WO2020006686A1 - 建立地图的方法、定位方法、终端及计算机可读存储介质 - Google Patents

建立地图的方法、定位方法、终端及计算机可读存储介质 Download PDF

Info

Publication number
WO2020006686A1
WO2020006686A1 PCT/CN2018/094331 CN2018094331W WO2020006686A1 WO 2020006686 A1 WO2020006686 A1 WO 2020006686A1 CN 2018094331 W CN2018094331 W CN 2018094331W WO 2020006686 A1 WO2020006686 A1 WO 2020006686A1
Authority
WO
WIPO (PCT)
Prior art keywords
map
information
shooting
description information
feature information
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.)
Ceased
Application number
PCT/CN2018/094331
Other languages
English (en)
French (fr)
Inventor
韩立明
林义闽
廉士国
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.)
Cloudminds Shenzhen Robotics Systems Co Ltd
Original Assignee
Cloudminds Shenzhen Robotics Systems 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 Cloudminds Shenzhen Robotics Systems Co Ltd filed Critical Cloudminds Shenzhen Robotics Systems Co Ltd
Priority to CN201880001106.XA priority Critical patent/CN109074676B/zh
Priority to PCT/CN2018/094331 priority patent/WO2020006686A1/zh
Publication of WO2020006686A1 publication Critical patent/WO2020006686A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three-dimensional [3D] modelling for computer graphics
    • G06T17/05—Geographic models
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
    • G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods

Definitions

  • the present application relates to the field of navigation, and in particular, to a method for establishing a map, a positioning method, a terminal, and a computer-readable storage medium.
  • VSLAM Current Visual Simultaneous localization and mapping
  • a visual sensor uses feature extraction methods to extract feature points that characterize the spatial environment from the image. These feature points are mainly corner points in the scene. Aiming at the extracted feature points, the position information of the feature points in space is calculated by methods such as binocular parallax or monocular motion parallax. Obviously, if a camera with depth information is used, the position information corresponding to the feature points can also be directly obtained.
  • the terminal can form a map for positioning in VSLAM based on the captured images.
  • the position and posture of the terminal (hereinafter referred to as posture) can be obtained by matching the image captured by the image sensor at the current time with the map.
  • posture the position and posture of the terminal
  • the matching of the feature information of the current captured image of the terminal with the feature information of the map is the core issue of the VSLAM technology.
  • the inventor discovered during the research of the prior art that when the shooting conditions of the terminal are different, such as shooting under natural light during the day and shooting under night light, or when the terminal normally shoots and rotates 120 degrees, the terminal captures the same object in the image
  • the extracted feature points are very different, making the feature points in the captured image unable to match the map points, which seriously affects the positioning ability of the terminal.
  • a technical problem to be solved in some embodiments of the present application is how to improve the positioning capability of the terminal.
  • An embodiment of the present application provides a method for establishing a map, including: obtaining position information of a map point and N first images of the map points; wherein the corresponding shooting information of the N first images is different, and N is greater than An integer of 1; determining the feature information set of the map point according to the feature information of the map point in the N first images; establishing a map according to the feature information set of the map point and the position information of the map point, wherein the map is stored in the map The feature information collection of points and the location information of map points.
  • An embodiment of the present application further provides a positioning method, including: acquiring a second image for positioning; extracting feature information of a map point in the second image; and determining a feature of the map point in the map and the second image Feature information with matching information; where the map stores the feature information set of the map points and the location information of the map points; obtains the location information of the map points corresponding to the matched feature information from the map, and determines the positioning based on the obtained location information result.
  • An embodiment of the present application further provides a terminal including at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor.
  • the processor executes to enable at least one processor to execute the method for establishing a map mentioned in the foregoing embodiment.
  • An embodiment of the present application further provides a terminal including at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor.
  • the processor executes to enable at least one processor to execute the positioning method mentioned in the foregoing embodiment.
  • An embodiment of the present application further provides a computer-readable storage medium storing a computer program, wherein the computer program implements the method for establishing a map mentioned in the foregoing embodiment when executed by a processor.
  • An embodiment of the present application further provides a computer-readable storage medium storing a computer program, wherein the computer program implements the positioning method mentioned in the foregoing embodiment when executed by a processor.
  • the embodiments of the present application store feature information of map points corresponding to different shooting information in a map, which enriches the feature information of map points in the map, so that during the positioning process, shooting can be improved.
  • the probability that the feature information of the map points in the image matches the feature information of the map points in the map will improve the positioning ability.
  • FIG. 1 is a flowchart of a method for establishing a map according to a first embodiment of the present application
  • FIG. 2 is a flowchart of a method for establishing a map according to a second embodiment of the present application
  • FIG. 3 is a flowchart of a method for establishing a map according to a third embodiment of the present application.
  • FIG. 4 is a flowchart of a positioning method according to a fourth embodiment of the present application.
  • FIG. 5 is a flowchart of a positioning method according to a fifth embodiment of the present application.
  • FIG. 6 is a schematic diagram of a relationship between a method for establishing a map and a positioning method for a terminal according to a fifth embodiment of the present application;
  • FIG. 7 is a schematic structural diagram of a terminal according to a sixth embodiment of the present application.
  • FIG. 8 is a schematic structural diagram of a terminal according to a seventh embodiment of the present application.
  • the terminal executing the method of establishing a map and the terminal executing the positioning method may be the same terminal or different terminals.
  • the terminal that executes the method for establishing a map and the terminal that executes the positioning method are taken as an example for description.
  • the first embodiment of the present application relates to a method for establishing a map, which is applied to a terminal.
  • the method for establishing a map includes the following steps:
  • Step 101 Obtain position information of a map point and N first images of the map point.
  • the shooting information corresponding to each of the N first images is different, and N is an integer greater than 1.
  • Different shooting information can be different shooting brightness or different shooting angles. For example, a certain map point is a tree on the street, and images of the four seasons of the tree taken at various angles, images of the tree under sunlight, and images of the tree under light are acquired.
  • Step 102 Determine the feature information set of the map points according to the feature information of the map points in the N first images.
  • the terminal extracts the feature information of the map points in each first image, and combines the feature information of the same map points in the N first images to obtain the feature information set of the map points.
  • the terminal numbers the map points in the first image, where the same map points in different first images have the same number.
  • the terminal combines the feature information of the map points with the same number according to the map point number to obtain the feature information set of the map points.
  • the feature information of the map point includes the description information of the map point, and the description information of the map point may be a corner point of the map point or other characteristics of the map point.
  • the terminal determines a corner point of a map point by using a corner point detection algorithm, such as a Harris corner point detection algorithm.
  • the feature information of the map point includes description information of the map point and shooting information corresponding to the description information of the map point.
  • the shooting information corresponding to the description information of the map point is determined according to the shooting information of the image where the description information of the map point is located.
  • Step 103 Create a map according to the feature information set of the map points and the position information of the map points.
  • the position information of the map points is the spatial three-dimensional coordinates of the map points.
  • the terminal establishes a map according to the spatial three-dimensional coordinates of the map points and the feature information set, so that the map stores the feature information set of the map points and the position information of the map points.
  • the method for establishing a map stores the feature information of map points corresponding to different shooting information in the map, which enriches the feature information of map points in the map, and makes the positioning process easier.
  • the probability that the feature information of the map points in the captured image matches the feature information of the map points in the map can be improved, thereby improving the positioning ability.
  • the second embodiment of the present application relates to a method for establishing a map.
  • This embodiment is a further refinement of the first embodiment, and specifically describes step 102.
  • the feature information of the map points is the description information of the map points, so the feature information set of the map points is composed of the description information of the map points.
  • this embodiment includes steps 201 to 204.
  • Steps 201 and 204 are substantially the same as steps 101 and 103 in the first embodiment, respectively, and will not be described in detail here. The differences are mainly introduced below:
  • Step 202 Cluster the description information of the map points in the N first images through a clustering algorithm to determine the clustered description information.
  • the terminal clusters the description information of the map points in the N first images, classifies the description information of the similar map points into one category, and records the center points of the category as the clustered description information.
  • the process of determining the description information after clustering is as follows: After determining that there is description information of unclassified map points, the terminal randomly selects one map point description information from the description information of unclassified map points. As the center point. For this center point, the terminal performs the following operations: finds all description information that is within a first preset value from the center point and records it as set M; determines the vector from the center point to each element in set M, and compares all vectors Add to get the offset vector; control the center point to move in the direction of the offset vector, the distance of travel is half the modulus of the offset vector; determine whether the modulus of the offset vector is less than the second preset value, and if it is less, record the center point , Otherwise, determine the vector from the current center point to each element in the set M, add all the vectors to get the offset vector, control the center point to move in the direction of the offset vector, and move the distance by half the modulus of the offset vector ... ... until the magnitude of the offset vector is less than the
  • Step 203 Determine the feature information set of the map points according to the clustered description information.
  • the method for establishing a map stores the feature information of map points corresponding to different shooting information into a map, and clusters the description information of the map points. At the same time as the feature information of the map points in the map, the amount of map data is reduced, so that during the positioning process, the probability of successful matching of the feature information of the map points in the captured image and the feature information of the map points in the map can be improved. Improved positioning capabilities.
  • the third embodiment of the present application relates to a method for establishing a map.
  • This embodiment is a further refinement of the first embodiment, and specifically describes step 102.
  • the feature information of the map points includes description information of the map points and shooting information corresponding to the description information of the map points.
  • this embodiment includes steps 301 to 304.
  • steps 301 and 304 are substantially the same as steps 101 and 103 in the first embodiment, respectively, and will not be described in detail here. The differences are mainly introduced below:
  • Step 302 cluster the description information of the map points in the N first images through a clustering algorithm, determine the clustered description information, and determine the shooting information corresponding to the clustered description information.
  • the process of clustering the description information by the clustering algorithm can refer to the related description of the second embodiment, which will not be described in detail here.
  • the method for determining the shooting information corresponding to the clustered description information will be described below.
  • the clustering algorithm aggregates the L description information into one category, then according to the shooting information corresponding to the L description information, the shooting information corresponding to the description information clustered by the L description information is determined, and L is an integer greater than 1.
  • the shooting information includes shooting brightness and shooting angle.
  • the terminal calculates an average value of the shooting brightness corresponding to the L description information as the first average value, and uses the first average value as the shooting brightness corresponding to the description information clustered by the L description information.
  • the terminal calculates an average value of the shooting angles corresponding to the L description information as the second average value, and uses the second average value as the shooting angle corresponding to the description information clustered by the L description information.
  • the following describes the process of determining the shooting information corresponding to the clustered description information in combination with the actual scene.
  • the description information corresponding to the map point P includes first description information (ka), second description information (kb), third description information (kc), fourth description information (kd), fifth description information (ke) ... ....
  • the shooting brightness of ka is the first shooting brightness (hka)
  • the shooting brightness of kb is the second shooting brightness (hkb)
  • the shooting brightness of kc is the third shooting brightness (hkc)
  • the shooting angle of ka is the first The shooting angle (tka)
  • the shooting angle of kb is the second shooting angle (tkb)
  • the shooting angle of kc is the third shooting angle (tkc) ...
  • ka, kb, and kc are divided into one group,
  • the shooting brightness of the description information after the class (hka + hkb + hkc) / 3
  • the shooting angle of the description information after the cluster (tka + tkb + tkc) / 3.
  • Step 303 Determine the feature information set of the map point according to the clustered description information and the shooting information corresponding to the clustered description information.
  • the shooting information corresponding to the description information is recorded, so that during the positioning process, the description information for matching can be filtered by the shooting information, which improves the positioning efficiency of the terminal.
  • the method for establishing a map stores the feature information of map points corresponding to different shooting information into a map, and clusters the description information of map points in a rich manner.
  • the amount of map data is reduced, so that during the positioning process, the probability of successful matching of the feature information of the map points in the captured image and the feature information of the map points in the map can be increased, thereby increasing Positioning capabilities.
  • the shooting information corresponding to the description information is recorded, so that during the positioning process, the description information for matching can be filtered by the shooting information, which improves the positioning efficiency of the terminal.
  • the fourth embodiment of the present application relates to a positioning method, which is applied to a terminal.
  • the positioning method includes:
  • Step 401 Acquire a second image for positioning.
  • Step 402 Extract feature information of a map point in the second image.
  • the terminal collects an image of a current environment through an image sensor, and extracts feature information of a map point in the image.
  • Step 403 Determine feature information in the map that matches feature information of a map point in the second image.
  • a map stores feature information sets of map points and position information of the map points.
  • the terminal matches the feature information of the map points in the second image with the feature information set of the map points in the map, and determines the matched feature information.
  • Step 404 Obtain position information of a map point corresponding to the matched feature information from the map, and determine a positioning result according to the obtained position information.
  • the terminal uses a pose estimation algorithm according to a matching result between a map point in the map and a map point in the second image, for example, point perspective (Perspective n Points (PnP) pose measurement algorithm to determine positioning results.
  • the positioning result includes the pose information of the terminal.
  • the terminal may use a beam method to adjust (bundle) adjustment) to optimize the pose information.
  • the positioning method provided in this embodiment stores feature information of map points corresponding to different shooting information in the map
  • the feature information of map points in the captured image can be improved during the positioning process.
  • the probability of successful matching with the feature information of the map points in the map further improves the positioning ability.
  • the fifth embodiment of the present application relates to a positioning method.
  • This embodiment is a further refinement of the fourth embodiment, specifically describes step 403, and adds other related steps before step 404.
  • the positioning method of this embodiment includes steps 501 to 507, where steps 501, 502, and 507 are substantially the same as steps 401, 402, and 404, respectively, and are not described here. Describe the differences:
  • Steps 501 and 502 are performed.
  • Step 503 Determine shooting information of the second image.
  • the shooting information of the second image may be determined by analyzing the information of the second image, or may be determined based on data detected by a sensor on the terminal, for example, the shooting brightness detected by the photosensitive sensor when shooting the second image.
  • Step 504 According to the shooting information of the second image and the shooting information corresponding to each description information in the feature information set of the map points in the map, filtering is obtained from the feature information set of the map points in the map for matching description information. .
  • the shooting information includes shooting brightness and shooting angle.
  • the terminal separately calculates a first difference between the shooting brightness of the second image and the shooting brightness corresponding to each description information, and a second difference between the shooting angle of the second image and the shooting angle corresponding to each description information; according to the first difference Value and the second difference, from the feature information set of the map point, M pieces of description information are selected as the description information for matching.
  • M is a positive integer.
  • the following describes the process by which the terminal obtains the descriptive information for matching from the feature information set of the map points in the map in combination with the actual scenario.
  • the terminal acquires the shooting brightness of the map points in the second image as H, the shooting angle is L, and the feature information set of the map points in the map is ⁇ (description information a1, shooting brightness h1, shooting angle l1), (description information a2 , Shooting brightness h2, shooting angle l2), (description information a3, shooting brightness h3, shooting angle l3) ... ⁇ , that is, the shooting brightness corresponding to the description information a1 is h1, the corresponding shooting angle is l1, and the description information a2 corresponds to The shooting brightness is h2, and the corresponding shooting angle is l2 ...
  • the terminal calculates the difference between h1 and H and the difference between l1 and L, and sets different weights for the two differences according to actual needs, so as to determine the second image.
  • the terminal calculates the distance between the shooting information of the map points of the second image and the shooting information corresponding to each description information in the feature information set of the map points in the map.
  • the terminal sorts each description information in the feature information set of the map points in the map in the order of the distance from small to large, and selects the first M description information ranked as the description information for matching.
  • a method of setting a distance preset value can also be used to filter the feature information set, that is, the distance of the shooting information corresponding to the description information of the map point in the second image.
  • the description information smaller than the distance preset value is used as the description information for matching.
  • Step 505 From the description information for matching, determine description information that matches the description information of the map point in the second image.
  • the description information for matching is matched with the description information of the map points in the second image, and the matching description information is determined.
  • Step 506 Determine that at least T map points in the second image match the map successfully.
  • T is a positive integer, for example, T is equal to 10.
  • the pose information of the terminal is calculated to avoid the insufficient number of successful matches and the inability to locate the resource waste caused by the positioning result.
  • the positioning method provided in this embodiment stores feature information of map points corresponding to different shooting information in the map
  • the feature information of map points in the captured image can be improved during the positioning process.
  • the probability of successful matching with the feature information of the map points in the map further improves the positioning ability.
  • the terminal filters the feature information set of the map points in the map according to the shooting information corresponding to the description information, determines the description information for matching, and improves the positioning efficiency of the terminal. After the number of successfully matched map points reaches T, the pose information of the terminal is calculated to avoid the insufficient number of successful matches and the inability to locate, and determine the waste of resources caused by the positioning result.
  • the terminal establishes a map by acquiring characteristic information of the map points corresponding to different shooting information, and in the positioning process, determines the description information for matching according to the specific shooting information, thereby determining the positioning result of the terminal.
  • a sixth embodiment of the present application relates to a terminal.
  • the terminal includes at least one processor 601; and a memory 602 communicatively connected to the at least one processor 601.
  • the memory 602 stores instructions that can be executed by the at least one processor 601, and the instructions are executed by the at least one processor 601, so that the at least one processor 601 can execute the foregoing method of establishing a map.
  • a seventh embodiment of the present application relates to a terminal.
  • the terminal includes at least one processor 701; and a memory 702 communicatively connected to the at least one processor 701.
  • the memory 702 stores instructions executable by the at least one processor 701, and the instructions are executed by the at least one processor 701, so that the at least one processor 701 can execute the positioning method.
  • the processor is a central processing unit (CPU) as an example
  • the memory is a read-write memory (Random Access) Memory, RAM) as an example.
  • the processor and the memory may be connected through a bus or in other manners. In FIG. 7 and FIG. 8, connection through a bus is taken as an example.
  • the memory is a non-volatile computer-readable storage medium, and can be used to store non-volatile software programs, non-volatile computer executable programs, and modules. For example, map description information in the embodiments of the present application is stored in the memory. .
  • the processor executes various functional applications and data processing of the device by running non-volatile software programs, instructions, and modules stored in the memory, that is, the above-mentioned method for establishing a map or positioning method.
  • the memory may include a storage program area and a storage data area, wherein the storage program area may store an operating system and an application program required for at least one function; the storage data area may store a list of options and the like.
  • the memory may include a high-speed random access memory, and may further include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage device.
  • the memory may optionally include a memory remotely set relative to the processor, and these remote memories may be connected to an external device through a network. Examples of the above network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
  • One or more modules are stored in the memory, and when executed by one or more processors, execute a method for establishing a map or a positioning method in any of the foregoing method embodiments.
  • the above product can execute the method provided in the embodiment of the present application, and has the corresponding functional modules and beneficial effects of the execution method.
  • the above product can execute the method provided in the embodiment of the present application, and has the corresponding functional modules and beneficial effects of the execution method.
  • An eighth embodiment of the present application relates to a computer-readable storage medium storing a computer program.
  • the computer program is executed by the processor, the method for building a map described in any of the above method embodiments is implemented.
  • An eighth embodiment of the present application relates to a computer-readable storage medium storing a computer program.
  • the computer program is executed by the processor, the positioning method described in any of the above method embodiments is implemented.
  • the program is stored in a storage medium and includes several instructions to make a device ( It may be a single-chip microcomputer, a chip, or the like) or a processor that executes all or part of the steps of the method described in each embodiment of the present application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disks or optical disks and other media that can store program code .

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Geometry (AREA)
  • Software Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Remote Sensing (AREA)
  • Computer Graphics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Image Analysis (AREA)
  • Navigation (AREA)

Abstract

一种建立地图的方法、定位方法、终端及计算机可读存储介质。该建立地图的方法包括：获取地图点的位置信息和地图点的N幅第一图像（101）；其中，N幅第一图像各自对应的拍摄信息不同，N为大于1的整数；根据N幅第一图像中的地图点的特征信息，确定地图点的特征信息集合（102）；根据地图点的特征信息集合以及地图点的位置信息，建立地图（103），其中，地图中存储有地图点的特征信息集合和地图点的位置信息。

Description

建立地图的方法、定位方法、终端及计算机可读存储介质 技术领域
本申请涉及导航领域，尤其涉及一种建立地图的方法、定位方法、终端及计算机可读存储介质。
 背景技术
当前的视觉即时定位和建图（Visual Simultaneous localization and mapping，VSLAM）技术，使用视觉传感器采集一组图像，通过特征提取方法，从图像中提取表征空间环境的特征点。这些特征点主要是场景中的角点。针对提取的特征点，通过双目视差或单目运动视差等方法，计算出特征点在空间中的位置信息。显然的，如果使用带有深度信息的摄像头，也可以直接获取特征点对应的位置信息。终端根据拍摄的图像，可以组成VSLAM中用于定位的地图。在终端移动过程中，将当前时刻图像传感器拍摄的图像与地图匹配，能够得到终端的位置和姿态（以下简称位姿）。上述公开的VSLAM技术方案中，终端当前拍摄图像的特征信息与地图的特征信息的匹配是VSLAM技术的核心问题。
 技术问题
发明人在研究现有技术过程中发现，当终端的拍摄条件不同时，如白天的自然光下拍摄与晚上的灯光下拍摄，或终端正常拍摄与旋转120度拍摄，终端对同一物体采集的图像中提取的特征点区别很大，使得拍摄的图像中的特征点无法与地图点匹配，严重影响终端的定位能力。
可见，如何提高终端的定位能力，是需要解决的问题。
 技术解决方案
本申请部分实施例所要解决的一个技术问题在于如何提高终端的定位能力。
本申请的一个实施例提供了一种建立地图的方法，包括：获取地图点的位置信息和地图点的N幅第一图像；其中，N幅第一图像各自对应的拍摄信息不同，N为大于1的整数；根据N幅第一图像中的地图点的特征信息，确定地图点的特征信息集合；根据地图点的特征信息集合以及地图点的位置信息，建立地图，其中，地图中存储有地图点的特征信息集合和地图点的位置信息。
本申请的一个实施例还提供了一种定位方法，包括：获取用于定位的第二图像；提取第二图像中的地图点的特征信息；确定地图中与第二图像中的地图点的特征信息相匹配的特征信息；其中，地图中存储有地图点的特征信息集合和地图点的位置信息；从地图中获取相匹配的特征信息对应的地图点的位置信息，根据获取的位置信息确定定位结果。
本申请的一个实施例还提供了一种终端，包括至少一个处理器；以及，与至少一个处理器通信连接的存储器；其中，存储器存储有可被至少一个处理器执行的指令，指令被至少一个处理器执行，以使至少一个处理器能够执行上述实施例提及的建立地图的方法。
本申请的一个实施例还提供了一种终端，包括至少一个处理器；以及，与至少一个处理器通信连接的存储器；其中，存储器存储有可被至少一个处理器执行的指令，指令被至少一个处理器执行，以使至少一个处理器能够执行上述实施例提及的定位方法。
本申请的一个实施例还提供了一种计算机可读存储介质，存储有计算机程序，其中，计算机程序被处理器执行时实现上述实施例提及的建立地图的方法。
本申请的一个实施例还提供了一种计算机可读存储介质，存储有计算机程序，其中，计算机程序被处理器执行时实现上述实施例提及的定位方法。
 有益效果
本申请的实施例相对于现有技术而言，将不同拍摄信息各自对应的地图点的特征信息存储至地图中，丰富了地图中的地图点的特征信息，使得在定位过程中，能够提高拍摄的图像中地图点的特征信息与地图中地图点的特征信息匹配成功的概率，进而提高了定位能力。
 附图说明
一个或多个实施例通过与之对应的附图中的图片进行示例性说明，这些示例性说明并不构成对实施例的限定，附图中具有相同参考数字标号的元件表示为类似的元件，除非有特别申明，附图中的图不构成比例限制。
图1是本申请第一实施例的建立地图的方法的流程图；
图2是本申请第二实施例的建立地图的方法的流程图；
图3是本申请第三实施方式的建立地图的方法的流程图；
图4是本申请第四实施例的定位方法的流程图；
图5是本申请第五实施例的定位方法的流程图；
图6是本申请第五实施例的终端的建立地图的方法和定位方法的关系示意图；
图7是本申请第六实施例的终端的结构示意图；
图8是本申请第七实施例的终端的结构示意图。
 本发明的实施方式
为了使本申请的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本申请部分实施例进行进一步详细说明。应当理解，此处所描述的具体实施例仅仅用以解释本申请，并不用于限定本申请。
需要说明的是，执行建立地图的方法的终端与执行定位方法的终端可以是同一终端，也可以是不同终端。本申请的实施例中，以执行建立地图的方法的终端与执行定位方法的终端是同一终端为例进行说明。
本申请的第一实施例涉及一种建立地图的方法，应用于终端。如图1所示，该建立地图的方法包括以下步骤：
步骤101：获取地图点的位置信息和地图点的N幅第一图像。
具体地说，N幅第一图像各自对应的拍摄信息不同，N为大于1的整数。拍摄信息不同可以是拍摄亮度不同，也可以是拍摄角度不同。例如，某一地图点是街道上的树，获取各个角度下拍摄的树的四季的图像、树在阳光照射下的图像、树在灯光照射下的图像等。
步骤102：根据N幅第一图像中的地图点的特征信息，确定地图点的特征信息集合。
具体地说，终端提取每幅第一图像中的地图点的特征信息，并将N幅第一图像中的相同地图点的特征信息进行合并，得到地图点的特征信息集合。例如，终端对第一图像中的地图点进行编号，其中，不同第一图像中的相同地图点的编号相同。终端根据地图点的编号，将编号相同的地图点的特征信息合并，得到地图点的特征信息集合。
具体实现中，地图点的特征信息包括地图点的描述信息，地图点的描述信息可以是地图点的角点，也可以是地图点的其他特征。具体实现中，终端通过角点检测算法例如哈里斯（harris）角点检测算法，确定地图点的角点。
另一具体实现中，地图点的特征信息包括地图点的描述信息，以及地图点的描述信息对应的拍摄信息。其中，地图点的描述信息对应的拍摄信息根据该地图点的描述信息所在的图像的拍摄信息确定。
步骤103：根据地图点的特征信息集合以及地图点的位置信息，建立地图。
具体地说，地图点的位置信息为地图点的空间三维坐标。终端根据地图点的空间三维坐标和特征信息集合，建立地图，以使地图中存储有地图点的特征信息集合和地图点的位置信息。
与现有技术相比，本实施例中提供的建立地图的方法，将不同拍摄信息各自对应的地图点的特征信息存储至地图中，丰富了地图中的地图点的特征信息，使得在定位过程中，能够提高拍摄的图像中地图点的特征信息与地图中地图点的特征信息匹配成功的概率，进而提高了定位能力。
本申请的第二实施例涉及一种建立地图的方法，本实施例是对第一实施例的进一步细化，具体说明了步骤102。
需要说明的是，本实施例中，地图点的特征信息为地图点的描述信息，故地图点的特征信息集合由地图点的描述信息组成。
如图2所示，本实施例包括步骤201至步骤204。其中，步骤201、步骤204分别与第一实施例中的步骤101、步骤103大致相同，此处不再详述，下面主要介绍不同之处：
执行步骤201。
步骤202：通过聚类算法对N幅第一图像中的地图点的描述信息进行聚类，确定聚类后的描述信息。
具体地说，终端对N幅第一图像中的地图点的描述信息进行聚类，将相近的地图点的描述信息归为一类，记录该类的中心点，作为聚类后的描述信息。
具体实现中，确定聚类后的描述信息的过程如下：终端在确定存在未被分类的地图点的描述信息后，从未被分类的地图点的描述信息中，随机选择一个地图点的描述信息作为中心点。针对该中心点，终端进行以下操作：找到与中心点距离在第一预设值之内的所有描述信息，记作集合M；确定中心点到集合M中每个元素的向量，将所有向量相加，得到偏移向量；控制中心点沿偏移向量的方向移动，移动距离为偏移向量的模的一半；判断偏移向量的模是否小于第二预设值，若小于，记录该中心点，否则，确定当前中心点到集合M中每个元素的向量，将所有向量相加，得到偏移向量，控制中心点沿偏移向量的方向移动，移动距离为偏移向量的模的一半……直至偏移向量的模小于第二预设值。终端确定地图点的所有描述信息都被分类后，根据记录的中心点，确定聚类后的描述信息。
步骤203：根据聚类后的描述信息，确定地图点的特征信息集合。
值得一提的是，通过聚类算法，将相似的地图点的描述信息合并，减小了地图的数据量。
执行步骤204。
与现有技术相比，本实施例中提供的建立地图的方法，将不同拍摄信息各自对应的地图点的特征信息存储至地图的过程中，对地图点的描述信息进行聚类，在丰富了地图中的地图点的特征信息的同时，减小了地图的数据量，使得在定位过程中，能够提高拍摄的图像中地图点的特征信息与地图中地图点的特征信息匹配成功的概率，进而提高了定位能力。
本申请的第三实施例涉及一种建立地图的方法，本实施例是对第一实施例的进一步细化，具体说明了步骤102。
需要说明的是，本实施例中，地图点的特征信息包括地图点的描述信息和地图点的描述信息对应的拍摄信息。
如图3所示，本实施例包括步骤301至步骤304。其中，步骤301、304分别与第一实施例中的步骤101、103大致相同，此处不再详述，下面主要介绍不同之处：
执行步骤301。
步骤302：通过聚类算法对N幅第一图像中的地图点的描述信息进行聚类，确定聚类后的描述信息，以及确定聚类后的描述信息对应的拍摄信息。
其中，通过聚类算法对描述信息进行聚类的过程可以参考第二实施例的相关描述，此处不再详述，以下对确定聚类后的描述信息对应的拍摄信息的方法进行说明。
若聚类算法将L个描述信息聚为一类，则根据L个描述信息对应的拍摄信息，确定L个描述信息聚类后的描述信息对应的拍摄信息，L为大于1的整数。
具体地说，拍摄信息包括拍摄亮度和拍摄角度。终端计算L个描述信息对应的拍摄亮度的平均值作为第一平均值，将第一平均值作为L个描述信息聚类后的描述信息对应的拍摄亮度。终端计算L个描述信息对应的拍摄角度的平均值作为第二平均值，将第二平均值作为L个描述信息聚类后的描述信息对应的拍摄角度。
以下结合实际场景，说明确定聚类后的描述信息对应的拍摄信息的过程。
例如，地图点P对应的描述信息包括第一描述信息（ka）、第二描述信息（kb）、第三描述信息（kc）、第四描述信息（kd）、第五描述信息（ke）……。其中，ka的拍摄亮度为第一拍摄亮度（hka），kb的拍摄亮度为第二拍摄亮度（hkb），kc的拍摄亮度为第三拍摄亮度（hkc）……，ka的拍摄角度为第一拍摄角度（tka），kb的拍摄角度为第二拍摄角度（tkb），kc的拍摄角度为第三拍摄角度（tkc）……通过聚类算法，ka、kb和kc被分为一类，聚类后的描述信息的拍摄亮度=（hka+hkb+hkc）/3，聚类后的描述信息的拍摄角度=（tka+tkb+tkc）/3。
步骤303：根据聚类后的描述信息，以及聚类后的描述信息对应的拍摄信息，确定地图点的特征信息集合。
值得一提的是，建立地图的过程中，对描述信息对应的拍摄信息进行记录，使得定位过程中可以通过拍摄信息筛选用于匹配的描述信息，提高了终端的定位效率。
执行步骤304。
与现有技术相比，本实施例中提供的建立地图的方法，将不同拍摄信息各自对应的地图点的特征信息存储至地图中的过程中，对地图点的描述信息进行聚类，在丰富地图中地图点的特征信息的同时，减小了地图的数据量，使得在定位过程中，能够提高拍摄的图像中地图点的特征信息与地图中地图点的特征信息匹配成功的概率，进而提高了定位能力。除此之外，建立地图的过程中，对描述信息对应的拍摄信息进行记录，使得定位过程中可以通过拍摄信息筛选用于匹配的描述信息，提高了终端的定位效率。
本申请的第四实施例涉及一种定位方法，应用于终端。如图4所示，定位方法包括：
步骤401：获取用于定位的第二图像。
步骤402：提取第二图像中的地图点的特征信息。
具体地说，终端通过图像传感器采集当前所在环境的图像，提取图像中的地图点的特征信息。
步骤403：确定地图中与第二图像中的地图点的特征信息相匹配的特征信息。
具体地说，地图中存储有地图点的特征信息集合和地图点的位置信息。终端将第二图像中的地图点的特征信息与地图中的地图点的特征信息集合进行匹配，确定相匹配的特征信息。
步骤404：从地图中获取相匹配的特征信息对应的地图点的位置信息，根据获取的位置信息确定定位结果。
具体地说，终端根据地图中的地图点与第二图像中的地图点的匹配结果，采用位姿估计算法，例如，点透视（Perspective n Points，PnP）位姿测量算法，确定定位结果。其中，定位结果中包括终端的位姿信息。
需要说明的是，终端在使用PnP位姿算法确定终端的位姿信息的过程中，可以通过光束法平差（bundle adjustment），优化计算得到的位姿信息。
与现有技术相比，本实施例中提供的定位方法，由于地图中存储有不同拍摄信息各自对应的地图点的特征信息，使得在定位过程中，能够提高拍摄的图像中地图点的特征信息与地图中地图点的特征信息匹配成功的概率，进而提高了定位能力。
本申请的第五实施例涉及一种定位方法，本实施例是对第四实施例的进一步细化，具体说明了步骤403，并在步骤404之前增加了其他相关步骤。
如图5所示，本实施例的定位方法包括步骤501至步骤507，其中，步骤501、步骤502和步骤507分别与步骤401、步骤402和步骤404大致相同，此处不再赘述，下面主要介绍不同之处：
执行步骤501和步骤502。
步骤503：确定第二图像的拍摄信息。
具体地说，第二图像的拍摄信息可以通过分析第二图像的信息确定，也可以根据终端上的传感器检测的数据确定，例如，光敏传感器在第二图像拍摄时检测到的拍摄亮度。
步骤504：根据第二图像的拍摄信息，以及地图中的地图点的特征信息集合中每个描述信息对应的拍摄信息，从地图中的地图点的特征信息集合中筛选得到用于匹配的描述信息。
具体实现中，拍摄信息包括拍摄亮度和拍摄角度。终端分别计算第二图像的拍摄亮度与每个描述信息对应的拍摄亮度的第一差值，以及第二图像的拍摄角度与每个描述信息对应的拍摄角度的第二差值；根据第一差值和第二差值，从地图点的特征信息集合中，选择M个描述信息作为用于匹配的描述信息。其中，M为正整数。
以下结合实际场景说明终端从地图中的地图点的特征信息集合中筛选得到用于匹配的描述信息的过程。
假设终端获取第二图像中的地图点的拍摄亮度为H，拍摄角度为L，地图中的地图点的特征信息集合为{（描述信息a1，拍摄亮度h1，拍摄角度l1），（描述信息a2，拍摄亮度h2，拍摄角度l2），（描述信息a3，拍摄亮度h3，拍摄角度l3）……}，即描述信息a1对应的拍摄亮度为h1，对应的拍摄角度为l1，描述信息a2对应的拍摄亮度为h2，对应的拍摄角度为l2……终端计算h1与H的差值和l1与L的差值，并根据实际需要，为两个差值设置不同的权重，从而确定第二图像中的地图点的拍摄信息与地图中的地图点的拍摄信息的距离dt，即dt=a*（H-h1）+b*（L-l1），其中，a为拍摄亮度的差值的权重，b为拍摄角度的差值权重。以此类推，终端计算第二图像的地图点的拍摄信息与地图中的地图点的特征信息集合中每个描述信息对应的拍摄信息的距离。终端按照该距离从小到大的顺序，对地图中的地图点的特征信息集合中每个描述信息进行排序，选择排在前面的前M个描述信息作为用于匹配的描述信息。
需要说明的是，本领域技术人员可以理解，实际应用中，也可以通过设置距离预设值的方法，筛选特征信息集合，即将与第二图像中的地图点的描述信息对应的拍摄信息的距离小于距离预设值的描述信息作为用于匹配的描述信息。
步骤505：从用于匹配的描述信息中，确定与第二图像中的地图点的描述信息相匹配的描述信息。
具体地说，将用于匹配的描述信息与第二图像中的地图点的描述信息匹配，确定相匹配的描述信息。
步骤506：确定第二图像中至少存在T个地图点与地图匹配成功。其中，T为正整数，例如，T等于10。
值得一提的是，在匹配成功的地图点的个数达到T后，再对终端的位姿信息进行计算，避免匹配成功个数不足，无法定位的情况下，确定定位结果造成的资源浪费。
执行步骤507。
与现有技术相比，本实施例中提供的定位方法，由于地图中存储有不同拍摄信息各自对应的地图点的特征信息，使得在定位过程中，能够提高拍摄的图像中地图点的特征信息与地图中地图点的特征信息匹配成功的概率，进而提高了定位能力。除此之外，终端根据描述信息对应的拍摄信息，对地图中的地图点的特征信息集合进行筛选，确定用于匹配的描述信息，提高了终端的定位效率。在匹配成功的地图点的个数达到T后，再对终端的位姿信息进行计算，避免匹配成功个数不足，无法定位的情况下，确定定位结果造成的资源浪费。
需要说明的是，终端建立地图的过程和定位过程的关系如图6所示。终端通过获取不同拍摄信息各自对应的地图点的特征信息建立地图，并在定位过程中，根据特定的拍摄信息，确定用于匹配的描述信息，从而确定终端的定位结果。
本申请的第六实施例涉及一种终端，如图7所示，包括至少一个处理器601；以及，与至少一个处理器601通信连接的存储器602。其中，存储器602存储有可被至少一个处理器601执行的指令，指令被至少一个处理器601执行，以使至少一个处理器601能够执行上述建立地图的方法。
本申请的第七实施例涉及一种终端，如图8所示，包括至少一个处理器701；以及，与至少一个处理器701通信连接的存储器702。其中，存储器702存储有可被至少一个处理器701执行的指令，指令被至少一个处理器701执行，以使至少一个处理器701能够执行上述定位方法。
第六实施例和第七实施例中，处理器以中央处理器（Central Processing Unit，CPU）为例，存储器以可读写存储器（Random Access Memory，RAM）为例。处理器、存储器可以通过总线或者其他方式连接，图7和图8中以通过总线连接为例。存储器作为一种非易失性计算机可读存储介质，可用于存储非易失性软件程序、非易失性计算机可执行程序以及模块，如本申请实施例中地图的描述信息就存储于存储器中。处理器通过运行存储在存储器中的非易失性软件程序、指令以及模块，从而执行设备的各种功能应用以及数据处理，即实现上述建立地图的方法或定位方法。
存储器可以包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需要的应用程序；存储数据区可存储选项列表等。此外，存储器可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他非易失性固态存储器件。在一些实施例中，存储器可选包括相对于处理器远程设置的存储器，这些远程存储器可以通过网络连接至外接设备。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
一个或者多个模块存储在存储器中，当被一个或者多个处理器执行时，执行上述任意方法实施例中的建立地图的方法或定位方法。
上述产品可执行本申请实施例所提供的方法，具备执行方法相应的功能模块和有益效果，未在本实施例中详尽描述的技术细节，可参见本申请实施例所提供的方法。
本申请的第八实施例涉及一种计算机可读存储介质，存储有计算机程序。计算机程序被处理器执行时实现以上任意方法实施例所描述的建立地图的方法。
本申请的第八实施例涉及一种计算机可读存储介质，存储有计算机程序。计算机程序被处理器执行时实现以上任意方法实施例所描述的定位方法。
即，本领域技术人员可以理解，实现上述实施例方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成，该程序存储在一个存储介质中，包括若干指令用以使得一个设备（可以是单片机，芯片等）或处理器（processor）执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器（ROM，Read-Only Memory）、随机存取存储器（RAM，Random Access Memory）、磁碟或者光盘等各种可以存储程序代码的介质。
本领域的普通技术人员可以理解，上述各实施例是实现本申请的具体实施例，而在实际应用中，可以在形式上和细节上对其作各种改变，而不偏离本申请的精神和范围。

Claims (13)

  1. 一种建立地图的方法，其中，包括：
    获取地图点的位置信息和地图点的N幅第一图像；其中，所述N幅第一图像各自对应的拍摄信息不同，N为大于1的整数；
    根据所述N幅第一图像中的地图点的特征信息，确定所述地图点的特征信息集合；
    根据所述地图点的特征信息集合以及所述地图点的位置信息，建立地图，其中，所述地图中存储有所述地图点的特征信息集合和所述地图点的位置信息。
  2. 根据权利要求1所述的建立地图的方法，其中，所述地图点的特征信息包括所述地图点的描述信息；
    所述根据所述N幅第一图像中的地图点的特征信息，确定所述地图点的特征信息集合，具体包括：
    通过聚类算法对所述N幅第一图像中的地图点的描述信息进行聚类，确定聚类后的描述信息；
    根据所述聚类后的描述信息，确定所述地图点的特征信息集合。
  3. 根据权利要求1所述的建立地图的方法，其中，所述地图点的特征信息包括所述地图点的描述信息，以及所述地图点的描述信息对应的拍摄信息；
    所述根据所述N幅第一图像中的地图点的特征信息，确定所述地图点的特征信息集合，具体包括：
    通过聚类算法对所述N幅第一图像中的地图点的描述信息进行聚类，确定聚类后的描述信息，以及确定所述聚类后的描述信息对应的拍摄信息；其中，若通过所述聚类算法将L个描述信息聚为一类，则根据所述L个描述信息对应的拍摄信息，确定所述L个描述信息聚类后的描述信息对应的拍摄信息，L为大于1的整数；
    根据所述聚类后的描述信息，以及所述聚类后的描述信息对应的拍摄信息，确定所述地图点的特征信息集合。
  4. 根据权利要求3所述的建立地图的方法，其中，所述拍摄信息包括拍摄亮度和拍摄角度；
    所述根据所述L个描述信息对应的拍摄信息，确定所述L个描述信息聚类后的描述信息对应的拍摄信息，具体包括：
    计算所述L个描述信息对应的拍摄亮度的平均值作为第一平均值，将所述第一平均值作为所述L个描述信息聚类后的描述信息对应的拍摄亮度；
    计算所述L个描述信息对应的拍摄角度的平均值作为第二平均值，将所述第二平均值作为所述L个描述信息聚类后的描述信息对应的拍摄角度。
  5. 根据权利要求1至4任一项所述的建立地图的方法，其中，在所述根据所述N幅第一图像中的地图点的特征信息，确定所述地图点的特征信息集合之前，所述建立地图的方法还包括：
    提取每幅第一图像中的地图点的特征信息。
  6. 一种定位方法，其中，包括：
    获取用于定位的第二图像；
    提取所述第二图像中的地图点的特征信息；
    确定地图中与所述第二图像中的地图点的特征信息相匹配的特征信息；其中，所述地图中存储有地图点的特征信息集合和地图点的位置信息；
    从所述地图中获取所述相匹配的特征信息对应的地图点的位置信息，根据获取的位置信息确定定位结果。
  7. 根据权利要求6所述的定位方法，其中，所述地图点的特征信息包括所述地图点的描述信息，以及所述地图点的描述信息对应的拍摄信息；
    所述确定地图中与所述第二图像中的地图点的特征信息相匹配的特征信息，具体包括：
    确定所述第二图像的拍摄信息；
    根据所述第二图像的拍摄信息，以及所述地图中的地图点的特征信息集合中每个描述信息对应的拍摄信息，从所述地图中的地图点的特征信息集合中筛选得到用于匹配的描述信息；
    从所述用于匹配的描述信息中，确定与所述第二图像中的地图点的描述信息相匹配的描述信息。
  8. 根据权利要求7所述的定位方法，其中，所述拍摄信息包括拍摄亮度和拍摄角度；
    所述根据所述第二图像的拍摄信息，以及所述地图中的地图点的特征信息集合中每个描述信息对应的拍摄信息，从所述地图中的地图点的特征信息集合中筛选得到用于匹配的描述信息，具体包括：
    分别计算所述第二图像的拍摄亮度与每个描述信息对应的拍摄亮度的第一差值，以及所述第二图像的拍摄角度与每个描述信息对应的拍摄角度的第二差值；
    根据所述第一差值和所述第二差值，从所述地图点的特征信息集合中，选择M个描述信息作为所述用于匹配的描述信息；其中，M为正整数。
  9. 根据权利要求6至8任一项所述的定位方法，其中，在所述确定地图中与所述第二图像中的地图点的特征信息相匹配的特征信息之后，在所述根据获取的位置信息确定定位结果之前，所述定位方法还包括：
    确定所述第二图像中至少存在T个地图点与所述地图匹配成功，其中，T为正整数。
  10. 一种终端，其中，包括至少一个处理器；以及，
    与所述至少一个处理器通信连接的存储器；其中，所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行如权利要求1至5任一项所述的建立地图的方法。
  11. 一种终端，其中，包括至少一个处理器；以及，
    与所述至少一个处理器通信连接的存储器；其中，所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行如权利要求6至9任一项所述的定位方法。
  12. 一种计算机可读存储介质，存储有计算机程序，其中，所述计算机程序被处理器执行时实现权利要求1至5任一项所述的建立地图的方法。
  13. 一种计算机可读存储介质，存储有计算机程序，其中，所述计算机程序被处理器执行时实现权利要求6至9任一项所述的定位方法。
PCT/CN2018/094331 2018-07-03 2018-07-03 建立地图的方法、定位方法、终端及计算机可读存储介质 Ceased WO2020006686A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201880001106.XA CN109074676B (zh) 2018-07-03 2018-07-03 建立地图的方法、定位方法、终端及计算机可读存储介质
PCT/CN2018/094331 WO2020006686A1 (zh) 2018-07-03 2018-07-03 建立地图的方法、定位方法、终端及计算机可读存储介质

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2018/094331 WO2020006686A1 (zh) 2018-07-03 2018-07-03 建立地图的方法、定位方法、终端及计算机可读存储介质

Publications (1)

Publication Number Publication Date
WO2020006686A1 true WO2020006686A1 (zh) 2020-01-09

Family

ID=64789259

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/094331 Ceased WO2020006686A1 (zh) 2018-07-03 2018-07-03 建立地图的方法、定位方法、终端及计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN109074676B (zh)
WO (1) WO2020006686A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2020014941A1 (zh) * 2018-07-20 2020-01-23 深圳前海达闼云端智能科技有限公司 一种建立地图的方法、定位方法、装置、终端及存储介质
CN113099114A (zh) * 2021-04-02 2021-07-09 上海有个机器人有限公司 远程查看机器人摄像头方法、装置、终端及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160379092A1 (en) * 2015-06-26 2016-12-29 Intel Corporation System for building a map and subsequent localization
CN106909877A (zh) * 2016-12-13 2017-06-30 浙江大学 一种基于点线综合特征的视觉同时建图与定位方法
CN107204015A (zh) * 2017-05-27 2017-09-26 中山大学 基于色彩图像和红外图像融合的即时定位与建图系统
CN107223244A (zh) * 2016-12-02 2017-09-29 深圳前海达闼云端智能科技有限公司 定位方法和装置

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103424113B (zh) * 2013-08-01 2014-12-31 毛蔚青 移动终端基于图像识别技术的室内定位与导航方法
JP6842618B2 (ja) * 2015-12-14 2021-03-17 インターナショナル・ビジネス・マシーンズ・コーポレーションＩｎｔｅｒｎａｔｉｏｎａｌ Ｂｕｓｉｎｅｓｓ Ｍａｃｈｉｎｅｓ Ｃｏｒｐｏｒａｔｉｏｎ ３ｄマップの作成

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160379092A1 (en) * 2015-06-26 2016-12-29 Intel Corporation System for building a map and subsequent localization
CN107223244A (zh) * 2016-12-02 2017-09-29 深圳前海达闼云端智能科技有限公司 定位方法和装置
CN106909877A (zh) * 2016-12-13 2017-06-30 浙江大学 一种基于点线综合特征的视觉同时建图与定位方法
CN107204015A (zh) * 2017-05-27 2017-09-26 中山大学 基于色彩图像和红外图像融合的即时定位与建图系统

Also Published As

Publication number Publication date
CN109074676A (zh) 2018-12-21
CN109074676B (zh) 2023-07-07

Similar Documents

Publication Publication Date Title
US20200334499A1 (en) Vision-based positioning method and aerial vehicle
CN110533694B (zh) 图像处理方法、装置、终端及存储介质
CN106683071B (zh) 图像的拼接方法和装置
CN112884256B (zh) 路径规划方法、装置、计算机设备和存储介质
EP3308323B1 (en) Method for reconstructing 3d scene as 3d model
WO2019076304A1 (zh) 基于双目相机的无人机视觉slam方法、无人机及存储介质
WO2020006685A1 (zh) 一种建立地图的方法、终端和计算机可读存储介质
CN110399789B (zh) 行人重识别方法、模型构建方法、装置、设备和存储介质
KR20180054487A (ko) Dvs 이벤트 처리 방법 및 장치
CN111127524A (zh) 一种轨迹跟踪与三维重建方法、系统及装置
CN113298871B (zh) 地图生成方法、定位方法及其系统、计算机可读存储介质
CN111767839B (zh) 一种车辆行驶轨迹确定方法、装置、设备及介质
CN111079535B (zh) 一种人体骨架动作识别方法、装置及终端
WO2024083010A9 (zh) 一种视觉定位方法及相关装置
CN111815672A (zh) 动态跟踪控制方法、装置及控制设备
WO2020006686A1 (zh) 建立地图的方法、定位方法、终端及计算机可读存储介质
CN114723883A (zh) 一种三维场景重建方法、装置、设备及存储介质
CN110348351A (zh) 一种图像语义分割的方法、终端和可读存储介质
CN115329111B (zh) 一种基于点云与影像匹配的影像特征库构建方法及系统
WO2020014941A1 (zh) 一种建立地图的方法、定位方法、装置、终端及存储介质
CN112257666B (zh) 目标图像内容的聚合方法、装置、设备及可读存储介质
CN113674331B (zh) 图像对齐方法和装置、电子设备和计算机可读存储介质
CN111161397B (zh) 人脸三维重建方法、装置、电子设备及可读存储介质
WO2025016092A1 (zh) 视觉定位方法、装置、设备及介质
CN115731260A (zh) 特征匹配方法及装置、场景重建方法及装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18925232

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 17.05.2021)

122 Ep: pct application non-entry in european phase

Ref document number: 18925232

Country of ref document: EP

Kind code of ref document: A1