CN111159459B - Landmark positioning method, landmark positioning device, computer equipment and storage medium - Google Patents
Landmark positioning method, landmark positioning device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN111159459B CN111159459B CN201911225170.9A CN201911225170A CN111159459B CN 111159459 B CN111159459 B CN 111159459B CN 201911225170 A CN201911225170 A CN 201911225170A CN 111159459 B CN111159459 B CN 111159459B
- Authority
- CN
- China
- Prior art keywords
- landmark
- information
- image
- identified
- acquiring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/587—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using geographical or spatial information, e.g. location
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/5866—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The application particularly relates to a landmark positioning method, a landmark positioning device, computer equipment and a storage medium, wherein the landmark positioning method comprises the following steps: acquiring an image to be identified corresponding to an external scene of an automobile; acquiring landmark position information and depth information of a landmark in an image to be identified; acquiring coordinate information of a landmark; searching landmark description information corresponding to the landmark in a preset landmark database according to the coordinate information of the landmark; and acquiring user description information corresponding to the positioning target location, searching the positioning target location in the landmark according to the user description information and the landmark description information, and acquiring coordinate information of the positioning target location. According to the application, the current external image is acquired through the automobile camera, then the landmark in the image is identified, the destination landmark in the landmark is determined through the description information of the user, the destination location is performed, the location accuracy of the target location is improved through the description of the user on the target location, the probability of location error can be effectively reduced, and the location efficiency of the landmark is improved.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a landmark positioning method, apparatus, computer device, and storage medium.
Background
Positioning refers to determining an orientation. With the development of science and technology, positioning systems such as GPS (Global Positioning System ) have emerged, by which the current position of a user can be precisely determined.
However, when locating a target site where a user is traveling in a vehicle, if the target site is a street, the street address is long and complicated, which results in that whether using a touch screen, buttons and dials, or voice input, it takes a long time for the street address to be input into a navigation system of a car, and because roads of the same name are easily confused: multiple addresses in the same area may use the same name, which means that the driver or car may choose the wrong destination, which inevitably leads to errors, affecting the efficiency of landmark positioning.
Disclosure of Invention
Based on this, there is a need to provide a landmark positioning method, a device, a computer device and a storage medium capable of improving landmark positioning efficiency, aiming at the technical problems that a navigation system is complicated to input a street address and positioning efficiency is affected.
A landmark positioning method, comprising:
acquiring an image to be identified corresponding to an external scene of an automobile, wherein the image to be identified is provided by a vehicle-mounted camera of the automobile;
acquiring landmark position information, depth information and current coordinate information of an automobile of a landmark in the image to be identified, and acquiring the coordinate information of the landmark according to the landmark position information, the depth information and the current coordinate information of the automobile, wherein the landmark position information is the position information of the landmark in the image to be identified;
searching landmark description information corresponding to the landmark in a preset landmark database according to the coordinate information of the landmark;
and acquiring user description information corresponding to the positioning target location, searching the positioning target location in the landmark according to the user description information and the landmark description information, and acquiring coordinate information of the positioning target location, wherein the user description information is input by a user through voice and then acquired through voice recognition.
In one embodiment, the obtaining landmark position information, depth information and current coordinate information of the car of the landmark in the image to be identified, and obtaining the coordinate information of the landmark according to the landmark position information, the depth information and the current coordinate information of the car includes:
acquiring landmark position information, depth of field information and current coordinate information of an automobile of a landmark in the image to be identified;
determining the direction information of the landmark relative to the automobile according to the landmark position information, and determining the distance information of the landmark relative to the automobile according to the depth of field information;
and determining the coordinate information of the landmark according to the current coordinate information of the automobile, the direction information and the distance information of the landmark relative to the automobile.
In one embodiment, the determining the direction information of the landmark relative to the car according to the landmark position information includes:
acquiring the distance between the landmark and the image longitudinal bisector according to the landmark position information of the landmark;
acquiring the half length of the image transverse edge of the image to be identified and the maximum viewing angle of the vehicle-mounted camera;
and determining the direction information of the landmark relative to the automobile according to the distance between the landmark and the image longitudinal bisector, the half length of the image transverse side and the maximum viewing angle.
In one embodiment, the acquiring landmark position information and depth information of the landmark in the image to be identified includes:
inputting the image to be identified into a preset landmark identification model, and identifying landmark position information of landmarks in the image to be identified;
and acquiring depth of field information of the landmark through a laser radar according to the landmark position information.
In one embodiment, the obtaining the user description information corresponding to the positioning target location, and searching for the positioning target location in the landmark according to the user description information and the landmark description information, and obtaining the coordinate information of the positioning target location includes:
acquiring user description information corresponding to a positioning target place, and extracting description keywords in the user description information;
matching the description keywords with the landmark description information through fuzzy matching;
when landmark description information matched with the matching keywords exists, landmarks corresponding to the landmark description information matched with the matching keywords are used as positioning target places, and coordinate information of the positioning target places is obtained.
In one embodiment, after the matching the description keyword with the landmark description information through fuzzy matching, the method further includes:
when landmark description information matched with the matching keywords does not exist, labeling the landmarks in the images to be identified, and then pushing the labeled images to be identified to a user;
and receiving target selection information fed back by a user according to the image to be identified, taking a landmark corresponding to the target selection information as a positioning target place, and acquiring coordinate information of the positioning target place.
A landmark positioning device, the device comprising:
the image acquisition module is used for acquiring an image to be identified corresponding to an external scene of the automobile, wherein the image to be identified is provided by a vehicle-mounted camera of the automobile;
the landmark information acquisition module is used for acquiring landmark position information, depth information and current coordinate information of the automobile of the landmark in the image to be identified, and acquiring the coordinate information of the landmark according to the landmark position information, the depth information and the current coordinate information of the automobile, wherein the landmark position information is the position information of the landmark in the image to be identified;
the description information acquisition module is used for searching landmark description information corresponding to the landmark in a preset landmark database according to the coordinate information of the landmark;
the target positioning module is used for acquiring user description information corresponding to a positioning target place, searching the positioning target place in the landmark according to the user description information and the landmark description information, and acquiring coordinate information of the positioning target place, wherein the user description information is input by a user through voice and then acquired through voice recognition.
In one embodiment, the landmark information obtaining module is specifically configured to:
determining the direction information of the landmark relative to the automobile according to the landmark position information, and determining the distance information of the landmark relative to the automobile according to the depth of field information;
and determining the coordinate information of the landmark according to the current coordinate information of the automobile, the direction information and the distance information of the landmark relative to the automobile.
A computer device comprising a memory storing a computer program and a processor which when executing the computer program performs the steps of:
acquiring an image to be identified corresponding to an external scene of an automobile, wherein the image to be identified is provided by a vehicle-mounted camera of the automobile;
acquiring landmark position information, depth information and current coordinate information of an automobile of a landmark in the image to be identified, and acquiring the coordinate information of the landmark according to the landmark position information, the depth information and the current coordinate information of the automobile, wherein the landmark position information is the position information of the landmark in the image to be identified;
searching landmark description information corresponding to the landmark in a preset landmark database according to the coordinate information of the landmark;
and acquiring user description information corresponding to the positioning target location, searching the positioning target location in the landmark according to the user description information and the landmark description information, and acquiring coordinate information of the positioning target location, wherein the user description information is input by a user through voice and then acquired through voice recognition.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
acquiring an image to be identified corresponding to an external scene of an automobile, wherein the image to be identified is provided by a vehicle-mounted camera of the automobile;
acquiring landmark position information, depth information and current coordinate information of an automobile of a landmark in the image to be identified, and acquiring the coordinate information of the landmark according to the landmark position information, the depth information and the current coordinate information of the automobile, wherein the landmark position information is the position information of the landmark in the image to be identified;
searching landmark description information corresponding to the landmark in a preset landmark database according to the coordinate information of the landmark;
and acquiring user description information corresponding to the positioning target location, searching the positioning target location in the landmark according to the user description information and the landmark description information, and acquiring coordinate information of the positioning target location, wherein the user description information is input by a user through voice and then acquired through voice recognition.
According to the landmark positioning method, the landmark positioning device, the computer equipment and the storage medium, the images to be identified corresponding to the external scenes of the automobile are obtained; acquiring landmark position information and depth information of a landmark in an image to be identified; acquiring coordinate information of a landmark according to the landmark position information, the depth of field information and the current coordinate information of the automobile; searching landmark description information corresponding to the landmark in a preset landmark database according to the coordinate information of the landmark; and acquiring user description information corresponding to the positioning target location, searching the positioning target location in the landmark according to the user description information and the landmark description information, and acquiring coordinate information of the positioning target location. According to the application, the current external image is acquired through the automobile camera, then the landmark in the image is identified, the destination landmark in the landmark is determined through the description information of the user, the destination location is performed, the location accuracy of the target location is improved through the description of the user on the target location, the probability of location error can be effectively reduced, and the location efficiency of the landmark is improved.
Drawings
FIG. 1 is a diagram of an application environment for a landmark positioning method in one embodiment;
FIG. 2 is a flow chart of a landmark positioning method according to one embodiment;
FIG. 3 is a schematic flow chart illustrating a sub-process of step S400 of FIG. 2 in one embodiment;
FIG. 4 is a schematic flow chart illustrating a sub-process of step S800 of FIG. 2 in one embodiment;
FIG. 5 is a block diagram of a landmark positioning device in one embodiment;
fig. 6 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
The landmark positioning method provided by the application can be applied to an application environment shown in fig. 1, wherein a terminal 102 is arranged on an automobile and is connected with a vehicle-mounted camera, and the terminal 102 is also connected with a positioning server 104; firstly, a terminal 102 acquires images to be identified corresponding to an external scene of an automobile through a vehicle-mounted camera, and then the images to be identified are sent to a positioning server 104 to perform positioning operation; the positioning server 104 acquires an image to be recognized corresponding to an external scene of the automobile, and acquires landmark position information and depth of field information of a landmark in the image to be recognized, wherein the landmark position information is the position information of the landmark in the image to be recognized; acquiring coordinate information of a landmark according to the landmark position information, the depth of field information and the current coordinate information of the automobile; searching landmark description information corresponding to the landmark in a preset landmark database according to the coordinate information of the landmark; and acquiring user description information corresponding to the positioning target location, searching the positioning target location in the landmark according to the user description information and the landmark description information, and acquiring coordinate information of the positioning target location, wherein the user description information is acquired by a user through voice input and then through voice recognition. Wherein the terminal 102 may specifically be an in-vehicle terminal. The positioning server 104 may be implemented as a stand-alone server or as a server cluster of multiple servers. It should be noted that the landmark positioning method of the present application may also be directly applied to the terminal 102, where the user operates on the terminal 102, and the landmark positioning method is performed by the terminal.
As shown in fig. 2, in one embodiment, the landmark positioning method of the present application is implemented by a positioning server, and specifically includes the following steps:
s200, acquiring an image to be identified corresponding to an external scene of the automobile, wherein the image to be identified is provided by a vehicle-mounted camera of the automobile.
The images to be identified are images shot by the vehicle-mounted camera, the images can be specifically collected by a plurality of cameras facing the outside of the vehicle on the vehicle body, the images can cover 360-degree directions around the vehicle body, and the landmark positioning method can search a target place input by a user from the collected images to perform landmark positioning. Firstly, when positioning is started, the terminal controls a vehicle-mounted camera of the automobile to shoot, acquires images to be recognized corresponding to external scenes around the automobile, and then sends the images to be recognized to the positioning server.
S400, landmark position information, depth information and current coordinate information of an automobile of a landmark in an image to be identified are obtained, and the coordinate information of the landmark is obtained according to the landmark position information, the depth information and the current coordinate information of the automobile, wherein the landmark position information is the position information of the landmark in the image to be identified;
specifically, the coordinate information refers to coordinate information of a landmark or an automobile in a world coordinate system. Landmarks refer to buildings or natural objects with unique geographic features in a place, tourists or other general people can see where to find themselves, and the landmarks have the function of Beidou stars, such as skyscrapers, churches, temples, statues, lighthouses, bridges and the like. Within the scope of the present application, besides the landmarks defined above, also generic objects that can be used for specifying geographical locations can be included more broadly, such as in daily life we may say: "I wait for you just under the cards next to the gate," then "cards next to the gate" here can also be considered landmarks. The depth of field refers to the range of distances between the front and back of a subject measured at the front of a camera lens or other imager that is capable of taking a clear image. The method comprises the steps that the server can be used for identifying the landmarks in the images to be identified, determining the positions of the landmarks in the images to be identified, feeding back the positions of the landmarks in the images to be identified to the terminal, and then controlling the camera through the terminal to obtain depth information corresponding to each landmark. Meanwhile, the terminal can also feed back the current coordinate information of the automobile and the depth information of the landmarks to the server through the navigation system automobile, and the server determines the coordinate information of each landmark in the image to be identified in the actual navigation map through acquiring the landmark position information, the depth information and the current coordinate information of the automobile.
S600, searching landmark description information corresponding to the landmark in a preset landmark database according to the coordinate information of the landmark.
The description information of the landmark can be information such as a white building, a red stone pier, a black lighthouse and the like, and the name of the landmark. The preset landmark database can be information corresponding to each landmark in the pre-established city, and the landmark database contains names, coordinate information and description information of the landmarks. And the server searches landmark description information corresponding to the landmark according to the coordinate information of the landmark in a preset landmark database. In particular, for landmarks that are not in the database, such as a general signal lamp post, a corresponding picture at the landmark can be cut out from the original image, and the cut-out landmark picture is input into an imaging and mapping task related model in deep learning, and the model can generally adopt an encoder (cnn) -decoder (rnn) structure, such as GCN-LSTM, so as to extract landmark description related information.
S800, user description information corresponding to the positioning target location is obtained, the positioning target location in the landmark is searched according to the user description information and the landmark description information, coordinate information of the positioning target location is obtained, and the user description information is obtained through voice input and then voice recognition by a user.
In the application, when a user needs to locate, specific address information or street name and other information are not required to be input, the description information of the landmark existing near the location target location can be directly input by voice, the terminal carries out voice recognition on voice input, the recognized user description information is uploaded to the server, the server matches the user description information with the found landmark description information, the location target location of the user location in the landmark is found, and then coordinate information of the location target location is directly obtained, so that target location is completed.
According to the landmark positioning method, the image to be identified corresponding to the external scene of the automobile is obtained; the method comprises the steps of obtaining landmark position information, depth information and current coordinate information of an automobile of a landmark in an image to be identified, and obtaining the coordinate information of the landmark according to the landmark position information, the depth information and the current coordinate information of the automobile; searching landmark description information corresponding to the landmark in a preset landmark database according to the coordinate information of the landmark; and acquiring user description information corresponding to the positioning target location, searching the positioning target location in the landmark according to the user description information and the landmark description information, and acquiring coordinate information of the positioning target location. According to the application, the current external image is acquired through the automobile camera, then the landmark in the image is identified, the destination landmark in the landmark is determined through the description information of the user, the destination location is performed, the location accuracy of the target location is improved through the description of the user on the target location, the probability of location error can be effectively reduced, and the location efficiency of the landmark is improved.
As shown in fig. 3, in one embodiment, step S400 includes:
s410, landmark position information, depth of field information and current coordinate information of an automobile of a landmark in an image to be identified are obtained;
s430, determining the direction information of the landmark relative to the automobile according to the landmark position information, and determining the distance information of the landmark relative to the automobile according to the depth of field information;
s450, determining coordinate information of the landmark according to current coordinate information of the automobile, direction information and distance information of the landmark relative to the automobile.
Specifically, the coordinate information refers to coordinate information of a landmark or an automobile in a world coordinate system. The method comprises the steps that firstly, landmark position information, depth information and current coordinate information of landmarks in an image to be identified and a server are obtained from a terminal on an automobile, the direction information of each landmark relative to the current automobile can be determined according to the position information of the landmarks in the image to be identified, the distance of each landmark relative to the automobile can be identified according to the depth information, and the actual coordinate information of each landmark can be obtained by combining the direction information and the distance information. The actual coordinates of the landmarks in the images acquired by the cameras can be efficiently positioned through the current coordinate information of the automobile and the landmark related information acquired by the vehicle-mounted cameras.
In one embodiment, step S430 includes: acquiring the distance between the landmark and the image longitudinal bisector according to the landmark position information of the landmark; acquiring the half length of the image transverse edge of the image to be identified and the maximum viewing angle of the vehicle-mounted camera; and determining the direction information of the landmark relative to the automobile according to the distance between the landmark and the image longitudinal bisector, the half length of the image transverse edge and the maximum viewing angle.
The direction information of a specific landmark relative to an automobile can be obtained by combining the following formula: the abscissa offset angle of the landmark and the camera coordinate system= (distance of the landmark from the image longitudinal bisector)/(half-length of the image lateral side) × (camera lateral maximum viewing angle) × 0.5. The ordinate offset angle of the landmark and the camera coordinate system= (distance of the landmark from the horizontal bisector of the image)/(half length of the image vertical side) × (maximum viewing angle of the camera vertical direction) × 0.5. After the offset angles of the transverse direction and the longitudinal direction are obtained, one determined direction in the 3-dimensional space can be directly obtained. The camera coordinate system is a coordinate system where a camera for collecting an image to be identified corresponding to the landmark is located, the camera coordinate system is converted into a vehicle coordinate system, and the vehicle coordinate system is converted into a world coordinate system, so that the direction information of the landmark relative to the vehicle in the world coordinate system can be obtained.
In one embodiment, step S410 includes:
inputting an image to be identified into a preset landmark identification model, and identifying landmark position information of landmarks in the image to be identified; and acquiring depth of field information of the landmark through a laser radar according to the landmark position information.
The preset landmark recognition model may be specifically a YOLO model or a Mask RCNN model, where the YOLO model is suitable for a target detection model, and the Mask RCNN model is a model for target detection and image segmentation. The landmark can be regarded as a detection target to train an initial YOLO model or an initial Mask RCNN model to obtain a preset landmark identification model, and the region containing the specific landmark in the input image to be identified is identified through the preset landmark identification model. After the positions of landmarks in an image to be identified are determined, depth of field information corresponding to the positions can be obtained through a laser radar, rays are emitted to the directions through the laser radar according to the obtained direction information, and in a point cloud output by the laser radar, the positions of the centroids of n points (n is a preset value) closest to the rays, which are away from a camera, can be regarded as distance/depth of field; the position of the camera in the laser radar coordinate system can be obtained by the installation information of each camera pre-stored in the server on the vehicle. The linear distance information between the landmarks corresponding to the positions and the current automobile can be effectively identified through the depth information. Landmarks within images to be identified may be quickly detected by machine learning techniques. In another embodiment, the laser radar can be replaced by a depth camera, and the depth information corresponding to the positions is acquired through the depth camera.
As shown in fig. 4, in one embodiment, step S800 includes:
s810, acquiring user description information corresponding to the positioning target place, and extracting description keywords in the user description information.
And S830, matching the description keywords with landmark description information through fuzzy matching.
S850, when landmark descriptive information matched with the matching keywords exists, landmarks corresponding to the landmark descriptive information matched with the matching keywords are used as positioning target sites, and coordinate information of the positioning target sites is obtained.
The server firstly recognizes voice information input by a user to obtain literal user description information, the user description information is related to a positioning target place which the user needs to position, and then description keywords in the user description information are extracted. In one embodiment, extracting descriptive keywords may be accomplished through a deep learning model, which may be used to extract keywords including a BERT model and natural language processing models such as an ERNIE model. After the keywords are extracted, the extracted keywords can be matched with landmark description information in a preset landmark database through fuzzy matching, landmarks matched with the user description information are found, then the landmarks are used as positioning target sites for positioning the user, and coordinate information corresponding to the sites is acquired, so that the positioning process is completed. In particular, when the user inputs a unique landmark, such as a yellow river mother image, the deep learning model can directly output the corresponding recognition result of the landmark, and the description and the coordinates of the landmark can be directly obtained from the database. By identifying the input keywords and performing fuzzy matching according to the keywords, the positioning target sites in the landmarks in the images to be identified can be effectively searched, the landmark positioning process is completed, and the landmark positioning efficiency is improved.
In one embodiment, step S850 further includes:
and when landmark description information matched with the matched keywords does not exist, labeling the landmark in the image to be identified, and pushing the labeled image to be identified to the user.
And receiving target selection information fed back by a user according to the image to be identified, taking a landmark corresponding to the target selection information as a positioning target place, and acquiring coordinate information of the positioning target place.
When the user description information input by the user cannot be matched with the landmark description information of the collected landmarks through fuzzy matching, the server can mark all the identified landmarks in the collected images to be identified, then push the identified landmarks to the user, the user selects a positioning target place in the landmarks, the landmark positioning process is completed, the problem that the landmarks cannot be positioned due to matching errors can be effectively avoided through pushing the marked images to be identified, and the landmark positioning efficiency is improved.
It should be understood that, although the steps in the flowcharts of fig. 2-4 are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in fig. 2-4 may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor do the order in which the sub-steps or stages are performed necessarily occur sequentially, but may be performed alternately or alternately with at least a portion of the sub-steps or stages of other steps or steps.
As shown in fig. 5, the present application further includes a landmark positioning apparatus, including:
the image acquisition module 200 is configured to acquire an image to be identified corresponding to an external scene of an automobile, where the image to be identified is provided by a vehicle-mounted camera of the automobile;
the landmark information obtaining module 400 is configured to obtain landmark position information, depth information and current coordinate information of an automobile of a landmark in the image to be identified, and obtain coordinate information of the landmark according to the landmark position information, the depth information and the current coordinate information of the automobile, where the landmark position information is the position information of the landmark in the image to be identified;
the description information obtaining module 600 is configured to search landmark description information corresponding to the landmark in a preset landmark database according to coordinate information of the landmark;
the target positioning module 800 is configured to obtain user description information corresponding to a positioning target location, search a positioning target location in a landmark according to the user description information and the landmark description information, obtain coordinate information of the positioning target location, and obtain the user description information through voice input and then through voice recognition.
In one embodiment, the landmark information acquisition module 400 is specifically configured to: acquiring landmark position information, depth of field information and current coordinate information of an automobile of a landmark in an image to be identified; determining the direction information of the landmark relative to the automobile according to the landmark position information, and determining the distance information of the landmark relative to the automobile according to the depth of field information; and determining coordinate information of the landmark according to the current coordinate information of the automobile, the direction information and the distance information of the landmark relative to the automobile.
In one embodiment, the landmark information acquisition module 400 is further configured to: acquiring the distance between the landmark and the image longitudinal bisector according to the landmark position information of the landmark; acquiring the half length of the image transverse edge of the image to be identified and the maximum viewing angle of the vehicle-mounted camera; and determining the direction information of the landmark relative to the automobile according to the distance between the landmark and the image longitudinal bisector, the half length of the image transverse edge and the maximum viewing angle.
In one embodiment, the landmark information acquisition module 400 is further configured to: inputting an image to be identified into a preset landmark identification model, and identifying landmark position information of landmarks in the image to be identified; and acquiring depth of field information of the landmark through a laser radar according to the landmark position information.
In one embodiment, the object location module 800 is specifically configured to: acquiring user description information corresponding to a positioning target place, and extracting description keywords in the user description information; matching the description keywords with landmark description information through fuzzy matching; when landmark descriptive information matched with the matched keywords exists, landmarks corresponding to the landmark descriptive information matched with the matched keywords are used as positioning target places, and coordinate information of the positioning target places is obtained.
In one embodiment, the object location module 800 is further configured to: when landmark description information matched with the matched keywords does not exist, labeling the landmarks in the images to be identified, pushing the labeled images to be identified to the user; and receiving target selection information fed back by a user according to the image to be identified, taking a landmark corresponding to the target selection information as a positioning target place, and acquiring coordinate information of the positioning target place.
For specific limitations of the landmark positioning device, reference may be made to the above limitation of the landmark positioning method, and no further description is given here. The various modules in the landmark positioning device described above may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a terminal, and the internal structure of which may be as shown in fig. 6. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a landmark positioning method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in FIG. 6 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:
acquiring an image to be identified corresponding to an external scene of an automobile, wherein the image to be identified is provided by a vehicle-mounted camera of the automobile;
acquiring landmark position information, depth information and current coordinate information of an automobile of a landmark in an image to be identified, and acquiring the coordinate information of the landmark according to the landmark position information, the depth information and the current coordinate information of the automobile, wherein the landmark position information is the position information of the landmark in the image to be identified;
searching landmark description information corresponding to the landmark in a preset landmark database according to the coordinate information of the landmark;
and acquiring user description information corresponding to the positioning target location, searching the positioning target location in the landmark according to the user description information and the landmark description information, and acquiring coordinate information of the positioning target location, wherein the user description information is acquired by a user through voice input and then through voice recognition.
In one embodiment, the processor when executing the computer program further performs the steps of: acquiring landmark position information, depth of field information and current coordinate information of an automobile of a landmark in an image to be identified; determining the direction information of the landmark relative to the automobile according to the landmark position information, and determining the distance information of the landmark relative to the automobile according to the depth of field information; and determining coordinate information of the landmark according to the current coordinate information of the automobile, the direction information and the distance information of the landmark relative to the automobile.
In one embodiment, the processor when executing the computer program further performs the steps of: acquiring the distance between the landmark and the image longitudinal bisector according to the landmark position information of the landmark; acquiring the half length of the image transverse edge of the image to be identified and the maximum viewing angle of the vehicle-mounted camera; and determining the direction information of the landmark relative to the automobile according to the distance between the landmark and the image longitudinal bisector, the half length of the image transverse edge and the maximum viewing angle.
In one embodiment, the processor when executing the computer program further performs the steps of: inputting an image to be identified into a preset landmark identification model, and identifying landmark position information of landmarks in the image to be identified; and acquiring depth of field information of the landmark through a laser radar according to the landmark position information.
In one embodiment, the processor when executing the computer program further performs the steps of: acquiring user description information corresponding to a positioning target place, and extracting description keywords in the user description information; matching the description keywords with landmark description information through fuzzy matching; when landmark descriptive information matched with the matched keywords exists, landmarks corresponding to the landmark descriptive information matched with the matched keywords are used as positioning target places, and coordinate information of the positioning target places is obtained.
In one embodiment, the processor when executing the computer program further performs the steps of: when landmark description information matched with the matched keywords does not exist, labeling the landmarks in the images to be identified, pushing the labeled images to be identified to the user; and receiving target selection information fed back by a user according to the image to be identified, taking a landmark corresponding to the target selection information as a positioning target place, and acquiring coordinate information of the positioning target place.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring an image to be identified corresponding to an external scene of an automobile, wherein the image to be identified is provided by a vehicle-mounted camera of the automobile;
acquiring landmark position information, depth information and current coordinate information of an automobile of a landmark in an image to be identified, and acquiring the coordinate information of the landmark according to the landmark position information, the depth information and the current coordinate information of the automobile, wherein the landmark position information is the position information of the landmark in the image to be identified;
searching landmark description information corresponding to the landmark in a preset landmark database according to the coordinate information of the landmark;
and acquiring user description information corresponding to the positioning target location, searching the positioning target location in the landmark according to the user description information and the landmark description information, and acquiring coordinate information of the positioning target location, wherein the user description information is acquired by a user through voice input and then through voice recognition.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring landmark position information, depth of field information and current coordinate information of an automobile of a landmark in an image to be identified; determining the direction information of the landmark relative to the automobile according to the landmark position information, and determining the distance information of the landmark relative to the automobile according to the depth of field information; and determining coordinate information of the landmark according to the current coordinate information of the automobile, the direction information and the distance information of the landmark relative to the automobile.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring the distance between the landmark and the image longitudinal bisector according to the landmark position information of the landmark; acquiring the half length of the image transverse edge of the image to be identified and the maximum viewing angle of the vehicle-mounted camera; and determining the direction information of the landmark relative to the automobile according to the distance between the landmark and the image longitudinal bisector, the half length of the image transverse edge and the maximum viewing angle.
In one embodiment, the computer program when executed by the processor further performs the steps of: inputting an image to be identified into a preset landmark identification model, and identifying landmark position information of landmarks in the image to be identified; and acquiring depth of field information of the landmark through a laser radar according to the landmark position information.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring user description information corresponding to a positioning target place, and extracting description keywords in the user description information; matching the description keywords with landmark description information through fuzzy matching; when landmark descriptive information matched with the matched keywords exists, landmarks corresponding to the landmark descriptive information matched with the matched keywords are used as positioning target places, and coordinate information of the positioning target places is obtained.
In one embodiment, the computer program when executed by the processor further performs the steps of: when landmark description information matched with the matched keywords does not exist, labeling the landmarks in the images to be identified, pushing the labeled images to be identified to the user; and receiving target selection information fed back by a user according to the image to be identified, taking a landmark corresponding to the target selection information as a positioning target place, and acquiring coordinate information of the positioning target place.
Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.
Claims (10)
1. A landmark positioning method, the method comprising:
acquiring an image to be identified corresponding to an external scene of an automobile, wherein the image to be identified is provided by a vehicle-mounted camera of the automobile;
acquiring landmark position information, depth of field information and current coordinate information of an automobile of a landmark in the image to be identified, wherein the landmark position information is the position information of the landmark in the image to be identified;
acquiring the distance between the landmark and an image longitudinal bisector according to the landmark position information of the landmark, acquiring the image lateral half-length of the image to be identified and the maximum viewing angle of the vehicle-mounted camera, determining the direction information of the landmark relative to the vehicle according to the distance between the landmark and the image longitudinal bisector, the image lateral half-length and the maximum viewing angle, and determining the distance information of the landmark relative to the vehicle according to the depth information;
determining coordinate information of the landmark according to current coordinate information of the automobile, direction information and distance information of the landmark relative to the automobile;
searching landmark description information corresponding to the landmark in a preset landmark database according to the coordinate information of the landmark;
and acquiring user description information corresponding to the positioning target location, searching the positioning target location in the landmark according to the user description information and the landmark description information, and acquiring coordinate information of the positioning target location, wherein the user description information is input by a user through voice and then acquired through voice recognition.
2. The method of claim 1, wherein the description information of the landmark includes a name of the landmark.
3. The method of claim 1, wherein the coordinate information of the landmark is coordinate information of the landmark in a world coordinate system.
4. The method of claim 1, wherein the acquiring landmark position information and depth information for landmarks within the image to be identified comprises:
inputting the image to be identified into a preset landmark identification model, and identifying landmark position information of landmarks in the image to be identified;
and acquiring depth of field information of the landmark through a laser radar according to the landmark position information.
5. The method according to claim 1, wherein the obtaining the user description information corresponding to the positioning target location, and searching for the positioning target location in the landmark according to the user description information and the landmark description information, and obtaining the coordinate information of the positioning target location includes:
acquiring user description information corresponding to a positioning target place, and extracting description keywords in the user description information;
matching the description keywords with the landmark description information through fuzzy matching;
when landmark descriptive information matched with the descriptive keywords exists, landmarks corresponding to the landmark descriptive information matched with the descriptive keywords are used as positioning target places, and coordinate information of the positioning target places is obtained.
6. The method of claim 5, wherein after matching the description keyword with the landmark description information by fuzzy matching, further comprising:
when landmark description information matched with the description keywords does not exist, labeling the landmarks in the images to be identified, and pushing the labeled images to be identified to a user;
and receiving target selection information fed back by a user according to the image to be identified, taking a landmark corresponding to the target selection information as a positioning target place, and acquiring coordinate information of the positioning target place.
7. A landmark positioning device, the device comprising:
the image acquisition module is used for acquiring an image to be identified corresponding to an external scene of the automobile, wherein the image to be identified is provided by a vehicle-mounted camera of the automobile;
the landmark information acquisition module is used for acquiring landmark position information, depth of field information and current coordinate information of an automobile of a landmark in the image to be identified, wherein the landmark position information is the position information of the landmark in the image to be identified, acquiring the distance between the landmark and an image longitudinal bisector according to the landmark position information of the landmark, acquiring the image transverse half length of the image to be identified and the maximum viewing angle of the vehicle-mounted camera, determining the direction information of the landmark relative to the automobile according to the distance between the landmark and the image longitudinal bisector, the image transverse half length and the maximum viewing angle, determining the distance information of the landmark relative to the automobile according to the current coordinate information of the automobile, and determining the coordinate information of the landmark according to the direction information and the distance information of the landmark relative to the automobile;
the description information acquisition module is used for searching landmark description information corresponding to the landmark in a preset landmark database according to the coordinate information of the landmark;
the target positioning module is used for acquiring user description information corresponding to a positioning target place, searching the positioning target place in the landmark according to the user description information and the landmark description information, and acquiring coordinate information of the positioning target place, wherein the user description information is input by a user through voice and then acquired through voice recognition.
8. The apparatus of claim 7, wherein the description information of the landmark comprises a name of the landmark.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911225170.9A CN111159459B (en) | 2019-12-04 | 2019-12-04 | Landmark positioning method, landmark positioning device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911225170.9A CN111159459B (en) | 2019-12-04 | 2019-12-04 | Landmark positioning method, landmark positioning device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111159459A CN111159459A (en) | 2020-05-15 |
| CN111159459B true CN111159459B (en) | 2023-08-11 |
Family
ID=70556348
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911225170.9A Active CN111159459B (en) | 2019-12-04 | 2019-12-04 | Landmark positioning method, landmark positioning device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111159459B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111931702B (en) * | 2020-09-14 | 2021-02-26 | 宁波均联智行科技股份有限公司 | Target pushing method, system and equipment based on eyeball tracking |
| CN112261584A (en) * | 2020-10-13 | 2021-01-22 | 恒大新能源汽车投资控股集团有限公司 | Geographic fence determination method and device and electronic equipment |
| CN112896176B (en) * | 2021-01-25 | 2022-10-18 | 合创汽车科技有限公司 | Vehicle use environment perception method, system, computer device and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007078408A (en) * | 2005-09-12 | 2007-03-29 | Alpine Electronics Inc | In-car navigation apparatus |
| WO2015113270A1 (en) * | 2014-01-29 | 2015-08-06 | 华为技术有限公司 | Mobile terminal positioning method and apparatus |
| CN104956184A (en) * | 2013-01-29 | 2015-09-30 | 高通股份有限公司 | Landmark based positioning with verbal input |
| CN105277190A (en) * | 2014-06-30 | 2016-01-27 | 现代自动车株式会社 | Apparatus for a self localization of a vehicle |
| CN108694882A (en) * | 2017-04-11 | 2018-10-23 | 百度在线网络技术（北京）有限公司 | Method, apparatus and equipment for marking map |
| CN109029444A (en) * | 2018-06-12 | 2018-12-18 | 深圳职业技术学院 | One kind is based on images match and sterically defined indoor navigation system and air navigation aid |
| CN109073404A (en) * | 2016-05-02 | 2018-12-21 | 谷歌有限责任公司 | For the system and method based on terrestrial reference and real time image generation navigation direction |
| CN109964260A (en) * | 2016-08-10 | 2019-07-02 | 兹沃公司 | For providing the method and apparatus of object-oriented navigation direction |
| CN110503123A (en) * | 2018-05-17 | 2019-11-26 | 奥迪股份公司 | Image position method, device, computer equipment and storage medium |
-
2019
- 2019-12-04 CN CN201911225170.9A patent/CN111159459B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007078408A (en) * | 2005-09-12 | 2007-03-29 | Alpine Electronics Inc | In-car navigation apparatus |
| CN104956184A (en) * | 2013-01-29 | 2015-09-30 | 高通股份有限公司 | Landmark based positioning with verbal input |
| WO2015113270A1 (en) * | 2014-01-29 | 2015-08-06 | 华为技术有限公司 | Mobile terminal positioning method and apparatus |
| CN105277190A (en) * | 2014-06-30 | 2016-01-27 | 现代自动车株式会社 | Apparatus for a self localization of a vehicle |
| CN109073404A (en) * | 2016-05-02 | 2018-12-21 | 谷歌有限责任公司 | For the system and method based on terrestrial reference and real time image generation navigation direction |
| CN109964260A (en) * | 2016-08-10 | 2019-07-02 | 兹沃公司 | For providing the method and apparatus of object-oriented navigation direction |
| CN108694882A (en) * | 2017-04-11 | 2018-10-23 | 百度在线网络技术（北京）有限公司 | Method, apparatus and equipment for marking map |
| CN110503123A (en) * | 2018-05-17 | 2019-11-26 | 奥迪股份公司 | Image position method, device, computer equipment and storage medium |
| CN109029444A (en) * | 2018-06-12 | 2018-12-18 | 深圳职业技术学院 | One kind is based on images match and sterically defined indoor navigation system and air navigation aid |
Non-Patent Citations (1)
| Title |
|---|
| 姜海涛 ; 田国会 ; 薛英花 ; 李荣宽 ; .新型人工地标的设计、识别、定位及应用.山东大学学报(工学版).2011,(02),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111159459A (en) | 2020-05-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107563419B (en) | Train positioning method combining image matching and two-dimensional code | |
| CN111159459B (en) | Landmark positioning method, landmark positioning device, computer equipment and storage medium | |
| EP2450667B1 (en) | Vision system and method of analyzing an image | |
| US9324003B2 (en) | Location of image capture device and object features in a captured image | |
| EP2458336B1 (en) | Method and system for reporting errors in a geographic database | |
| CN109029444B (en) | Indoor navigation system and method based on image matching and space positioning | |
| KR20190082071A (en) | Method, apparatus, and computer readable storage medium for updating electronic map | |
| KR102200299B1 (en) | A system implementing management solution of road facility based on 3D-VR multi-sensor system and a method thereof | |
| CN109596121B (en) | Automatic target detection and space positioning method for mobile station | |
| US8687853B2 (en) | Method, system and computer-readable recording medium for providing service using electronic map | |
| WO2020039937A1 (en) | Position coordinates estimation device, position coordinates estimation method, and program | |
| CN111256687A (en) | Map data processing method and device, acquisition equipment and storage medium | |
| US20200189527A1 (en) | Information processing system, program, and information processing method | |
| JP2006119591A (en) | Map information generation method, map information generation program and map information collection apparatus | |
| CN111837013A (en) | Method and system for determining geographic position based on image | |
| JP2011112556A (en) | Search target position locating device, method, and computer program | |
| CN112689234B (en) | Indoor vehicle positioning method, device, computer equipment and storage medium | |
| CN109997052B (en) | Method and system for generating environment model and positioning by using cross sensor feature point reference | |
| CN116097128A (en) | Method and device for determining the position of a vehicle | |
| CN110503123B (en) | Image positioning method, device, computer equipment and storage medium | |
| US10930009B2 (en) | Geolocation system | |
| JPH08255245A (en) | Landmark recognizing device and landmark recognizing method | |
| JP2021068240A (en) | Road surface image management system and road surface image management method thereof | |
| TWI770511B (en) | An image recognition and navigation device | |
| US11250275B2 (en) | Information processing system, program, and information processing method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210111 Address after: 511458 room 1402, basement and jinmaowan (building T7), No.01, jinmaozhong 2nd Street, Huangge Town, Nansha District, Guangzhou City, Guangdong Province Applicant after: Hengda hengchi new energy automobile technology (Guangdong) Co.,Ltd. Address before: 511458 room 1403, jinmaowan (T7 building) and basement, No.01, jinmaozhong 2nd Street, Huangge Town, Nansha District, Guangzhou City, Guangdong Province Applicant before: Evergrande new energy vehicle technology (Guangdong) Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |