, the initial pose coordinates of the VR headset are determined based on the target atlas established by the VR headset, the target atlas dividing area is obtained based on the initial pose coordinates and the target atlas, and then the atlas evaluation result corresponding to the target atlas is generated based on the projection quantity of target projections generated by respective projections of a plurality of map points in the target atlas dividing area, so that the technical problem that tracking of the VR headset cannot be accurately completed due to low atlas quality in the SLAM algorithm is solved, the technical effect that the terminal equipment can evaluate the atlas established by the VR headset is achieved, the quality of the atlas can be determined, and the accuracy of tracking of the VR headset is further guaranteed.
Based on the first embodiment of the evaluation method of the atlas of the present application described above, a second embodiment of the evaluation method of the atlas of the present application is presented herein.
Further, in a possible embodiment, after the step S4023, the evaluation method of the atlas of the present application may further include the following steps:
Step A10: determining a target azimuth angle area in a plurality of azimuth angle areas based on the abnormal comparison result, and determining a point location optimization area in a plurality of target areas in the target map set division area according to the target azimuth angle area;
in this embodiment, when determining that the map set evaluation result of the target map set is that the target map set needs to be optimized, the terminal device determines, based on the map evaluation set result, a target azimuth area in which the number of map points is smaller than a threshold of the number of projections in a plurality of azimuth areas in the equatorial plane, and at the same time, reads a plurality of target projections included in the target azimuth area, so that, based on map points and the target azimuth areas corresponding to the plurality of target projections, a point location optimization area in which the map points need to be supplemented is determined in a plurality of target areas included in the target map set division area.
Step A20: generating optimization prompt information according to the point position optimization region, and outputting the optimization prompt information to the virtual reality headset so that the virtual reality headset can acquire target map points in the point position optimization region;
In this embodiment, the terminal device generates the optimized prompt information based on the point location optimization area, and outputs the optimized prompt information to the virtual headset device, so that the virtual headset device can display the optimized prompt information to the user through the display module configured by the terminal device, thereby enabling the user to change the pose of the virtual reality headset device based on the optimized prompt information, aiming at the point location optimization area where the optimized prompt information reminds, and collecting the target map points which are not recorded in the target map set through the point location optimization area.
Step A30: optimizing the target map set based on the target map points to obtain an optimized map set;
in this embodiment, the virtual reality headset optimizes a target map set based on the acquired target map points to generate an optimized map set, and stores the optimized map set for location tracking.
For example, when the SLAM module determines that the atlas evaluation of the objective atlas is required to be optimized, the SLAM module determines the objective azimuth area with the objective projection number smaller than the projection number threshold value in the azimuth areas 1 to 4 contained in the equatorial plane based on the atlas evaluation result, and at the same time, the SLAM module determines the point location optimization area R requiring the supplement of the map points in the objective areas R1 to R6 contained in the objective atlas division area based on the map points respectively corresponding to the objective projections contained in the objective azimuth area m The SLAM module is further based on the point location optimization region R n Generating optimized prompt information, inputting the optimized prompt information to VR (virtual reality) head-mounted equipment, and enabling the VR head-mounted equipment to display the optimized prompt information to an outward user based on a display device configured by the VR head-mounted equipment, so that the user can adjust the VR head-mounted equipment based on the optimized prompt information, and the VR head-mounted equipment can acquire the point position optimized region R n The VR headset further optimizes the target map set established by the VR headset based on the target map points to obtain an optimized map set, and stores the optimized map set so that the SLAM module can track the pose coordinates of the VR headset based on the optimized map set. Therefore, the terminal equipment can timely generate optimization information when determining that the target atlas needs to be optimized, and guide the user to rotate the virtual reality head-mounted equipment to change the pose, so that target map points which are not recorded in the atlas are supplemented in the area lacking map points, and further optimization of the target atlas is completed.
Based on the first embodiment and/or the second embodiment of the evaluation method of the atlas of the present application described above, preferred embodiments of the evaluation method of the atlas of the present application are presented herein.
Further, referring to fig. 6, fig. 6 is a flow chart of a preferred embodiment of an evaluation method of a map set of the present application, as shown in fig. 6, in this embodiment, when the VR headset operates, the VR headset firstly invokes a SLAM algorithm through a SLAM module configured in the terminal device to construct a target map set corresponding to a surrounding environment, then the SLAM module determines initial pose coordinates of the VR headset in the target map set based on the target map set and a preset normal SLAM tracking strategy, the SLAM module further uses the initial pose coordinates as a sphere center, and constructs a target map set dividing region formed by a target annular region R1 to a target annular region R6, and simultaneously, the SLAM module reads the target map set dividing region and identifies a plurality of map points contained in the target map set dividing region through a preset ORB algorithm, the SLAM module further determines the number of map points contained in each of the target annular region R1 to the target annular region R6 based on a plurality of points, calculates the number of map points contained in each map set and calculates the number of map points contained in each map annular region, and compares the number of map points with the number of target annular region to a target annular region, and further compares the number of target map sets with the number of target map sets respectively to a threshold value, and then the number of the threshold value is calculated by the threshold value is calculated when the number of the threshold value is equal to the number of the threshold value is calculated by the threshold value, and the threshold value is calculated by comparing the threshold value of the threshold value and the threshold value is calculated by the threshold value and the threshold value of the threshold value, determining that the map set evaluation result corresponding to the target map set is that the target map set does not need to be optimized, SLAM further controls VR headset equipment to store the target map set, and ending the evaluation operation of the target map set;
If the SLAM module determines that the plurality of comparison results are uneven and the target projection quantity is larger than or equal to the projection quantity threshold value, determining that the atlas evaluation result corresponding to the target atlas is required to be optimized for the target atlas, and further determining that the map is lack in the azimuth area 1 to the azimuth area 4 based on the atlas evaluation resultThe target azimuth area of the point, and determining a point position optimization area R needing to supplement map points in the target annular area R1 to the target annular area R6 based on the position information of map points corresponding to the projection of a plurality of targets in the target azimuth area n And optimizing the region R based on the point location n Generating an optimized prompt message, inputting the optimized prompt message to the VR headset by the SLAM module, and continuously displaying the optimized prompt message by the VR headset based on a display device configured by the VR headset to the outside of a user wearing the VR headset so as to guide the user to change the pose of the VR headset, thereby enabling the VR headset to identify the point position optimized region R n And the target map points which are contained in the target map set and are not recorded in the target map set are collected to optimize the target map set.
In addition, in order to achieve the above objective, the present application further provides an apparatus for evaluating a atlas, referring to fig. 7, fig. 7 is a schematic diagram of functional modules related to an embodiment of the apparatus for evaluating an atlas of the present application, as shown in fig. 7, where the apparatus includes:
the pose calculation module 10 is configured to obtain a target atlas established by the virtual reality headset, and determine initial pose coordinates of the virtual reality headset according to the target atlas;
a region generation module 20, configured to generate a target atlas division region based on the initial pose coordinate and the target atlas, and determine a plurality of map points contained in the target atlas division region;
a number calculation module 30 for determining target projections of each of the plurality of map points on an equatorial plane within the target map set division area, and determining a number of projections in the equatorial plane from each of the target projections;
and a result generating module 40, configured to determine a atlas evaluation result corresponding to the target atlas based on the projection number.
Further, the area generating module 20 includes:
the point position determining unit is used for determining the initial pose coordinates as a target space center and determining a first pole and a second pole based on the target space center;
The region construction unit is used for generating an equatorial plane based on the target space center, the first pole and the second pole, and generating a target atlas division region based on the equatorial plane and a preset region division rule.
Further, the region construction unit includes:
the step distance determining subunit is used for acquiring a preset region division rule and determining a target step distance according to the region division rule;
a region dividing subunit for determining a plurality of target regions based on the target pitch, the equatorial plane, the first pole, and the second pole;
and the region construction subunit is used for generating a target map set dividing region according to a plurality of target regions.
Further, the result generating module 40 includes:
the plane dividing unit is used for acquiring a preset azimuth dividing rule and determining a plurality of azimuth areas contained in the equatorial plane based on the azimuth dividing rule;
and the plane recognition unit is used for determining the target projection quantity corresponding to each of the azimuth areas based on the projection quantity, and determining a map set evaluation result corresponding to the target map set according to each target projection quantity.
Further, the plane recognition unit includes:
the quantity comparison subunit is used for acquiring a preset projection quantity threshold value, and comparing the projection quantity of each target with the projection quantity threshold value respectively to obtain a plurality of comparison results;
the result detection subunit is used for judging whether a plurality of comparison results contain abnormal comparison results or not, wherein the abnormal comparison results are that the number of the target projections is smaller than the projection number threshold;
the first generation subunit is used for determining that the atlas evaluation result corresponding to the target atlas is the target atlas to be optimized if judging that the plurality of comparison results contain the abnormal comparison result;
and the second generation subunit is used for determining that the atlas evaluation result corresponding to the target atlas is the target atlas and does not need to be optimized if the comparison results do not contain the abnormal comparison results.
Further, the result generating module 40 further includes:
the region screening unit is used for determining a target azimuth region in a plurality of azimuth regions based on the abnormal comparison result, and determining a point location optimization region in a plurality of target regions in the target map set dividing region according to the target azimuth region;
The information output unit is used for generating optimization prompt information according to the point position optimization area and outputting the optimization prompt information to the virtual reality headset so that the virtual reality headset can acquire target map points in the point position optimization area;
and the data optimization unit is used for optimizing the target map set based on the target map points to obtain an optimized map set.
Further, the pose calculation module 10 includes:
the feature extraction unit is used for reading each image feature point contained in the target atlas and determining a feature description value corresponding to each image feature point;
and the pose calculating unit is used for determining initial pose coordinates of the virtual reality head-mounted equipment based on the feature description values.
In addition, the application further provides a terminal device, the terminal device is provided with a computer program capable of running on a processor, and the terminal device realizes the steps of the method for evaluating the atlas according to any one of the above embodiments when executing the computer program.
The specific embodiment of the terminal device in the present application is substantially the same as each embodiment of the method for evaluating a atlas described above, and will not be described herein.
Furthermore, the present application provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps of the method for evaluating a atlas according to any one of the embodiments above.
The specific embodiments of the computer readable storage medium are basically the same as the embodiments of the method for evaluating a atlas described above, and are not described herein.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present application are merely for describing, and do not represent advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) as described above, including several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method described in the embodiments of the present application.
The foregoing description is only of the preferred embodiments of the present application, and is not intended to limit the scope of the claims, and all equivalent structures or equivalent processes using the descriptions and drawings of the present application, or direct or indirect application in other related technical fields are included in the scope of the claims of the present application.

Claims (10)

1. The method for evaluating the atlas is characterized by comprising the following steps of:
acquiring a target map set established by virtual reality head-mounted equipment, and determining initial pose coordinates of the virtual reality head-mounted equipment according to the target map set;
generating a target map set dividing region based on the initial pose coordinates and the target map set, and determining a plurality of map points contained in the target map set dividing region;
determining target projections of each of a plurality of map points on an equatorial plane within the target map set partition area, and determining the number of projections in the equatorial plane according to each of the target projections;
and determining a map set evaluation result corresponding to the target map set based on the projection quantity.
2. The method of evaluating a atlas of claim 1, wherein the step of generating a target atlas partitioning region based on the initial pose coordinates and the target atlas comprises:
Determining the initial pose coordinates as a target space center, and determining a first pole and a second pole based on the target space center;
and generating an equatorial plane based on the target space center, the first pole and the second pole, and generating a target atlas division region based on the equatorial plane and a preset region division rule.
3. The method of evaluating a atlas according to claim 2, wherein the step of generating a target atlas division region based on the equatorial plane and a preset region division rule comprises:
acquiring a preset region division rule, and determining a target pitch according to the region division rule;
determining a plurality of target regions based on the target pitch, the equatorial plane, the first pole, and the second pole;
and generating a target atlas division area according to the target areas.
4. The method of evaluating a atlas according to claim 1, wherein the step of determining an atlas evaluation result corresponding to the target atlas based on the projection number includes:
acquiring a preset azimuth dividing rule, and determining a plurality of azimuth areas contained in the equatorial plane based on the azimuth dividing rule;
And determining the target projection quantity corresponding to each of the azimuth areas based on the projection quantity, and determining a map set evaluation result corresponding to the target map set according to each target projection quantity.
5. The method of evaluating a atlas according to claim 4, wherein the step of determining an atlas evaluation result corresponding to the target atlas based on each of the target projection numbers includes:
acquiring a preset projection quantity threshold, and comparing the projection quantity of each target with the projection quantity threshold to obtain a plurality of comparison results;
judging whether a plurality of comparison results contain abnormal comparison results or not, wherein the abnormal comparison results are that the number of the target projections is smaller than the threshold value of the number of projections;
if the comparison results contain the abnormal comparison results, determining that the atlas evaluation result corresponding to the target atlas is the target atlas to be optimized;
and if the comparison results do not contain the abnormal comparison results, determining that the atlas evaluation result corresponding to the target atlas is the target atlas and optimization is not needed.
6. The method for evaluating a atlas according to claim 5, wherein after the step of determining that the atlas evaluation result corresponding to the target atlas is that the target atlas needs to be optimized, the method further comprises:
Determining a target azimuth angle area in a plurality of azimuth angle areas based on the abnormal comparison result, and determining a point location optimization area in a plurality of target areas in the target map set division area according to the target azimuth angle area;
generating optimization prompt information according to the point position optimization region, and outputting the optimization prompt information to the virtual reality headset so that the virtual reality headset can acquire target map points in the point position optimization region;
and optimizing the target map set based on the target map points to obtain an optimized map set.
7. The method of evaluating a atlas of claim 1, wherein the step of determining initial pose coordinates of the virtual reality headset from the target atlas comprises:
reading each image characteristic point contained in the target map set, and determining a characteristic description value corresponding to each image characteristic point;
and determining initial pose coordinates of the virtual reality headset based on each characteristic description value.
8. An apparatus for evaluating a atlas, the apparatus comprising:
the pose calculation module is used for acquiring a target atlas established by the virtual reality head-mounted equipment and determining initial pose coordinates of the virtual reality head-mounted equipment according to the target atlas;
The region generation module is used for generating a target map set dividing region based on the initial pose coordinates and the target map set and determining a plurality of map points contained in the target map set dividing region;
a number calculation module, configured to determine target projections of each of the map points on an equatorial plane within the target map set division area, and determine a number of projections in the equatorial plane according to each of the target projections;
and the result generation module is used for determining a map set evaluation result corresponding to the target map set based on the projection quantity.
9. A terminal device, characterized in that the terminal device comprises: memory, a processor, on which a computer program is stored which is executable on the processor, the computer program implementing the steps of the atlas evaluation method according to any one of claims 1 to 7 when executed by the processor.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of the method for evaluating a atlas according to any one of claims 1 to 7.
CN202311442518.6A 2023-10-31 2023-10-31 Method and device for evaluating atlas, terminal equipment and computer storage medium Pending CN117392101A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311442518.6A CN117392101A (en) 2023-10-31 2023-10-31 Method and device for evaluating atlas, terminal equipment and computer storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311442518.6A CN117392101A (en) 2023-10-31 2023-10-31 Method and device for evaluating atlas, terminal equipment and computer storage medium

Publications (1)

Publication Number Publication Date
CN117392101A true CN117392101A (en) 2024-01-12

Family

ID=89440597

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311442518.6A Pending CN117392101A (en) 2023-10-31 2023-10-31 Method and device for evaluating atlas, terminal equipment and computer storage medium

Country Status (1)

Country Link
CN (1) CN117392101A (en)

Similar Documents

Publication Publication Date Title
US10694175B2 (en) Real-time automatic vehicle camera calibration
US8803800B2 (en) User interface control based on head orientation
KR20200076169A (en) Electronic device for recommending a play content and operating method thereof
US11789528B1 (en) On-the-fly calibration for improved on-device eye tracking
US11816924B2 (en) Method for behaviour recognition based on line-of-sight estimation, electronic equipment, and storage medium
EP3767435B1 (en) 6-dof tracking using visual cues
CN110248401B (en) WiFi scanning control method and device, storage medium and mobile terminal
CN113031839B (en) Image processing method, device, equipment and medium in video call
KR20210087181A (en) An electronic device detecting a location and a method thereof
KR20180097912A (en) Emotion analysis method and system for analyzing user emotion using user terminal
AU2019101558A4 (en) Method and apparatus for displaying display object according to real-time information
CN110809083B (en) Mobile terminal information reminding method, mobile terminal and storage medium
CN117392101A (en) Method and device for evaluating atlas, terminal equipment and computer storage medium
CN113432620B (en) Error estimation method and device, vehicle-mounted terminal and storage medium
CN112150983B (en) Screen brightness adjusting method and device, storage medium and electronic equipment
CN113935678A (en) Method, device, equipment and storage medium for determining multiple distribution terminals held by distributor
CN114170620A (en) Palm position determining method and device, electronic equipment and storage medium
CN114623836A (en) Vehicle pose determining method and device and vehicle
CN117392099A (en) Method and device for evaluating atlas, terminal equipment and computer storage medium
CN115086861B (en) Audio processing method, device, equipment and computer readable storage medium
US20230059119A1 (en) Information processing device, control method, and non-transitory computer-readable medium
CN111879331B (en) Navigation method and device and electronic equipment
CN109634862B (en) Application analysis method, device and storage medium
CN117372525A (en) Pose initialization method, device, equipment and medium of virtual reality head-mounted equipment
CN117392340A (en) Method and device for merging atlas, terminal equipment and computer storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination