CN107610177A - A kind of method and apparatus that characteristic point is determined in synchronous superposition - Google Patents
A kind of method and apparatus that characteristic point is determined in synchronous superposition Download PDFInfo
- Publication number
- CN107610177A CN107610177A CN201710909238.XA CN201710909238A CN107610177A CN 107610177 A CN107610177 A CN 107610177A CN 201710909238 A CN201710909238 A CN 201710909238A CN 107610177 A CN107610177 A CN 107610177A
- Authority
- CN
- China
- Prior art keywords
- point
- information
- spatial position
- characteristic features
- position change
- 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.)
- Granted
Links
Landscapes
- Image Analysis (AREA)
Abstract
The embodiments of the invention provide the method and apparatus that characteristic point is determined in a kind of synchronous superposition, wherein methods described includes：Image information is gathered using image acquisition equipment；Image information based on collection, obtain the fisrt feature point set in described image information；The non-static characteristic point in the fisrt feature point set is analyzed, wherein, the non-static characteristic point is characteristic point corresponding to mobile object；The non-static characteristic point is filtered in the fisrt feature point set, to generate second feature point set.The present invention can simply and easily remove non-static characteristic point, improve the accuracy and speed of map structuring.
Description
Technical field
The present embodiments relate to the field of cloud map structuring, determined in more particularly to a kind of synchronous superposition
The method and apparatus of characteristic point.
Background technology
The core for being synchronously positioned at map structuring is extracted by camera collection image, and by feature point extraction algorithm
Characteristic point in image, then with characteristic point and key frame structure point cloud map, follow-up positioning is then completed by a cloud and led
Boat.Thus characteristic point is the basic element of V-SLAM maps, and it is static that a good characteristic point, which should have, can be detected again.
And in actual scene, existing a large amount of non-static characteristic points if not rejecting these non-static characteristic points, will influence a little
The precision of cloud.V-SLAM, using strategies such as various optimizations, consumes substantial amounts of computing resource to reject these characteristic points.Cause
This, if it is possible to a kind of method that can easily extract static nature point is proposed, the structure speed of cloud map can be optimized.
The content of the invention
The embodiments of the invention provide it is a kind of being capable of the synchronous positioning of one kind simple and convenient and that resource can be optimized and map structure
The method and apparatus for building middle determination characteristic point.
In order to solve the above-mentioned technical problem, the embodiments of the invention provide following technical scheme：
A kind of method that characteristic point is determined in synchronous superposition, it includes：
Image information is gathered using image acquisition equipment；
Image information based on collection, obtain the fisrt feature point set in described image information；
The non-static characteristic point in the fisrt feature point set is analyzed, wherein, the non-static characteristic point is motive objects
Characteristic point corresponding to body；
The non-static characteristic point is filtered in the fisrt feature point set, to generate second feature point set.
In a preferred embodiment, the non-static characteristic point in the analysis fisrt feature point set includes：
The fisrt feature point set in described image information at different moments is obtained respectively；
Determine the same characteristic features point in the fisrt feature point set at each moment；
The same characteristic features point based on determination, and described image obtain movement state information point of the equipment at each moment
Analyse the non-static characteristic point.
In a preferred embodiment, the same characteristic features point based on determination, and described image obtain equipment and existed
The movement state information at each moment, which analyzes the non-static characteristic point, to be included：
The depth information of the same characteristic features point based on determination, calculate the spatial position change letter of the same characteristic features point
Breath；
Obtain the spatial position change information that described image obtains equipment；
The locus change of equipment is obtained based on the spatial position change information of the same characteristic features point, and described image
Change information, analysis determines the non-static characteristic point.
In a preferred embodiment, the spatial position change information based on the same characteristic features point, and the figure
Spatial position change information as obtaining equipment, analysis determine that the non-static characteristic point includes：
The spatial position change information of equipment is obtained based on described image, to the spatial position change of the same characteristic features point
Operation is normalized in information, to obtain normed space change in location information；
Based on the normed space change in location information, cluster operation is carried out to the same characteristic features point, with described in acquisition
Non-static characteristic point.
In a preferred embodiment, the depth information of the same characteristic features point based on determination, calculate described identical
The spatial position change information of characteristic point includes：
The depth information of the same characteristic features point based on each moment, determine the positional information of the same characteristic features point；
Difference between the positional information of each same characteristic features point based on each moment determines the spatial position change information.
In a preferred embodiment, the spatial position change information that equipment is obtained based on described image, to the phase
Operation is normalized in spatial position change information with characteristic point, is included with obtaining normed space change in location information：
Described image is obtained into the spatial position change information of equipment and the spatial position change of same characteristic features point is believed
Breath carries out difference operation, obtains the normed space change in location information.
In a preferred embodiment, it is described to be based on the normed space change in location information, the same characteristic features are clicked through
Row cluster operation, included with obtaining the non-static characteristic point：
Using the normed space change in location information as core, cluster operation is carried out to the same characteristic features point；
Calculate the class spacing sum of all kinds of same characteristic features points；
The larger a kind of characteristic point of the class spacing sum is judged as non-static characteristic point.
The embodiment of the present invention additionally provides the equipment that characteristic point is determined in a kind of synchronous superposition, and it includes：
Image collection module, it is configured to gather image information at different moments respectively；
Processor, it is configured to the image information of collection, obtains the fisrt feature point set in described image information；
The non-static characteristic point in the fisrt feature point set is analyzed, wherein, the non-static characteristic point is corresponding to mobile object
Characteristic point；The non-static characteristic point is filtered in the fisrt feature point set, to generate second feature point set.
In a preferred embodiment, the processor is further configured to obtain described image information at different moments respectively
In fisrt feature point set；Determine the same characteristic features point in the fisrt feature point set at each moment；Institute based on determination
Same characteristic features point is stated, and described image obtains movement state information of the equipment at each moment and analyzes the non-static characteristic point.
In a preferred embodiment, the processor is further configured to the depth of the same characteristic features point based on determination
Information, calculate the spatial position change information of the same characteristic features point；
Obtain the spatial position change information that described image obtains equipment；
The locus change of equipment is obtained based on the spatial position change information of the same characteristic features point, and described image
Change information, analysis determines the non-static characteristic point.
Based on disclosed above, it can know that the embodiment of the present invention has following beneficial effect：
1st, because method provided in an embodiment of the present invention can directly remove non-static characteristic point, then can effectively reduce
To the consumption of computing resource during SLAM back-end processings, point cloud structure speed is improved；
2nd, in position fixing process, cloud map construction device can determine the current location of itself by multipoint positioning, non-
The presence of static nature point can increase the probability of erroneous matching, cause the reduction of positioning precision, and the embodiment of the present invention can be in structure
Cloud of laying foundations filters to characteristic point before, removes behavioral characteristics point therein, significantly improves positioning precision；
3rd, to the filtering of behavioral characteristics point, the openness of some clouds can be improved, and does not influence the positioning precision of a cloud, together
When in positioning stage, can significantly reduce the amount of calculation of positioning, lift locating speed.
Brief description of the drawings
Fig. 1 is the principle stream for the method that characteristic point is determined in a kind of synchronous superposition in the embodiment of the present invention
Cheng Tu；
Fig. 2 is the flow for the method that the non-static characteristic point in the fisrt feature point set is analyzed in the embodiment of the present invention
Figure；
Fig. 3 is the same characteristic features point based on determination in the embodiment of the present invention, and described image acquisition equipment is each
The movement state information at moment analyzes the method flow diagram of the non-static characteristic point；
Fig. 4 is the method flow diagram that non-static characteristic point is further determined that in the embodiment of the present invention；
Fig. 5 is the Method And Principle flow chart for determining non-static characteristic point in the embodiment of the present invention by clustering processing analysis；
Fig. 6 is the theory structure for the equipment that characteristic point is determined in the synchronous superposition in the embodiment of the present invention
Figure；
Fig. 7 is the theory structure schematic diagram of the processor in the embodiment of the present invention.
Embodiment
Below, the specific embodiment of the present invention is described in detail with reference to accompanying drawing, but it is not as limiting to the invention.
It should be understood that disclosed embodiments can be made with various modifications.Therefore, description above should not regard
To limit, and only as the example of embodiment.Those skilled in the art will expect within the scope and spirit of this
Other modifications.
Comprising in the description and the accompanying drawing of a part for constitution instruction shows embodiment of the disclosure, and with it is upper
What face provided is used to explain the disclosure together to the substantially description of the disclosure and the detailed description given below to embodiment
Principle.
It is of the invention by the description to the preferred form of the embodiment that is given as non-limiting examples with reference to the accompanying drawings
These and other characteristic will become apparent.
It is also understood that although with reference to some instantiations, invention has been described, but people in the art
Member realize with can determine the present invention many other equivalents, they have feature as claimed in claim and therefore all
In the protection domain limited whereby.
When read in conjunction with the accompanying drawings, in view of described further below, above and other aspect, the feature and advantage of the disclosure will become
It is more readily apparent.
The specific embodiment of the disclosure is described hereinafter with reference to accompanying drawing；It will be appreciated, however, that the disclosed embodiments are only
The example of the disclosure, it can use various ways to implement.Function and structure that is known and/or repeating is not described in detail to avoid
Unnecessary or unnecessary details make it that the disclosure is smudgy.Therefore, specific structural and feature disclosed herein is thin
Section is not intended to restrictions, but as just the basis of claim and representative basis for instruct those skilled in the art with
Substantially any appropriate detailed construction diversely uses the disclosure.
This specification can be used phrase " in one embodiment ", " in another embodiment ", " in another embodiment
In " or " in other embodiments ", it may refer to according to one or more of identical or different embodiment of the disclosure.
Below, the embodiment of the present invention is described in detail with reference to accompanying drawing, the embodiments of the invention provide a kind of synchronous positioning with
The method that characteristic point is determined in map structuring, this method can apply the extraction for static nature point in V-SLAM maps
Cheng Zhong, the speed and precision of component cloud map can be greatly promoted by the non-static characteristic point removed in image characteristic point.Its
In, synchronous superposition is (SLAM or Simultaneous localization and mapping).
As shown in figure 1, to determine the method for characteristic point in a kind of synchronous superposition in the embodiment of the present invention
Principle flow chart, being synchronously positioned in map structuring in the embodiment of the present invention determine that the method for characteristic point can include：
Image information is gathered using image acquisition equipment；
Image information based on collection, obtain the fisrt feature point set in described image information；
The non-static characteristic point in the fisrt feature point set is analyzed, wherein, the non-static characteristic point is motive objects
Characteristic point corresponding to body；
The non-static characteristic point is filtered in the fisrt feature point set, to generate second feature point set.
In the embodiment of the present invention, the technical field in map structuring can be applied, wherein can be obtained first with image
Equipment gathers image information, and the image acquisition equipment can include depth camera, or cameras people etc., be obtained by image
Taking equipment can gather image information, and the image information can be the image information with depth information.Meanwhile obtained in image
Also there is corresponding temporal information, i.e., each image is associated with corresponding temporal information in image information acquired in equipment.
In addition, in the embodiment of the present invention, after the image information at each moment is obtained, can the image information based on acquisition, obtain image
Fisrt feature point set in information, you can to carry out feature point extraction to image information according to preset algorithm, obtain including more
The fisrt feature point set of individual characteristic point.Wherein, the preset algorithm of the embodiment of the present invention can include the calculation of FAST feature point detections
Method or SIFT (scale invariant feature conversion) algorithm, the operation of features described above point extraction can be performed by above-mentioned algorithm.Example
Such as, the Tm moment is gathered, the image information f (t) with depth information, the image information can be represented with RGB data, by above-mentioned pre-
Fisrt feature point set P ∈ { pm0, pm1, pm2 ... pmn } in imputation method (FAST/SIFT) extraction image information, wherein collecting
Each characteristic point closed in P can be indicated with positional information, such as pixel coordinate information.Preferably, when extracting characteristic point also
The characterization information on each characteristic point in fisrt feature point set can be generated, this feature description can be expressed as D ∈
{ dm0, dm1, dm2 ... dmn }, this feature description information can include the characteristic information of characteristic point, for identifying and distinguishing between
Each characteristic point.After above-mentioned fisrt feature point set and the description of corresponding feature is obtained, corresponding it can enter with time Tm
Row storage.The fisrt feature point set of the image information of each moment collection and corresponding spy can be obtained based on said process
Levy the characterization information of point.
After the fisrt feature point set of image information at each moment is obtained, each fisrt feature point set can be divided
Analysis, to identify the non-static characteristic point in fisrt feature point set.Wherein, the non-static characteristic point is corresponding to mobile object
Characteristic point.Also, the non-static feature can filtered in the fisrt feature point set after identifying non-static characteristic point
Point, to generate second feature point set.Each characteristic point in the second feature point set is static nature point.Utilize each moment
Second feature point set used as map structuring, the accuracy and speed of the process can be improved.
It can directly be removed due to method provided in an embodiment of the present invention non-static in the image information of each moment acquisition
Characteristic point, then consumption when can effectively reduce SLAM back-end processings to computing resource, improve point cloud structure speed；Exist in addition
In position fixing process, cloud map construction device can determine the current location of itself by multipoint positioning, non-static characteristic point
In the presence of the probability that can increase erroneous matching, cause the reduction of positioning precision, the embodiment of the present invention can be right before structure point cloud
Characteristic point is filtered, and is removed behavioral characteristics point therein, is significantly improved positioning precision；Filtering to behavioral characteristics point simultaneously,
The openness of some clouds can be improved, and does not influence the positioning precision of a cloud, while in positioning stage, can significantly reduce positioning
Amount of calculation, lifted locating speed.
Further, as shown in Fig. 2 to analyze the non-static spy in the fisrt feature point set in the embodiment of the present invention
The flow chart of the method for point is levied, the process can include：
The fisrt feature point set in described image information at different moments is obtained respectively；
Determine the same characteristic features point in the fisrt feature point set at each moment；
The same characteristic features point based on determination, and described image obtain movement state information point of the equipment at each moment
Analyse the non-static characteristic point.
As described in above-mentioned embodiment, image information at different moments can be obtained by image acquisition equipment, and based on should
Image information can further extract fisrt feature point set therein, therefore, can obtain the image information institute at each moment
Corresponding fisrt feature point set, such as the fisrt feature point set at Tm moment and the fisrt feature point set at Tm+1 moment.Obtaining
The same characteristic features point that can also be obtained after P after the fisrt feature point set at each moment in each fisrt feature point set is taken, such as may be used
Clicked through with the feature in each characteristic point in the fisrt feature point set by the Tm+1 moment and the fisrt feature point set at Tm moment
Row characteristic point Similarity measures, find out the characteristic point that Tm matches with the Tm+1 moment, i.e. same characteristic features point.Here, the present invention is real
Each fisrt feature can be determined according to the characterization information corresponding to for each characteristic point in fisrt feature point set by applying example
Same characteristic features point in point set, due to being the letter that can represent characteristic point stationary state for the characterization information of characteristic point
Cease (information that will not typically change), therefore the characteristic point of characterization information matching can be judged as identical feature
Point.
Further, after the same characteristic features point in judging the fisrt feature point set at each moment, it is also based on really
The fixed same characteristic features point, and described image obtain movement state information of the equipment at each moment and analyze the non-static spy
Sign point.
The same characteristic features point based on determination is illustrated in figure 3 in the embodiment of the present invention, and described image is obtained and set
The standby movement state information at each moment analyzes the method flow diagram of the non-static characteristic point, institute wherein in the embodiment of the present invention
The same characteristic features point based on determination is stated, and described image is obtained described in movement state information analysis of the equipment at each moment
Non-static characteristic point can include：
The depth information of the same characteristic features point based on determination, calculate the spatial position change letter of the same characteristic features point
Breath；
Obtain the spatial position change information that described image obtains equipment；
The locus change of equipment is obtained based on the spatial position change information of the same characteristic features point, and described image
Change information, analysis determines the non-static characteristic point.
In embodiments of the present invention, it is determined that after same characteristic features point in each fisrt feature point set, can be based on determining
Same characteristic features point depth information, calculate same characteristic features point spatial position change information.
As described above, the image acquisition equipment in the embodiment of the present invention can obtain the image letter with depth information
Cease, each characteristic point in the fisrt feature point set of extraction there can also be depth information, then can be based on carrying depth herein
The positional information (such as coordinate information) of each characteristic point of information, determine the spatial position change information of each characteristic point.
Specifically, the depth information of the same characteristic features point based on determination described in the embodiment of the present invention, described in calculating
The spatial position change information of same characteristic features point can include：
The depth information of the same characteristic features point based on each moment, determine the positional information of the same characteristic features point；
Difference between the positional information of each same characteristic features point based on each moment determines the spatial position change information.
That is, the positional information of each same characteristic features point based on the depth information of each same characteristic features point, can be determined, should
Positional information is indicated with space coordinates, afterwards can be by the coordinate value of each same characteristic features point at Tm+1 moment and Tm moment
The coordinate value of each same characteristic features point carries out the difference operation of space vector, so as to obtain the spatial position change of each same characteristic features point
Information.For example, can the intrinsic parameter based on the camera of image acquisition equipment, such as depth information, calculate Tm the and Tm+1 moment
The coordinate value (Xm, Ym, Zm) and (Xm+1, Ym+1, Zm+1) under coordinate system of each same characteristic features point, then the Tm+1 moment relative to
The spatial variations information of the same characteristic features point at Tm moment can be expressed as space vector (Xm+1-Xm, Ym+1-Ym, Zm+1-Zm).
Further, since image acquisition equipment perform image obtain during, the position of its camera, orientation, angle
It will change, the image acquisition equipment in the embodiment of the present invention can also obtain it in real time in mobile speed at different moments
The parameter informations such as degree, direction, angle, positional information, and the corresponding spatial position change information for determining image acquisition equipment.Example
Tm to Tm+1 moment code-disc (Odometry) data (v, θ) can be such as obtained, the data represent that image obtains in 1 time interval
The speed of the camera movement of taking equipment and drift angle.That is, it can also be obtained at each moment in the embodiment of the present invention
The positional information (utilization space coordinate representation) of image acquisition equipment, and the relative position obtained between each moment can also be corresponded to
Change, i.e. spatial position change information.For example, calculating the positional information of Tm and Tm+1 moment image acquisition equipments, such as sitting
Respectively (Xc, Yc, Zc) and (Xc+1, Yc+1, Zc+1), then the Tm+1 moment is identical relative to the Tm moment for the lower coordinate value of mark system
The spatial variations information of characteristic point can be expressed as space vector (Xc+1-Xc, Yc+1-Yc, Zc+1-Zc).
The spatial position change information of image acquisition equipment and the sky of each same characteristic features point between obtaining at different moments
Between position change information when, non-static characteristic point can be determined based on above- mentioned information.
It is illustrated in figure 4 the method flow diagram that non-static characteristic point is further determined that in the embodiment of the present invention, wherein this hair
In bright embodiment, the spatial position change information based on the same characteristic features point, and described image obtain the sky of equipment
Between position change information, analysis determines that the non-static characteristic point includes：
The spatial position change information of equipment is obtained based on described image, to the spatial position change of the same characteristic features point
Operation is normalized in information, to obtain normed space change in location information；
Based on the normed space change in location information, cluster operation is carried out to the same characteristic features point, with described in acquisition
Non-static characteristic point.
The spatial position change information of image acquisition equipment and the sky of each same characteristic features point between obtaining at different moments
Between position change information when, can based on described image obtain equipment spatial position change information, to the same characteristic features point
Spatial position change information operation is normalized, the normalization operation can include：Described image is obtained to the sky of equipment
Between the spatial position change information of position change information and same characteristic features point carry out difference operation, obtain the normed space
Change in location information.
Can be by the spatial position change information for the image acquisition equipment that synchronization is calculated and the phase at the moment
Spatial position change information with characteristic point carries out difference operation, such as can calculate image of the Tm+1 moment relative to the Tm moment
The spatial position change information for obtaining equipment is (Xc+1-Xc, Yc+1-Yc, Zc+1-Zc), and the space bit of same characteristic features point
It is (Xm+1-Xm, Ym+1-Ym, Zm+1-Zm) to put change information, then above-mentioned to be grasped for Tm+1 moment, the normalization of each same characteristics
The result of work is the difference between (Xc+1-Xc, Yc+1-Yc, Zc+1-Zc) and (Xm+1-Xm, Ym+1-Ym, Zm+1-Zm), should
Difference can be expressed as normed space change in location information.
Illustrated with following formula, (Lx, Ly, Lz) can be expressed as standard control change in location information, (Xc, Yc,
Zc) represent that the spatial position change information of image acquisition equipment, and (Xm+1, Ym+1, Zm+1) can be expressed as same characteristic features
Point spatial position change information, then the relation between three can be：
It is possible to further carry out cluster behaviour to the same characteristic features point based on the normed space change in location information
Make, to obtain the non-static characteristic point.It is as shown in figure 5, non-quiet to be determined in the embodiment of the present invention by clustering processing analysis
The Method And Principle flow chart of state characteristic point, wherein, it is described to be based on the normed space change in location information, to the same characteristic features
Point carries out cluster operation, can be included with obtaining the non-static characteristic point：
Using the normed space change in location information as core, cluster operation is carried out to the same characteristic features point
Calculate the class spacing sum of all kinds of same characteristic features points；
The big a kind of same characteristic features point of the class spacing sum is judged as non-static characteristic point.
In the embodiment of the present invention, using k=2 k-means clustering methods, circulating repetition K time intervals, to same identical
Characteristic point P standard control change in location information carries out cluster analysis, wherein can be respectively by the same characteristic features point at a certain moment
Normed space change in location information as characteristic vector, all same characteristic features point P normed space change in location information is entered
Row clustering processing, and between class distance sum is calculated, the feature point set for taking between class distance sum small is combined into static nature point, class spacing
The big non-static characteristic point in characteristic point position of sum.The analysis and determination of non-static characteristic point can be realized by the process, from
Above-mentioned non-static characteristic point is removed in fisrt feature point set can obtain second feature point set.Adopted in the embodiment of the present invention
Non-static characteristic point is determined with the mode of above-mentioned cluster analysis, improvement is not made for clustering algorithm, simply by normed space
Change in location information carries out cluster analysis, and obtains cluster result, and non-static characteristic point is realized according to the cluster result really
It is fixed, no longer clustering algorithm is repeated herein.
Based on disclosed above, it can know that the embodiment of the present invention has following beneficial effect：Due to the embodiment of the present invention
The method of offer can directly remove non-static characteristic point, then to computing resource when can effectively reduce SLAM back-end processings
Consumption, improve point cloud structure speed；In position fixing process, cloud map construction device can determine itself by multipoint positioning
Current location, the presence of non-static characteristic point can increase the probability of erroneous matching, cause the reduction of positioning precision, and the present invention is implemented
Example can filter before structure point cloud to characteristic point, remove behavioral characteristics point therein, significantly improve positioning precision；It is right
The filtering of behavioral characteristics point, the openness of some clouds can be improved, and not influence the positioning precision of a cloud, while in positioning rank
Section, the amount of calculation of positioning can be significantly reduced, lift locating speed.
In addition, the embodiment of the present invention additionally provides the equipment that characteristic point is determined in a kind of synchronous superposition, should
Equipment can apply the method that characteristic point is determined in the synchronous superposition as described in above-mentioned embodiment.And pass through removal
Non-static characteristic point in image characteristic point can greatly promote the speed and precision of component cloud map.Wherein, synchronous positioning with
Map structuring is (SLAM or Simultaneous localization and mapping).
As shown in fig. 6, to determine the original of the equipment of characteristic point in the synchronous superposition in the embodiment of the present invention
Structure chart is managed, wherein it is possible to including：
Image collection module 1, it is configured to gather image information at different moments respectively；
Processor 2, it is configured to the image information of collection, obtains the fisrt feature point set in described image information
Close；The non-static characteristic point in the fisrt feature point set is analyzed, wherein, the non-static characteristic point is corresponding for mobile object
Characteristic point；The non-static characteristic point is filtered in the fisrt feature point set, to generate second feature point set.
Determine that the equipment of characteristic point can be applied in map structuring in the embodiment of the present invention, in synchronous superposition
Technical field, the equipment can utilize image collection module 1 to gather image information, and the image collection module 1 can include deep
Camera, or cameras people etc. are spent, image information can be gathered by image collection module 1, the image information can be
Image information with depth information.Meanwhile also there is the corresponding time in the image information acquired in image collection module
Information, i.e., each image are associated with corresponding temporal information.
In addition, in the embodiment of the present invention, the theory structure schematic diagram of processor in the embodiment of the present invention is illustrated in figure 7,
Processor 2 wherein in the embodiment of the present invention can be structured as a data processing device, while can also include multiple subnumbers
According to processing module, so as to realize different functions.
As shown in Fig. 2 the processor 2 in the embodiment of the present invention can include：Extraction module 21 and analysis module 22, wherein
Extraction module 21 can from the reading of image collection module 1 each moment of acquisition image information, and can be based on the acquisition
Image information, extract the fisrt feature point set in image information, you can to carry out feature to image information according to preset algorithm
Point extraction, obtains the fisrt feature point set for including multiple characteristic points.Wherein, the preset algorithm of the embodiment of the present invention can include
FAST feature point detection algorithms or SIFT (scale invariant feature conversion) algorithm, can be held by above-mentioned algorithm extraction module 21
The operation of row features described above point extraction.For example, the collection Tm moment, the image information f (t) with depth information, the image information can
To be represented with RGB data, the fisrt feature point set P ∈ in image information are extracted by above-mentioned preset algorithm (FAST/SIFT)
{ pm0, pm1, pm2 ... pmn }, wherein each characteristic point in set P can be indicated with positional information, as pixel coordinate is believed
Breath.Preferably, extraction module 21, can be with corresponding generation on each spy in fisrt feature point set when extracting each characteristic point
The characterization information of point is levied, this feature description can be expressed as D ∈ { dm0, dm1, dm2 ... dmn }, this feature description information
The characteristic information of characteristic point can be included, for identifying and distinguishing between each characteristic point.Obtaining above-mentioned fisrt feature point set
And after corresponding feature description, corresponding it can be stored with time Tm.It can obtain each moment based on above-mentioned and adopt
The fisrt feature point set of the image information of collection and the characterization information of corresponding characteristic point.
After the fisrt feature point set for extracting the image information at each moment from image information in extraction module 21, mould is analyzed
Block 22 can be analyzed each fisrt feature point set, to identify the non-static characteristic point in fisrt feature point set.Wherein,
The non-static characteristic point is characteristic point corresponding to mobile object.Also, analysis module 22 is after non-static characteristic point is identified
The non-static characteristic point can be further filtered from the fisrt feature point set, to generate second feature point set.Should
Each characteristic point in second feature point set is static nature point.Map structure is used as by the use of the second feature point set at each moment
Use is built, the accuracy and speed of the process can be improved.
It can directly be removed due to equipment provided in an embodiment of the present invention non-static in the image information of each moment acquisition
Characteristic point, then consumption when can effectively reduce SLAM back-end processings to computing resource, improve point cloud structure speed；Exist in addition
In position fixing process, cloud map construction device can determine the current location of itself by multipoint positioning, non-static characteristic point
In the presence of the probability that can increase erroneous matching, cause the reduction of positioning precision, the embodiment of the present invention can be right before structure point cloud
Characteristic point is filtered, and is removed behavioral characteristics point therein, is significantly improved positioning precision；Filtering to behavioral characteristics point simultaneously,
The openness of some clouds can be improved, and does not influence the positioning precision of a cloud, while in positioning stage, can significantly reduce positioning
Amount of calculation, lifted locating speed.
Further, analysis module 22 performs the analysis process of above-mentioned non-static characteristic point and can wrapped in the embodiment of the present invention
Include：Fisrt feature point set in the described image information for obtaining at different moments from extraction module 21 respectively；Determine each moment
Same characteristic features point in the fisrt feature point set；The same characteristic features point based on determination, and described image obtain mould
Movement state information of the block at each moment analyzes the non-static characteristic point.
As described in above-mentioned embodiment, image information at different moments can be obtained by image collection module 1, and extract
Module 21, which is based on the image information, can further extract generation feature description letter corresponding to fisrt feature point set merging therein
Breath.Equipment in the preferable embodiment of the present invention can further include memory 3, and the memory 3 can obtain with image
Module 1 and processor 2 are connected, and for the image information acquired in storage image acquisition module 1, and processor 2 is generated
Feature point description information of fisrt feature point set and correlation etc..
Analysis module 22 in the embodiment of the present invention obtains from extraction module 21 or memory 3 can obtain each moment
Image information corresponding to fisrt feature point set, such as the fisrt feature point set and the fisrt feature at Tm+1 moment at Tm moment
Point set.Analysis module 22 can also obtain each fisrt feature point set after P after obtaining the fisrt feature point set at each moment
Same characteristic features point in conjunction, such as can be special by the first of each characteristic point in the fisrt feature point set at Tm+1 moment and Tm moment
The characteristic point levied in point set carries out characteristic point Similarity measures, finds out the characteristic point that Tm matches with the Tm+1 moment, i.e., identical
Characteristic point.Here, the feature description that the embodiment of the present invention can be according to corresponding to for each characteristic point in fisrt feature point set
Information determines the same characteristic features point in each fisrt feature point set, because the characterization information for characteristic point is being capable of table
Show the information (information that will not typically change) of characteristic point stationary state, therefore the characteristic point of characterization information matching is
It may determine that as identical characteristic point.
Further, analysis module 22 is after the same characteristic features point in judging the fisrt feature point set at each moment, also
Can the same characteristic features point based on determination, and described image acquisition module each moment movement state information analyze institute
State non-static characteristic point.
Specifically, the same characteristic features point of the analysis module 22 based on determination wherein in the embodiment of the present invention, and it is described
Movement state information of the image collection module at each moment, which analyzes the non-static characteristic point, to be included：
The depth information of the same characteristic features point based on determination, calculate the spatial position change letter of the same characteristic features point
Breath；Obtain the spatial position change information of described image acquisition module；Spatial position change letter based on the same characteristic features point
Breath, and the spatial position change information of described image acquisition module, analysis determine the non-static characteristic point.
In embodiments of the present invention, can after the same characteristic features point during analysis module 22 determines each fisrt feature point set
With the depth information of the same characteristic features point based on determination, the spatial position change information of calculating same characteristic features point.
As described above, the image collection module in the embodiment of the present invention can obtain the image letter with depth information
Cease, each characteristic point in the fisrt feature point set of extraction there can also be depth information, then can be based on carrying depth herein
The positional information (such as coordinate information) of each characteristic point of information, determine the spatial position change information of each characteristic point.
Specifically, in the embodiment of the present invention same characteristic features point of the analysis module 22 based on determination depth information, meter
Calculating the spatial position change information of the same characteristic features point can include：
The depth information of the same characteristic features point based on each moment, determine the positional information of the same characteristic features point；Base
Difference between the positional information of each same characteristic features point at each moment determines the spatial position change information.
That is, analysis module 22 obtains the depth information of the depth information, i.e. characteristic point of image module 1, and can be with
Based on the depth information of each same characteristic features point, the positional information of each same characteristic features point is determined, the positional information is entered with space coordinates
Row expression, afterwards can be by the coordinate value of each same characteristic features point at Tm+1 moment and the coordinate value of each same characteristic features point at Tm moment
The difference operation of space vector is carried out, so as to obtain the spatial position change information of each same characteristic features point.For example, figure can be based on
As the intrinsic parameter of the camera of acquisition module, such as depth information, calculate Tm and Tm+1 moment each same characteristic features point in coordinate
Coordinate value (Xm, Ym, Zm) and (Xm+1, Ym+1, Zm+1) under system, then the Tm+1 moment is relative to the same characteristic features point at Tm moment
Spatial variations information can be expressed as space vector (Xm+1-Xm, Ym+1-Ym, Zm+1-Zm).
Further, since image collection module 1, during performing image and obtaining, its position, orientation, angle can all occur
Change, the image collection module in the embodiment of the present invention can also obtain in real time its translational speed at different moments, direction,
The parameter informations such as angle, positional information, and the corresponding spatial position change information for determining image collection module.Such as analyze mould
Block 22 can obtain Tm to Tm+1 moment code-disc (Odometry) data (v, θ), and the data represent the image in 1 time interval
The speed of the camera movement of acquisition module and drift angle.That is, it can also be obtained at each moment in the embodiment of the present invention
Image collection module positional information (utilization space coordinate representation), and can also correspond to and obtain relative position between each moment
Put change, i.e. spatial position change information.For example, calculating the positional information of Tm and Tm+1 moment image collection modules, such as exist
Coordinate value under coordinate system is respectively (Xc, Yc, Zc) and (Xc+1, Yc+1, Zc+1), then the Tm+1 moment relative to the Tm moment phase
Spatial variations information with characteristic point can be expressed as space vector (Xc+1-Xc, Yc+1-Yc, Zc+1-Zc).
The spatial position change information of image collection module and the sky of each same characteristic features point between obtaining at different moments
Between position change information when, non-static characteristic point can be determined based on above- mentioned information.
Spatial position change information of the analysis module 22 based on the same characteristic features point in the embodiment of the present invention, and it is described
The spatial position change information of image collection module, analysis determine that the non-static characteristic point can include：
Spatial position change information based on described image acquisition module, to the spatial position change of the same characteristic features point
Operation is normalized in information, to obtain normed space change in location information；
Based on the normed space change in location information, cluster operation is carried out to the same characteristic features point, with described in acquisition
Non-static characteristic point.
The spatial position change information of image collection module between analysis module 22 obtains at different moments and each identical
During the spatial position change information of characteristic point, can the spatial position change information based on described image acquisition module, to described
Operation is normalized in the spatial position change information of same characteristic features point, and the normalization operation can include：Described image is obtained
The spatial position change information of modulus block and the spatial position change information of same characteristic features point carry out difference operation, obtain institute
State normed space change in location information.
Can be by the spatial position change information for the image collection module that synchronization is calculated and the phase at the moment
Spatial position change information with characteristic point carries out difference operation, such as can calculate image of the Tm+1 moment relative to the Tm moment
The spatial position change information of acquisition module is (Xc+1-Xc, Yc+1-Yc, Zc+1-Zc), and the space bit of same characteristic features point
It is (Xm+1-Xm, Ym+1-Ym, Zm+1-Zm) to put change information, then above-mentioned to be grasped for Tm+1 moment, the normalization of each same characteristics
The result of work is the difference between (Xc+1-Xc, Yc+1-Yc, Zc+1-Zc) and (Xm+1-Xm, Ym+1-Ym, Zm+1-Zm), should
Difference can be expressed as normed space change in location information.
Illustrated with following formula, (Lx, Ly, Lz) can be expressed as standard control change in location information, (Xc, Yc,
Zc) represent that the spatial position change information of image collection module, and (Xm+1, Ym+1, Zm+1) can be expressed as same characteristic features
Point spatial position change information, then the relation between three can be：
It is possible to further carry out cluster behaviour to the same characteristic features point based on the normed space change in location information
Make, to obtain the non-static characteristic point.In the embodiment of the present invention, analysis module 22 is believed based on the normed space change in location
Breath, cluster operation is carried out to the same characteristic features point, can be included with obtaining the non-static characteristic point：
Using the normed space change in location information as core, cluster operation is carried out to the same characteristic features point
Calculate the class spacing sum of all kinds of same characteristic features points；
The big a kind of same characteristic features point of the class spacing sum is judged as non-static characteristic point.
In the embodiment of the present invention, analysis module 22 can use k=2 k-means clustering methods, circulating repetition K times
Interval, cluster analysis is carried out to same same characteristic features point P standard control change in location information, wherein can be respectively by certain a period of time
The normed space change in location information of the same characteristic features point at quarter is as characteristic vector, to all same characteristic features point P normed space
Change in location information carries out clustering processing, and calculates between class distance sum, and the feature point set for taking between class distance sum small is combined into quiet
State characteristic point, the big non-static characteristic point in characteristic point position of class spacing sum.Non-static characteristic point can be realized by the process
Analysis and determination, above-mentioned non-static characteristic point is removed from fisrt feature point set can obtain second feature point set.
Non-static characteristic point is determined in the embodiment of the present invention by the way of above-mentioned cluster analysis, does not make and changing for clustering algorithm
Enter, normed space change in location information is simply subjected to cluster analysis, and obtain cluster result, realized according to the cluster result
The determination of non-static characteristic point, is no longer repeated clustering algorithm herein.
Based on disclosed above, it can know that the embodiment of the present invention has following beneficial effect：Due to the embodiment of the present invention
The equipment of offer can directly remove non-static characteristic point, then to computing resource when can effectively reduce SLAM back-end processings
Consumption, improve point cloud structure speed；In position fixing process, cloud map construction device can determine itself by multipoint positioning
Current location, the presence of non-static characteristic point can increase the probability of erroneous matching, cause the reduction of positioning precision, and the present invention is implemented
Example can filter before structure point cloud to characteristic point, remove behavioral characteristics point therein, significantly improve positioning precision；It is right
The filtering of behavioral characteristics point, the openness of some clouds can be improved, and not influence the positioning precision of a cloud, while in positioning rank
Section, the amount of calculation of positioning can be significantly reduced, lift locating speed.
It is apparent to those skilled in the art that for convenience and simplicity of description, the data of foregoing description
The electronic equipment that processing method is applied to, the corresponding description in before-mentioned products embodiment is may be referred to, will not be repeated here.
Above example is only the exemplary embodiment of the present invention, is not used in the limitation present invention, protection scope of the present invention
It is defined by the claims.Those skilled in the art can make respectively in the essence and protection domain of the present invention to the present invention
Kind modification or equivalent substitution, this modification or equivalent substitution also should be regarded as being within the scope of the present invention.
Claims (10)
1. determining the method for characteristic point in a kind of synchronous superposition, it includes：
Image information is gathered using image acquisition equipment；
Image information based on collection, obtain the fisrt feature point set in described image information；
The non-static characteristic point in the fisrt feature point set is analyzed, wherein, the non-static characteristic point is mobile object pair
The characteristic point answered；
The non-static characteristic point is filtered in the fisrt feature point set, to generate second feature point set.
2. the method according to claim 11, wherein, the non-static characteristic point in the analysis fisrt feature point set
Including：
The fisrt feature point set in described image information at different moments is obtained respectively；
Determine the same characteristic features point in the fisrt feature point set at each moment；
The same characteristic features point based on determination, and described image obtain movement state information of the equipment at each moment and analyze institute
State non-static characteristic point.
3. the method according to claim 11, wherein, the same characteristic features point based on determination, and described image
The movement state information analysis non-static characteristic point that equipment is obtained at each moment includes：
The depth information of the same characteristic features point based on determination, calculate the spatial position change information of the same characteristic features point；
Obtain the spatial position change information that described image obtains equipment；
The spatial position change letter of equipment is obtained based on the spatial position change information of the same characteristic features point, and described image
Breath, analysis determine the non-static characteristic point.
4. according to the method for claim 3, the spatial position change information based on the same characteristic features point, Yi Jisuo
The spatial position change information of image acquisition equipment is stated, analysis determines that the non-static characteristic point includes：
The spatial position change information of equipment is obtained based on described image, to the spatial position change information of the same characteristic features point
Operation is normalized, to obtain normed space change in location information；
Based on the normed space change in location information, cluster operation is carried out to the same characteristic features point, it is described non-quiet to obtain
State characteristic point.
5. according to the method for claim 3, wherein, the depth information of the same characteristic features point based on determination, count
Calculating the spatial position change information of the same characteristic features point includes：
The depth information of the same characteristic features point based on each moment, determine the positional information of the same characteristic features point；
Difference between the positional information of each same characteristic features point based on each moment determines the spatial position change information.
6. according to the method for claim 5, wherein, the spatial position change that equipment is obtained based on described image is believed
Breath, operation is normalized to the spatial position change information of the same characteristic features point, to obtain normed space change in location letter
Breath includes：
Described image is obtained into the spatial position change information of equipment and the spatial position change information of same characteristic features point is entered
Row difference operation, obtain the normed space change in location information.
7. the method according to claim 11, wherein, it is described to be based on the normed space change in location information, to the phase
Cluster operation is carried out with characteristic point, is included with obtaining the non-static characteristic point：
Using the normed space change in location information as core, cluster operation is carried out to the same characteristic features point；
Calculate the class spacing sum of all kinds of same characteristic features points；
The larger a kind of characteristic point of the class spacing sum is judged as non-static characteristic point.
8. determining the equipment of characteristic point in a kind of synchronous superposition, it includes：
Image collection module, it is configured to gather image information at different moments respectively；
Processor, it is configured to the image information of collection, obtains the fisrt feature point set in described image information；Analysis
Non-static characteristic point in the fisrt feature point set, wherein, the non-static characteristic point is feature corresponding to mobile object
Point；The non-static characteristic point is filtered in the fisrt feature point set, to generate second feature point set.
9. equipment according to claim 8, wherein, the processor is further configured to obtain institute at different moments respectively
State the fisrt feature point set in image information；Determine the same characteristic features point in the fisrt feature point set at each moment；Base
In it is determined that the same characteristic features point, and described image obtain equipment each moment movement state information analysis it is described non-quiet
State characteristic point.
10. equipment according to claim 9, wherein, the processor is further configured to described identical based on determination
The depth information of characteristic point, calculate the spatial position change information of the same characteristic features point；
Obtain the spatial position change information that described image obtains equipment；
The spatial position change letter of equipment is obtained based on the spatial position change information of the same characteristic features point, and described image
Breath, analysis determine the non-static characteristic point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710909238.XA CN107610177B (en) | 2017-09-29 | 2017-09-29 | The method and apparatus of characteristic point is determined in a kind of synchronous superposition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710909238.XA CN107610177B (en) | 2017-09-29 | 2017-09-29 | The method and apparatus of characteristic point is determined in a kind of synchronous superposition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107610177A true CN107610177A (en) | 2018-01-19 |
| CN107610177B CN107610177B (en) | 2019-10-29 |
Family
ID=61067238
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710909238.XA Active CN107610177B (en) | 2017-09-29 | 2017-09-29 | The method and apparatus of characteristic point is determined in a kind of synchronous superposition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107610177B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108460779A (en) * | 2018-02-12 | 2018-08-28 | 浙江大学 | A kind of mobile robot image vision localization method under dynamic environment |
| CN110309240A (en) * | 2018-03-14 | 2019-10-08 | 北京京东尚科信息技术有限公司 | The method and apparatus for removing dynamic object |
| CN110533055A (en) * | 2018-05-25 | 2019-12-03 | 北京京东尚科信息技术有限公司 | A kind for the treatment of method and apparatus of point cloud data |
| CN111860057A (en) * | 2019-04-29 | 2020-10-30 | 北京眼神智能科技有限公司 | Face image blurring and living body detection method and device, storage medium and equipment |
| CN112435278A (en) * | 2021-01-26 | 2021-03-02 | 华东交通大学 | Visual SLAM method and device based on dynamic target detection |
| CN112767409A (en) * | 2019-11-05 | 2021-05-07 | 珠海格力电器股份有限公司 | Image processing method and device before positioning, storage medium and computer equipment |
| WO2022110473A1 (en) * | 2020-11-24 | 2022-06-02 | 深圳市优必选科技股份有限公司 | Robot mapping method and device, computer readable storage medium, and robot |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7200282B2 (en) * | 2001-12-12 | 2007-04-03 | Sony Corporation | Implementation of Hough transform and its application in line detection and video motion analysis |
| CN103154666A (en) * | 2011-06-14 | 2013-06-12 | 日产自动车株式会社 | Distance measurement device and environment map generation apparatus |
| CN103456022A (en) * | 2013-09-24 | 2013-12-18 | 中国科学院自动化研究所 | High-resolution remote sensing image feature matching method |
| CN103955948A (en) * | 2014-04-03 | 2014-07-30 | 西北工业大学 | Method for detecting space moving object in dynamic environment |
| CN104424481A (en) * | 2013-09-02 | 2015-03-18 | 联想(北京)有限公司 | Information processing method and intelligent equipment |
| CN104424635A (en) * | 2013-08-30 | 2015-03-18 | 联想(北京)有限公司 | Information processing method, system and equipment |
| CN105303554A (en) * | 2015-09-16 | 2016-02-03 | 东软集团股份有限公司 | Image feature point 3D reconstruction method and device |
| CN107146238A (en) * | 2017-04-24 | 2017-09-08 | 西安电子科技大学 | The preferred motion target tracking method of feature based block |
-
2017
- 2017-09-29 CN CN201710909238.XA patent/CN107610177B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7200282B2 (en) * | 2001-12-12 | 2007-04-03 | Sony Corporation | Implementation of Hough transform and its application in line detection and video motion analysis |
| CN103154666A (en) * | 2011-06-14 | 2013-06-12 | 日产自动车株式会社 | Distance measurement device and environment map generation apparatus |
| CN104424635A (en) * | 2013-08-30 | 2015-03-18 | 联想(北京)有限公司 | Information processing method, system and equipment |
| CN104424481A (en) * | 2013-09-02 | 2015-03-18 | 联想(北京)有限公司 | Information processing method and intelligent equipment |
| CN103456022A (en) * | 2013-09-24 | 2013-12-18 | 中国科学院自动化研究所 | High-resolution remote sensing image feature matching method |
| CN103955948A (en) * | 2014-04-03 | 2014-07-30 | 西北工业大学 | Method for detecting space moving object in dynamic environment |
| CN105303554A (en) * | 2015-09-16 | 2016-02-03 | 东软集团股份有限公司 | Image feature point 3D reconstruction method and device |
| CN107146238A (en) * | 2017-04-24 | 2017-09-08 | 西安电子科技大学 | The preferred motion target tracking method of feature based block |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108460779A (en) * | 2018-02-12 | 2018-08-28 | 浙江大学 | A kind of mobile robot image vision localization method under dynamic environment |
| CN108460779B (en) * | 2018-02-12 | 2021-09-24 | 浙江大学 | Mobile robot image visual positioning method in dynamic environment |
| CN110309240A (en) * | 2018-03-14 | 2019-10-08 | 北京京东尚科信息技术有限公司 | The method and apparatus for removing dynamic object |
| CN110533055A (en) * | 2018-05-25 | 2019-12-03 | 北京京东尚科信息技术有限公司 | A kind for the treatment of method and apparatus of point cloud data |
| CN110533055B (en) * | 2018-05-25 | 2022-04-26 | 北京京东尚科信息技术有限公司 | Point cloud data processing method and device |
| CN111860057A (en) * | 2019-04-29 | 2020-10-30 | 北京眼神智能科技有限公司 | Face image blurring and living body detection method and device, storage medium and equipment |
| CN112767409A (en) * | 2019-11-05 | 2021-05-07 | 珠海格力电器股份有限公司 | Image processing method and device before positioning, storage medium and computer equipment |
| WO2022110473A1 (en) * | 2020-11-24 | 2022-06-02 | 深圳市优必选科技股份有限公司 | Robot mapping method and device, computer readable storage medium, and robot |
| CN112435278A (en) * | 2021-01-26 | 2021-03-02 | 华东交通大学 | Visual SLAM method and device based on dynamic target detection |
| CN112435278B (en) * | 2021-01-26 | 2021-05-04 | 华东交通大学 | Visual SLAM method and device based on dynamic target detection |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107610177B (en) | 2019-10-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107610177B (en) | The method and apparatus of characteristic point is determined in a kind of synchronous superposition | |
| CN104834922B (en) | Gesture identification method based on hybrid neural networks | |
| CN105046197B (en) | Multi-template pedestrian detection method based on cluster | |
| US8855363B2 (en) | Efficient method for tracking people | |
| Zhang et al. | Pedestrian detection method based on Faster R-CNN | |
| CN104933414B (en) | A kind of living body faces detection method based on WLD-TOP | |
| CN105740780B (en) | Method and device for detecting living human face | |
| CN103310194A (en) | Method for detecting head and shoulders of pedestrian in video based on overhead pixel gradient direction | |
| CN102708380B (en) | Indoor common object identification method based on machine vision | |
| CN107067410B (en) | Manifold regularization related filtering target tracking method based on augmented samples | |
| CN104537689B (en) | Method for tracking target based on local contrast conspicuousness union feature | |
| Zhang et al. | Fast moving pedestrian detection based on motion segmentation and new motion features | |
| CN111508006A (en) | Moving target synchronous detection, identification and tracking method based on deep learning | |
| Kheirkhah et al. | A hybrid face detection approach in color images with complex background | |
| JP2019536164A (en) | Image processing apparatus, image processing method, and image processing program | |
| CN106529441A (en) | Fuzzy boundary fragmentation-based depth motion map human body action recognition method | |
| CN110007764B (en) | Gesture skeleton recognition method, device and system and storage medium | |
| CN113642385B (en) | Facial nevus recognition method and system based on deep learning | |
| Juang et al. | Stereo-camera-based object detection using fuzzy color histograms and a fuzzy classifier with depth and shape estimations | |
| CN102509308A (en) | Motion segmentation method based on mixtures-of-dynamic-textures-based spatiotemporal saliency detection | |
| Zhu et al. | Scene text relocation with guidance | |
| CN111444875A (en) | Face tracking method, device, equipment and computer readable storage medium | |
| US10140509B2 (en) | Information processing for detection and distance calculation of a specific object in captured images | |
| KR20160148806A (en) | Object Detecter Generation Method Using Direction Information, Object Detection Method and Apparatus using the same | |
| Kumar et al. | Skin based occlusion detection and face recognition using machine learning techniques |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |