CN109710705A - Map point of interest treating method and apparatus - Google Patents
Map point of interest treating method and apparatus Download PDFInfo
- Publication number
- CN109710705A CN109710705A CN201811473453.0A CN201811473453A CN109710705A CN 109710705 A CN109710705 A CN 109710705A CN 201811473453 A CN201811473453 A CN 201811473453A CN 109710705 A CN109710705 A CN 109710705A
- Authority
- CN
- China
- Prior art keywords
- interest
- point
- frame image
- image data
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Image Analysis (AREA)
Abstract
The application proposes a kind of map point of interest treating method and apparatus, wherein method includes: the image data for obtaining the first user acquisition；Image data is pre-processed, to obtain frame image to be processed from image data；It whether detects in each frame image to be processed comprising point of interest；If in first frame image including the first interest point data, according to the acquisition position of first frame image, each effective point of interest is obtained；Verify the first point of interest whether with any effective interest points matching；If the first point of interest does not match with any effective point of interest, it is determined that include point of interest to be updated at the acquisition position of first frame image.This method can be realized promotion treatment effeciency, reduce the collection period of interest point data, and save acquisition cost.
Description
Technical field
This application involves technical field of image processing more particularly to a kind of map point of interest treating method and apparatus.
Background technique
With the continuous development of terminal technology and Internet technology, various application program (Application, abbreviations
APP it) continuously emerges like the mushrooms after rain.User can install different classes of APP, example on the terminal device according to self-demand
Such as map class APP, social category APP, payment class APP, and the extensive use of map class APP, so that the life of user is further
It is convenient.Wherein, map datum, i.e. point of interest (Point of Interest, abbreviation POI) are the basis of map, the trip of user
It is unable to do without and covers the complete and accurate POI data of coordinate.
In the related technology, for the POI data in map class APP, be by profession map producing quotient be acquired, and
It is obtained after being processed.
However, this data acquisition modes not only higher cost, but also data acquisition, the period of processing are longer.
Summary of the invention
The application proposes a kind of map point of interest treating method and apparatus, to realize promotion treatment effeciency, reduces point of interest
The collection period of data, and acquisition cost is saved, it is longer for solving data acquisition, the period of processing in the prior art, and
The technical issues of higher cost.
The application one side embodiment proposes a kind of map point of interest processing method, comprising:
Obtain the image data of the first user acquisition；
The image data is pre-processed, to obtain frame image to be processed from the image data；
It whether detects in each frame image to be processed comprising point of interest；
If in first frame image including the first interest point data, according to the acquisition position of the first frame image, obtain
Each effective point of interest；
Verify the first point of interest whether with any effective interest points matching；
If first point of interest does not match with any effective point of interest, it is determined that the acquisition position of the first frame image
It sets place and includes point of interest to be updated.
The map point of interest processing method of the embodiment of the present application, by obtaining the image data of the first user acquisition, and it is right
Image data is pre-processed, and to obtain frame image to be processed from image data, later, detecting in each frame image to be processed is
No includes point of interest, if in first frame image including the first interest point data, according to the acquisition position of first frame image, is obtained
Each effective point of interest, and verify the first point of interest whether with any effective interest points matching, if not, it is determined that first frame image
It include point of interest to be updated at acquisition position.It is handled in real time according to the image data that the first user acquires as a result, with true
Surely it whether there is point of interest to be updated, treatment effeciency can be promoted, reduce the collection period of interest point data, and, it is only necessary to
First user carries out the acquisition of image data, can reduce artificial degree of participation, saves acquisition cost.
The another aspect embodiment of the application proposes a kind of map point of interest processing unit, comprising:
First obtains module, for obtaining the image data of the first user acquisition；
Processing module, for being pre-processed to the image data, to obtain frame to be processed from the image data
Image；
Detection module, for whether detecting in each frame image to be processed comprising point of interest；
Second obtains module, if for including the first interest point data in first frame image, according to the first frame figure
The acquisition position of picture obtains each effective point of interest；
Inspection module, for verify the first point of interest whether with any effective interest points matching；
First determining module, if not matched for first point of interest with any effective point of interest, it is determined that described
It include point of interest to be updated at the acquisition position of first frame image.
The map point of interest processing unit of the embodiment of the present application, by obtaining the image data of the first user acquisition, and it is right
Image data is pre-processed, and to obtain frame image to be processed from image data, later, detecting in each frame image to be processed is
No includes point of interest, if in first frame image including the first interest point data, according to the acquisition position of first frame image, is obtained
Each effective point of interest, and verify the first point of interest whether with any effective interest points matching, if not, it is determined that first frame image
It include point of interest to be updated at acquisition position.It is handled in real time according to the image data that the first user acquires as a result, with true
Surely it whether there is point of interest to be updated, treatment effeciency can be promoted, reduce the collection period of interest point data, and, it is only necessary to
First user carries out the acquisition of image data, can reduce artificial degree of participation, saves acquisition cost.
The another aspect embodiment of the application proposes a kind of computer equipment, comprising: memory, processor and is stored in
On reservoir and the computer program that can run on a processor, when the processor executes described program, realize as before the application
State the map point of interest processing method of embodiment proposition.
The another aspect embodiment of the application proposes a kind of non-transitorycomputer readable storage medium, is stored thereon with meter
Calculation machine program, which is characterized in that the map interest proposed such as the application previous embodiment is realized when the program is executed by processor
Point processing method.
To achieve the goals above, the 5th aspect embodiment of the application proposes a kind of computer program product, when described
When instruction in computer program product is executed by processor, execute at the map point of interest proposed such as the application previous embodiment
Reason method.
The additional aspect of the application and advantage will be set forth in part in the description, and will partially become from the following description
It obtains obviously, or recognized by the practice of the application.
Detailed description of the invention
The application is above-mentioned and/or additional aspect and advantage will become from the following description of the accompanying drawings of embodiments
Obviously and it is readily appreciated that, in which:
Fig. 1 is the flow diagram of map point of interest processing method provided by the embodiment of the present application one；
Fig. 2 is the flow diagram of map point of interest processing method provided by the embodiment of the present application two；
Fig. 3 is the flow diagram of map point of interest processing method provided by the embodiment of the present application three；
Fig. 4 is the flow diagram of map point of interest processing method provided by the embodiment of the present application four；
Fig. 5 is the flow diagram of map point of interest processing method provided by the embodiment of the present application five；
Fig. 6 is the structural schematic diagram of map point of interest processing unit provided by the embodiment of the present application six；
Fig. 7 is the structural schematic diagram of map point of interest processing unit provided by the embodiment of the present application seven；
Fig. 8 shows the block diagram for being suitable for the exemplary computer device for being used to realize the application embodiment.
Specific embodiment
Embodiments herein is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, it is intended to for explaining the application, and should not be understood as the limitation to the application.
Currently, the collection process of POI data is divided into field data acquisition link and interior industry processing link.Wherein, field data acquisition ring
Section carries out the acquisition of image data and coordinate data with equipment such as photographic device, panorama vehicle, smart phones, and data acquisition is completed
Afterwards, into interior industry processing link, the extraction and cleaning of POI data are carried out by interior industry machining tool.
Due to two links that field data acquisition link and interior industry processing link are independent separate, it is intended to protect in each link
The accuracy and safety of data are demonstrate,proved, process cycle is longer.For example, when professional team acquires POI data, general POI data
Production time may break through moon grade, and when crowdsourcing user acquires POI data, the production time of general POI data about one week.
The period longer technical problem that the application is acquired mainly for POI data in the prior art, processed, provides one kind
Map point of interest processing method.
The map point of interest processing method of the embodiment of the present application, by obtaining the image data of the first user acquisition, and it is right
Image data is pre-processed, and to obtain frame image to be processed from image data, later, detecting in each frame image to be processed is
No includes point of interest, if in first frame image including the first interest point data, according to the acquisition position of first frame image, is obtained
Each effective point of interest, and verify the first point of interest whether with any effective interest points matching, if not, it is determined that first frame image
It include point of interest to be updated at acquisition position.It is handled in real time according to the image data that the first user acquires as a result, with true
Surely it whether there is point of interest to be updated, treatment effeciency can be promoted, reduce the collection period of interest point data, and, it is only necessary to
First user carries out the acquisition of image data, can reduce artificial degree of participation, saves acquisition cost.
Below with reference to the accompanying drawings the map point of interest treating method and apparatus of the embodiment of the present application is described.Specifically describing this Shen
It please be before embodiment, in order to make it easy to understand, essential term is introduced first:
First user, for the user for acquiring image data.
Second user, when in the second frame image not include point of interest, the user of acquisition verification image data.
Third user, when being that the acquisition position of first frame image includes point of interest to be updated, acquisition verification image data
User.
Wherein, term " first ", " second ", " third " are used for description purposes only, and are not understood to indicate or imply phase
To importance or implicitly indicate the quantity of indicated technical characteristic.
Fig. 1 is the flow diagram of map point of interest processing method provided by the embodiment of the present application one.
The embodiment of the present application is configured in map point of interest processing unit with the map point of interest processing method and is illustrated
Illustrate, which can be configured in any computer equipment, so that the computer equipment executes ground
Figure point of interest processing function.
Wherein, computer equipment can be PC (Personal Computer, abbreviation PC), cloud device, movement
Equipment etc., mobile device can for example have for mobile phone, tablet computer, personal digital assistant, wearable device, mobile unit etc.
The hardware device of various operating systems, touch screen and/or display screen.
As shown in Figure 1, the map point of interest processing method the following steps are included:
Step 101, the image data of the first user acquisition is obtained.
In the embodiment of the present application, can include by relevant devices, acquisitions such as photographic device, mobile devices by the first user
The image data of each point of interest.
As a kind of possible implementation, in order to promote the treatment effeciency of map point of interest in subsequent step, the application
In embodiment, the first user can carry out the real-time acquisition of image data with direct-seeding, and the image data of acquisition can be sent
To map point of interest processing unit.Further, in order to guarantee image data send real-time and safety, can be by image
Data carry out coded treatment, and by way of Streaming Media, the image data after coding is sent in real time at map point of interest
Device is managed, at the same time it can also which the information such as acquisition position, acquisition angles are sent to map point of interest processing unit, correspondingly, ground
Figure point of interest processing unit can be decoded processing after getting the image data after coding to it, to determine that first uses
The image data of family acquisition.
In the embodiment of the present application, the first user acquisition is the image data in real world, it is ensured that the number of acquisition
According to validity and reasonability.
Step 102, image data is pre-processed, to obtain frame image to be processed from image data.
It should be noted that will be made comprising multiple image if all being handled in real time each frame image in image data
At the waste of computing resource, also, the algorithm in subsequent step between progress frame processing result image when association is complex, because
This, in the embodiment of the present application, in order to reduce the workload of calculating, promotes the real-time of processing, in map point of interest processing unit
After getting image data, image data can be pre-processed, to obtain frame image to be processed from image data.
As a kind of possible implementation of the embodiment of the present application, since there are similar for the content between sequential frame image
Property promotes the real-time of processing to reduce the workload of calculating, can be by the similar different frame image of height in the application
Carry out duplicate removal processing.Specifically, can according to the similarity between each frame picture material in image data, to image data into
Row duplicate removal processing.For example, similarity can be higher than to the different frame image of preset threshold, duplicate removal processing is carried out.Wherein, threshold is preset
It is pre-set for being worth, for example, 90%.
As the alternatively possible implementation of the embodiment of the present application, in order to reduce the workload of calculating, promotion processing
Real-time, in the application, image data can also be carried out to take out frame processing.Specifically, can according to preset pumping frame pitch,
Cutting processing is carried out to image data.Wherein, it is pre-set for taking out frame pitch, such as marking the pumping frame pitch is d.
As another possible implementation of the embodiment of the present application, due to the close different frame image of acquisition position it
Between content there are similitudes, in order to reduce the workload of calculating, promote the real-time of processing, can be to basis in the application
The corresponding acquisition position of each frame image, carries out segment processing for image data in image data, then can be from each segment data
It is middle to obtain frame image to be processed.For example, being directed to each segment data, a frame image can be randomly selected as frame image to be processed, or
Person, using the first frame image of each segment data as frame image to be processed, with no restriction to this.
It should be noted that above-mentioned only execute example, practical application with duplicate removal processing, cutting processing and segment processing side by side
When, frame image to be processed can also be determined, to be promoted in subsequent step according to duplicate removal processing, cutting processing and/or segment processing
The accuracy and reliability of processing result.
For example, after getting image data, pumping frame can be carried out to first frame image, such as mark the first frame
Image is I1, then, the extraction of the second frame image, such as the second frame of label can be carried out to image data according to frame pitch d is taken out
Image is I2, at this point it is possible to judge whether the similarity between I2 and I1 content is higher than preset threshold, if so, deleting to I2
It removes, at this point it is possible to carry out the extraction of third frame image to image data, such as label third frame image is I3, and continues to judge
Whether the similarity between I3 and I1 content is higher than preset threshold ..., until determining that similarity is lower than each frame image of preset threshold,
And each frame image using similarity lower than preset threshold is as frame image to be processed.
Step 103, whether detect in each frame image to be processed includes point of interest.
In the embodiment of the present application, point of interest refers to lives closely related geographical entity with user, and point of interest for example can be with
It for school, bank, restaurant, gas station, hospital, supermarket etc., or can be a house, a retail shop, mailbox, one
A bus station etc., with no restriction to this.
In the embodiment of the present application, after determining each frame image to be processed, it can be determined that whether wrapped in each frame image to be processed
Containing point of interest.
As a kind of possible implementation, each frame to be processed can be determined based on the image processing techniques of deep learning
It whether include point of interest in image, to promote the accuracy of testing result.Specifically, it can use and be largely labeled with point of interest
Sample image is trained target detection model (such as Faster-RCNN model etc.), is then examined using the target after training
Model is surveyed, each frame image to be processed is identified, that is, whether can determine in each frame image to be processed comprising point of interest.
Step 104, if including the first interest point data in first frame image, according to the acquisition position of first frame image,
Obtain each effective point of interest.
In the embodiment of the present application, acquisition position can be coordinate data, or can uniquely position geographical location for other
Data, such as street number etc., with no restriction to this.Effective point of interest refer in map currently point of interest, i.e.,
The point of interest for including in figure.
In the embodiment of the present application, when including interest point data in first frame image, it is emerging to be denoted as first in the embodiment of the present application
When interesting point data, can also judge whether first point of interest is already present effective point of interest in map.Specifically, Ke Yigen
According to the acquisition position of first frame image, obtained and the matched each effective point of interest of the acquisition position from map.
For example, can be obtained near location point A from map when the acquisition position of first frame image is location point A
Each active position point, alternatively, from each active position point obtained in map at a distance from location point A in preset range.
Step 105, verification the first point of interest whether with any effective interest points matching.
In the embodiment of the present application, each effective point of interest for including in the first point of interest and map can be matched, really
Fixed first point of interest whether with any effective interest points matching, if the first point of interest and one of them effective interest points matching,
Show that the first point of interest is present in map, at this point it is possible to first point of interest be abandoned, if it is not, thening follow the steps 106.
Step 106, if the first point of interest does not match with any effective point of interest, it is determined that the acquisition position of first frame image
It sets place and includes point of interest to be updated.
In the embodiment of the present application, when the first point of interest and any effective point of interest mismatch, then show that this is first emerging
Interest point do not exist in map, at this point it is possible to determine first frame image acquisition position at include point of interest to be updated.
Further, it after at the acquisition position for determining first frame image comprising point of interest to be updated, can treat more
New interest point carries out replacement or delete processing.
For example, when the acquisition position according to first frame image, determine that the number of effective point of interest is 3, respectively
Point of interest A, point of interest B and point of interest C, it is assumed that the first point of interest is point of interest D, if point of interest D and point of interest A, point of interest B and
Point of interest C is mismatched, at this point, there may be two kinds of situations, it is a kind of are as follows: in point of interest A, point of interest B and point of interest C wherein
One point of interest is substituted by point of interest D, another are as follows: on the basis of point of interest A, point of interest B and point of interest C, increases newly
Therefore one point of interest D when the first point of interest does not match with any effective point of interest, can determine first frame image
Acquisition position at include point of interest to be updated, at this point it is possible to be replaced to point of interest to be updated or delete processing.
The map point of interest processing method of the embodiment of the present application, by obtaining the image data of the first user acquisition, and it is right
Image data is pre-processed, and to obtain frame image to be processed from image data, later, detecting in each frame image to be processed is
No includes point of interest, if in first frame image including the first interest point data, according to the acquisition position of first frame image, is obtained
Each effective point of interest, and verify the first point of interest whether with any effective interest points matching, if not, it is determined that first frame image
It include point of interest to be updated at acquisition position.It is handled in real time according to the image data that the first user acquires as a result, with true
Surely it whether there is point of interest to be updated, treatment effeciency can be promoted, reduce the collection period of interest point data, and, it is only necessary to
First user carries out the acquisition of image data, can reduce artificial degree of participation, saves acquisition cost.
As a kind of possible implementation, due to, needing to take out in a step 102 to the frame image in image data
Frame processing, duplicate removal processing and/or cutting processing, therefore, before step 102, it is thus necessary to determine that the frame figure for including in image data
As quantity is greater than first threshold.Wherein, first threshold is pre-set.
As a kind of possible implementation, when not including point of interest in a certain frame image in frame image to be processed,
Verification image data can be acquired by multiple other users, and according to the verification image data, is verified and whether wrapped in the frame image
Containing point of interest, to promote the accuracy and reliability of definitive result.Below with reference to Fig. 2, the above process is described in detail.
Fig. 2 is the flow diagram of map point of interest processing method provided by the embodiment of the present application two.
As shown in Fig. 2, on the basis of embodiment shown in Fig. 1, after step 103, the map point of interest processing method
Can with the following steps are included:
Step 201, if not including point of interest in the second frame image, according to the acquisition position of the second frame image, the is generated
One crowdsourcing verifies task.
Step 202, the first crowdsourcing verification task is issued to multiple second users, so that multiple second users acquisition verification shadow
As data.
As a kind of possible implementation, in order to save journey cost and time cost, can be worked as according to each user
The location information at preceding place and the corresponding acquisition position of the second frame image, determine multiple second users.Specifically, it can determine every
The location information that a user is currently located, and the position that the corresponding acquisition position of the second frame image and each user are currently located is believed
Breath is compared, if the distance between the corresponding acquisition position of the second frame image and the location information of user being currently located are less than
Pre-determined distance, it is determined that the user is second user.
Step 203, whether the verification image data acquired according to multiple second users verifies in the second frame image comprising emerging
Interesting point.
In the embodiment of the present application, when not including point of interest in the second frame image, for example, only including in the second frame image
Tree, road, sky etc., at this point, can not determine whether at the corresponding acquisition position of the second frame image include point of interest.Therefore,
In the application, it can generate the first crowdsourcing according to the acquisition position of the second frame image and verify task, and under multiple second users
Send out the first crowdsourcing verification task, thus after multiple second users receive the first crowdsourcing verification task, can according to this first
The acquisition position carried in crowdsourcing verification task, resurveys verification image data, thus the map interest of the embodiment of the present application
Point processing unit, after the verification image data for receiving the acquisition of multiple second users, can verify in the second frame image whether
Comprising point of interest, the accuracy and reliability that point of interest determines is promoted, and then guarantees the accuracy of POI data in map.
It further, does not include interest in the second frame image in order to promote the accuracy and reliability that point of interest determines
When point, it can also generate the first crowdsourcing according to the acquisition position and acquisition angles of the second frame image and verify task, and to multiple the
Two users issue the first crowdsourcing verification task, thus after multiple second users receive the first crowdsourcing verification task, Ke Yigen
According to the acquisition position and acquisition angles carried in the first crowdsourcing verification task, verification image data is resurveyed, thus this Shen
Please the map point of interest processing unit of embodiment can school after the verification image data for receiving the acquisition of multiple second users
It whether tests in the second frame image comprising point of interest, promotes the accuracy and reliability that point of interest determines, and then guarantee POI in map
The accuracy of data.
The map point of interest processing method of the embodiment of the present application, when by not including point of interest in the second frame image, root
It according to the acquisition position of the second frame image, generates the first crowdsourcing and verifies task, and issue the first crowdsourcing verification to multiple second users
Task, so that multiple second users acquisition verification image data, according to the verification image data that multiple second users acquire, verification
It whether include point of interest in second frame image.In the application, verification image data is acquired by multiple second users, and according to multiple
Whether the verification image data of second user acquisition, verifying in the second frame image includes point of interest, can promote point of interest and determine
Accuracy and reliability, to guarantee the accuracy of POI data in map.
It include point of interest to be updated at the acquisition position for determining first frame image as a kind of possible implementation
Later, can in map currently each effective point of interest verified, judge each effective point of interest whether with currently
Any one interest points matching detected, if some effective point of interest and currently detected one of interest points matching,
Then determine that effective point of interest is effective, if some effective point of interest is mismatched with any one currently detected point of interest,
Then determine that effective point of interest is point of interest to be updated.Below with reference to Fig. 3, the above process is described in detail.
Fig. 3 is the flow diagram of map point of interest processing method provided by the embodiment of the present application three.
As shown in figure 3, on the basis of Fig. 1 and embodiment illustrated in fig. 2, which can also include
Following steps:
Step 301, each effectively point of interest of judgement whether with the second interest points matching for including in each third frame image,
In, the acquisition position of third frame image between the acquisition position of first frame image at a distance from be less than threshold value.
Wherein, threshold value is pre-set, it is to be understood that threshold value is lesser distance value.
In the embodiment of the present application, acquisition position and first frame image can be determined according to the acquisition position of first frame image
Acquisition position between distance be less than the third frame image of threshold value, that is, determine similar with first frame picture material third frame figure
Picture.For each effective point of interest, it can be determined that effective point of interest whether with the second interest for including in each third frame image
Point matching, if so, determining that effective point of interest is effective, if not, it is determined that effective point of interest is point of interest to be updated.
Step 302, if first effective point of interest does not match with each second point of interest, it is determined that first effective point of interest
For point of interest to be updated.
In the embodiment of the present application, when first effective point of interest does not match with each second point of interest, it is determined that this
One effective point of interest is point of interest to be updated.Thus, it is possible to realize in map currently each effective point of interest carry out school
It tests, to determine whether corresponding effective point of interest is effective, each effective point of interest that may be implemented in map carries out Dynamic Maintenance, mentions
Rise the accuracy and real-time of POI data in map.
It include point of interest to be updated at the acquisition position for determining first frame image as a kind of possible implementation
When, verification image data can be acquired by multiple other users, and according to the verification image data, verify the acquisition of the frame image
It whether include point of interest to be updated at position, to promote the accuracy and reliability of definitive result.Below with reference to Fig. 4, to upper
The process of stating is described in detail.
Fig. 4 is the flow diagram of map point of interest processing method provided by the embodiment of the present application four.
As shown in figure 4, the map point of interest processing method may comprise steps of:
Step 401, it according to the acquisition position of first frame image and each effective point of interest, generates the second crowdsourcing verification and appoints
Business.
Step 402, the second crowdsourcing verification task is issued to multiple third users, so that multiple third users acquire verification shadow
As data.
As a kind of possible implementation, in order to save journey cost and time cost, can be worked as according to each user
The location information and the corresponding acquisition position of first frame image at preceding place, determine multiple third users.Specifically, it can determine every
The location information that a user is currently located, and the position that the corresponding acquisition position of first frame image and each user are currently located is believed
Breath is compared, if the distance between the corresponding acquisition position of first frame image and the location information of user being currently located are less than
Pre-determined distance, it is determined that the user is third user.
Step 403, according to the verification image data of multiple third users acquisition, at the acquisition position for determining first frame image
The point of interest to be updated for including.
It, can be with when at the acquisition position for determining first frame image including point of interest to be updated in the embodiment of the present application
It according to the acquisition position of first frame image and each effective point of interest, generates the second crowdsourcing and verifies task, and used to multiple thirds
Family issues the second crowdsourcing verification task, can be according to the thus after multiple third users receive the second crowdsourcing verification task
Two crowdsourcings verify the acquisition position that task carries, and verification image data are resurveyed, thus the map interest of the embodiment of the present application
Point processing unit can be according to each effective point of interest, really after the verification image data for receiving multiple third user acquisitions
Determine the point of interest to be updated for including at the acquisition position of first frame image.
Further, in order to promote the accuracy and reliability that point of interest to be updated determines, first frame image is being determined
Acquisition position at when including point of interest to be updated, can also be according to the acquisition position of first frame image, acquisition angles and every
A effective point of interest generates the second crowdsourcing and verifies task, and issues the second crowdsourcing verification task to multiple third users, to work as
It, can be according to the acquisition position carried in the second crowdsourcing verification task after multiple third users receive the second crowdsourcing verification task
It sets and acquisition angles, verification image data is resurveyed, so that the map point of interest processing unit of the embodiment of the present application, is receiving
After the verification image data acquired to multiple third users, adopting for first frame image can be determined according to each effective point of interest
The point of interest to be updated that Ji Weizhichu includes.
It verifies, is promoted comprising point of interest to be updated at the acquisition position to first frame image thus, it is possible to realize
The confidence level that point of interest to be updated determines, and then guarantee the accuracy of POI data in map.
It as an example, is map point of interest processing method provided by the embodiment of the present application five referring to Fig. 5, Fig. 5
Flow diagram.
As shown in figure 5, the map point of interest processing method includes two process flows, respectively field data acquisition process and interior
Industry automatic processing and human assistance process flow.
Wherein, field data acquisition process:
(1) personnel are adopted outside, the first user is denoted as in the embodiment of the present application, it can be by equipment such as cameras, with the side of live streaming
The real-time acquisition of formula progress POI data.The image data of acquisition can upload to video content services by way of Streaming Media
Device, at the same time it can also upload acquisition position and acquisition angles together.
It (2) can be the independent identification code PID of each first user setting, also, acquire image in each first user
When data, interim identity TID can be established for the image data of acquisition, wherein interim identity is when acquiring image data
It generates, is destroyed after terminating acquisition.
It, can be by disappearing when the frame amount of images for including in the image data of each first user acquisition is greater than first threshold
Push-mechanism is ceased, image data is pushed into video image processing links.The recording mechanism of tag images data are as follows: PID_TID_
INDEX, wherein during the first user acquires image data, when pushing image data every time, INDEX can be incremented by successively,
For example, it is assumed that the PID of the first user is p23, the image data currently acquired in real time establishes interim identity TID and is
20180924123212, then during this acquisition image data in real time, the recording mechanism of the image data of push is p23_
201809241232123_1, p23_201809241232123_2, p23_201809241232123_3 etc..
Field data acquisition process and interior industry automatic processing and human assistance process flow:
(3) image data can be pre-processed, to obtain frame image to be processed from image data.Specifically, right
The image data that INDEX is 1 in recording mechanism PID_TID_INDEX carries out the extraction of first frame image, such as marks the first frame
Image is I1, then, the extraction of the second frame image, such as the second frame of label can be carried out to image data according to frame pitch d is taken out
Image is I2, at this point it is possible to judge whether the similarity between I2 and I1 content is higher than preset threshold, if so, deleting to I2
It removes, at this point it is possible to carry out the extraction of third frame image to image data, such as label third frame image is I3, and continues to judge
Whether the similarity between I3 and I1 content is higher than preset threshold ..., until determining that similarity is lower than each frame image of preset threshold,
Frame end is taken out, determines each frame image to be processed.
(4) point of interest identification is carried out to each frame image to be processed of extraction, for example, deep learning target detection can be passed through
The computer vision techniques such as algorithm, such as Faster-RCNN algorithm identify the point of interest in each frame image to be processed.
For each frame image to be processed, if there are points of interest in the frame image, by each effective point of interest in point of interest and map
It is matched, it is determined whether successful match completes POI verifying, if not, it is determined that this is emerging if so, determining that the point of interest is effective
Interest point is newly-increased point of interest.
(5) if point of interest is not present in the frame image, the first crowdsourcing can be generated according to the acquisition position of the frame image
Verification task, and multiple second users are issued to, so that multiple second users acquisition verification image data, so as to according to more
Whether the verification image data of a second user acquisition, verify comprising point of interest in the frame image, if so, can be by the frame figure
The point of interest for including as in is matched with each effective point of interest in map, to determine whether the point of interest is effective.
In the embodiment of the present application, second user and third user all can be Internet user, by multiple Internet users
Point of interest in image is verified, the cost of professional's culture can be reduced.
In order to realize above-described embodiment, the application also proposes a kind of map point of interest processing unit.
Fig. 6 is the structural schematic diagram of map point of interest processing unit provided by the embodiment of the present application six.
As shown in fig. 6, the map point of interest processing unit 100 includes: the first acquisition module 101, processing module 102, inspection
It surveys module 103, second and obtains module 104, inspection module 105 and the first determining module 106.
Wherein, first module 101 is obtained, for obtaining the image data of the first user acquisition.
Processing module 102, for being pre-processed to image data, to obtain frame image to be processed from image data.
As a kind of possible implementation, processing module 102 is specifically used for: according to each frame figure in image data
As the similarity between content, duplicate removal processing is carried out to image data.
As alternatively possible implementation, processing module 102 is specifically used for: according to preset pumping frame pitch, to shadow
As data carry out cutting processing.
As another possible implementation, processing module 102 is specifically used for: according to frame figure each in image data
As corresponding acquisition position, image data is subjected to segment processing, to obtain frame image to be processed from each segment data.
Detection module 103, for whether detecting in each frame image to be processed comprising point of interest.
Second obtains module 104, if for including the first interest point data in first frame image, according to first frame image
Acquisition position, obtain each effective point of interest.
Inspection module 105, for verify the first point of interest whether with any effective interest points matching.
First determining module 106, if not matched for the first point of interest with any effective point of interest, it is determined that first frame
It include point of interest to be updated at the acquisition position of image.
Further, in a kind of possible implementation of the embodiment of the present application, referring to Fig. 7, embodiment shown in Fig. 6
On the basis of, which can also include:
Generation module 107, if for not including point of interest in the second frame image, according to the acquisition position of the second frame image
It sets, generates the first crowdsourcing and verify task.
Module 108 is issued, for issuing the first crowdsourcing verification task to multiple second users, so that multiple second users are adopted
Collection verification image data.
Correction verification module 109, the verification image data for being acquired according to multiple second users, verifying in the second frame image is
No includes point of interest.
Second determining module 110, for before issuing the first crowdsourcing verification task to multiple second users, according to each
The location information and the corresponding acquisition position of the second frame image that user is currently located, determine multiple second users.
Judgment module 111, for judge each effective point of interest whether with the second interest for including in each third frame image
Point matching, wherein the acquisition position of third frame image between the acquisition position of first frame image at a distance from be less than threshold value.
Third determining module 112, if not matched for first effective point of interest with each second point of interest, it is determined that the
It include point of interest to be updated at the acquisition position of one frame image.
As a kind of possible implementation, generation module 107 is also used to: according to the acquisition position of first frame image and
Each effective point of interest generates the second crowdsourcing and verifies task.
Module 108 is issued, is also used to issue the second crowdsourcing verification task to multiple third users, so that multiple third users
Acquisition verification image data.
Second determining module 110, is also used to: the verification image data acquired according to multiple third users determines first frame
The point of interest to be updated for including at the acquisition position of image.
Replace removing module 113, at the acquisition position for determining first frame image include point of interest to be updated it
Afterwards, point of interest to be updated is replaced or delete processing.
4th determining module 114, for before pre-processing to image data, determining the frame for including in image data
Amount of images is greater than first threshold.
It should be noted that the explanation of aforementioned to map point of interest processing method embodiment is also applied for the embodiment
Map point of interest processing unit 100, details are not described herein again.
The map point of interest processing unit of the embodiment of the present application, by obtaining the image data of the first user acquisition, and it is right
Image data is pre-processed, and to obtain frame image to be processed from image data, later, detecting in each frame image to be processed is
No includes point of interest, if in first frame image including the first interest point data, according to the acquisition position of first frame image, is obtained
Each effective point of interest, and verify the first point of interest whether with any effective interest points matching, if not, it is determined that first frame image
It include point of interest to be updated at acquisition position.It is handled in real time according to the image data that the first user acquires as a result, with true
Surely it whether there is point of interest to be updated, treatment effeciency can be promoted, reduce the collection period of interest point data, and, it is only necessary to
First user carries out the acquisition of image data, can reduce artificial degree of participation, saves acquisition cost.
In order to realize above-described embodiment, the application also proposes a kind of computer equipment, comprising: memory, processor and deposits
The computer program that can be run on a memory and on a processor is stored up, when processor executes program, is realized as the application is aforementioned
The map point of interest processing method that embodiment proposes.
In order to realize above-described embodiment, the application also proposes a kind of non-transitorycomputer readable storage medium, deposits thereon
Contain computer program, which is characterized in that realize that the application previous embodiment such as proposes ground when the program is executed by processor
Figure point of interest processing method.
In order to realize above-described embodiment, the application also proposes a kind of computer program product, when in computer program product
Instruction when being executed by processor, execute the map point of interest processing method proposed such as the application previous embodiment.
Fig. 8 shows the block diagram for being suitable for the exemplary computer device for being used to realize the application embodiment.What Fig. 8 was shown
Computer equipment 12 is only an example, should not function to the embodiment of the present application and use scope bring any restrictions.
As shown in figure 8, computer equipment 12 is showed in the form of universal computing device.The component of computer equipment 12 can be with
Including but not limited to: one or more processor or processing unit 16, system storage 28 connect different system components
The bus 18 of (including system storage 28 and processing unit 16).
Bus 18 indicates one of a few class bus structures or a variety of, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.It lifts
For example, these architectures include but is not limited to industry standard architecture (Industry Standard
Architecture；Hereinafter referred to as: ISA) bus, microchannel architecture (Micro Channel Architecture；Below
Referred to as: MAC) bus, enhanced isa bus, Video Electronics Standards Association (Video Electronics Standards
Association；Hereinafter referred to as: VESA) local bus and peripheral component interconnection (Peripheral Component
Interconnection；Hereinafter referred to as: PCI) bus.
Computer equipment 12 typically comprises a variety of computer system readable media.These media can be it is any can be by
The usable medium that computer equipment 12 accesses, including volatile and non-volatile media, moveable and immovable medium.
Memory 28 may include the computer system readable media of form of volatile memory, such as random access memory
Device (Random Access Memory；Hereinafter referred to as: RAM) 30 and/or cache memory 32.Computer equipment 12 can be with
It further comprise other removable/nonremovable, volatile/non-volatile computer system storage mediums.Only as an example,
Storage system 34 can be used for reading and writing immovable, non-volatile magnetic media, and (Fig. 8 do not show, commonly referred to as " hard drive
Device ").Although being not shown in Fig. 8, the disk for reading and writing to removable non-volatile magnetic disk (such as " floppy disk ") can be provided and driven
Dynamic device, and to removable anonvolatile optical disk (such as: compact disc read-only memory (Compact Disc Read Only
Memory；Hereinafter referred to as: CD-ROM), digital multi CD-ROM (Digital Video Disc Read Only
Memory；Hereinafter referred to as: DVD-ROM) or other optical mediums) read-write CD drive.In these cases, each driving
Device can be connected by one or more data media interfaces with bus 18.Memory 28 may include that at least one program produces
Product, the program product have one group of (for example, at least one) program module, and it is each that these program modules are configured to perform the application
The function of embodiment.
Program/utility 40 with one group of (at least one) program module 42 can store in such as memory 28
In, such program module 42 include but is not limited to operating system, one or more application program, other program modules and
It may include the realization of network environment in program data, each of these examples or certain combination.Program module 42 is usual
Execute the function and/or method in embodiments described herein.
Computer equipment 12 can also be with one or more external equipments 14 (such as keyboard, sensing equipment, display 24
Deng) communication, the equipment interacted with the computer system/server 12 can be also enabled a user to one or more to be communicated, and/
Or with enable the computer system/server 12 and one or more of the other any equipment (example for being communicated of calculating equipment
Such as network interface card, modem etc.) communication.This communication can be carried out by input/output (I/O) interface 22.Also, it calculates
Machine equipment 12 can also pass through network adapter 20 and one or more network (such as local area network (Local Area
Network；Hereinafter referred to as: LAN), wide area network (Wide Area Network；Hereinafter referred to as: WAN) and/or public network, example
Such as internet) communication.As shown, network adapter 20 is communicated by bus 18 with other modules of computer equipment 12.It answers
When understanding, although not shown in the drawings, other hardware and/or software module can be used in conjunction with computer equipment 12, including but not
Be limited to: microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and
Data backup storage system etc..
Processing unit 16 by the program that is stored in system storage 28 of operation, thereby executing various function application and
Data processing, such as realize the map point of interest processing method referred in previous embodiment.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is contained at least one embodiment or example of the application.In the present specification, schematic expression of the above terms are not
It must be directed to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be in office
It can be combined in any suitable manner in one or more embodiment or examples.In addition, without conflicting with each other, the skill of this field
Art personnel can tie the feature of different embodiments or examples described in this specification and different embodiments or examples
It closes and combines.
In addition, defining " first ", the feature of " second " can explicitly or implicitly include at least one of the features.?
In the description of the present application, the meaning of " plurality " is at least two, such as two, three etc., unless otherwise specifically defined.
Any process described otherwise above or method description are construed as in flow chart or herein, and expression includes
It is one or more for realizing custom logic function or process the step of executable instruction code module, segment or portion
Point, and the range of the preferred embodiment of the application includes other realization, wherein can not press shown or discussed suitable
Sequence, including according to related function by it is basic simultaneously in the way of or in the opposite order, Lai Zhihang function, this should be by the application
Embodiment person of ordinary skill in the field understood.
Expression or logic and/or step described otherwise above herein in flow charts, for example, being considered use
In the order list for the executable instruction for realizing logic function, may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (such as computer based system, including the system of processor or other can be held from instruction
The instruction fetch of row system, device or equipment and the system executed instruction) it uses, or combine these instruction execution systems, device or set
It is standby and use.For the purpose of this specification, " computer-readable medium ", which can be, any may include, stores, communicates, propagates or pass
Defeated program is for instruction execution system, device or equipment or the dress used in conjunction with these instruction execution systems, device or equipment
It sets.The more specific example (non-exhaustive list) of computer-readable medium include the following: there is the electricity of one or more wirings
Interconnecting piece (electronic device), portable computer diskette box (magnetic device), random access memory (RAM), read-only memory
(ROM), erasable edit read-only storage (EPROM or flash memory), fiber device and portable optic disk is read-only deposits
Reservoir (CDROM).In addition, computer-readable medium can even is that the paper that can print described program on it or other are suitable
Medium, because can then be edited, be interpreted or when necessary with it for example by carrying out optical scanner to paper or other media
His suitable method is handled electronically to obtain described program, is then stored in computer storage.
It should be appreciated that each section of the application can be realized with hardware, software, firmware or their combination.Above-mentioned
In embodiment, software that multiple steps or method can be executed in memory and by suitable instruction execution system with storage
Or firmware is realized.Such as, if realized with hardware in another embodiment, following skill well known in the art can be used
Any one of art or their combination are realized: have for data-signal is realized the logic gates of logic function from
Logic circuit is dissipated, the specific integrated circuit with suitable combinational logic gate circuit, programmable gate array (PGA), scene can compile
Journey gate array (FPGA) etc..
Those skilled in the art are understood that realize all or part of step that above-described embodiment method carries
It suddenly is that relevant hardware can be instructed to complete by program, the program can store in a kind of computer-readable storage medium
In matter, which when being executed, includes the steps that one or a combination set of embodiment of the method.
It, can also be in addition, can integrate in a processing module in each functional unit in each embodiment of the application
It is that each unit physically exists alone, can also be integrated in two or more units in a module.Above-mentioned integrated mould
Block both can take the form of hardware realization, can also be realized in the form of software function module.The integrated module is such as
Fruit is realized and when sold or used as an independent product in the form of software function module, also can store in a computer
In read/write memory medium.
Storage medium mentioned above can be read-only memory, disk or CD etc..Although having been shown and retouching above
Embodiments herein is stated, it is to be understood that above-described embodiment is exemplary, and should not be understood as the limit to the application
System, those skilled in the art can be changed above-described embodiment, modify, replace and become within the scope of application
Type.
Claims (14)
1. a kind of map point of interest processing method, which is characterized in that the described method comprises the following steps:
Obtain the image data of the first user acquisition；
The image data is pre-processed, to obtain frame image to be processed from the image data；
It whether detects in each frame image to be processed comprising point of interest；
If in first frame image including the first interest point data, according to the acquisition position of the first frame image, acquisition respectively has
Imitate point of interest；
Verify the first point of interest whether with any effective interest points matching；
If first point of interest does not match with any effective point of interest, it is determined that at the acquisition position of the first frame image
Include point of interest to be updated.
2. map point of interest processing method as described in claim 1, which is characterized in that described to be carried out in advance to the image data
Processing, comprising:
According to the similarity between each frame picture material in the image data, duplicate removal processing is carried out to the image data.
3. map point of interest processing method as described in claim 1, which is characterized in that described to be carried out in advance to the image data
Processing, comprising:
According to preset pumping frame pitch, cutting processing is carried out to the image data.
4. map point of interest processing method as described in claim 1, which is characterized in that described to be carried out in advance to the image data
Processing, comprising:
According to the corresponding acquisition position of frame image each in the image data, the image data is subjected to segment processing, with
Frame image to be processed is obtained from each segment data.
5. map point of interest processing method as described in claim 1, which is characterized in that on each frame image to be processed of detection
Whether comprising after point of interest, further includes:
If in the second frame image not including point of interest, according to the acquisition position of the second frame image, the first crowdsourcing school is generated
Test task；
The first crowdsourcing verification task is issued to multiple second users, so that the multiple second user acquisition verification image number
According to；
Whether according to the verification image data that the multiple second user acquires, verifying in the second frame image includes interest
Point.
6. map point of interest processing method as claimed in claim 5, which is characterized in that described to issue institute to multiple second users
Before stating the first crowdsourcing verification task, further includes:
The location information and the corresponding acquisition position of the second frame image being currently located according to each user, determine the multiple
Second user.
7. the map point of interest processing method as described in claim 1-6 is any, which is characterized in that the determination first frame
Comprising after point of interest to be updated at the acquisition position of image, further includes:
The each effectively point of interest of judgement whether with the second interest points matching for including in each third frame image, wherein third frame figure
The acquisition position of picture between the acquisition position of the first frame image at a distance from be less than threshold value；
If first effective point of interest does not match with each second point of interest, it is determined that at the acquisition position of the first frame image
Include point of interest to be updated.
8. the map point of interest processing method as described in claim 1-6 is any, which is characterized in that the determination first frame
Comprising after point of interest to be updated at the acquisition position of image, further includes:
According to the acquisition position of the first frame image and each effective point of interest, generates the second crowdsourcing and verify task；
The second crowdsourcing verification task is issued to multiple third users, so that the multiple third user acquires verification image number
According to；
According to the verification image data that the multiple third user acquires, determines at the acquisition position of the first frame image and include
Point of interest to be updated.
9. map point of interest processing method as claimed in claim 8, which is characterized in that the determination first frame image
Comprising after point of interest to be updated at acquisition position, further includes:
The point of interest to be updated is replaced or delete processing.
10. the map point of interest processing method as described in claim 1-6 is any, which is characterized in that described to the image number
According to before being pre-processed, further includes:
Determine that the frame amount of images for including in the image data is greater than first threshold.
11. a kind of map point of interest processing unit, which is characterized in that described device includes:
First obtains module, for obtaining the image data of the first user acquisition；
Processing module, for being pre-processed to the image data, to obtain frame image to be processed from the image data；
Detection module, for whether detecting in each frame image to be processed comprising point of interest；
Second obtains module, if for including the first interest point data in first frame image, according to the first frame image
Acquisition position obtains each effective point of interest；
Inspection module, for verify the first point of interest whether with any effective interest points matching；
First determining module, if not matched for first point of interest with any effective point of interest, it is determined that described first
It include point of interest to be updated at the acquisition position of frame image.
12. a kind of computer equipment, which is characterized in that including memory, processor and store on a memory and can handle
The computer program run on device when the processor executes described program, is realized as described in any in claim 1-10
Map point of interest processing method.
13. a kind of non-transitorycomputer readable storage medium, is stored thereon with computer program, which is characterized in that the program
The map point of interest processing method as described in any in claim 1-10 is realized when being executed by processor.
14. a kind of computer program product, which is characterized in that when the instruction in the computer program product is executed by processor
When, execute the map point of interest processing method as described in any in claim 1-10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811473453.0A CN109710705A (en) | 2018-12-04 | 2018-12-04 | Map point of interest treating method and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811473453.0A CN109710705A (en) | 2018-12-04 | 2018-12-04 | Map point of interest treating method and apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109710705A true CN109710705A (en) | 2019-05-03 |
Family
ID=66253880
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811473453.0A Pending CN109710705A (en) | 2018-12-04 | 2018-12-04 | Map point of interest treating method and apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109710705A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110245205A (en) * | 2019-06-20 | 2019-09-17 | 腾讯科技（深圳）有限公司 | Verification method, device, equipment and the storage medium of map interest point data |
| CN110442606A (en) * | 2019-07-16 | 2019-11-12 | 浙江大华技术股份有限公司 | A kind of processing method of data, equipment and computer storage medium |
| CN110795994A (en) * | 2019-09-16 | 2020-02-14 | 腾讯科技（深圳）有限公司 | Intersection image selection method and device |
| CN111310654A (en) * | 2020-02-13 | 2020-06-19 | 北京百度网讯科技有限公司 | Map element positioning method and device, electronic equipment and storage medium |
| CN111858807A (en) * | 2020-07-16 | 2020-10-30 | 北京百度网讯科技有限公司 | Task processing method, device, equipment and storage medium |
| CN112381162A (en) * | 2020-11-19 | 2021-02-19 | 北京百度网讯科技有限公司 | Information point identification method and device and electronic equipment |
| CN112818276A (en) * | 2019-11-18 | 2021-05-18 | 百度在线网络技术（北京）有限公司 | Interest point picture processing method and device, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103914546A (en) * | 2014-04-09 | 2014-07-09 | 百度在线网络技术（北京）有限公司 | Data updating method and device thereof |
| CN106294458A (en) * | 2015-05-29 | 2017-01-04 | 北京四维图新科技股份有限公司 | A kind of map point of interest update method and device |
| CN107798110A (en) * | 2017-11-01 | 2018-03-13 | 百度在线网络技术（北京）有限公司 | Point of interest address checking method, device, server and storage medium |
| CN107807929A (en) * | 2016-09-08 | 2018-03-16 | 北京搜狗科技发展有限公司 | A kind of information processing method, device and equipment |
| CN107885763A (en) * | 2017-09-20 | 2018-04-06 | 百度在线网络技术（北京）有限公司 | The update method of interest point information, device and computer-readable medium in indoor figure |
| CN108833527A (en) * | 2018-06-08 | 2018-11-16 | 腾讯大地通途（北京）科技有限公司 | A kind of point of interest inserting method and relevant device |
-
2018
- 2018-12-04 CN CN201811473453.0A patent/CN109710705A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103914546A (en) * | 2014-04-09 | 2014-07-09 | 百度在线网络技术（北京）有限公司 | Data updating method and device thereof |
| CN106294458A (en) * | 2015-05-29 | 2017-01-04 | 北京四维图新科技股份有限公司 | A kind of map point of interest update method and device |
| CN107807929A (en) * | 2016-09-08 | 2018-03-16 | 北京搜狗科技发展有限公司 | A kind of information processing method, device and equipment |
| CN107885763A (en) * | 2017-09-20 | 2018-04-06 | 百度在线网络技术（北京）有限公司 | The update method of interest point information, device and computer-readable medium in indoor figure |
| CN107798110A (en) * | 2017-11-01 | 2018-03-13 | 百度在线网络技术（北京）有限公司 | Point of interest address checking method, device, server and storage medium |
| CN108833527A (en) * | 2018-06-08 | 2018-11-16 | 腾讯大地通途（北京）科技有限公司 | A kind of point of interest inserting method and relevant device |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110245205A (en) * | 2019-06-20 | 2019-09-17 | 腾讯科技（深圳）有限公司 | Verification method, device, equipment and the storage medium of map interest point data |
| CN110245205B (en) * | 2019-06-20 | 2023-08-29 | 腾讯科技（深圳）有限公司 | Verification method, device, equipment and storage medium for map interest point data |
| CN110442606A (en) * | 2019-07-16 | 2019-11-12 | 浙江大华技术股份有限公司 | A kind of processing method of data, equipment and computer storage medium |
| CN110795994A (en) * | 2019-09-16 | 2020-02-14 | 腾讯科技（深圳）有限公司 | Intersection image selection method and device |
| CN112818276A (en) * | 2019-11-18 | 2021-05-18 | 百度在线网络技术（北京）有限公司 | Interest point picture processing method and device, electronic equipment and storage medium |
| CN112818276B (en) * | 2019-11-18 | 2023-12-15 | 百度在线网络技术（北京）有限公司 | Point-of-interest picture processing method and device, electronic equipment and storage medium |
| CN111310654A (en) * | 2020-02-13 | 2020-06-19 | 北京百度网讯科技有限公司 | Map element positioning method and device, electronic equipment and storage medium |
| CN111310654B (en) * | 2020-02-13 | 2023-09-08 | 北京百度网讯科技有限公司 | Map element positioning method and device, electronic equipment and storage medium |
| CN111858807A (en) * | 2020-07-16 | 2020-10-30 | 北京百度网讯科技有限公司 | Task processing method, device, equipment and storage medium |
| CN111858807B (en) * | 2020-07-16 | 2024-03-05 | 北京百度网讯科技有限公司 | Task processing method, device, equipment and storage medium |
| CN112381162A (en) * | 2020-11-19 | 2021-02-19 | 北京百度网讯科技有限公司 | Information point identification method and device and electronic equipment |
| CN112381162B (en) * | 2020-11-19 | 2024-05-07 | 北京百度网讯科技有限公司 | Information point identification method and device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109710705A (en) | Map point of interest treating method and apparatus | |
| CN107545241B (en) | Neural network model training and living body detection method, device and storage medium | |
| CN107067003B (en) | Region-of-interest boundary extraction method, device, equipment and computer storage medium | |
| US11403766B2 (en) | Method and device for labeling point of interest | |
| CN110874594A (en) | Human body surface damage detection method based on semantic segmentation network and related equipment | |
| CN108229364B (en) | Building contour generation method and device, computer equipment and storage medium | |
| CN111754541A (en) | Target tracking method, device, equipment and readable storage medium | |
| CN108573268A (en) | Image-recognizing method and device, image processing method and device and storage medium | |
| CN110490238A (en) | A kind of image processing method, device and storage medium | |
| CN108229375B (en) | Method and device for detecting face image | |
| EP3588325A1 (en) | Method, device and system for processing image tagging information | |
| CN111860377A (en) | Live broadcast method and device based on artificial intelligence, electronic equipment and storage medium | |
| CN105469103B (en) | Scene restoration methods based on low quality RGB-D data and device | |
| CN108154103A (en) | Detect method, apparatus, equipment and the computer storage media of promotion message conspicuousness | |
| CN111340015B (en) | Positioning method and device | |
| CN115471775A (en) | Information verification method, device and equipment based on screen recording video and storage medium | |
| Rahmat et al. | Android-based automatic detection and measurement system of highway billboard for tax calculation in Indonesia | |
| Liu et al. | A crack detection system of subway tunnel based on image processing | |
| US8532393B2 (en) | Method and system for line segment extraction | |
| CN109558505A (en) | Visual search method, apparatus, computer equipment and storage medium | |
| CN112101191A (en) | Expression recognition method, device, equipment and medium based on frame attention network | |
| CN113869218B (en) | Face living body detection method and device, electronic equipment and readable storage medium | |
| CN106092016B (en) | A kind of forest volume of timber automatic dipping system and method based on depth transducer | |
| CN112348112B (en) | Training method and training device for image recognition model and terminal equipment | |
| CN111753625B (en) | Pedestrian detection method, device, equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190503 |