CN115439768A - Computer room AR positioning correction system and method and medium - Google Patents

Computer room AR positioning correction system and method and medium Download PDF

Info

Publication number
CN115439768A
CN115439768A CN202211064487.0A CN202211064487A CN115439768A CN 115439768 A CN115439768 A CN 115439768A CN 202211064487 A CN202211064487 A CN 202211064487A CN 115439768 A CN115439768 A CN 115439768A
Authority
CN
China
Prior art keywords
cabinet
glasses
positioning
machine room
equipment
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
CN202211064487.0A
Other languages
Chinese (zh)
Inventor
董贇
梁仲峰
张希翔
孟椿智
蒙琦
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.)
Guangxi Power Grid Co Ltd
Original Assignee
Guangxi Power Grid 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 Guangxi Power Grid Co Ltd filed Critical Guangxi Power Grid Co Ltd
Priority to CN202211064487.0A priority Critical patent/CN115439768A/en
Publication of CN115439768A publication Critical patent/CN115439768A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/20—Scenes; Scene-specific elements in augmented reality scenes
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00—Measuring arrangements characterised by the use of optical techniques
    • G01B11/002—Measuring arrangements characterised by the use of optical techniques for measuring two or more coordinates
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00—Measuring arrangements characterised by the use of optical techniques
    • G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/51—Indexing; Data structures therefor; Storage structures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/07—Target detection

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Image Analysis (AREA)

Abstract

The invention discloses an AR positioning correction system for a machine room.A cabinet feature library establishing module establishes a cabinet feature library of an information machine room; the serial number identification module of the cabinet identifies the serial number of the cabinet for positioning calculation; the characteristic library matching module of the cabinet obtains the position of each cabinet for positioning calculation in the machine room map and the corresponding cabinet outline size; the AR glasses positioning module determines the position of AR glasses in an information machine room; and the positioning correction module is used for correcting the SLAM positioning in the information machine room according to the position of the AR glasses in the information machine room. According to the method, the SLAM technology is utilized, the target detection technology, the feature library matching technology and the positioning technology are combined, the SLAM positioning is corrected according to the backward-deducing position of the first visual angle image of the AR glasses, and the positioning problem under the environment with similar feature points is solved.

Description

Computer room AR positioning correction system and method and medium
Technical Field
The invention relates to the technical field of information machine room positioning correction, in particular to a positioning correction system, a positioning correction method and a positioning correction medium based on an AR (Augmented Reality) machine room.
Background
In the case that the environment information is unknown, the SLAM technology (Simultaneous Localization and Mapping) continuously constructs the environment information in the process of movement through a specified sensor and estimates the position of the SLAM technology (Simultaneous Localization and Mapping); when a camera is used as a sensor, it is called "visual SLAM".
Object detection is one of the most fundamental and challenging problems in the field of computer vision, and has been widely researched and explored by various social circles in recent years. As an important task in the field of computer vision, target detection generally needs to be accomplished by: a specific location of a certain type of visual object, such as a human being, an animal or an automobile, in the digital image is provided. The target detection is image segmentation based on target geometry and statistical characteristics, the segmentation and the identification of a target are combined into a whole, and the accuracy and the real-time performance of the image segmentation are important capabilities of the whole system. Especially, in a complex scene, when a plurality of targets need to be processed in real time, automatic target extraction and identification are particularly important. From an application point of view, target detection can be divided into two research topics: object detection in general scenarios and object detection in specific categories. The difference between the two is: the former is similar to the vision and cognition of a simulated human, and mainly aims to explore a method for detecting different classes of objects under a unified framework; the latter refers to detection under specific application scenarios, such as human face detection, pedestrian detection, vehicle detection, and other tasks. In recent years, the rapid development of deep learning technology brings significant breakthrough to target detection. Object detection has been widely used in many real-world scenarios, such as autopilot, robot vision, video surveillance, etc.
With the development of positioning technology, GPS and base station positioning technology have achieved accurate positioning of most outdoor scenes. But in a few outdoor scenes or indoors, due to the presence of various obstacles, the GNSS signals decay rapidly or even not, so that accurate positioning cannot be achieved in these areas. Meanwhile, indoor scenes such as an information machine room have unified environmental characteristics, so that higher requirements are put forward on positioning. Technologies currently applied to indoor positioning mainly include wifi positioning technology, bluetooth positioning technology, infrared positioning technology, ultrasonic positioning technology, geomagnetic positioning technology, RFID positioning, ultra-wideband positioning, and the like. However, these techniques have different defects in terms of positioning accuracy, coverage, reliability, power consumption, cost, and the like. If the wifi positioning hot spot is greatly influenced by the surrounding environment, the positioning precision is low and the maintenance cost is high; the RFID positioning coverage range is small, and the communication capability is not available; the ultra-wideband positioning technology has higher cost, complex network deployment and the like.
Disclosure of Invention
The invention aims to provide a computer room AR positioning correction system, a computer room AR positioning correction method and a computer room AR positioning correction medium.
In order to achieve the purpose, the AR positioning correction system for the machine room is characterized by comprising a cabinet feature library establishing module, a serial number identification module of the cabinet, a feature library matching module of the cabinet, an AR glasses positioning module and a positioning correction module;
the equipment cabinet characteristic library establishing module is used for establishing an equipment cabinet characteristic library of the information machine room;
the number identification module of the equipment cabinet is used for detecting the target of each equipment cabinet in the first visual field of the AR glasses by using a target detection technology when the complete equipment cabinet exists in the first visual field of the AR glasses in the scene of the information equipment room, identifying characters of each complete equipment cabinet detected by the target, and identifying the serial number of the equipment cabinet, namely the serial number of the equipment cabinet for positioning calculation;
the characteristic library matching module of the cabinet is used for matching in the cabinet characteristic library according to the serial number of each positioning calculation cabinet, and obtaining the position of each positioning calculation cabinet in the machine room map and the corresponding cabinet outline size through correlation;
the AR glasses positioning module is used for determining the position of the AR glasses relative to each positioning calculation cabinet in the first visual angle image according to the position of each positioning calculation cabinet in the machine room map and the corresponding cabinet outline size, and determining the position of the AR glasses in the information machine room according to the coordinates of each positioning calculation cabinet and the position of the AR glasses relative to each positioning calculation cabinet in the first visual angle image;
and the positioning correction module is used for correcting the SLAM positioning in the information machine room according to the position of the AR glasses in the information machine room.
The invention has the beneficial effects that:
the invention creates a characteristic library of a machine cabinet and equipment of a machine room, combines the technologies of characteristic library matching, target detection, character recognition and the like for use, firstly carries out target detection on the equipment in the machine room, then carries out character recognition on each recognized target, and finally carries out matching in the characteristic library through a character recognition result field to obtain the associated information of the machine cabinet and the equipment. Based on the correlation information, the position of the AR glasses is reversely deduced, the SLAM positioning is corrected according to a reverse deduction result, the situation of positioning error caused by similar environmental characteristics is avoided, the SLAM is easily positioned to another environment similar place in a similar environment, and if the SLAM positioning is inconsistent with the reverse deduction position of the first visual angle of the AR glasses, the reverse deduction position is used as the standard.
Drawings
FIG. 1 is a schematic view of the structure of the present invention;
FIG. 2 is a flow chart of the method of the present invention;
FIG. 3 is a schematic diagram of a P3P (Perspective-Three-Point) Three-Point Perspective view of a complete cabinet;
FIG. 4 is a P3P three-point perspective schematic view for a complete cabinet;
FIG. 5 is a schematic diagram of a P3P three-point perspective view of equipment within a cabinet;
FIG. 6 is a schematic diagram of a P3P three point perspective for equipment within a cabinet;
Detailed Description
The invention is described in further detail below with reference to the following figures and specific examples:
the AR positioning correction system for the machine room shown in the figure 1 is characterized by comprising a cabinet feature library establishing module, a serial number identification module of a cabinet, a feature library matching module of the cabinet, an AR glasses positioning module and a positioning correction module;
the equipment cabinet feature library establishing module is used for establishing an equipment cabinet feature library of an information equipment room, and the equipment cabinet feature library comprises equipment cabinet numbers (Nx) and equipment cabinet outline dimensions (S1, S2 and S3), wherein the outline dimensions mainly comprise the length, the width and the diagonal length of an equipment cabinet panel, the positions (X1 and Y1) of the mass center of the equipment cabinet in a large map of the equipment room, equipment (category and number) installed in the equipment cabinet, the mass center positions (X2 and Y2) of each equipment panel in the equipment cabinet panel, and the outline dimensions (S1, S2 and S3) of each equipment mainly comprise the length, the width and the diagonal length of the equipment panel;
the number identification module of the equipment cabinet is used for carrying out target detection on each equipment cabinet in the first visual field of the AR glasses by utilizing a target detection technology based on image identification when the complete equipment cabinet exists in the first visual field of the AR glasses in the scene of the information equipment room, carrying out character identification on each complete equipment cabinet detected by the target, and identifying the equipment cabinet number which is the number of the equipment cabinet for positioning calculation;
the characteristic library matching module of the cabinet is used for matching in the cabinet characteristic library according to the serial number of each positioning calculation cabinet (character recognition is used for obtaining the serial number of the cabinet, matching is carried out in the library according to the serial number field of the cabinet, if the recognized serial number of the cabinet is consistent with that of a certain cabinet in the library, information in the cabinet library is correlated), and the position of each positioning calculation cabinet in the machine room map and the corresponding cabinet outline size are obtained through correlation;
the AR glasses positioning module is used for determining the position of the AR glasses relative to each positioning calculation cabinet in the first visual angle image according to the position of each positioning calculation cabinet in the machine room map and the corresponding cabinet outline size, and determining the position of the AR glasses in the information machine room according to the coordinates of each positioning calculation cabinet and the position of the AR glasses relative to each positioning calculation cabinet in the first visual angle image (if a plurality of cabinets are detected, the position is reversely pushed according to the first visual angle image of each cabinet respectively, then the reversely pushed positions are added and then averaged, so that the error can be averaged, and the condition that a single calculation error is large is prevented; the target detection technology can detect all the matched targets in the visual field, the target detection can detect which complete cabinets exist in the first visual field, then character recognition is carried out on the nameplates of the complete cabinets, the numbers of the complete cabinets are obtained after the character recognition, then information such as the size and the coordinates of the complete cabinets are obtained according to the matching of the number fields of the complete cabinets, and then positioning reverse calculation is carried out according to the information;
the positioning correction module is used for correcting the position of the AR glasses positioned by the SLAM in the information machine room according to the position of the AR glasses in the information machine room, and correcting the positioning to a correct position if the positioning of the AR glasses is wrong due to similarity of environmental characteristics.
In the technical scheme, the system further comprises an equipment target detection module and a feature library matching module of the equipment, wherein the equipment target detection module is used for carrying out target detection on the equipment in each cabinet in a visual field by using a target detection technology under the scene of an information machine room when no complete cabinet exists in a first visual field of AR glasses, and determining the type and the number of the equipment in each cabinet and the mass center position of each equipment panel in a cabinet panel. In patrolling and examining the in-process, personnel can be close to the rack gradually, and after being close to the rack, the rack marks the tablet just can not be seen in the first image of AR glasses, can't carry out the word discernment to marking the tablet, just can't obtain the rack serial number, so when unable through the word discernment obtain the rack serial number, the accessible matches in the characteristic storehouse to establishing classification, quantity, the position of equipment in the rack to confirm the rack, acquire size isoparametric.
The feature library matching module of the equipment is used for matching the type and the quantity of the equipment in the cabinet determined by target detection, the mass center position of each equipment panel in the cabinet panel with the cabinet feature library to obtain the cabinet number (the number, the type and the position of each cabinet in the library) of each positioning calculation cabinet in the first view field of the AR glasses, if the equipment number, the identification and the position of a certain cabinet in the first view field are consistent with those of a certain cabinet in the feature library, the cabinet number field is given to the cabinet), the matching is carried out in the cabinet feature library according to each positioning calculation cabinet number, and the coordinates (the position of the positioning calculation cabinet in the machine room map) of each positioning calculation cabinet and the corresponding equipment contour size in the cabinet are obtained in a correlated mode.
The AR glasses positioning module is used for determining the position of the AR glasses relative to each positioning calculation cabinet in the first visual angle image according to the coordinates of each positioning calculation cabinet and the corresponding equipment contour size in the cabinet, and determining the position of the AR glasses in the information machine room according to the coordinates of each positioning calculation cabinet and the position of the AR glasses relative to each positioning calculation cabinet in the first visual angle image.
In the above technical solution, the specific method for the AR glasses positioning module to determine the position of the AR glasses relative to the cabinet for positioning calculation in the first perspective image according to the coordinate of a certain cabinet for positioning calculation and the corresponding cabinet contour size, and to determine the position of the AR glasses in the information room according to the coordinate of the cabinet for positioning calculation and the position of the AR glasses relative to the cabinet for positioning calculation in the first perspective image, includes:
since the angle aOb = aOb; angle aOc = aOc; the expression of < cOb = < COB is obtained by using the cosine theorem, as shown in FIG. 3:
OA 2 +OB 2 -2OA*OB*cosθAB＝AB 2
OB 2 +OC 2 -2OB*OC*cosθBC＝BC 2
OA 2 +OC 2 -2OA*OC*cosθAC＝AC 2
thus, as shown in FIG. 4;
Figure BDA0003827172500000061
Figure BDA0003827172500000062
Figure BDA0003827172500000063
the point O represents the position of the front lens of the AR glasses, the points A, B and C represent three vertexes of the outline of the cabinet for positioning calculation in the real world, the points a, B and C represent three vertexes of the outline of the cabinet for positioning calculation in the first visual angle image, and the points OA, OB and OC represent the distances between the three vertexes of the outline of the cabinet for positioning calculation in the real world and the front lens of the AR glasses respectively; AB. BC and AC represent the side length between adjacent fixed points of the outline of the cabinet for calculation in the real world; cos theta AB represents a cosine function of < AOB, cos theta AC represents the cosine function of < AOC, cos theta BC represents the cosine function of < BOC, S 1 ＝AB，S 2 ＝AC、S 3 ＝BC，L A ＝OA，L B ＝OB，L C ＝OC；
And obtaining the lengths of OA, OB and OC, and determining the position of the AR glasses in the information machine room by combining the coordinates of the machine cabinet and the position of the AR glasses from the machine cabinet. After target detection and character recognition are carried out, matching and association are carried out through a feature library, the position coordinates of the cabinet in the floor plan of the machine room are obtained, the distance between the AR glasses and each vertex of the contour of the cabinet is known, the distance between one point and each vertex of the contour of the cabinet can be obtained through calculation, the distance is consistent with OA, OB and OC, and the point is the position of the AR glasses.
In the above technical solution, the specific method for determining the position of the AR glasses in the information room according to the coordinate of a certain cabinet for positioning calculation and the contour size of the corresponding equipment in the cabinet by the AR glasses positioning module, and according to the coordinate of the cabinet for positioning calculation and the position of the AR glasses in the first perspective image by the cabinet for positioning calculation, the specific method for determining the position of the AR glasses in the information room comprises:
due to the fact that 1 Ob 1 ＝∠A 1 OB 1 ；∠a 1 Oc 1 ＝∠A 1 OC 1 ；∠c 1 Ob 1 ＝∠C 1 OB 1 Using the cosine theorem, as shown in fig. 5:
OA 1 2 +OB 1 2 -2OA 1 *OB 1 *cosθA 1 B 1 ＝A 1 B 1 2
OB 1 2 +OC 1 2 -2OB 1 *OC 1 *cosθB 1 C 1 ＝B 1 C 1 2
OA 1 2 +OC 1 2 -2OA 1 *OC 1 *cosθA 1 C 1 ＝A 1 C 1 2
thus, as shown in FIG. 6;
S1 1 2 ＝A 1 B 1 2 ＝L1 A 2 +L1 B 2 -2L1 A L1 B cosθA 1 B 1
S1 2 2 ＝A 1 C 1 2 ＝L1 A 2 +L1 C 2 -2L1 A L1 C cosθA 1 C 1
S1 3 2 ＝B 1 C 1 2 ＝L1 B 2 +L1 C 2 -2L1 B L1 C cosθB 1 C 1
wherein, the point O represents the front lens position of the AR glasses, A 1 、B 1 、C 1 Points represent the three vertices of the contour of the equipment in the cabinet for positioning calculation in the real world, a 1 、b 1 、c 1 Points represent the three vertices of the outline of the equipment in the positioning computing cabinet, OA, in the first perspective image 1 、OB 1 、OC 1 Representing distances between three vertexes of the outline of equipment in a cabinet for positioning calculation in the real world and the front lens of the AR glassesSeparating; a. The 1 B 1 、B 1 C 1 、A 1 C 1 Representing the side length between adjacent fixed points of the outline of equipment in the cabinet for calculation in the real world; cos θ A 1 B 1 Represents < A 1 OB 1 Cosine function of (c), cos θ A 1 C 1 Expression of < A 1 OC 1 Cosine function of (1), cos θ B 1 C 1 Expression of < B 1 OC 1 Cosine function of, S1 1 ＝A 1 B 1 ，S1 2 ＝A 1 C 1 、S1 3 ＝B 1 C 1 ，L1 A ＝OA 1 ，L1 B ＝OB 1 ，L1 C ＝OC 1 ；
Results OA 1 、OB 1 、OC 1 And determining the position of the AR glasses in the information machine room by combining the coordinates of the machine cabinet and the position of the AR glasses from the equipment in the machine cabinet. After target detection and character recognition, matching and association are carried out through a feature library, the position coordinates of the cabinet in the machine room map are obtained, the distance between the AR glasses and each vertex of equipment in the cabinet outline is known, and the distance between one point and each vertex of the equipment outline in the cabinet and the OA distance can be obtained through calculation 1 、OB 1 、OC 1 And if the two points are consistent, the point is the AR glasses position.
In the above technical solution, the rack feature library establishing module is configured to establish a rack feature library of an information machine room according to a construction drawing and an equipment specification.
In the above technical solution, the specific method for the positioning correction module to correct the SLAM positioning in the information machine room according to the position of the AR glasses in the information machine room is as follows: and if the position of the AR glasses positioned by the SLAM is not consistent with the first visual angle reverse-deducing position of the AR glasses, taking the reverse-deducing position as a standard.
An AR positioning correction method for a machine room, as shown in fig. 2, includes the following steps:
step 1: establishing a cabinet feature library of an information machine room, wherein the cabinet feature library comprises a cabinet number (Nx), cabinet outline dimensions (S1, S2 and S3), positions (X1 and Y1) of a cabinet centroid in a large map of the machine room, equipment (types and numbers) installed in the cabinet, positions (X2 and Y2) of centroids of equipment panels in the cabinet panel and outline dimensions (S1, S2 and S3) of the equipment;
step 2: in an information machine room scene, when complete cabinets exist in a first view field of AR glasses, target detection is carried out on all cabinets in the first view field of the AR glasses by using a target detection technology based on image identification, character identification is carried out on all the complete cabinets detected by the targets, and the identified cabinet number is the number of the cabinet for positioning calculation;
matching in a cabinet feature library according to the serial number of each positioning calculation cabinet (character recognition is used for obtaining the serial number of the cabinet, matching is carried out in the library according to the serial number field of the cabinet, if the identified serial number of the cabinet is consistent with that of a certain cabinet in the library, information in the cabinet library is correlated), and the position of each positioning calculation cabinet in a machine room map and the corresponding cabinet outline size are obtained through correlation;
determining the position of the AR glasses relative to each positioning calculation cabinet in the first visual angle image according to the position of each positioning calculation cabinet in the machine room map and the corresponding cabinet outline size, and determining the position of the AR glasses in the information machine room according to the coordinates of each positioning calculation cabinet and the position of the AR glasses relative to each positioning calculation cabinet in the first visual angle image;
in an information machine room scene, when no complete cabinet exists in a first view of the AR glasses, target detection is carried out on equipment in each cabinet in the view by using a target detection technology, and the category and the number of the equipment in each cabinet and the mass center position of each equipment panel in each cabinet panel are determined.
Matching the category and the number of the equipment in the cabinet determined by target detection, the mass center position of each equipment panel in the cabinet panel and a cabinet feature library to obtain the cabinet number of each positioning calculation cabinet in the first view of the AR glasses, matching in the cabinet feature library according to each positioning calculation cabinet number, and correlating to obtain the coordinate (the position of each positioning calculation cabinet in a machine room map) of each positioning calculation cabinet and the outline size of the corresponding equipment in the cabinet;
determining the position of the AR glasses relative to each positioning calculation cabinet in the first visual angle image according to the coordinates of each positioning calculation cabinet and the corresponding equipment contour size in the cabinet, and determining the position of the AR glasses in the information machine room according to the coordinates of each positioning calculation cabinet and the position of the AR glasses relative to each positioning calculation cabinet in the first visual angle image;
and 3, step 3: and correcting the SLAM positioning in the information machine room according to the position of the AR glasses in the information machine room.
A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the above-mentioned method steps.
Details not described in this specification are within the skill of the art that are well known to those skilled in the art.

Claims (10)

1. An AR positioning correction system for a machine room is characterized by comprising a cabinet feature library establishing module, a serial number identification module of a cabinet, a feature library matching module of the cabinet, an AR glasses positioning module and a positioning correction module;
the equipment cabinet characteristic library establishing module is used for establishing an equipment cabinet characteristic library of an information machine room;
the number identification module of the equipment cabinet is used for detecting the target of each equipment cabinet in the first visual field of the AR glasses by using a target detection technology when the complete equipment cabinet exists in the first visual field of the AR glasses in the scene of the information equipment room, identifying characters of each complete equipment cabinet detected by the target, and identifying the serial number of the equipment cabinet, namely the serial number of the equipment cabinet for positioning calculation;
the characteristic library matching module of the cabinet is used for matching in the cabinet characteristic library according to the serial number of each positioning calculation cabinet, and obtaining the position of each positioning calculation cabinet in the machine room map and the corresponding cabinet outline size through correlation;
the AR glasses positioning module is used for determining the position of the AR glasses relative to each positioning calculation cabinet in the first visual angle image according to the position of each positioning calculation cabinet in the machine room map and the corresponding cabinet outline size, and determining the position of the AR glasses in the information machine room according to the coordinate of each positioning calculation cabinet and the position of the AR glasses relative to each positioning calculation cabinet in the first visual angle image;
and the positioning correction module is used for correcting the SLAM positioning in the information machine room according to the position of the AR glasses in the information machine room.
2. The machine room AR positioning correction system of claim 1, characterized in that: the system further comprises an equipment target detection module, wherein the equipment target detection module is used for carrying out target detection on equipment in each cabinet in a visual field by using a target detection technology under the scene of the information machine room when no complete cabinet exists in the first visual field of the AR glasses, and determining the type and the number of the equipment in each cabinet and the mass center position of each equipment panel in the cabinet panel.
3. The machine room AR positioning correction system of claim 2, characterized in that: the device further comprises a feature library matching module of the device, wherein the feature library matching module of the device is used for matching the type and the number of the devices in the cabinet determined by target detection, the mass center position of each device panel in the cabinet panel with the feature library of the cabinet to obtain the cabinet number of each cabinet for positioning calculation in the first view of the AR glasses, matching is carried out in the feature library of the cabinet according to the cabinet number for positioning calculation, and the coordinates of each cabinet for positioning calculation and the outline size of the corresponding device in the cabinet are obtained through correlation.
4. The machine room AR positioning correction system of claim 3, characterized in that: the AR glasses positioning module is used for determining the position of the AR glasses relative to each positioning calculation cabinet in the first visual angle image according to the coordinates of each positioning calculation cabinet and the outline size of the corresponding equipment in the cabinet, and determining the position of the AR glasses in the information machine room according to the coordinates of each positioning calculation cabinet and the position of the AR glasses relative to each positioning calculation cabinet in the first visual angle image.
5. The machine room AR positioning correction system of claim 1, characterized in that: the specific method for determining the position of the AR glasses in the information room according to the coordinate of a certain cabinet for positioning calculation and the corresponding cabinet outline size by the AR glasses positioning module, and the coordinate of the cabinet for positioning calculation and the position of the AR glasses in the first view image relative to the cabinet for positioning calculation comprises the following steps:
since the angle aOb is less than the angle AOB; angle aOc = AOC; the method for reducing the resistance of the steel comprises the following steps of (1) reducing the resistance of steel:
OA 2 +OB 2 -2OA*OB*cosθAB＝AB 2
OB 2 +OC 2 -2OB*OC*cosθBC＝BC 2
OA 2 +OC 2 -2OA*OC*cosθAC＝AC 2
thus;
Figure FDA0003827172490000021
Figure FDA0003827172490000022
Figure FDA0003827172490000023
the point O represents the position of the AR glasses front lens, the points A, B and C represent three vertexes of the cabinet outline for positioning calculation in the real world, the points a, B and C represent three vertexes of the cabinet outline for positioning calculation in the first visual angle image, and the points OA, OB and OC represent the distances between the three vertexes of the cabinet outline for positioning calculation in the real world and the AR glasses front lens respectively; AB. BC and AC represent the side length between adjacent fixed points of the outline of the cabinet for calculation in the real world; cos theta AB represents a cosine function of < AOB, cos theta AC represents the cosine function of < AOC, cos theta BC represents the cosine function of < BOC, S 1 ＝AB，S 2 ＝AC、S 3 ＝BC，L A ＝OA，L B ＝OB，L C ＝OC；
Obtaining the lengths of OA, OB and OC, determining the position of AR glasses in an information machine room by combining the coordinates of the machine room and the position of the AR glasses from the machine room, matching and associating through a feature library after target detection and character recognition to obtain the position coordinates of the machine room in a map of the machine room, knowing the distance between the AR glasses and each vertex of the outline of the machine room, and obtaining that the distance between one point and each vertex of the outline of the machine room is consistent with OA, OB and OC through calculation, wherein the point is the position of the AR glasses.
6. The machine room AR positioning correction system of claim 4, characterized in that: the specific method for determining the position of the AR glasses in the information computer room by the AR glasses positioning module according to the coordinate of a certain positioning calculation cabinet and the corresponding contour size of the equipment in the cabinet and according to the coordinate of the positioning calculation cabinet and the position of the AR glasses in the first visual angle image of the positioning calculation cabinet comprises the following steps:
due to the fact that 1 Ob 1 ＝∠A 1 OB 1 ；∠a 1 Oc 1 ＝∠A 1 OC 1 ；∠c 1 Ob 1 ＝∠C 1 OB 1 The cosine theorem is used as follows:
OA 1 2 +OB 1 2 -2OA 1 *OB 1 *cosθA 1 B 1 ＝A 1 B 1 2
OB 1 2 +OC 1 2 -2OB 1 *OC 1 *cosθB 1 C 1 ＝B 1 C 1 2
OA 1 2 +OC 1 2 -2OA 1 *OC 1 *cosθA 1 C 1 ＝A 1 C 1 2
thus;
S1 1 2 ＝A 1 B 1 2 ＝L1 A 2 +L1 B 2 -2L1 A L1 B cosθA 1 B 1
S1 2 2 ＝A 1 C 1 2 ＝L1 A 2 +L1 C 2 -2L1 A L1 C cosθA 1 C 1
S1 3 2 ＝B 1 C 1 2 ＝L1 B 2 +L1 C 2 -2L1 B L1 C cosθB 1 C 1
wherein, the point O represents the front lens position of the AR glasses, A 1 、B 1 、C 1 Points represent the three vertices of the contour of the equipment in the positioning calculation cabinet in the real world, a 1 、b 1 、c 1 The points represent three vertices, OA, of the contour of the equipment in the positioning computation cabinet in the first perspective image 1 、OB 1 、OC 1 Representing the distances between three vertexes of the outline of equipment in the cabinet for positioning calculation in the real world and the front lens of the AR glasses respectively; a. The 1 B 1 、B 1 C 1 、A 1 C 1 Representing the side length between adjacent fixed points of the outline of equipment in the cabinet for calculation in the real world; cos θ A 1 B 1 Represents < A 1 OB 1 Cosine function of (1), cos θ A 1 C 1 Expression of < A 1 OC 1 Cosine function of (cos θ B) 1 C 1 Expression of < B 1 OC 1 Cosine function of, S1 1 ＝A 1 B 1 ，S1 2 ＝A 1 C 1 、S1 3 ＝B 1 C 1 ，L1 A ＝OA 1 ，L1 B ＝OB 1 ，L1 C ＝OC 1 ；
Results OA 1 、OB 1 、OC 1 The length is combined with the coordinates of the cabinet and the positions of the AR glasses from the equipment in the cabinet to determine the positions of the AR glasses in the information machine room, the coordinates of the positions of the cabinet in the map of the machine room are obtained through target detection and character recognition and matching association of a feature library, the distances between the AR glasses and the vertexes of the equipment in the outline of the cabinet are known, and the calculation is carried outThe distance from a point to each vertex of the contour of the device in the cabinet and the OA can be obtained 1 、OB 1 、OC 1 And if the two points are consistent, the point is the AR glasses position.
7. The machine room AR positioning correction system of claim 1, characterized in that: the equipment cabinet characteristic library establishing module is used for establishing an equipment cabinet characteristic library of the information machine room according to the construction drawing and the equipment specification.
8. The machine room AR positioning correction system of claim 1, characterized in that: the specific method for the positioning correction module to correct the SLAM positioning in the information machine room according to the position of the AR glasses in the information machine room comprises the following steps: and if the position of the AR glasses positioned by the SLAM is not consistent with the first visual angle reverse-deducing position of the AR glasses, taking the reverse-deducing position as a standard.
9. A computer room AR positioning correction method is characterized by comprising the following steps:
step 1: establishing a cabinet feature library of an information machine room;
step 2: under the scene of an information machine room, when complete cabinets exist in the first visual field of the AR glasses, target detection is carried out on all cabinets in the first visual field of the AR glasses by using a target detection technology based on image identification, character identification is carried out on all the complete cabinets detected by the targets, and the identified cabinet number is the number of the cabinet for positioning calculation;
matching in the cabinet feature library according to the serial number of each positioning calculation cabinet, and correlating to obtain the position of each positioning calculation cabinet in the machine room map and the corresponding cabinet outline size;
determining the position of the AR glasses relative to each positioning calculation cabinet in the first visual angle image according to the position of each positioning calculation cabinet in the machine room map and the corresponding cabinet outline size, and determining the position of the AR glasses in the information machine room according to the coordinates of each positioning calculation cabinet and the position of the AR glasses relative to each positioning calculation cabinet in the first visual angle image;
in an information machine room scene, when no complete machine cabinet exists in a first visual field of AR glasses, performing target detection on equipment in each machine cabinet in the visual field by using a target detection technology, and determining the type and the number of the equipment in each machine cabinet and the mass center position of each equipment panel in a machine cabinet panel;
matching the category and the number of the equipment in the cabinet determined by target detection, the mass center position of each equipment panel in the cabinet panel and the cabinet feature library to obtain the cabinet number of each positioning calculation cabinet in the first view of the AR glasses, matching in the cabinet feature library according to each positioning calculation cabinet number, and correlating to obtain the coordinates of each positioning calculation cabinet and the corresponding equipment contour size in the cabinet;
determining the position of the AR glasses relative to each positioning calculation cabinet in the first visual angle image according to the coordinates of each positioning calculation cabinet and the corresponding equipment contour size in the cabinet, and determining the position of the AR glasses in the information machine room according to the coordinates of each positioning calculation cabinet and the position of the AR glasses relative to each positioning calculation cabinet in the first visual angle image;
and step 3: and correcting the SLAM positioning in the information machine room according to the position of the AR glasses in the information machine room.
10. A computer-readable storage medium storing a computer program, the computer program characterized in that: which when executed by a processor implements the steps of the method as claimed in claim 9.
CN202211064487.0A 2022-09-01 2022-09-01 Computer room AR positioning correction system and method and medium Pending CN115439768A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211064487.0A CN115439768A (en) 2022-09-01 2022-09-01 Computer room AR positioning correction system and method and medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211064487.0A CN115439768A (en) 2022-09-01 2022-09-01 Computer room AR positioning correction system and method and medium

Publications (1)

Publication Number Publication Date
CN115439768A true CN115439768A (en) 2022-12-06

Family

ID=84243865

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211064487.0A Pending CN115439768A (en) 2022-09-01 2022-09-01 Computer room AR positioning correction system and method and medium

Country Status (1)

Country Link
CN (1) CN115439768A (en)

Similar Documents

Publication Publication Date Title
Paya et al. A state-of-the-art review on mapping and localization of mobile robots using omnidirectional vision sensors
EP3650814B1 (en) Vision augmented navigation
CN102419178B (en) Mobile robot positioning system and method based on infrared road sign
Pintaric et al. Affordable infrared-optical pose-tracking for virtual and augmented reality
CN107103056B (en) Local identification-based binocular vision indoor positioning database establishing method and positioning method
CN104936283A (en) Indoor positioning method, server and system
CN106370160A (en) Robot indoor positioning system and method
US20220327737A1 (en) Determining position using computer vision, lidar, and trilateration
Chen et al. Vision-based autonomous vehicle guidance for indoor security patrolling by a SIFT-based vehicle-localization technique
CN111028358B (en) Indoor environment augmented reality display method and device and terminal equipment
CN104536009A (en) Laser infrared composite ground building recognition and navigation method
CN106295512A (en) Many correction line indoor vision data base construction method based on mark and indoor orientation method
Momeni-k et al. Height estimation from a single camera view
CN106352871A (en) Indoor visual positioning system and method based on artificial ceiling beacon
CN109282813B (en) Unmanned ship global obstacle identification method
CN114413958A (en) Monocular vision distance and speed measurement method of unmanned logistics vehicle
Avgeris et al. Single vision-based self-localization for autonomous robotic agents
CN112422653A (en) Scene information pushing method, system, storage medium and equipment based on location service
CN112884841B (en) Binocular vision positioning method based on semantic target
Kim et al. External vehicle positioning system using multiple fish-eye surveillance cameras for indoor parking lots
Cipolla et al. Image-based localization
CN115439768A (en) Computer room AR positioning correction system and method and medium
CN111964681B (en) Real-time positioning system of inspection robot
JP2016038790A (en) Image processor and image feature detection method thereof, program and device
Ruotsalainen et al. Monocular visual SLAM for tactical situational awareness

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