WO2020135326A1 - 一种基于图片的方向标注方法及装置 - Google Patents

一种基于图片的方向标注方法及装置 Download PDF

Info

Publication number
WO2020135326A1
WO2020135326A1 PCT/CN2019/127399 CN2019127399W WO2020135326A1 WO 2020135326 A1 WO2020135326 A1 WO 2020135326A1 CN 2019127399 W CN2019127399 W CN 2019127399W WO 2020135326 A1 WO2020135326 A1 WO 2020135326A1
Authority
WO
WIPO (PCT)
Prior art keywords
street view
information
view data
unit
road
Prior art date
Application number
PCT/CN2019/127399
Other languages
English (en)
French (fr)
Inventor
安建军
Original Assignee
阿里巴巴集团控股有限公司
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 阿里巴巴集团控股有限公司 filed Critical 阿里巴巴集团控股有限公司
Publication of WO2020135326A1 publication Critical patent/WO2020135326A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29—Geographical information databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
    • G06T17/05—Geographic models
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/176—Urban or other man-made structures

Definitions

  • the present invention relates to the field of image processing technology, and in particular, to a method and device for marking directions based on pictures.
  • the compass In daily life, people need to determine how to travel to reach their destination by the location of their location (east, west, south, north), such as finding tourist attractions when traveling. This need for direction has been around since ancient times, and one of China’s four inventions, the compass, is a solution. Now with the development of technology, the sensor-based electronic compass has become a substitute for compass.
  • the compass or the electronic compass can only give the user a single direction (north) indication, and cannot give an intuitive and explicit direction indication in combination with the street building where the user is currently located.
  • the direction indication information of the electronic compass it is difficult to convert it into an effective application in the actual environment, and the user still needs to match the orientation.
  • the user wants to distinguish the current road direction he needs to use the electronic compass
  • the direction indication information is converted into the current road direction, which is difficult for users who are not familiar with the direction recognition, and it is also very inconvenient to use.
  • the present invention proposes a picture-based direction labeling method and device.
  • the main purpose is to provide street users with real-time direction reference information using street view pictures.
  • the present invention mainly provides the following technical solutions:
  • the present invention provides a picture-based direction marking method, which specifically includes:
  • street view photos and location information of the street view photos where the street view photos contain at least image information of roads and buildings;
  • the present invention provides a picture-based direction marking device, which specifically includes:
  • a receiving unit configured to receive street view photos and location information of the street view photos, where the street view photos contain at least image information of roads and buildings;
  • An obtaining unit configured to obtain street view data within a preset range according to the location information received by the receiving unit
  • An extraction unit for extracting the image information in the street view photo received by the receiving unit
  • a matching unit configured to match the image information extracted by the extraction unit with the street view data acquired by the acquisition unit;
  • a parsing unit used for parsing the direction information corresponding to the street view data successfully matched by the matching unit
  • a direction labeling unit which is used to mark the direction signs of roads and buildings in the street view photos according to the direction information analyzed by the analyzing unit;
  • the sending unit is used to send a street view photo containing the direction label marked by the direction labeling unit.
  • the present invention provides a storage medium for storing a computer program, wherein, when the computer program is running, it controls the device where the storage medium is located to perform the above-mentioned image-based direction labeling method.
  • the present invention provides a processor for running a computer program, where the computer program executes the above image-based direction annotation method when the computer program is running.
  • the present invention provides a picture-based direction labeling method and device, according to the location information corresponding to receiving the street view photo, find the street view data matching the street view photo, and extract the successful matching street view data Contain the direction information, mark the direction information on the street view photos, and then feed back to the user a street view photo marked with direction signs.
  • the user only needs to send a photo of the road and buildings on the street near the current location at the location where the direction needs to be distinguished, and can receive the picture marked with the direction logo on the photo, without the user using the electronic
  • the compass comes to check the direction, and then recognize the direction of the road in the street view or the orientation of the building.
  • FIG. 1 shows a flowchart of a picture-based direction labeling method according to an embodiment of the present invention
  • FIG. 2 shows a flowchart of another image-based direction labeling method according to an embodiment of the present invention
  • FIG. 3 shows a schematic diagram of a street view photo marked with a direction sign according to an embodiment of the present invention
  • FIG. 4 shows a block diagram of a composition of a picture-based direction labeling device according to an embodiment of the present invention
  • FIG. 5 shows a block diagram of another picture-based direction labeling device according to an embodiment of the present invention.
  • Embodiments of the present invention provide a picture-based direction labeling method.
  • the method is generally applied to a server with powerful picture calculation and processing capabilities, receives street view photos sent by a user terminal for processing, and then marks the direction marked Photo feedback to users.
  • the specific steps are shown in Figure 1.
  • the method includes:
  • Step 101 Receive a street view photo and location information of the street view photo.
  • the received street view photos contain at least image information of roads and buildings. That is, there are certain content requirements for the street view photos taken by the user. First, if it is a street view, this is because the present invention is based on a database that collects a large amount of street view data to identify the direction of the scene. Therefore, the user needs to send a street view Photos are not recognizable for indoor photos or landscape photos or the recognition accuracy is low. Secondly, the content of the street view photos taken must have at least image information such as roads and/or buildings. This is the core content of identifying specific directions in the street view photos. Generally, roads have clear directionality. The direction marking can make it easy for the user to understand the specific orientation, and the building has features that are easy to identify, and can quickly and accurately match the street view photos with the stored street view data.
  • the location information where the street view photo is located may be the location information obtained by the user through the positioning device when taking the street view photo, and the location information is sent along with the street view photo. It may also be position information determined by recognizing roads or buildings therein through image recognition technology. In the case of positioning information, the location information is mainly used to initially determine the location range of the scene in the street view photo, so as to narrow the matching range of the subsequent street view data.
  • Step 102 Acquire street view data within a preset range according to location information.
  • the preset range is an empirical setting value, which is mainly used to avoid positioning errors caused by position information during positioning.
  • the positioning information is taken as the center of the circle, and a range is determined with the preset setting value as the radius, which is defined as the preset range. Acquire corresponding street view data within the preset range.
  • Step 103 Extract image information in a street view photo and match it with street view data.
  • the image information is roads and buildings taken in street view photos
  • street view data is street view data including roads, buildings and other content collected in advance in the database.
  • this step can be divided into two steps of extracting image information of street view photos and matching operation of image information and street view data.
  • image recognition algorithms such as the algorithm based on image feature comparison, to compare the features in street view photos with the features and preset roads and buildings to identify street view photos Which part is a road and which part is a building.
  • the invention does not limit the specific image recognition algorithm used.
  • matching image information with street scene data it can be implemented by an image matching algorithm, such as a gray matching algorithm or a feature-based matching algorithm.
  • image matching algorithm such as a gray matching algorithm or a feature-based matching algorithm.
  • the specific algorithm used is not limited in the present invention.
  • the text information in the street view photos it is preferable to identify the text information in the street view photos through an image recognition algorithm, which may be the name of the road or The name of the building. Because, in the matching operation, the accuracy of matching the text information is the highest. For example, if the road name or building name in the figure is recognized, the road or building can be determined very accurately without the need for further According to the features in the captured street view image, which road or which building is matched from the street view data is matched. However, there may be a large amount of text information in a street view photo. Therefore, it is necessary to filter the recognized text information to determine whether the text information contains the name of the road or building. If so, use these again. The name of the road or building matches the street view data within the preset range.
  • the matching is successful, indicating that the current location of the user can be found in the street view data within the preset range.
  • the matching fails , That is, there is no data that matches the image information in the street view data within the preset range.
  • the preset range in step 102 can be appropriately enlarged, Obtain the extended range of street view data and then perform the matching operation in this step.
  • the specific expanded range value can be determined by a preset value, which is an empirical value. The determination of the preset value will mainly refer to the expanded range of street view data The increment size and positioning offset are set.
  • Step 104 Analyze the direction information corresponding to the successfully matched street view data.
  • the street view data collected in the database all correspond to the location information, and according to the street view data matched successfully, the relative position of each scene in the street view photo can be calculated to obtain the corresponding direction information.
  • the direction information may include four directions of east, south, west and north set with reference to the position where the street view photo is taken.
  • Step 105 Mark direction signs of roads and buildings in street view photos according to direction information.
  • This step is to mark specific direction information on the basis of street view photos, and the method and form of marking are not specifically limited. It is common to mark direction signs on roads and buildings to facilitate user reading and identification.
  • Step 106 Send a street view photo containing direction signs.
  • the street view photos marked with direction signs are fed back to the user.
  • the image-based direction labeling method mainly matches the roads and buildings in the street view photos sent by the user through image recognition, and calculates the roads and buildings relative to The direction information of the location where the street view photo is taken, and then add the direction information to the street view photo in the form of a direction mark, so as to mark the direction mark on the street view photo.
  • the user can receive a street view photo containing a direction sign at the shooting location, and directly identify the direction corresponding to the actual scene in the manner of the street view photo.
  • the embodiments of the present invention are simpler and easier to use, without requiring users to learn how to use them, and the directions matched by the present invention are obtained by matching street view data stored in a database.
  • the accuracy is higher, and there will be no problem of inaccurate direction recognition caused by the use of electronic compass or compass due to the magnetic field.
  • the embodiment of the present invention will specifically describe the matching of street view photos with three-dimensional street view data in the database in conjunction with FIG. 2 And mark the direction of the street view photo feedback to the user.
  • the method is shown in Figure 2 and includes:
  • Step 201 Acquire 3D stereoscopic street view data within a preset range according to location information.
  • the database storing the street view data collects a three-dimensional street view data set.
  • Different data sets correspond to different geographic locations.
  • the data set may be a country, region, or city as a unit, or It is a data set that is based on geographic regions divided by latitude, longitude, altitude and other parameters.
  • Each data set stores three-dimensional street view data corresponding to all roads in the geographic area.
  • This step is based on the location information of the street view photos taken and sent by the user in real time, and matched to the corresponding 3D stereoscopic street view data set. From this data set, the street view data corresponding to the specific location can be further extracted according to the location information.
  • Step 202 Match image information in the three-dimensional street view data using an image matching algorithm.
  • the image information in the street view photo can be matched with the determined three-dimensional street view data through an image matching algorithm, and the specific algorithm for image matching is not limited, such as a gray-scale matching algorithm or a feature-based matching algorithm.
  • the three-dimensional street view data is a data set with a certain range, that is, it can be regarded as a data set composed of data from multiple location points, so the purpose of this step is to match the street view photos with the data set
  • the specific location points of the image information matched by the image information, the specific matching process is to convert the three-dimensional stereoscopic street view data of each location point into two-dimensional pictures of different angles, and then calculate the similarity with the image information in the street view photos. When the degree value reaches the threshold, it is determined that the street view photo successfully matches the corresponding three-dimensional stereoscopic street view data.
  • Step 203 Calculate the direction information of the road and/or building in the successfully matched three-dimensional street view data based on the three-dimensional coordinate system.
  • the position information of the position point can be calculated by the 3D stereoscopic coordinate system, where the 3D stereoscopic coordinate system It is set based on geographic direction. Therefore, the directions of roads and buildings in the three-dimensional street view data can be calculated.
  • the calculated direction is the direction information on the two-dimensional plane where the street view photo is located.
  • Step 204 Mark a road direction mark along the direction of the road on the road of the street view photo, and mark a direction mark relative to the road above the building.
  • the image information in this figure is mainly roads and buildings on both sides of the road.
  • Street view photos that is, using image recognition algorithms to extract street view photos
  • Roads and buildings commonly used image recognition algorithms such as the ORB algorithm based on feature matching
  • extract roads and building display areas in street view photos and determine the roads and buildings in street view photos based on the direction information calculated in step 203
  • the direction of the thing, where the direction of the road is determined according to the direction of the road, and the direction of the building is determined relative to the road.
  • the direction of the road is from bottom to top, from south to north, and the two The buildings on the side are also marked with corresponding direction signs in the vicinity of the displayed area for users to use as direction reference.
  • the direction sign is marked on a street view photo with specified information (roads and buildings), which is convenient for the user to identify the direction.
  • the implementation of the present invention is mainly based on the matching of a large amount of street view data with the content in the street view photos, based on the powerful computing power of the server, the street view data that has been successfully matched is parsed to obtain the corresponding direction information, and then marked on the street view photos Direction sign.
  • the present invention can also be executed on the user's terminal.
  • the photo marked with the direction logo is directly obtained, or in the user's framing frame It directly analyzes the framed image and displays the corresponding direction information. In this way, the operation process required by the user when recognizing the direction of the scene can be more simplified, and the user can easily recognize the specific direction of the current location.
  • an embodiment of the present invention provides a picture-based direction tagging device, which can feed back a street view photo marked with a direction mark to the user based on the street view photo taken by the user. To help users identify the direction of the current location.
  • this embodiment of the device will not repeat the details in the foregoing method embodiments one by one, but it should be clear that the device in this embodiment can correspondingly implement all the contents in the foregoing method embodiments.
  • the device is shown in Figure 4 and specifically includes:
  • the receiving unit 31 is configured to receive a street view photo and location information of the street view photo, where the street view photo contains at least image information of roads and buildings;
  • the obtaining unit 32 is configured to obtain street view data within a preset range according to the location information received by the receiving unit 31;
  • An extracting unit 33 configured to extract image information in the street view photo received by the receiving unit 31;
  • the matching unit 34 is configured to match the image information extracted by the extraction unit 33 with the street view data acquired by the acquisition unit 32;
  • the parsing unit 35 is used to parse the direction information corresponding to the street view data successfully matched by the matching unit 34;
  • the direction labeling unit 36 is configured to label the direction signs of roads and buildings in the street view photo according to the direction information analyzed by the analyzing unit 35;
  • the sending unit 37 is used to send a street view photo containing the direction label marked by the direction labeling unit 36.
  • the obtaining unit 32 is further configured to expand the preset range according to a preset value when the matching unit 34 fails to match the image information in the street view photo with the street view data, And obtain the street view data included after expanding the preset range.
  • the extraction unit 33 includes:
  • the recognition module 331 is used for recognizing the text information in the street view photo by using an image recognition algorithm
  • the judgment module 332 is used to judge whether the text information recognized by the recognition module 331 contains the name of the road or the building;
  • the extracting module 333 is configured to extract the name as image information in the street view photo when the determining module 332 determines that the name includes a road or a building.
  • the acquiring unit 32 is further configured to acquire three-dimensional stereoscopic street scene data within a preset range
  • the matching unit 34 is further configured to match the image information in the three-dimensional street view data using an image matching algorithm
  • the parsing unit 35 is also used to calculate the direction information of the road and/or building in the three-dimensional stereoscopic street view data that is successfully matched based on the three-dimensional stereoscopic coordinate system.
  • the direction labeling unit 36 includes:
  • the recognition module 361 is used to recognize the roads and buildings in the street view photos by using an image recognition algorithm
  • the direction labeling module 362 is configured to label a road direction identifier along the direction of the road on the road identified by the recognition module according to the direction information of the road and/or building in the three-dimensional street view data. A direction sign relative to the road is marked above the building to obtain a street view photo marked with the direction sign.
  • the image-based direction labeling method and device adopted in the embodiments of the present invention use image recognition and matching techniques to match corresponding data from a large amount of street view data on street view photos taken by users.
  • the direction indicator is marked, so that the user can directly read the corresponding direction information on the processed street view photo, which helps the user to quickly and simply identify the direction under the current scene.
  • the principle of the present invention is different from the existing method in the process of identifying the direction, so it will not be disturbed by magnetic field factors, and its accuracy is higher .
  • the operation process of the present invention is very simple.
  • the operation process for the user is the same as that of taking a photo, the difference is that the user needs to clarify the content to be taken to ensure the accuracy of data matching and identification. It can be seen that the direction labeling method and device proposed by the present invention provide users with a new direction recognition idea, which simplifies user operations, and also makes full use of the powerful data storage and computing capabilities of the server to make the direction marked for users More accurate.
  • an embodiment of the present invention further provides a storage medium for storing a computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to perform the above image-based direction labeling method.
  • an embodiment of the present invention further provides a processor for running a computer program, wherein, when the computer program runs, the above image-based direction annotation method is executed.
  • the memory may include non-permanent memory, random access memory (RAM) and/or non-volatile memory in computer-readable media, such as read only memory (ROM) or flash memory (flash RAM), and the memory includes At least one memory chip.
  • RAM random access memory
  • ROM read only memory
  • flash RAM flash random access memory
  • the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program code.
  • computer usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
  • These computer program instructions may also be stored in a computer readable memory that can guide a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, the instructions
  • the device implements the functions specified in one block or multiple blocks of the flowchart one flow or multiple flows and/or block diagrams.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operating steps are performed on the computer or other programmable device to produce computer-implemented processing, which is executed on the computer or other programmable device
  • the instructions provide steps for implementing the functions specified in one block or multiple blocks of the flowchart one flow or multiple flows and/or block diagrams.
  • the computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
  • processors CPUs
  • input/output interfaces network interfaces
  • memory volatile and non-volatile memory
  • the memory may include non-permanent memory, random access memory (RAM) and/or non-volatile memory in a computer-readable medium, such as read only memory (ROM) or flash memory (flash RAM).
  • RAM random access memory
  • ROM read only memory
  • flash RAM flash memory
  • Computer readable media including permanent and non-permanent, removable and non-removable media, can store information by any method or technology.
  • the information may be computer readable instructions, data structures, modules of programs, or other data.
  • Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, read-only compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, Magnetic tape cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media can be used to store information that can be accessed by computing devices.
  • computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.
  • the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program code.
  • computer usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Geometry (AREA)
  • Remote Sensing (AREA)
  • Computer Graphics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Databases & Information Systems (AREA)
  • Multimedia (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Image Analysis (AREA)

Abstract

一种基于图片的方向标注方法及装置，用于识别方向，其目的在于利用街景图片为用户提供实时的方向参考信息。所述方法包括：接收街景照片以及所述街景照片所在的位置信息（101），所述街景照片中至少含有道路和建筑物的图像信息；根据所述位置信息获取预置范围内的街景数据（102）；提取所述街景照片中的图像信息，与所述街景数据进行匹配（103）；解析匹配成功的街景数据对应的方向信息（104）；根据所述方向信息在所述街景照片中标注道路和建筑物的方向标识（105）；发送含有所述方向标识的街景照片（106）。

Description

一种基于图片的方向标注方法及装置
本申请要求2018年12月29日递交的申请号为201811646747.9、发明名称为“一种基于图片的方向标注方法及装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本发明涉及图像处理技术领域，尤其涉及一种基于图片的方向标注方法及装置。
背景技术
日常生活中，人们需要通过自身所处位置的方位(东西南北)来判断如何行进到达目的地，比如外出旅行时找寻旅游景点。这种对方向的需求自古已有，中国四大发明之一指南针便是一种解决方案。现在随着科技的发展，基于传感器的电子罗盘则成了指南针的替代品。
但是无论指南针还是电子罗盘，都只能给用户单一的方向(北)指示，无法结合当前用户所处位置的街道建筑给出直观显式的方位指示。使得用户在得到电子罗盘的方向指示信息后，也难以将其转换为有效地应用于实际环境中，依然需要用户进行方位的匹配，比如，用户要分辨当前道路的走向时，就需要将电子罗盘的方向指示信息转换为当前道路走向，这对于不熟悉方向识别的用户，具有一定操作难度，使用也十分不便。
发明内容
鉴于上述问题，本发明提出了一种基于图片的方向标注方法及装置，主要目的在于利用街景图片为用户提供实时的方向参考信息。
为达到上述目的，本发明主要提供如下技术方案：
一方面，本发明提供一种基于图片的方向标注方法，具体包括：
接收街景照片以及所述街景照片所在的位置信息，所述街景照片中至少含有道路和建筑物的图像信息；
根据所述位置信息获取预置范围内的街景数据；
提取所述街景照片中的图像信息，与所述街景数据进行匹配；
解析匹配成功的街景数据对应的方向信息；
根据所述方向信息在所述街景照片中标注道路和建筑物的方向标识；
发送含有所述方向标识的街景照片。
另一方面，本发明提供一种基于图片的方向标注装置，具体包括：
接收单元，用于接收街景照片以及所述街景照片所在的位置信息，所述街景照片中至少含有道路和建筑物的图像信息；
获取单元，用于根据所述接收单元接收的位置信息获取预置范围内的街景数据；
提取单元，用于提取所述接收单元接收的街景照片中的图像信息；
匹配单元，用于将所述提取单元提取的图像信息与所述获取单元获取的街景数据进行匹配；
解析单元，用于解析经过所述匹配单元匹配成功的街景数据对应的方向信息；
方向标注单元，用于根据所述解析单元解析的方向信息在所述街景照片中标注道路和建筑物的方向标识；
发送单元，用于发送含有所述方向标注单元标注的方向标识的街景照片。
另一方面，本发明提供一种存储介质，所述存储介质用于存储的计算机程序，其中，所述计算机程序运行时控制所述存储介质所在设备执行上述的基于图片的方向标注方法。
另一方面，本发明提供一种处理器，所述处理器用于运行计算机程序，其中，所述计算机程序运行时执行上述的基于图片的方向标注方法。
借由上述技术方案，本发明提供的一种基于图片的方向标注方法及装置，根据接收拍摄该街景照片所对应的位置信息，查找与街景照片相匹配街景数据，并提取匹配成功的街景数据中所含有的方向信息，将该方向信息标注在街景照片上，再反馈给用户一张标记有方向标识的街景照片。通过本方案，用户仅需要在需要辨别方向的位置发送一张拍摄有当前位置附近的道路以及街边建筑物的照片，就可以收到在该照片上标注有方向标识的图片，无需用户使用电子罗盘来校对方向，进而识别街景中道路的走向或建筑物的方位。通过使用图像识别与匹配的方法帮助用户快速的识别当前位置的具体方向，对于用户的使用而言简单易用，能够提升用户的使用体验。
上述说明仅是本发明技术方案的概述，为了能够更清楚了解本发明的技术手段，而可依照说明书的内容予以实施，并且为了让本发明的上述和其它目的、特征和优点能够更明显易懂，以下特举本发明的具体实施方式。
附图说明
通过阅读下文优选实施方式的详细描述，各种其他的优点和益处对于本领域普通技术人员将变得清楚明了。附图仅用于示出优选实施方式的目的，而并不认为是对本发明的限制。而且在整个附图中，用相同的参考符号表示相同的部件。在附图中：
图1示出了本发明实施例提出的一种基于图片的方向标注方法的流程图；
图2示出了本发明实施例提出的另一种基于图片的方向标注方法的流程图；
图3示出了本发明实施例标注有方向标识的街景照片示意图；
图4示出了本发明实施例提出的一种基于图片的方向标注装置的组成框图；
图5示出了本发明实施例提出的另一种基于图片的方向标注装置的组成框图。
具体实施方式
下面将参照附图更详细地描述本发明的示例性实施例。虽然附图中显示了本发明的示例性实施例，然而应当理解，可以以各种形式实现本发明而不应被这里阐述的实施例所限制。相反，提供这些实施例是为了能够更透彻地理解本发明，并且能够将本发明的范围完整的传达给本领域的技术人员。
本发明实施例提供了一种基于图片的方向标注方法，该方法一般应用于具有强大图片计算与处理能力的服务端，接收用户终端所发送的街景照片进行处理，之后再将标记有方向标识的照片反馈给用户。具体步骤如图1所示，该方法包括：
步骤101、接收街景照片以及该街景照片所在的位置信息。
其中，所接收的街景照片中至少含有道路和建筑物的图像信息。即，对用户所拍摄的街景照片需要有一定的内容要求，首先，要是街景，这是因为，本发明是基于收集有大量街景数据的数据库来识别场景方向的，因此，用户需要发送的是街景照片，对于像室内照片或风景照片是不能够识别的或者识别的准确率是较低的。其次，所拍摄的街景照片的内容中，至少要具有道路和/或建筑物等图像信息，这是识别该街景照片中具体方向的核心内容，一般地，道路具有较明确的方向指向性，对其标注方向标识可以让用户容易理解具体的方位，而建筑物具有便于识别的特征，可以快速、准确地将街景照片与存储的街景数据进行数据匹配。
此外，街景照片所在的位置信息可以是用户在拍摄街景照片时通过定位装置获取的定位信息，并将该定位信息随街景照片一同发出。也可以是通过图像识别技术对其中的道路或建筑物识别后所确定的位置信息。若为定位信息，该位置信息主要用于初步确定街景照片中景物的位置范围，以便缩小后续街景数据的匹配范围。
步骤102、根据位置信息获取预置范围内的街景数据。
其中，预置范围是一个经验设定值，其主要用于避免位置信息在定位过程中产生的定位误差。具体实现时，一般是以定位信息为圆心，以预设的设定值为半径确定一个范围，定义其为预置范围。在该预置范围内获取对应的街景数据。
步骤103、提取街景照片中的图像信息，与街景数据进行匹配。
其中，该图像信息为街景照片中拍摄的道路以及建筑物等内容，而街景数据则是存储在数据库中预先采集的包括道路、建筑物等内容的街景数据。
具体地，本步骤可分为对街景照片的图像信息提取操作，以及图像信息与街景数据匹配操作两个步骤。对于提取街景照片中的图像信息，可以通过图像识别算法，如基于图像特征对比的算法，将街景照片中的特征与预置的道路、建筑物的特征及进行对比，以此来识别街景照片中哪部分为道路，哪些部分为建筑物。本发明不限定所采用的具体图像识别算法。
而对于图像信息与街景数据匹配的操作，则可通过图像匹配算法实现，如灰度匹配算法或者是基于特征的匹配算法，具体使用的算法在本发明中不做限定。
进一步的，在本发明的一个优选实施例中，对于所提取的街景照片中的图像信息，优选的是通过图像识别算法来识别街景照片中的文字信息，该文字信息可以是道路的名称或者是建筑物的名称。因为，在进行匹配操作时，对文字信息匹配的准确率是最高的，比如，如果识别出图中的道路名称，或建筑物名称，就可以很准确地确定该道路或建筑物，而无需再根据所拍摄的街景图像中的特征从街景数据匹配是哪条道路或是哪座建筑物。然而，一幅街景照片中可能存在有大量的文字信息，为此，需要对所识别出的文字信息进行过滤，以判断这些文字信息中是否含有道路或建筑物的名称，若含有，再用这些道路或建筑物的名称与预置范围内的街景数据进行匹配。
经过本步骤的处理，存在有两种处理结果，一种是匹配成功，说明在预置范围内的街景数据中可以找到用户的当前位置，此时，继续执行步骤104；另一种是匹配失败，即在预置范围内的街景数据中没有与图像信息相匹配的数据，此时，很可能是由于定位偏移所导致的，因此，可以将步骤102中的预置范围进行适当放大后，获取扩大范围的街景数据再执行本步骤中的匹配操作，其中，对于范围具体扩大的值可通过预设值确定，为一经验值，该预设值的确定主要会参考扩大范围后的街景数据增量大小以及定位偏移量的大小而设置。对于匹配失败的情况，可以通过反复放大获取街景数据的预置范围进行匹配，直至匹配成功，或始终无法匹配成功时，向用户发送街景照片无法匹配的信息， 以告知用户其拍摄的街景照片有问题。
步骤104、解析匹配成功的街景数据对应的方向信息。
在数据库中所采集的街景数据都对应有位置信息，而根据匹配成功的街景数据，可以计算出街景照片中各个景物的相对位置，从而得到对应的方向信息。其中，该方向信息中可以包括以拍摄街景照片的位置为参考点设置的东、南、西、北四个方位。
步骤105、根据方向信息在街景照片中标注道路和建筑物的方向标识。
该步骤是在街景照片的基础上，标注具体的方向信息，标注的方式及形式不做具体限定。常见的是将方向标识标注在道路和建筑物上，以方便用户的读取和辨认。
步骤106、发送含有方向标识的街景照片。
根据接收街景照片的用户信息，如用户ID、设备编号等，将标注有方向标识的街景照片反馈给用户。
通过上述实施例中的具体实现方式可以看出，该基于图片的方向标注方法，主要是将用户发送的街景照片经过图像识别对其中的道路以及建筑物进行数据匹配，计算道路及建筑物相对于拍摄该街景照片的位置的方向信息，再将这些方向信息以方向标识的形式添加到该街景照片上，实现在街景照片上标记方向标识。如此，用户可以在拍摄地点接收到含有方向标识的街景照片，并直接以该街景照片上的方式标识对应着实际场景来辨别方向。相对于使用指南针或是电子罗盘识别方向，本发明实施例更加简便易用，无需用户学习使用方法，并且，本发明所匹配出的方向是通过数据库中存储的街景数据匹配得到的，其方向的准确性更高，不会出现使用电子罗盘或指南针受磁场影响而导致方向识别不准确的问题。
为了进一步详细的阐明基于图片的方向标注方法，特别是对上述实施例中步骤102至步骤105的实现，本发明实施例将结合图2具体说明将街景照片与数据库中的三维立体街景数据进行匹配并在街景照片上标注方向标识反馈给用户的方式。该方法具体如图2所示，包括：
步骤201、根据位置信息获取预置范围内的三维立体街景数据。
本实施例中，存储街景数据的数据库所采集的为三维立体街景的数据集，不同的数据集对应于不同的地理位置，比如，可以是以国家、地区或城市为单位的数据集，也可以是以经纬度、海拔等参数划分的地理区域为单位的数据集。每一个数据集中存储有对应该地理区域中所有道路的三维立体街景数据。
本步骤是根据用户实时拍摄并发送的街景照片所在的位置信息，匹配到对应的三维 立体街景的数据集，从该数据集中还可以进一步的根据位置信息来提取具体位置所对应的街景数据。
步骤202、利用图像匹配算法在三维立体街景数据中匹配图像信息。
具体的匹配可通过图像匹配算法将街景照片中的图像信息与所确定的三维立体街景数据进行匹配，不限定图像匹配的具体算法，如灰度匹配算法或者基于特征的匹配算法。
由于三维立体街景数据是具有一定范围内的数据集合，即可以视为由多个位置点的数据所组合成的数据集，因此，本步骤的目的就是要在该数据集中匹配出与街景照片中的图像信息相匹配的具体位置点，其具体的匹配过程就是将每个位置点的三维立体街景数据转换为不同角度的二维图片，再与街景照片中的图像信息进行相似度计算，当相似度的值达到阈值时，就确定该街景照片成功匹配到对应的三维立体街景数据。
步骤203、基于三维立体坐标系计算匹配成功的三维立体街景数据中道路和/或建筑物的方向信息。
由于三维立体街景数据在本实施例中都有对应的位置点，因此，对于匹配成功的三维立体街景数据，其位置点的位置信息可以通过三维立体坐标系计算得到，其中，该三维立体坐标系是基于地理方向设置的。从而可以计算得到该三维立体街景数据中道路、建筑物的方向。
需要说明的是，计算出的方向是在街景照片所在二维平面上的方向信息。
步骤204、在街景照片的道路上沿所述道路的走向标注道路方向标识，在建筑物上方标注相对所述道路的方向标识。
在街景照片上标注方向标识的具体效果如图3所示，该图中的图像信息主要为道路，以及道路两旁的建筑物，通过对街景照片的识别，即利用图像识别算法来提取街景照片中的道路和建筑物，常用的图像识别算法如基于特征匹配的ORB算法，提取街景照片中的道路以及建筑物的显示区域，根据步骤203中计算得到的方向信息，确定街景照片中的道路以及建筑物的方向，其中，道路的方向是按照道路的走向确定，而建筑物的方向则是相对于道路确定的方向，在图3中，道路的走向是由下至上为由南向北，而两侧的建筑物在其显示的区域附近也标记出对应的方向标识，以供用户作为方向参考。
经过以上步骤的执行，就实现了在一张具有指定信息(道路及建筑物)的街景照片上标记方向标识，方便用户辨别方向的目的。其中，本发明的实现主要是依据大量的街景数据与街景照片中的内容进行匹配，基于服务器的强大计算能力，对匹配成功的街景数据进行解析，得到对应的方向信息，进而在街景照片上标注方向标识。当然，在用户 的终端具有存储大量街景数据以及强大的计算资源时，本发明也可以在用户的终端上执行，在用户拍摄照片后，直接得到标记有方向标识的照片，或者在用户的取景框中直接对所框定的图像进行解析并显示相应的方向信息。如此，可以更加简化用户在识别场景方向时所需的操作过程，让用户可以轻松的识别当前所在位置的具体方向。
进一步的，作为对上述图1与图2所示方法的实现，本发明实施例提供了一种基于图片的方向标注装置，能够基于用户拍摄的街景照片向用户反馈标注有方向标识的街景照片，以帮助用户识别当前位置的方向。为便于阅读，本装置实施例不再对前述方法实施例中的细节内容进行逐一赘述，但应当明确，本实施例中的装置能够对应实现前述方法实施例中的全部内容。该装置如图4所示，具体包括：
接收单元31，用于接收街景照片以及所述街景照片所在的位置信息，所述街景照片中至少含有道路和建筑物的图像信息；
获取单元32，用于根据所述接收单元31接收的位置信息获取预置范围内的街景数据；
提取单元33，用于提取所述接收单元31接收的街景照片中的图像信息；
匹配单元34，用于将所述提取单元33提取的图像信息与所述获取单元32获取的街景数据进行匹配；
解析单元35，用于解析经过所述匹配单元34匹配成功的街景数据对应的方向信息；
方向标注单元36，用于根据所述解析单元35解析的方向信息在所述街景照片中标注道路和建筑物的方向标识；
发送单元37，用于发送含有所述方向标注单元36标注的方向标识的街景照片。
进一步，如图5所示，所述获取单元32还用于，当所述匹配单元34对街景照片中的图像信息与所述街景数据匹配失败时，根据预设值扩大所述预置范围，并获取扩大预置范围后包括的街景数据。
进一步，如图5所示，所述提取单元33包括：
识别模块331，用于利用图像识别算法识别所述街景照片中的文字信息；
判断模块332，用于判断所述识别模块331识别的文字信息中是否含有道路或建筑物的名称；
提取模块333，用于当所述判断模块332确定含有道路或建筑物的名称时，提取所述名称作为所述街景照片中的图像信息。
进一步，如图5所示，所述获取单元32还用于，获取预置范围内的三维立体街景数 据；
所述匹配单元34还用于，利用图像匹配算法在所述三维立体街景数据中匹配所述图像信息；
所述解析单元35还用于，基于三维立体坐标系计算匹配成功的三维立体街景数据中道路和/或建筑物的方向信息。
进一步，如图5所示，所述方向标注单元36包括：
识别模块361，用于利用图像识别算法识别所述街景照片中的道路和建筑物；
方向标注模块362，用于根据所述三维立体街景数据中道路和/或建筑物的方向信息，在所述识别模块识别出的道路上沿所述道路的走向标注道路方向标识，在识别出的所述建筑物上方标注相对所述道路的方向标识，得到标注有方向标识的街景照片。
综上所述，本发明实施例所采用的基于图片的方向标注方法及装置，是在用户拍摄的街景照片上，利用图像的识别以及匹配技术，从大量的街景数据中匹配出对应的数据，并根据该街景数据对应的方向信息标注方向标识，使得用户能够在处理后的街景照片上直接读取到对应的方向信息，帮助用户快速、简单的识别当前场景下的方向。相对目前使用指南针或电子罗盘等指向设备来识别方向的方法，本发明在识别方向的过程中，其识别的原理与现有的方法不同，因而不会受到磁场因素的干扰，其准确度更高。并且，本发明的操作过程十分简便，对于用户的操作过程与拍摄照片相同，区别在于，需要用户明确所拍摄的内容，以保证数据匹配以及识别的准确。由此可见，本发明所提出的方向标注方法及装置为用户提供了一种新的方向识别思路，简化了用户操作，也充分利用了服务端的强大数据存储与运算能力，使得为用户标注的方向更为准确。
进一步的，本发明实施例还提供了一种存储介质，该存储介质用于存储计算机程序，其中，所述计算机程序运行时控制所述存储介质所在设备执行上述的基于图片的方向标注方法。
另外，本发明实施例还提供了一种处理器，所述处理器用于运行计算机程序，其中，所述计算机程序运行时执行上述的基于图片的方向标注方法。
在上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述的部分，可以参见其他实施例的相关描述。
可以理解的是，上述方法及装置中的相关特征可以相互参考。另外，上述实施例中的“第一”、“第二”等是用于区分各实施例，而并不代表各实施例的优劣。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统， 装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在此提供的算法和显示不与任何特定计算机、虚拟系统或者其它设备固有相关。各种通用系统也可以与基于在此的示教一起使用。根据上面的描述，构造这类系统所要求的结构是显而易见的。此外，本发明也不针对任何特定编程语言。应当明白，可以利用各种编程语言实现在此描述的本发明的内容，并且上面对特定语言所做的描述是为了披露本发明的最佳实施方式。
此外，存储器可能包括计算机可读介质中的非永久性存储器，随机存取存储器(RAM)和/或非易失性内存等形式，如只读存储器(ROM)或闪存(flash RAM)，存储器包括至少一个存储芯片。
本领域内的技术人员应明白，本申请的实施例可提供为方法、系统、或计算机程序产品。因此，本申请可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本申请是参照根据本申请实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
在一个典型的配置中，计算设备包括一个或多个处理器(CPU)、输入/输出接口、网 络接口和内存。
存储器可能包括计算机可读介质中的非永久性存储器，随机存取存储器(RAM)和/或非易失性内存等形式，如只读存储器(ROM)或闪存(flash RAM)。存储器是计算机可读介质的示例。
计算机可读介质包括永久性和非永久性、可移动和非可移动媒体可以由任何方法或技术来实现信息存储。信息可以是计算机可读指令、数据结构、程序的模块或其他数据。计算机的存储介质的例子包括，但不限于相变内存(PRAM)、静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、快闪记忆体或其他内存技术、只读光盘只读存储器(CD-ROM)、数字多功能光盘(DVD)或其他光学存储、磁盒式磁带，磁带磁磁盘存储或其他磁性存储设备或任何其他非传输介质，可用于存储可以被计算设备访问的信息。按照本文中的界定，计算机可读介质不包括暂存电脑可读媒体(transitory media)，如调制的数据信号和载波。
还需要说明的是，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、商品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、商品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括要素的过程、方法、商品或者设备中还存在另外的相同要素。
本领域技术人员应明白，本申请的实施例可提供为方法、系统或计算机程序产品。因此，本申请可采用完全硬件实施例、完全软件实施例或结合软件和硬件方面的实施例的形式。而且，本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
以上仅为本申请的实施例而已，并不用于限制本申请。对于本领域技术人员来说，本申请可以有各种更改和变化。凡在本申请的精神和原理之内所作的任何修改、等同替换、改进等，均应包含在本申请的权利要求范围之内。

Claims (12)

  1. 一种基于图片的方向标注方法，其特征在于，所述方法包括：
    接收街景照片以及所述街景照片所在的位置信息，所述街景照片中至少含有道路和建筑物的图像信息；
    根据所述位置信息获取预置范围内的街景数据；
    提取所述街景照片中的图像信息，与所述街景数据进行匹配；
    解析匹配成功的街景数据对应的方向信息；
    根据所述方向信息在所述街景照片中标注道路和建筑物的方向标识；
    发送含有所述方向标识的街景照片。
  2. 根据权利要求1所述的方法，其特征在于，根据所述位置信息获取预置范围内的街景数据包括：
    当所述街景照片中的图像信息与所述街景数据匹配失败时，根据预设值扩大所述预置范围，并获取扩大预置范围后包括的街景数据。
  3. 根据权利要求1所述的方法，其特征在于，所述提取所述街景照片中的图像信息包括：
    利用图像识别算法识别所述街景照片中的文字信息；
    判断所述文字信息中是否含有道路或建筑物的名称；
    若含有，则提取所述名称作为所述街景照片中的图像信息。
  4. 根据权利要求1-3中任一项所述的方法，其特征在于，所述根据所述位置信息获取预置范围内的街景数据包括：
    获取预置范围内的三维立体街景数据；
    所述提取所述街景照片中的图像信息，与所述街景数据进行匹配包括：
    利用图像匹配算法在所述三维立体街景数据中匹配所述图像信息；
    所述解析匹配成功的街景数据对应的方向信息包括：
    基于三维立体坐标系计算匹配成功的三维立体街景数据中道路和/或建筑物的方向信息。
  5. 根据权利要求4所述的方法，其特征在于，所述根据所述方向信息在所述街景照片中标注道路和建筑物的方向标识包括：
    利用图像识别算法识别所述街景照片中的道路和建筑物；
    根据所述三维立体街景数据中道路和/或建筑物的方向信息，在道路上沿所述道路的 走向标注道路方向标识，在所述建筑物上方标注相对所述道路的方向标识，得到标注有方向标识的街景照片。
  6. 一种基于图片的方向标注装置，其特征在于，所述装置包括：
    接收单元，用于接收街景照片以及所述街景照片所在的位置信息，所述街景照片中至少含有道路和建筑物的图像信息；
    获取单元，用于根据所述接收单元接收的位置信息获取预置范围内的街景数据；
    提取单元，用于提取所述接收单元接收的街景照片中的图像信息；
    匹配单元，用于将所述提取单元提取的图像信息与所述获取单元获取的街景数据进行匹配；
    解析单元，用于解析经过所述匹配单元匹配成功的街景数据对应的方向信息；
    方向标注单元，用于根据所述解析单元解析的方向信息在所述街景照片中标注道路和建筑物的方向标识；
    发送单元，用于发送含有所述方向标注单元标注的方向标识的街景照片。
  7. 根据权利要求6所述的装置，其特征在于，所述获取单元还用于，当所述匹配单元对街景照片中的图像信息与所述街景数据匹配失败时，根据预设值扩大所述预置范围，并获取扩大预置范围后包括的街景数据。
  8. 根据权利要求6所述的装置，其特征在于，所述提取单元包括：
    识别模块，用于利用图像识别算法识别所述街景照片中的文字信息；
    判断模块，用于判断所述识别模块识别的文字信息中是否含有道路或建筑物的名称；
    提取模块，用于当所述判断模块确定含有道路或建筑物的名称时，提取所述名称作为所述街景照片中的图像信息。
  9. 根据权利要求6-8中任一项所述的装置，其特征在于，所述获取单元还用于，获取预置范围内的三维立体街景数据；
    所述匹配单元还用于，利用图像匹配算法在所述三维立体街景数据中匹配所述图像信息；
    所述解析单元还用于，基于三维立体坐标系计算匹配成功的三维立体街景数据中道路和/或建筑物的方向信息。
  10. 根据权利要求9所述的装置，其特征在于，所述方向标注单元包括：
    识别模块，用于利用图像识别算法识别所述街景照片中的道路和建筑物；
    方向标注模块，用于根据所述三维立体街景数据中道路和/或建筑物的方向信息，在所述识别模块识别出的道路上沿所述道路的走向标注道路方向标识，在识别出的所述建筑物上方标注相对所述道路的方向标识，得到标注有方向标识的街景照片。
  11. 一种存储介质，其特征在于，所述存储介质用于存储计算机程序，其中，所述计算机程序运行时控制所述存储介质所在设备执行权利要求1-5中任意一项所述的基于图片的方向标注方法。
  12. 一种处理器，其特征在于，所述处理器用于运行计算机程序，其中，所述计算机程序运行时执行权利要求1-5中任意一项所述的基于图片的方向标注方法。
PCT/CN2019/127399 2018-12-29 2019-12-23 一种基于图片的方向标注方法及装置 WO2020135326A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811646747.9A CN111383271B (zh) 2018-12-29 2018-12-29 一种基于图片的方向标注方法及装置
CN201811646747.9 2018-12-29

Publications (1)

Publication Number Publication Date
WO2020135326A1 true WO2020135326A1 (zh) 2020-07-02

Family

ID=71125699

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/127399 WO2020135326A1 (zh) 2018-12-29 2019-12-23 一种基于图片的方向标注方法及装置

Country Status (2)

Country Link
CN (1) CN111383271B (zh)
WO (1) WO2020135326A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112100521A (zh) * 2020-09-11 2020-12-18 广州宸祺出行科技有限公司 一种街景识别定位并获取全景图片的方法及系统

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114299809B (zh) * 2021-12-30 2024-03-22 北京有竹居网络技术有限公司 方向信息显示方法、显示装置、电子设备和可读存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103677220A (zh) * 2012-08-30 2014-03-26 百度在线网络技术（北京）有限公司 一种自动开启实景地图的方法及具有该功能的移动终端
CN104050177A (zh) * 2013-03-13 2014-09-17 腾讯科技（深圳）有限公司 街景生成方法及服务器
CN104159036A (zh) * 2014-08-26 2014-11-19 惠州Tcl移动通信有限公司 一种图像方向信息的显示方法及拍摄设备
US20160323716A1 (en) * 2015-04-29 2016-11-03 Boe Technology Group Co., Ltd. Positioning method and positioning server
CN109059929A (zh) * 2018-08-30 2018-12-21 Oppo广东移动通信有限公司 导航方法、装置、穿戴式设备及存储介质

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8483447B1 (en) * 2010-10-05 2013-07-09 Google Inc. Labeling features of maps using road signs
CN102519478B (zh) * 2011-11-16 2016-01-13 深圳市凯立德科技股份有限公司 一种街景目的地引导方法及装置
KR102021050B1 (ko) * 2012-06-06 2019-09-11 삼성전자주식회사 내비게이션 정보를 제공하는 방법, 기계로 읽을 수 있는 저장 매체, 이동 단말 및 서버
CN103971589B (zh) * 2013-01-28 2017-10-03 腾讯科技（深圳）有限公司 将地图的兴趣点信息添加于街景图像中的处理方法及装置
CN103150759B (zh) * 2013-03-05 2015-11-25 腾讯科技（深圳）有限公司 一种对街景图像进行动态增强的方法和装置
CN103644921B (zh) * 2013-12-06 2017-10-31 北京奇虎科技有限公司 一种实现街景显示的方法和装置
CN105608128B (zh) * 2015-12-16 2019-10-15 北京百度网讯科技有限公司 基于路径规划的街景视频生成方法和装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103677220A (zh) * 2012-08-30 2014-03-26 百度在线网络技术（北京）有限公司 一种自动开启实景地图的方法及具有该功能的移动终端
CN104050177A (zh) * 2013-03-13 2014-09-17 腾讯科技（深圳）有限公司 街景生成方法及服务器
CN104159036A (zh) * 2014-08-26 2014-11-19 惠州Tcl移动通信有限公司 一种图像方向信息的显示方法及拍摄设备
US20160323716A1 (en) * 2015-04-29 2016-11-03 Boe Technology Group Co., Ltd. Positioning method and positioning server
CN109059929A (zh) * 2018-08-30 2018-12-21 Oppo广东移动通信有限公司 导航方法、装置、穿戴式设备及存储介质

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
ANONYMOUS: "How powerful is WeChat Scan? These functions are wasted by you!", 7 October 2018 (2018-10-07), pages 1 - 10, XP055714270, Retrieved from the Internet <URL:https://www.sohu.com/a/258039867_404443> *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112100521A (zh) * 2020-09-11 2020-12-18 广州宸祺出行科技有限公司 一种街景识别定位并获取全景图片的方法及系统
CN112100521B (zh) * 2020-09-11 2023-12-22 广州宸祺出行科技有限公司 一种街景识别定位并获取全景图片的方法及系统

Also Published As

Publication number Publication date
CN111383271B (zh) 2023-06-23
CN111383271A (zh) 2020-07-07

Similar Documents

Publication Publication Date Title
CN107677279B (zh) 一种定位建图的方法及系统
CN109582880B (zh) 兴趣点信息处理方法、装置、终端及存储介质
US9710946B2 (en) Method and apparatus for displaying point of interest
US11328401B2 (en) Stationary object detecting method, apparatus and electronic device
JP2019179021A (ja) 地図生成及び移動主体の位置決めの方法及び装置
CN105517679B (zh) 用户地理位置的确定
US20130243250A1 (en) Location of image capture device and object features in a captured image
Niu et al. Resource-efficient and automated image-based indoor localization
CN102867057B (zh) 一种基于视觉定位的虚拟向导构建方法
US20180188033A1 (en) Navigation method and device
US20120274642A1 (en) Automated fitting of interior maps to general maps
US10606824B1 (en) Update service in a distributed environment
US11106933B2 (en) Method, device and system for processing image tagging information
EP2672401A1 (en) Method and apparatus for storing image data
CN104281840A (zh) 一种基于智能终端定位识别建筑物的方法及装置
US10290137B2 (en) Auto-generation of map landmarks using sensor readable tags
CN107885763B (zh) 室内图中兴趣点信息的更新方法、装置及计算机可读介质
WO2020135326A1 (zh) 一种基于图片的方向标注方法及装置
CN111859002B (zh) 兴趣点名称生成方法及装置、电子设备和介质
Wenig et al. Pharos: Improving navigation instructions on smartwatches by including global landmarks
CN111832579B (zh) 地图兴趣点数据处理方法、装置、电子设备以及可读介质
WO2019062694A1 (zh) 可视化对象的生成方法、装置和设备
WO2014026021A1 (en) Systems and methods for image-based searching
US20220386071A1 (en) Road side positioning method and apparatus, device, and storage medium
CN110926478A (zh) 一种ar导航路线纠偏方法、系统及计算机可读存储介质

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: 19902789

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19902789

Country of ref document: EP

Kind code of ref document: A1