CN109186618B - Map construction method and device, computer equipment and storage medium - Google Patents
Map construction method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109186618B CN109186618B CN201811008409.2A CN201811008409A CN109186618B CN 109186618 B CN109186618 B CN 109186618B CN 201811008409 A CN201811008409 A CN 201811008409A CN 109186618 B CN109186618 B CN 109186618B
- Authority
- CN
- China
- Prior art keywords
- fixed point
- point
- preset
- image
- current
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
- G01C21/30—Map- or contour-matching
- G01C21/32—Structuring or formatting of map data
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Navigation (AREA)
- Instructional Devices (AREA)
Abstract
The invention discloses a map construction method, a map construction device, computer equipment and a storage medium, wherein the map construction method comprises the following steps: controlling the mobile shooting end to move to an original point in a fixed point coordinate system, and marking the original point as a current fixed point; acquiring an adjacent fixed point adjacent to the current fixed point according to a preset moving sequence; acquiring a current fixed point image according to the current fixed point and the adjacent fixed point, and splicing the current fixed point image and a historical fixed point image corresponding to the previous adjacent fixed point to form a historical fixed point image corresponding to the current fixed point; and controlling the moving shooting end according to a preset moving sequence and a preset step length, moving the shooting end from the current fixed point to any adjacent fixed point, and if the updated current fixed point is not the last preset point, repeatedly executing the step according to the preset moving sequence. The map construction method is beneficial to the server to position based on the fixed point navigation map, and improves the positioning accuracy and reliability.
Description
Technical Field
The present invention relates to the field of intelligent navigation, and in particular, to a map construction method and apparatus, a computer device, and a storage medium.
Background
In recent years, automobile intelligent technology is becoming widely used, which simplifies the driving operation of automobiles and improves the driving safety. For an obstacle avoidance vehicle running in an indoor unknown area, due to the shielding of an indoor environment or severe weather and the like, a GPS or Beidou navigation system has weak signals, and the obstacle avoidance vehicle is often in a state of no signal or weak signal and cannot provide effective positioning; therefore, the obstacle avoidance vehicle should have the capability of realizing real-time positioning in other ways, for example, the position of the obstacle avoidance vehicle can be positioned through an indoor map, and meanwhile, the surrounding environment information can be acquired, so that an important basis is provided for path planning. Therefore, how to create an accurate and reliable indoor map for indoor positioning becomes an urgent problem to be solved.
Disclosure of Invention
The embodiment of the invention provides a map construction method, a map construction device, computer equipment and a storage medium, and aims to solve the problem of establishing an accurate and reliable indoor map for indoor positioning.
A map construction method, comprising:
acquiring an original indoor map, wherein the original indoor map comprises an origin configured in a fixed point coordinate system and at least one preset point adjacent to the origin;
controlling the mobile shooting end to move to an original point in a fixed point coordinate system, and marking the original point as a current fixed point;
acquiring an adjacent fixed point adjacent to the current fixed point in a horizontal advancing direction or a vertical advancing direction according to a preset moving sequence;
acquiring a current fixed point image corresponding to the current fixed point according to the current fixed point and an adjacent fixed point, and splicing the current fixed point image and a historical fixed point image corresponding to a last adjacent fixed point by adopting a feature extraction algorithm to form a historical fixed point image corresponding to the current fixed point;
controlling a mobile shooting end according to a preset moving sequence and a preset step length, moving the mobile shooting end from a current fixed point to any adjacent fixed point, taking the adjacent fixed point moved by the mobile shooting end as an updated current fixed point, judging whether the updated current fixed point is the last preset point in the original indoor map, and taking a historical fixed point image as a fixed point navigation map if the updated current fixed point is the last preset point in the original indoor map; if the updated current fixed point is not the last preset point in the original indoor map, the step of obtaining an adjacent fixed point adjacent to the current fixed point in the horizontal or vertical forward direction according to the preset moving sequence is repeatedly performed until the updated current fixed point is the last preset point in the original indoor map.
A map building apparatus comprising:
the indoor map acquisition module is used for acquiring an original indoor map, and the original indoor map comprises an origin configured in a fixed point coordinate system and at least one preset point adjacent to the origin;
the current fixed point marking module is used for controlling the mobile shooting end to move to an original point in a fixed point coordinate system and marking the original point as a current fixed point;
the acquisition adjacent fixed point module is used for acquiring an adjacent fixed point adjacent to the current fixed point in the horizontal advancing direction or the vertical advancing direction according to a preset moving sequence;
the fixed point image acquisition module is used for acquiring a current fixed point image corresponding to a current fixed point according to the current fixed point and an adjacent fixed point, and splicing the current fixed point image and a historical fixed point image corresponding to a last adjacent fixed point by adopting a feature extraction algorithm to form a historical fixed point image corresponding to the current fixed point;
the navigation map acquisition module is used for controlling the moving of the shooting end according to a preset moving sequence and a preset step length, moving the shooting end from the current fixed point to any adjacent fixed point, taking the adjacent fixed point as an updated current fixed point, judging whether the updated current fixed point is the last preset point in the original indoor map or not, and if the updated current fixed point is the last preset point, taking the historical fixed point image as a fixed point navigation map; if the current fixed point is not the last preset point, the step of acquiring the adjacent fixed point adjacent to the current fixed point in the horizontal advancing direction or the vertical advancing direction according to the preset moving sequence is repeatedly executed.
A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the steps of the above-described mapping method being performed when the computer program is executed by the processor.
A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned map construction method.
According to the map construction method, the map construction device, the computer equipment and the storage medium, the server controls the mobile shooting end to collect the current fixed point image corresponding to the current fixed point at each preset point passing through the route according to the preset moving sequence, the current fixed point image corresponding to the current fixed point image is formed after the mobile shooting end moves to the last preset point on the route, the final fixed point navigation map is formed after the mobile shooting end collects and splices the last preset point, the map can be used as the fixed point navigation map for indoor route navigation, the map construction implementation process is favorable for each subsequent mobile shooting end to move to the preset point by collecting the corresponding current fixed point image at each preset point, the current position in the fixed point navigation map can be obtained by comparing the current fixed point image with the image shot at the current position, the server is favorable for planning the optimal navigation route based on the current position, and the accuracy and reliability of positioning through the fixed point navigation map are improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive labor.
FIG. 1 is a schematic diagram of an application environment of a map construction method according to an embodiment of the present invention;
FIG. 2 is a flow chart of a mapping method in an embodiment of the invention;
FIG. 3 is a diagram of a fixed point navigation map according to an embodiment of the present invention;
FIG. 4 is a diagram of a current pointing image in accordance with one embodiment of the present invention;
FIG. 5 is another flow chart of a mapping method in an embodiment of the invention;
FIG. 6 is a schematic diagram of a pointing coordinate system in accordance with an embodiment of the present invention;
FIG. 7 is another flow chart of a mapping method in an embodiment of the invention;
FIG. 8 is another flow chart of a mapping method in accordance with an embodiment of the invention;
FIG. 9 is a schematic diagram of peripheral pixels around a candidate point according to an embodiment of the present invention;
FIG. 10 is a schematic diagram of four point pairs within a circle centered on a feature point according to an embodiment of the present invention;
FIG. 11 is another flow chart of a mapping method in accordance with an embodiment of the invention;
FIG. 12 is another flow chart of a mapping method in accordance with an embodiment of the invention;
FIG. 13 is a schematic diagram of a mapping apparatus in accordance with an embodiment of the invention;
FIG. 14 is a schematic diagram of a computer device in an embodiment of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without inventive step based on the embodiments of the present invention, are within the scope of protection of the present invention.
The map construction method provided by the embodiment of the invention can be applied to the application environment shown in fig. 1, and the map construction method is applied to a map construction system, wherein the map construction system comprises a client and a server, and the client communicates with a detection server through a network. The client is also called a user side, and refers to a program corresponding to the server and providing local services for the client. The client can be installed on computer equipment such as but not limited to various personal computers, notebook computers, smart phones, tablet computers and portable wearable equipment. The detection server may be implemented by an independent server or a server cluster composed of a plurality of servers.
In an embodiment, as shown in fig. 2, a map building method is provided, which is described by taking the server in fig. 1 as an example, and includes the following steps:
s10, obtaining an original indoor map, wherein the original indoor map comprises an origin point configured in a fixed point coordinate system and at least one preset point adjacent to the origin point.
The original indoor map is generated according to the shape of the indoor ground, takes any one of four indoor vertexes as an origin of the fixed point coordinate system, and comprises at least two grid images of preset points on the fixed point coordinate system. It will be appreciated that the original indoor map only shows the fixed point coordinate system and the at least two pre-set points on the coordinate system on the image, excluding a true image of the indoor floor. The purpose of this embodiment is to add a corresponding real ground image to each preset point on the original indoor map to form a fixed-point navigation map, as shown in fig. 3, which is beneficial for the subsequent server to locate the fixed-point coordinates of the ground picture in the fixed-point coordinate system based on the ground pictures taken at different preset points, so as to achieve the purpose of location.
The fixed point coordinate system is a coordinate system which is used for designating any point of the edge of the indoor floor as an origin and respectively using two indoor floor sidelines intersected with the origin as a horizontal axis and a vertical axis.
The predetermined point is each intersection of the fixed point coordinate system and the mesh image formed by the original indoor map. It will be appreciated that the fixed point coordinates relative to the origin are (0, 0), and that each of the predetermined points also corresponds to the presence of a fixed point coordinate on the fixed point coordinate system, in terms of a step between each two of the predetermined points.
In step S10, the server may obtain an origin and at least two preset points configured in the fixed point coordinate system by obtaining the original indoor map, so as to facilitate the subsequent movement of the client to the position of the origin, and determine the movable direction of the mobile shooting end according to the at least two preset points.
And S20, controlling the mobile shooting end to move to an original point in the fixed point coordinate system, and marking the original point as the current fixed point.
The current fixed point is the current position of the mobile shooting end, and in this embodiment, the current position of the mobile shooting end is the origin.
In step S20, the purpose of moving the mobile terminal to the origin point by the server is to perform image acquisition on the indoor ground from a vertex angle of the indoor ground in a preset direction, which is beneficial to forming the integrity of the fixed-point navigation map and avoiding the occurrence of the situation of repeated acquisition of part of lines when image acquisition is performed from the middle position.
And S30, acquiring an adjacent fixed point adjacent to the current fixed point in the horizontal advancing direction or the vertical advancing direction according to a preset moving sequence.
The preset moving sequence can be S-shaped or W-shaped, so that when the moving shooting end moves away from the origin in the horizontal advancing direction to the indoor side line (i.e. the last preset point of the horizontal advancing mode), the moving shooting end can advance by one step length in the vertical advancing direction, then the horizontal advancing direction is reversely set and then the moving shooting end approaches the origin, and so on, until the moving shooting end starts from the origin and then moves to the last preset point of the original indoor map, the moving can be stopped, wherein the last preset point of the original indoor map is a preset point without adjacent points in the vertical advancing direction.
In step S30, the server controls the mobile terminal to move forward to an adjacent fixed point along the horizontal forward direction, and when there is no adjacent fixed point along the horizontal forward direction, controls the mobile terminal to move forward to an adjacent fixed point along the vertical forward direction. When the mobile shooting end moves forward to an adjacent fixed point along the vertical direction, the server reversely sets the current horizontal forward direction, so that the adjacent fixed point of the mobile shooting end along the horizontal forward direction can be obtained, and at the moment, the mobile shooting end can move forward to the adjacent fixed point along the horizontal forward direction. By analogy, when the adjacent fixed point does not exist when the moving shooting end moves along the vertical direction, the moving shooting end can stop moving. In this embodiment, the server controls the mobile camera to control the mobile camera to traverse each preset point along a preset moving sequence and a preset advancing direction (including a horizontal advancing direction and a vertical advancing direction), and image acquisition can be performed at each preset point to ensure the integrity of the fixed point navigation map.
S40, obtaining a current fixed point image corresponding to the current fixed point according to the current fixed point and the adjacent fixed points, and splicing the current fixed point image and a historical fixed point image corresponding to the last adjacent fixed point by adopting a feature extraction algorithm to form a historical fixed point image corresponding to the current fixed point.
The current fixed point image is a ground image including adjacent fixed points, which is acquired by the current fixed point in each forward direction (including a horizontal forward direction and a vertical forward direction), and is formed by stitching, as shown in fig. 4.
The historical fixed point image is a ground image formed by storing a current fixed point image which comprises the preset point and all preset points before the preset point, wherein each preset point corresponds to one preset point in the map building process. It is understood that the historical pointing image corresponding to the last preset point of the original indoor map is the pointing navigation map formed by the current pointing image including all the preset points.
In step S40, the server may extract the current feature point of the current fixed point image and the historical feature point corresponding to the historical fixed point image corresponding to the previous adjacent fixed point through a feature extraction algorithm, and then superimpose and splice the center of the current feature point and the center of the historical feature point, so as to form the historical fixed point image corresponding to the current fixed point. In this embodiment, the server may move at the mobile shooting end according to a preset moving sequence, so that each preset point in the original indoor map forms a corresponding historical fixed point image, and a fixed point navigation map corresponding to the whole indoor area may be formed through one traversal, which is convenient and fast.
S50, controlling a mobile shooting end according to a preset moving sequence and a preset step length, moving the mobile shooting end from a current fixed point to any adjacent fixed point, taking the adjacent fixed point to which the mobile shooting end moves as an updated current fixed point, judging whether the updated current fixed point is the last preset point in the original indoor map, and taking a historical fixed point image as a fixed point navigation map if the updated current fixed point is the last preset point in the original indoor map; if the updated current fixed point is not the last preset point in the original indoor map, the step of obtaining an adjacent fixed point adjacent to the current fixed point in the horizontal or vertical forward direction according to the preset moving sequence is repeatedly performed until the updated current fixed point is the last preset point in the original indoor map.
In this embodiment, the preset step length is a distance specified in the fixed point coordinate system between every two preset points, and the preset step length can be set to 1 meter for calculation.
The fixed point navigation map is a real shooting ground image comprising each preset point in a fixed point coordinate system, and is used for carrying out optimal route planning and indoor position location.
In step S50, the server controls the mobile terminal to move from the current fixed point to an adjacent fixed point in the horizontal forward direction according to a preset movement sequence (when there is no adjacent fixed point in the horizontal forward direction, the mobile terminal moves to the adjacent fixed point in the vertical forward direction), and updates the adjacent fixed point to the current fixed point. The purpose of the update is to determine whether the current setpoint of the update is the last preset point. Because the last preset point does not have adjacent fixed points along the horizontal advancing direction and the vertical advancing direction, namely when the preset point where the mobile shooting end is located cannot advance along the horizontal advancing direction and the vertical advancing direction, the current fixed point where the mobile shooting end is located can be judged to be the last preset point, and the historical fixed point image corresponding to the current fixed point can be used as a fixed point navigation image for optimal route planning and indoor position positioning. In this embodiment, the server repeatedly determines whether the mobile shooting end moves to the last preset point until the mobile shooting end moves to the last preset point, and then the historical fixed-point image corresponding to the last preset point can be used as the fixed-point navigation image, which is simple and fast.
In the map construction method provided in steps S10 to S50, the server may control the mobile shooting end to collect a current fixed point image corresponding to a current fixed point at each preset point passing through the route according to a preset moving sequence, and form a historical fixed point image corresponding to the current fixed point image after being spliced with the historical fixed point image until the mobile shooting end moves to a last preset point on the route to collect and splice a final fixed point navigation map, which may be used as a fixed point navigation map for indoor route navigation. The map construction implementation process is beneficial to acquiring the corresponding current fixed point image on each preset point, comparing the current fixed point image with the image shot at the current position to obtain the current position in the current fixed point navigation map when the subsequent mobile shooting end moves to the preset point, and is beneficial to planning the optimal navigation route by the server based on the current position, thereby improving the accuracy and reliability of positioning through the fixed point navigation map.
In one embodiment, as shown in fig. 5, in step S10, an original indoor map is obtained, where the original indoor map includes an origin configured in a fixed point coordinate system and at least one preset point adjacent to the origin, and the method specifically includes the following steps:
s11, obtaining an original indoor map configured with a fixed point coordinate system, and obtaining an origin based on the fixed point coordinate system.
In step S11, as shown in fig. 6, the server acquires, from the fixed point coordinate system, a side point of the original indoor map as an origin, and the origin coordinates corresponding to the origin are (0, 0). In this embodiment, the server may also determine the fixed point coordinates of each of the predetermined set points in the room by obtaining the origin in the fixed point coordinate system configured on the original indoor map, so as to facilitate the subsequent acquisition of the current fixed point image based on the position of each of the predetermined set points.
S12, respectively acquiring at least two vertical lines parallel to the longitudinal axis and at least two horizontal lines parallel to the transverse axis along the transverse axis direction or the longitudinal axis direction of the origin at intervals of a preset step length.
In step S12, the server sets a preset step size and generates a plurality of vertical lines and horizontal lines along the origin according to the length and width of the original indoor map, so as to obtain intersections of all the vertical lines and horizontal lines, that is, obtain all the preset points.
And S13, setting the intersection point of each vertical line and each horizontal line as a preset point and storing the preset point on the original indoor map.
In step S13, the server sets the intersection of each vertical line and each horizontal line as a preset point, and since the preset step is known, the fixed point coordinate of each preset point can also be calculated by the origin coordinate and the preset step. In this embodiment, the server may store each preset point and the fixed point coordinate corresponding to the preset point on the original indoor map for subsequent movement based on the original indoor map to draw the fixed point navigation map.
In steps S11 to S13, the server determines the origin of the original indoor map, that is, the fixed point coordinates of each preset point in the room, so as to facilitate the subsequent acquisition of the current fixed point image based on the position of each preset point. The server may store each preset point and the fixed point coordinate corresponding to the preset point on the original indoor map for subsequent movement based on the original indoor map to draw the fixed point navigation map.
In an embodiment, as shown in fig. 7, in the step S30, that is, the shooting end is controlled to move according to the preset moving sequence and the preset step length, and move from the current fixed point to an adjacent fixed point, the method specifically includes the following steps:
and S31, if the adjacent fixed point exists in the horizontal forward direction of the current fixed point, controlling the mobile shooting end to move for a preset step length along the horizontal forward direction of the current fixed point so as to reach the adjacent fixed point.
In this embodiment, if the shape of the indoor floor surface is a rectangle, the original indoor map formed by the indoor floor surface is also a rectangle, and if any vertex in the room is taken as the origin in the fixed-point coordinate system, the original indoor map is set to be a horizontal proceeding direction and a vertical proceeding direction along the two directions of the length and the width of the indoor floor surface, respectively. In step S31, the server defaults to move the shooting end forward one preset step length at a time along the horizontal forward direction. In this embodiment, the server sets the horizontal forward direction with more preset points as the default moving direction, which can reduce the time for determining the forward direction and is beneficial to quickly generating the fixed-point navigation map.
And S32, if the current fixed point does not have an adjacent fixed point along the horizontal advancing direction, controlling the mobile shooting end to move by a preset step length along the vertical advancing direction of the current fixed point so as to reach the adjacent fixed point, and reversely setting the horizontal advancing direction of the current fixed point so as to enable the mobile shooting end to have the adjacent fixed point along the horizontal advancing direction.
In step S32, since the moving direction of the moving camera is determined, the position of each preset point where there is no adjacent fixed point in the horizontal direction during the moving process of the moving camera can also be determined. The server can obtain fixed point coordinates of preset points without adjacent fixed points along the horizontal advancing direction, and when the mobile shooting end moves to the fixed point coordinates, the mobile shooting end is controlled to move for a preset step length along the vertical advancing direction, so that the mobile shooting end can be moved quickly.
In steps S31 to S32, the server sets the horizontal forward direction with more preset points as the default moving direction, which can reduce the time for determining the forward direction and the time for changing the moving direction, and is beneficial to quickly generating the fixed-point navigation map. The server can obtain fixed point coordinates of preset points without adjacent fixed points in the horizontal advancing direction, and when the mobile shooting end moves to the fixed point coordinates, the mobile shooting end is controlled to move for a preset step length in the vertical advancing direction, so that the mobile shooting end can be moved to change the moving direction quickly.
In an embodiment, as shown in fig. 8, in step S40, the current fixed point image and the historical fixed point image corresponding to the previous adjacent fixed point are stitched by using a feature extraction algorithm to form the historical fixed point image corresponding to the current fixed point, which specifically includes the following steps:
and S41, respectively extracting the characteristics of the current fixed point image and the historical fixed point image to obtain the characteristic points of the current image and the historical image.
The feature extraction algorithm (ordered FAST and rotaed BRIEF, hereinafter abbreviated as ORB algorithm) used in this embodiment is an algorithm for extracting and describing feature points quickly. The image feature points can be understood as more prominent points in the image, such as contour points, bright points in darker areas, dark points in lighter areas, and the like. The ORB algorithm is divided into two parts, including feature point extraction and feature point matching.
Specifically, the implementation process of extracting the features of the current fixed point image by using the ORB algorithm to obtain the feature points of the current image is as follows:
1. extracting feature points in the current fixed point image: more remarkable points on the current fixed point image, such as contour points, bright points in a darker area, dark points in a lighter area and the like are set as candidate points, pixel values on a circle with a designated selection radius around the candidate points are detected, and if gray values of enough pixel points in the field around the candidate points and the candidate points are different enough, the candidate points are considered as a feature point.
In order to obtain faster results, the following detection acceleration method can also be used: and 4 points around the test candidate point every 90 degrees are required to have at least 3 gray value differences with the candidate point which are large enough, otherwise, other points are not calculated, and the candidate point is directly considered not to be the characteristic point. The radius of the circle around the candidate point is an important parameter, and for simplicity and efficiency, the detection radius can be specified to be 3, and there are 16 peripheral pixels to be compared, as shown in fig. 9. To improve the efficiency of comparison, FAST-N, which is a comparison using only N neighboring pixels, is generally recommended, for FAST-9.
The process of extracting the feature points of the historical fixed point image is consistent with the process of extracting the feature points of the current fixed point image, and the process is not repeated herein.
In step S41, the server may use an ORB algorithm to respectively extract the historical image feature points of the historical fixed point image and the current image feature points of the current fixed point image, so as to facilitate subsequent feature matching based on the two image feature points.
And S42, performing feature matching on the current image feature points and the historical image feature points to obtain an image matching result.
The image matching result is the feature matching degree of the feature point of the current fixed point image and the feature point of the historical fixed point image, and is used for subsequently judging whether the feature point of the current fixed point image and the feature point of the historical fixed point image are the same feature point or not based on the feature matching degree.
Specifically, the implementation process of performing feature matching on the current image feature point and the historical image feature point is as follows:
1. calculating and storing feature point descriptors of current image feature points: after obtaining the current image Feature point of the current fixed-point image, the attribute of the Feature point needs to be described in some way, and the attribute output of the Feature point is the descriptor (Feature descriptor s) of the Feature point. The attribute process of the ORB algorithm for acquiring the image feature points comprises the following steps:
(1) And D is taken as the radius to make a circle O by taking the characteristic point P as the center of the circle.
(2) N point pairs are selected within the circle O. For convenience of description, N =4 may be selected in this embodiment, and as shown in fig. 10, N may be 512 in practical application.
The currently selected 4 point pairs are respectively marked as shown in the figure:
P 1 (A,B)、P 2 (A,B)、P 3 (A, B) and P 4 (A,B)。
(3) Defining T operations
Wherein, I A Representing the gray scale of point A, I B Representing the gray scale of point B.
(4) And respectively carrying out T operation on the selected point pairs, and combining the obtained results. The descriptor is illustrated with the above four points continuing as an example:
T(P 1 (A,B))＝1
T(P 2 (A,B))＝0
T(P 3 (A,B))＝1
T(P 4 (A,B))＝1
the final descriptor for the feature point P is 1011.
The process of calculating the feature point descriptors of the historical fixed point images is consistent with the process of calculating the feature point descriptors of the current fixed point images, and details are not repeated here.
2. And comparing the feature point descriptors of the current fixed point image with the feature point descriptors of the historical fixed point images one by one to obtain the feature matching degree. The process of comparing the feature point descriptors of the current fixed point image with the feature point descriptors of the historical fixed point images is illustrated as follows:
feature point descriptor a of the current fixed point image: 10101011
Feature point descriptor B of history fixed point image: 10101010
In this example, A and B differ only in the last digit, and the feature matching degree is 87.5%. And carrying out exclusive OR operation on the A and the B to calculate the feature matching degree of the A and the B. The exclusive-or operation can be completed by hardware, so that the efficiency is high, and the matching speed is accelerated.
3. And judging whether the feature matching degree of the feature point descriptors of the current fixed point image and the feature point descriptors of the historical fixed point image reaches a matching threshold value or not so as to obtain an image matching result.
Specifically, if the feature matching degree of the feature point descriptor of the current fixed point image and the feature point descriptor of the historical fixed point image reaches the matching threshold, the feature point descriptors of the current fixed point image and the historical fixed point image are determined to be the same feature point. In this embodiment, the matching threshold may be set to 85%, the feature matching degree of a and B in step 2 is 87.5%, and the matching threshold is exceeded, that is, it may be determined that the current image feature point of the current fixed point image and the historical image feature point of the historical fixed point image are derived from the same feature point. Correspondingly, if the feature matching degrees of the feature point descriptors of the current fixed point image and the feature point descriptors of the historical fixed point image do not reach the matching threshold value, the feature point descriptors of the current fixed point image and the feature point descriptors of the historical fixed point image are determined not to be the same feature point.
In step S41, the server may use ORB algorithm and obtain the feature matching degree of the feature point descriptor of each current fixed point image with respect to the feature point descriptor of the current fixed point image by using hardware, so as to provide a technical basis for preparing a historical fixed point image corresponding to the current fixed point image and the previous adjacent fixed point image.
S43, based on the image matching result, the current fixed point image and the historical fixed point image corresponding to the previous adjacent fixed point are spliced to form the historical fixed point image corresponding to the current fixed point.
Specifically, in step S42, it can be confirmed that the current image feature point of the current fixed point image and the historical image feature point of the historical fixed point image are from the same source feature point, so that after the same source feature point of the current fixed point image and the historical fixed point image are overlapped, the two images are spliced by keeping the directions of the current fixed point image and the historical fixed point image, and the historical fixed point image corresponding to the current fixed point can be formed after the splicing, as shown in fig. 4.
In steps S41 to S43, the server can directly obtain the same source feature point in the two images by using the ORB algorithm without using an image processing tool, and the two images can be overlapped and spliced based on the same source feature point to form a historical fixed point image corresponding to the current fixed point, which is simple and fast.
In one embodiment, as shown in fig. 11, after step S50, that is, after the step of using the historical fixed point image as the fixed point navigation map, the map construction method further includes the steps of:
s501, a map updating request is obtained, wherein the map updating request comprises an updating fixed point coordinate, at least one updating fixed point image corresponding to the updating fixed point coordinate and an image direction identifier.
The map updating request is a request received by the server for updating at least one local fixed point image corresponding to the designated preset point on the fixed point navigation map. It can be understood that, in practical applications, the ground image may have an updated state, and if the ground is updated but the fixed point navigation map is not updated correspondingly in time, there is a situation that it is difficult to perform position location in the fixed point navigation map subsequently. Therefore, when the indoor ground is updated, the fixed-point navigation map needs to be synchronized in time, that is, the map update request is sent to the server in time.
The updated fixed point image is the current fixed point image which is re-shot by the mobile shooting end at the preset point where the ground update occurs.
Whether the image orientation indicator indicates that the position of the updated indoor floor between the two preset points is in a horizontal or vertical progression direction facilitates the server to update the corresponding current pointing image based on the image orientation indicator.
In step S501, the server obtains the information in the request by receiving the map update request, and can correspondingly update the image corresponding to the predetermined point in the fixed-point navigation map based on the information in the request, so as to implement the small-range update without re-creating the fixed-point navigation map.
S502, based on the map updating request, updating the current fixed point image corresponding to the updated fixed point coordinate and in the same direction as the image direction identification into an updated fixed point image in the fixed point navigation map.
In step S502, the server may accurately confirm the current fixed point image specifically needing to be updated based on the image direction identifier and the updated fixed point coordinates. Because each preset point corresponds to the current fixed point images in two directions, the updated image can be accurately positioned through the image direction identification, and the updating speed of the fixed point navigation map is accelerated.
In steps S501 to S502, the server may obtain the updated fixed-point coordinates, at least one updated fixed-point image corresponding to the updated fixed-point coordinates, and the image direction identifier according to the map update request, and quickly locate the current fixed-point image that needs to be updated, so as to update the current fixed-point image to the updated fixed-point image, thereby implementing quick fixed-point update, and the operation is simple and quick.
In one embodiment, as shown in fig. 12, after step S50, that is, after the step of using the history fixed point image as the fixed point navigation map, the map construction method further includes the steps of:
s503, obtaining a route specification request, wherein the route specification request comprises an avoidance coordinate or two adjacent avoidance fixed points.
Wherein the route specification request is a request received by the server to avoid a set point on the fixed point navigation map. In practical applications, objects (hereinafter referred to as obstacles) blocking traffic may exist on the preset points or between routes formed by the preset points, and not every preset point may be used as a trafficable fixed point. Therefore, the server needs to mark an infeasible route on the fixed point navigation map in advance according to actual conditions, and the follow-up server is facilitated to carry out optimal path navigation on the mobile shooting end based on the marked fixed point navigation route. The avoidance coordinate is a fixed point that is not feasible among all the preset set points, and each fixed point of two adjacent avoidance set points is not necessarily infeasible, but a step route formed between the two adjacent avoidance set points is infeasible.
In step S503, the server updates the fixed point navigation map in time by receiving the route specification request, which is beneficial for the subsequent server to perform optimal path navigation for the mobile shooting end based on the updated fixed point navigation route.
S504, setting each step-size route connected with the avoidance coordinates as an avoidance route, or setting a step-size route formed between two adjacent avoidance fixed points as an avoidance route.
Wherein the step route is a route connecting between two adjacent preset points.
Specifically, the avoided route is an infeasible route marked in the fixed point navigation map, and includes two cases: when there is an obstacle at the preset point, it is not feasible to route every step connected to the preset point. When an obstacle exists between two adjacent avoidance points, it is possible that the two adjacent avoidance points are feasible, but a step-size route formed between the two adjacent avoidance points is not feasible, and at this time, the infeasible route is also set as an infeasible route.
In step S504, the server separately discusses two situations in which an obstacle may occur in route navigation in an actual situation, so that the practicability of the embodiment is wider.
And S505, updating the fixed point navigation map based on the evaded route.
In step S505, the server identifies the avoided routes obtained in step S504 in the fixed point navigation map, so as to avoid the avoided routes when subsequently performing route navigation based on the identification, so that the planned optimal navigation route is more flexible and accurate.
In steps S503 to S505, the server updates the fixed point navigation map in time according to the received route specification request, which is beneficial for the subsequent server to perform optimal path navigation planning for the mobile shooting end based on the updated fixed point navigation route. The server respectively discusses two situations that obstacles may appear in route navigation in actual situations, so that the practicability of the embodiment is wider. The server identifies the evaded routes in the fixed-point navigation map, and is used for avoiding the evaded routes when route navigation is carried out on the basis of the identification subsequently, so that the planned optimal navigation route is more flexible and accurate.
In the map construction method provided by this embodiment, the server may control the mobile shooting end to collect a current fixed point image corresponding to a current fixed point at each preset point passing through the route according to a preset moving sequence indoors, and form a historical fixed point image corresponding to the current fixed point image after being spliced with the historical fixed point image until the mobile shooting end moves to a last preset point on the route to collect and splice a final fixed point navigation map, which may be used as a fixed point navigation map for indoor route navigation. The map construction implementation process is beneficial to acquiring the corresponding current fixed point image on each preset point, comparing the current fixed point image with the image shot at the current position to obtain the current position in the current fixed point navigation map when the subsequent mobile shooting end moves to the preset point, and is beneficial to planning the optimal navigation route by the server based on the current position, thereby improving the accuracy and reliability of positioning through the fixed point navigation map.
Further, the server may determine the origin of the original indoor map, i.e. may determine the fixed point coordinates of each preset point in the room, so as to facilitate the subsequent acquisition of the current fixed point image based on the location of each preset point. The server may store each preset point and the fixed point coordinate corresponding to the preset point on the original indoor map for subsequent movement based on the original indoor map to draw the fixed point navigation map. The server sets the horizontal advancing direction with more preset points as the default moving direction, so that the time for judging the advancing direction can be reduced, the time for changing the moving direction can be reduced, and the fixed point navigation map can be generated quickly. The server can obtain fixed point coordinates of preset points without adjacent fixed points in the horizontal advancing direction, and when the mobile shooting end moves to the fixed point coordinates, the mobile shooting end is controlled to move for a preset step length in the vertical advancing direction, so that the mobile shooting end can be moved to change the moving direction quickly. The server can directly acquire the same source characteristic points in the two images by adopting an ORB algorithm without borrowing an image processing tool, and the two images can be overlapped and spliced based on the same source characteristic points to form a historical fixed point image corresponding to the current fixed point, so that the method is simple and rapid. The server can obtain the updated fixed point coordinate according to the map updating request, and quickly position the current fixed point image needing to be updated to the updated fixed point image by at least one updated fixed point image and the image direction identifier corresponding to the updated fixed point coordinate, so that the method is simple and quick. The server updates the fixed point navigation map in time by receiving the route specification request, so that the subsequent server can conveniently perform optimal path navigation on the mobile shooting end based on the updated fixed point navigation route. The server respectively discusses two situations that obstacles may appear in route navigation in actual situations, so that the practicability of the embodiment is wider. The server identifies the avoided routes in the fixed-point navigation map, so that the avoided routes are avoided when route navigation is performed subsequently based on the identification, and the planned optimal navigation route is more flexible and accurate.
In an embodiment, a map construction apparatus is provided, and the map construction apparatus corresponds to the map construction method in the above embodiment one to one. As shown in fig. 13, the map construction apparatus includes an indoor map acquisition module 10, a current pointing marking module 20, an adjacent pointing acquisition module 30, a pointing image acquisition module 40, and a navigation map acquisition module 50. The functional modules are explained in detail as follows:
an acquire indoor map module 10 for acquiring an original indoor map, the original indoor map including an origin point configured in a fixed point coordinate system and at least one preset point adjacent to the origin point.
And a mark current fixed point module 20, configured to control the mobile shooting end to move to an origin in the fixed point coordinate system, and mark the origin as a current fixed point.
The adjacent fixed point acquiring module 30 is configured to acquire an adjacent fixed point adjacent to the current fixed point in the horizontal forward direction or the vertical forward direction according to a preset moving sequence.
And the fixed point image obtaining module 40 is configured to obtain a current fixed point image corresponding to the current fixed point according to the current fixed point and an adjacent fixed point, and splice the current fixed point image and a historical fixed point image corresponding to a previous adjacent fixed point by using a feature extraction algorithm to form a historical fixed point image corresponding to the current fixed point.
A navigation map obtaining module 50, configured to control the moving camera according to a preset moving sequence and a preset step length, move the camera from a current fixed point to any adjacent fixed point, use the adjacent fixed point to which the moving camera moves as an updated current fixed point, determine whether the updated current fixed point is a last preset point in the original indoor map, and if the updated current fixed point is the last preset point in the original indoor map, use the historical fixed point image as a fixed point navigation map; if the updated current fixed point is not the last preset point in the original indoor map, the step of obtaining an adjacent fixed point adjacent to the current fixed point in the horizontal or vertical forward direction according to the preset moving sequence is repeatedly performed until the updated current fixed point is the last preset point in the original indoor map.
Preferably, the module for acquiring indoor map 10 includes an unit for acquiring indoor map 11, a unit for acquiring parallel lines 12 and a unit for setting preset points 13.
And an indoor map obtaining unit 11, configured to obtain an original indoor map configured with a fixed point coordinate system, and obtain an origin based on the fixed point coordinate system.
The parallel line acquiring unit 12 is configured to acquire at least two vertical lines parallel to the longitudinal axis and at least two horizontal lines parallel to the lateral axis, respectively, at intervals of a preset step length along the lateral axis direction or the longitudinal axis direction of the origin.
A preset point unit 13 is provided for setting the intersection of each vertical line and each horizontal line as a preset point and storing it on the original indoor map.
Preferably, acquiring the adjacent pointing module 30 includes reaching the adjacent pointing unit 31 and moving the unit 32 in a vertical direction.
And an adjacent fixed point reaching unit 31, configured to control the moving shooting end to move by a preset step length along the horizontal forward direction of the current fixed point to reach the adjacent fixed point if the current fixed point has an adjacent fixed point along the horizontal forward direction.
And the moving unit 32 in the vertical direction is used for controlling the moving shooting end to move by a preset step length along the vertical advancing direction of the current fixed point to reach the adjacent fixed point if the current fixed point does not have the adjacent fixed point along the horizontal advancing direction, and reversely setting the horizontal advancing direction of the current fixed point to enable the moving shooting end to have the adjacent fixed point along the horizontal advancing direction.
Preferably, the acquisition pointing images module 40 includes an acquisition image feature unit 41, an acquisition matching result unit 42, and a form pointing maps unit 43.
An image feature acquiring unit 41, configured to perform feature extraction on the current fixed point image and the historical fixed point image respectively, and acquire feature points of the current image and feature points of the historical image.
And an obtaining matching result unit 42, configured to perform feature matching on the current image feature point and the historical image feature point, and obtain an image matching result.
And a fixed point map forming unit 43, configured to splice the current fixed point image and the historical fixed point image corresponding to the previous adjacent fixed point based on the image matching result, so as to form a historical fixed point image corresponding to the current fixed point.
Preferably, the map building apparatus further comprises a get update request module 501 and an update fix image module 502.
An update request obtaining module 501 is configured to obtain a map update request, where the map update request includes an update fixed point coordinate, at least one update fixed point image corresponding to the update fixed point coordinate, and an image direction identifier.
And an update fixed point image module 502, configured to update, in the fixed point navigation map, a current fixed point image corresponding to the update fixed point coordinate and in the same direction as the image direction identifier to an update fixed point image based on the map update request.
Preferably, the map building device further comprises a get specification request module 503, a get avoidance route module 504 and an update navigation map module 505.
A get specification request module 503, configured to get a route specification request, where the route specification request includes one avoidance coordinate or two adjacent avoidance fixes.
An obtaining avoidance route module 504, configured to set each step route connected to the avoidance coordinates as an avoidance route, or set a step route formed between two adjacent avoidance fixed points as an avoidance route.
And the navigation map updating module 505 is configured to update the fixed point navigation map based on the avoided route.
For specific limitations of the map building apparatus, reference may be made to the above limitations of the map building method, which are not described in detail herein. The various modules in the mapping apparatus described above may be implemented in whole or in part by software, hardware, and combinations thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and the internal structure thereof may be as shown in fig. 14. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operating system and the computer program to run on the non-volatile storage medium. The database of the computer device is used for storing data required to be stored in the map construction method. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a map building method.
In an embodiment, a computer device is provided, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the computer program, the steps of the map building method according to the above embodiments are implemented, for example, steps S10 to S50 shown in fig. 2. Alternatively, the processor, when executing the computer program, realizes the functions of the respective modules/units of the map building apparatus in the above-described embodiments, such as the functions of the modules 10 to 50 shown in fig. 13. To avoid repetition, the description is omitted here.
In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which when executed by a processor implements the mapping method of the above-described embodiments, such as steps S10 to S50 shown in fig. 2. Alternatively, the computer program, when executed by the processor, implements the functions of each module/unit in the mapping apparatus in the above-described apparatus embodiment, for example, the functions of the modules 10 to 50 shown in fig. 13. To avoid repetition, further description is omitted here.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by hardware instructions of a computer program, which may be stored in a non-volatile computer-readable storage medium, and when executed, may include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct Rambus Dynamic RAM (DRDRAM), and Rambus Dynamic RAM (RDRAM), among others.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (9)
1. A map construction method, comprising:
acquiring an original indoor map, wherein the original indoor map comprises an origin configured in a fixed point coordinate system and at least one preset point adjacent to the origin;
controlling the mobile shooting end to move to an origin in the fixed point coordinate system, and marking the origin as a current fixed point;
acquiring an adjacent fixed point adjacent to the current fixed point in a horizontal advancing direction or a vertical advancing direction according to a preset moving sequence;
acquiring a current fixed point image corresponding to the current fixed point according to the current fixed point and the adjacent fixed point, and splicing the current fixed point image and a historical fixed point image corresponding to a last adjacent fixed point by adopting a feature extraction algorithm to form a historical fixed point image corresponding to the current fixed point, wherein the historical fixed point image is a ground image formed by the current fixed point image which is correspondingly stored at each preset point and comprises the preset point and all preset points before the preset point in the map construction process;
controlling the mobile shooting end according to the preset moving sequence and preset step length, moving the mobile shooting end from the current fixed point to any one of the adjacent fixed points, taking the adjacent fixed point to which the mobile shooting end moves as an updated current fixed point, judging whether the updated current fixed point is the last preset point in the original indoor map, and taking the historical fixed point image as a fixed point navigation map if the updated current fixed point is the last preset point in the original indoor map; if the updated current fixed point is not the last preset point in the original indoor map, repeating the step of acquiring an adjacent fixed point adjacent to the current fixed point in a horizontal forward direction or a vertical forward direction according to a preset moving sequence until the updated current fixed point is the last preset point in the original indoor map;
acquiring a map updating request, wherein the map updating request comprises an updating fixed point coordinate, at least one updating fixed point image corresponding to the updating fixed point coordinate and an image direction identifier, and the image direction identifier indicates whether the position of the updated indoor ground between two preset points is in a horizontal advancing direction or a vertical advancing direction;
and updating the current fixed point image corresponding to the updated fixed point coordinate and in the same direction as the image direction identifier into the updated fixed point image in the fixed point navigation map based on the map updating request.
2. The mapping method of claim 1, wherein the obtaining of the original indoor map, the original indoor map including an origin point configured in a fixed point coordinate system and at least one predetermined point adjacent to the origin point, comprises:
acquiring an original indoor map configured with a fixed point coordinate system, and acquiring an origin based on the fixed point coordinate system;
respectively acquiring at least two vertical lines parallel to the longitudinal axis and at least two horizontal lines parallel to the transverse axis at intervals of a preset step length along the transverse axis direction or the longitudinal axis direction of the origin;
setting an intersection of each of the vertical lines and each of the horizontal lines as a preset point and storing on the original indoor map.
3. The map construction method according to claim 1, wherein said controlling the moving photographing end to move from the current fixed point to an adjacent fixed point according to the preset moving sequence and preset step length comprises:
if the current fixed point has an adjacent fixed point along the horizontal advancing direction, controlling the mobile shooting end to move by a preset step length along the horizontal advancing direction of the current fixed point so as to reach the adjacent fixed point;
and if the current fixed point does not have an adjacent fixed point along the horizontal advancing direction, controlling the mobile shooting end to move for a preset step length along the vertical advancing direction of the current fixed point so as to reach the adjacent fixed point, and reversely setting the horizontal advancing direction of the current fixed point so as to enable the mobile shooting end to have the adjacent fixed point along the horizontal advancing direction.
4. The map construction method according to claim 1, wherein the using a feature extraction algorithm to stitch the current fixed point image and the historical fixed point image corresponding to the last adjacent fixed point to form the historical fixed point image corresponding to the current fixed point comprises:
respectively extracting the characteristics of the current fixed point image and the historical fixed point image to obtain the characteristic points of the current image and the historical image;
performing feature matching on the current image feature points and the historical image feature points to obtain an image matching result;
and splicing the current fixed point image and the historical fixed point image based on the image matching result to form a historical fixed point image corresponding to the current fixed point.
5. The map construction method according to claim 1, wherein after the step of using the history fixed point image as the fixed point navigation map, the map construction method further comprises:
obtaining a route specification request, wherein the route specification request comprises one avoidance coordinate or two adjacent avoidance fixed points;
setting each step route connected with the avoidance coordinates as an avoidance route, or setting a step route formed between two adjacent avoidance fixed points as an avoidance route;
and updating the fixed point navigation map based on the avoided route.
6. A map building apparatus, comprising:
the indoor map acquisition module is used for acquiring an original indoor map, wherein the original indoor map comprises an origin configured in a fixed point coordinate system and at least one preset point adjacent to the origin;
the current fixed point marking module is used for controlling the mobile shooting end to move to an original point in the fixed point coordinate system and marking the original point as a current fixed point;
the acquisition adjacent fixed point module is used for acquiring an adjacent fixed point adjacent to the current fixed point in a horizontal advancing direction or a vertical advancing direction according to a preset moving sequence;
the acquisition fixed point image module is used for acquiring a current fixed point image corresponding to the current fixed point according to the current fixed point and the adjacent fixed point, splicing the current fixed point image and a historical fixed point image corresponding to a last adjacent fixed point by adopting a feature extraction algorithm to form a historical fixed point image corresponding to the current fixed point, wherein the historical fixed point image is a ground image formed by the current fixed point image which is stored correspondingly for each preset point and comprises the preset point and all preset points before the preset point in the map construction process;
a navigation map obtaining module, configured to control the mobile shooting end according to the preset moving sequence and preset step length, move from the current fixed point to any one of the adjacent fixed points, use the adjacent fixed point to which the mobile shooting end moves as an updated current fixed point, determine whether the updated current fixed point is a last preset point in the original indoor map, and if the updated current fixed point is the last preset point in the original indoor map, use the historical fixed point image as a fixed point navigation map; if the updated current fixed point is not the last preset point in the original indoor map, repeating the step of acquiring an adjacent fixed point adjacent to the current fixed point in a horizontal forward direction or a vertical forward direction according to a preset moving sequence until the updated current fixed point is the last preset point in the original indoor map;
the map updating request module is used for acquiring a map updating request, wherein the map updating request comprises an updating fixed point coordinate, at least one updating fixed point image corresponding to the updating fixed point coordinate and an image direction identifier, and the image direction identifier indicates whether the position of the updated indoor ground between two preset points is in a horizontal advancing direction or a vertical advancing direction;
and the fixed point image updating module is used for updating the current fixed point image which corresponds to the updated fixed point coordinate and is in the same direction as the image direction identifier into the updated fixed point image in the fixed point navigation map based on the map updating request.
7. The mapping apparatus of claim 6, wherein the obtain indoor map module comprises:
the indoor map acquisition unit is used for acquiring an original indoor map configured with a fixed point coordinate system and acquiring an origin based on the fixed point coordinate system;
the parallel line acquisition unit is used for respectively acquiring at least two vertical lines parallel to the longitudinal axis and at least two horizontal lines parallel to the transverse axis at intervals of a preset step length along the transverse axis direction or the longitudinal axis direction of the origin;
and a preset point setting unit for setting the intersection point of each vertical line and each horizontal line as a preset point and storing the preset point on the original indoor map.
8. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the steps of the mapping method according to any of claims 1 to 5 are implemented by the processor when executing the computer program.
9. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of a mapping method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811008409.2A CN109186618B (en) | 2018-08-31 | 2018-08-31 | Map construction method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811008409.2A CN109186618B (en) | 2018-08-31 | 2018-08-31 | Map construction method and device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109186618A CN109186618A (en) | 2019-01-11 |
| CN109186618B true CN109186618B (en) | 2022-11-29 |
Family
ID=64917538
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811008409.2A Active CN109186618B (en) | 2018-08-31 | 2018-08-31 | Map construction method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109186618B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109781072A (en) * | 2019-01-18 | 2019-05-21 | 上海扩博智能技术有限公司 | Indoor navigation map foundation based on augmented reality, navigation methods and systems |
| CN111481111A (en) * | 2019-01-29 | 2020-08-04 | 北京奇虎科技有限公司 | Use method and device of internal memory of sweeper |
| CN109916417B (en) * | 2019-02-20 | 2023-04-11 | 广州市山丘智能科技有限公司 | Map establishing method, map establishing device, computer equipment and storage medium thereof |
| CN111522596A (en) * | 2020-03-25 | 2020-08-11 | 平安城市建设科技(深圳)有限公司 | Scene preloading optimization method and device, electronic equipment and storage medium |
| CN112146660B (en) * | 2020-09-25 | 2022-05-03 | 电子科技大学 | Indoor map positioning method based on dynamic word vector |
| CN113778086B (en) * | 2021-09-03 | 2024-06-18 | 上海擎朗智能科技有限公司 | Map construction and use method, robot and storage medium |
Family Cites Families (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001512252A (en) * | 1997-08-01 | 2001-08-21 | サーノフ コーポレイション | Method and apparatus for performing local / global multi-frame alignment for constructing a mosaic image |
| JP5246286B2 (en) * | 2011-03-15 | 2013-07-24 | カシオ計算機株式会社 | Image recording apparatus, image recording method, and program |
| CN103398717B (en) * | 2013-08-22 | 2016-04-20 | 成都理想境界科技有限公司 | The location of panoramic map database acquisition system and view-based access control model, air navigation aid |
| CN106485655A (en) * | 2015-09-01 | 2017-03-08 | 张长隆 | A kind of taken photo by plane map generation system and method based on quadrotor |
| CN105371847B (en) * | 2015-10-27 | 2018-06-29 | 深圳大学 | A kind of interior real scene navigation method and system |
| CN106885578A (en) * | 2015-12-16 | 2017-06-23 | 北京奇虎科技有限公司 | Map updating method and device |
| CN107038949A (en) * | 2016-02-03 | 2017-08-11 | 幸福在线（北京）网络技术有限公司 | A kind of generation method of live-action map, method for pushing and its device |
| CN105911988A (en) * | 2016-04-26 | 2016-08-31 | 湖南拓视觉信息技术有限公司 | Automatic drawing device and method |
| CN106197421B (en) * | 2016-06-24 | 2019-03-22 | 北京工业大学 | A kind of forward position target point generation method independently explored for mobile robot |
| CN106446200A (en) * | 2016-09-29 | 2017-02-22 | 北京百度网讯科技有限公司 | Positioning method and device |
| CN106767854B (en) * | 2016-11-07 | 2020-05-22 | 纵目科技（上海）股份有限公司 | Mobile device, garage map forming method and system |
| CN106980657A (en) * | 2017-03-15 | 2017-07-25 | 北京理工大学 | A kind of track level electronic map construction method based on information fusion |
| CN107845114B (en) * | 2017-11-10 | 2024-03-22 | 北京三快在线科技有限公司 | Map construction method and device and electronic equipment |
| CN108108396B (en) * | 2017-12-01 | 2020-10-02 | 上海市环境科学研究院 | Aerial photography picture splicing management system for aircraft |
| CN108053473A (en) * | 2017-12-29 | 2018-05-18 | 北京领航视觉科技有限公司 | A kind of processing method of interior three-dimensional modeling data |
| CN108259762A (en) * | 2018-03-23 | 2018-07-06 | 南京嘉码信息科技有限公司 | A kind of roaming type panorama sketch automatic shooting system and method |
-
2018
- 2018-08-31 CN CN201811008409.2A patent/CN109186618B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109186618A (en) | 2019-01-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109186618B (en) | Map construction method and device, computer equipment and storage medium | |
| US10964079B2 (en) | Method and apparatus for editing road element on map, electronic device, and storage medium | |
| US12025451B2 (en) | Method and device for locating obstacle in semantic map, computer apparatus, and storage medium | |
| CN112258567B (en) | Visual positioning method and device for object grabbing point, storage medium and electronic equipment | |
| CN110458112B (en) | Vehicle detection method and device, computer equipment and readable storage medium | |
| WO2021134325A1 (en) | Obstacle detection method and apparatus based on driverless technology and computer device | |
| CN111797650A (en) | Obstacle identification method and device, computer equipment and storage medium | |
| CN109099889B (en) | Close-range photogrammetry system and method | |
| CN109815831B (en) | Vehicle orientation obtaining method and related device | |
| CN111339802A (en) | Method and device for generating real-time relative map, electronic equipment and storage medium | |
| CN113984039B (en) | Motion trail correction method, device, system and storage medium | |
| CN110262487B (en) | Obstacle detection method, terminal and computer readable storage medium | |
| CN111159459B (en) | Landmark positioning method, landmark positioning device, computer equipment and storage medium | |
| CN111161202A (en) | Vehicle behavior information acquisition method and device, computer equipment and storage medium | |
| CN113034347B (en) | Oblique photography image processing method, device, processing equipment and storage medium | |
| WO2023025262A1 (en) | Excavator operation mode switching control method and apparatus and excavator | |
| CN112689234A (en) | Indoor vehicle positioning method and device, computer equipment and storage medium | |
| CN113607161B (en) | Robot navigation path width acquisition system, method, robot and storage medium | |
| CN112507857A (en) | Lane line updating method, device, equipment and storage medium | |
| US20230290055A1 (en) | Surveying assistance system, information display terminal, surveying assistance method, and storage medium storing surveying assistance program | |
| CN112683273A (en) | Adaptive incremental mapping method, system, computer equipment and storage medium | |
| CN116630442A (en) | Visual SLAM pose estimation precision evaluation method and device | |
| CN114459483B (en) | Landmark navigation map construction and application method and system based on robot navigation | |
| CN116934956A (en) | Method, device, equipment and storage medium for constructing three-dimensional model | |
| CN111426329B (en) | Road generation method and device, computer equipment and 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |