CN104050709B - A kind of three dimensional image processing method and electronic equipment - Google Patents
A kind of three dimensional image processing method and electronic equipment Download PDFInfo
- Publication number
- CN104050709B CN104050709B CN201410251325.7A CN201410251325A CN104050709B CN 104050709 B CN104050709 B CN 104050709B CN 201410251325 A CN201410251325 A CN 201410251325A CN 104050709 B CN104050709 B CN 104050709B
- Authority
- CN
- China
- Prior art keywords
- plane
- point
- normal vector
- classification
- belonging
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a kind of three dimensional image processing method, for improving image rendering noise removal capability.Methods described includes:Clustered for the three-dimensional point cloud of collection, obtain N number of classification, N is positive integer;Wherein each corresponding plane of classification, the three-dimensional point cloud is the three-dimensional point cloud obtained according to three dimensional object;It is the integer from 1 to N to take i, is followed the steps below respectively:The normal vector of each point in i-th of plane determines the normal vector of i-th of plane, and the normal vector of N number of plane is obtained;It is the integer from 1 to N to take i, is followed the steps below respectively:The point that i-th of plane includes is projected in a plane according to the normal vector of i-th of plane, the plane is the corresponding detection plane of i-th of plane;N number of detection plane is obtained;N number of detection plane is rendered, the corresponding 3-D view of the three dimensional object is obtained.The invention also discloses corresponding electronic equipment.
Description
Technical field
The present invention relates to three-dimensional rendering technical field, more particularly to a kind of three dimensional image processing method and electronic equipment.
Background technology
At present, large-scale three dimensional scenario building is mainly obtained using electronic equipments such as three-dimensional cameras.Basic procedure is by three
A series of depth image and coloured image in camera capturing scenes are tieed up, it is rendered afterwards.However, the sky of three-dimensional camera
Between error distribution it is complex, noise is relatively more, distribution also relatively in a jumble, how to the 3-D view denoising with depth to obtain
It must be the key issue in scene rendering to the more accurate 3-D view of scene description.
Existing depth image denoising method, mainly based on the methods such as time-domain filtering and space filtering, i.e., by each
The distribution of point in the vertex neighborhood of space is filtered to space point set.But in 3-D view, it is likely present some structures
Information, such as plane.If according to existing filtering mode, hardly considering the structural information in 3-D view, noise removal capability compared with
In difference, the 3-D view finally rendered, it should be that the place of plane is likely to become curved surface originally, cause three finally given
There is distortion in dimension image.
It can be seen that, existing rendering intent noise removal capability is poor, and obtained 3-D view can be caused distortion occur.
The content of the invention
The embodiment of the present invention provides a kind of three dimensional image processing method, for solving rendering intent denoising of the prior art
The poor technical problem of ability.
A kind of three dimensional image processing method, comprises the following steps:
Clustered for the three-dimensional point cloud of collection, obtain N number of classification, N is positive integer;Wherein each classification correspondence one
Plane, the three-dimensional point cloud is the three-dimensional point cloud obtained according to three dimensional object;
It is the integer from 1 to N to take i, is followed the steps below respectively:The normal vector of each point in i-th of plane is true
The normal vector of fixed i-th of plane, is obtained the normal vector of N number of plane;
It is the integer from 1 to N to take i, is followed the steps below respectively:The point that i-th of plane is included is according to described
The normal vector of i-th of plane is projected in a plane, and the plane is the corresponding detection plane of i-th of plane;N is obtained
Individual detection plane;
N number of detection plane is rendered, the corresponding 3-D view of the three dimensional object is obtained.
Optionally, clustered in the three-dimensional point cloud for collection, after the N number of classification of acquisition, in addition to:According to for institute
The space measurement precision of three dimensional object is stated, the coordinate each put in the three-dimensional point cloud is determined, and, according in wherein each classification
Point locus, it is determined that weight of each point in each self-corresponding classification.
Optionally, clustered for the three-dimensional point cloud of collection, obtain N number of classification, including:
Determine the normal vector for each point that the three-dimensional point cloud includes;
According to the normal vector and coordinate each put in the three-dimensional point cloud, the point that the three-dimensional point cloud includes is gathered
Class, obtains N number of classification.
Optionally, according to the normal vector and coordinate each put in the three-dimensional point cloud, the three-dimensional point cloud is included
Point is clustered, and obtains N number of classification, including:The point that normal vector and coordinate are satisfied by into same preparatory condition is polymerized to one
Individual classification, obtains N number of classification;Wherein, the preparatory condition is:Angle between normal vector and preset direction is located at first
In the range of default angle threshold value, and coordinate is located in the first predeterminable area.
Optionally, the normal vector of each point in i-th of plane determines the normal vector of i-th of plane, including:
The normal vector of each point in i-th of plane is weighted averagely according to each corresponding weight of point, described i-th is obtained
The normal vector of individual plane.
Optionally, the normal vector of i-th of plane is determined in the normal vector of each point in i-th of plane, altogether
After the normal vector for obtaining N number of plane, in addition to:
It is the integer from 1 to N to take i, is followed the steps below respectively:Judge whether be not belonging to wherein in the three-dimensional point cloud
The other point of any sort;If so, judge to be not belonging to normal vector and i-th of the plane of the point of any of which classification normal vector it
Between angle whether be less than the second default angle threshold value;
If the angle being not belonging between the normal vector of the point of any of which classification and the normal vector of wherein M plane is less than institute
The second predetermined threshold value is stated, determines to be not belonging to the distance between point and the M plane of any of which classification respectively, and determine not belong to
J-th of the plane belonged in the point of any of which classification in the M plane;Wherein, j-th of plane is:It is not belonging to this
The distance of the point of any of which classification most short plane;M is no more than N positive integer.
Optionally, it is determined that being not belonging to j-th of plane that the point of any of which classification belongs in the M plane, including:
Judge to be not belonging to whether the point of any of which classification is less than pre-determined distance with the distance of j-th of plane;
If less than the pre-determined distance, it is determined that the point for being not belonging to any of which classification belongs to j-th of plane.
Optionally, judging that be not belonging to the point of any of which classification presets with whether the distance of j-th of plane is less than
After distance, in addition to:If not less than the pre-determined distance, it is the integer from 1 to K to take k, is followed the steps below respectively:
Judge whether the angle being not belonging between the normal vector of the point of any of which classification and the normal vector of k-th of plane is small
In the 3rd default angle threshold value;Described 3rd default angle threshold value is more than the described second default angle threshold value;
If being less than, it is determined that the point for being not belonging to any of which classification belongs to k-th of plane;Wherein, K is no more than N's
Positive integer.
Optionally, it is determined that be not belonging to after the point of any of which classification belongs to k-th of plane, in addition to:According to
The normal vector of each point in N number of plane determines the normal vector and area of N number of plane respectively again.
A kind of electronic equipment, including:
Cluster module, is clustered for the three-dimensional point cloud for collection, obtains N number of classification, N is positive integer;It is wherein every
One plane of individual classification correspondence, the three-dimensional point cloud is the three-dimensional point cloud obtained according to three dimensional object;
First determining module, for taking i to be the integer from 1 to N, is followed the steps below respectively:According in i-th of plane
The normal vector each put determines the normal vector of i-th of plane, and the normal vector of N number of plane is obtained;
Projection module, for taking i to be the integer from 1 to N, is followed the steps below respectively:I-th of plane is included
Point projected to according to the normal vector of i-th of plane in a plane, the plane be the corresponding detection of i-th of plane
Plane;N number of detection plane is obtained;
Rendering module, for being rendered to N number of detection plane, obtains the corresponding graphics of the three dimensional object
Picture.
Optionally, the electronic equipment also includes the second determining module, is used for:Gathered in the three-dimensional point cloud for collection
Class, obtains after N number of classification, according to the space measurement precision for the three dimensional object, determines each in the three-dimensional point cloud
The coordinate of point, and, the locus of the point in wherein each classification, it is determined that power of each point in each self-corresponding classification
Weight.
Optionally, the cluster module specifically for:Determine the normal vector for each point that the three-dimensional point cloud includes;Root
According to the normal vector and coordinate each put in the three-dimensional point cloud, the point that the three-dimensional point cloud includes is clustered, institute is obtained
State N number of classification.
Optionally, the cluster module specifically for:It is right according to the normal vector and coordinate each put in the three-dimensional point cloud
The point that the three-dimensional point cloud includes is clustered, and obtains N number of classification, is specially:Normal vector and coordinate are satisfied by together
The point of one preparatory condition is polymerized to a classification, obtains N number of classification;Wherein, the preparatory condition is:Normal vector is with presetting
Angle between direction is located in the range of the first default angle threshold value, and coordinate is located in the first predeterminable area.
Optionally, first determining module specifically for:By in i-th of plane each point normal vector according to
Each is put corresponding weight and is weighted averagely, obtains the normal vector of i-th of plane.
Optionally, first determining module is additionally operable to:
The normal vector of i-th of plane is determined in the normal vector of each point in i-th of plane, is obtained N number of
After the normal vector of plane, it is the integer from 1 to N to take i, is followed the steps below respectively:Judge whether have in the three-dimensional point cloud
It is not belonging to the point of any of which classification;If so, judging to be not belonging to the normal vector of the point of any of which classification and i-th of plane
Normal vector between angle whether be less than the second default angle threshold value;
If the angle being not belonging between the normal vector of the point of any of which classification and the normal vector of wherein M plane is less than institute
The second predetermined threshold value is stated, determines to be not belonging to the distance between point and the M plane of any of which classification respectively, and determine not belong to
J-th of the plane belonged in the point of any of which classification in the M plane;Wherein, j-th of plane is:It is not belonging to this
The distance of the point of any of which classification most short plane;M is no more than N positive integer.
Optionally, first determining module is put down specifically for determining that the point for being not belonging to any of which classification belongs to the M
J-th of plane in face, be specially:Judge whether the point and the distance of j-th of plane that are not belonging to any of which classification are small
In pre-determined distance;If less than the pre-determined distance, it is determined that the point for being not belonging to any of which classification belongs to j-th of plane.
Optionally, first determining module is additionally operable to:Judging to be not belonging to the point of any of which classification and described j-th
Whether the distance of plane is less than after pre-determined distance, if not less than the pre-determined distance, it is the integer from 1 to K to take k, is entered respectively
Row following steps:
Judge whether the angle being not belonging between the normal vector of the point of any of which classification and the normal vector of k-th of plane is small
In the 3rd default angle threshold value;Described 3rd default angle threshold value is more than the described second default angle threshold value;
If being less than, it is determined that the point for being not belonging to any of which classification belongs to k-th of plane;Wherein, K is no more than N's
Positive integer.
Optionally, first determining module is additionally operable to:It is determined that the point for being not belonging to any of which classification belongs to the kth
After individual plane, the normal vector of each point in N number of plane determine respectively again N number of plane normal vector and
Area.
, can be by the spot projection in the three-dimensional point cloud of collection into different detection planes, finally in the embodiment of the present invention
Rendered according to detection plane, i.e., the structural information in 3-D view has been taken into full account in render process, has improved and renders
During noise removal capability, the result enabled to tries one's best accurately, ensures that obtained 3-D view will not distortion as far as possible.
Brief description of the drawings
Fig. 1 is the broad flow diagram of three dimensional image processing method in the embodiment of the present invention;
Fig. 2 is the primary structure block diagram of electronic equipment in the embodiment of the present invention.
Embodiment
The embodiment of the present invention provides a kind of three dimensional image processing method, including:Clustered for the three-dimensional point cloud of collection,
N number of classification is obtained, N is positive integer;Wherein each corresponding plane of classification, the three-dimensional point cloud is to be obtained according to three dimensional object
Three-dimensional point cloud;It is the integer from 1 to N to take i, is followed the steps below respectively:The normal vector of each point in i-th of plane
The normal vector of i-th of plane is determined, the normal vector of N number of plane is obtained;I is taken for integer from 1 to N, carry out respectively with
Lower step:The point that i-th of plane includes is projected in a plane according to the normal vector of i-th of plane, should
Plane is the corresponding detection plane of i-th of plane;N number of detection plane is obtained;Wash with watercolours is carried out to N number of detection plane
Dye, obtains the corresponding 3-D view of the three dimensional object
, can be by the spot projection in the three-dimensional point cloud of collection into different detection planes, finally in the embodiment of the present invention
Rendered according to detection plane, i.e., the structural information in 3-D view has been taken into full account in render process, has improved and renders
During noise removal capability, the result enabled to tries one's best accurately, ensures that obtained 3-D view will not distortion as far as possible.
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
A part of embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment obtained under the premise of creative work is not made, belongs to the scope of protection of the invention.
In addition, the terms "and/or", only a kind of incidence relation for describing affiliated partner, represents there may be
Three kinds of relations, for example, A and/or B, can be represented:Individualism A, while there is A and B, these three situations of individualism B.Separately
Outside, character "/" herein, unless otherwise specified, it is a kind of relation of "or" to typically represent forward-backward correlation object.
The preferred embodiment of the present invention is described in detail below in conjunction with the accompanying drawings.
Fig. 1 is referred to, the embodiment of the present invention provides a kind of three dimensional image processing method, the main flow description of methods described
It is as follows.
Step 101:Clustered for the three-dimensional point cloud of collection, obtain N number of classification, N is positive integer;Wherein each classification
One plane of correspondence, the three-dimensional point cloud is the three-dimensional point cloud obtained according to three dimensional object.
Optionally, in the embodiment of the present invention, clustered for the three-dimensional point cloud of collection, obtain N number of classification, can wrap
Include:Determine the normal vector for each point that the three-dimensional point cloud includes;According to the normal vector each put in the three-dimensional point cloud and
Coordinate, is clustered to the point that the three-dimensional point cloud includes, and obtains N number of classification.
Optionally, in the embodiment of the present invention, according to the normal vector and coordinate each put in the three-dimensional point cloud, to described three
The point that dimension point cloud includes is clustered, and is obtained N number of classification, can be included:Normal vector and coordinate are satisfied by same pre-
If the point of condition is polymerized to a classification, N number of classification is obtained;Wherein, the preparatory condition is:Normal vector and preset direction
Between angle be located in the range of the first default angle threshold value, and coordinate is located in the first predeterminable area.
For example, one of preparatory condition is:Angle between the normal vector and Y-axis of point is located at default angle threshold value scope
In A and the coordinate of point is respectively positioned on Y-axis negative direction, other in which preparatory condition is:Angle between the normal vector and Y-axis of point
In default angle threshold value scope B and point coordinate be respectively positioned on Y-axis positive direction, etc..
One plane of each classification correspondence, it can be understood as, multiple points are gathered for a class, these points are exactly corresponded to one
In individual plane.
Optionally, in the embodiment of the present invention, clustered in the three-dimensional point cloud for collection, obtain N number of classification it
Afterwards, it can also include:According to the space measurement precision for the three dimensional object, the seat each put in the three-dimensional point cloud is determined
Mark, and, the locus of the point in wherein each classification, it is determined that weight of each point in each self-corresponding classification.
After the three-dimensional point cloud is gathered, it may be determined that therein each to put corresponding coordinate.For example, it can be chosen
In a point as the origin of coordinates set up coordinate system, may thereby determine that the coordinate therein each put.
It is determined that after N number of classification, for each classification, it may be determined that wherein different weights of difference, i.e. for
For one point, its corresponding weight is the classification corresponding to the point.Determine that weight there can be different modes, for example
A kind of possible mode is:When gathering the three-dimensional point cloud by the electronic equipment, point and institute in the three-dimensional point cloud
State the distance between electronic equipment have it is remote have near, then the distance between can specify that in the three-dimensional point cloud with the electronic equipment
Nearer point weight is bigger.
Step 102:It is the integer from 1 to N to take i, is followed the steps below respectively:Each point in i-th of plane
Normal vector determines the normal vector of i-th of plane, and the normal vector of N number of plane is obtained.
After being clustered to the three-dimensional point cloud, N number of classification can be obtained, each classification corresponds to a plane,
That is N number of plane can be obtained, for each plane therein, its normal vector can be calculated, and can also calculate every
The area of individual plane and the central point for determining each plane.
For example, for i-th of plane therein, calculating its normal vector, a kind of calculation for example can be:By institute
State each point in i-th of plane normal vector be weighted according to each corresponding weight of point it is average, obtain described i-th it is flat
The normal vector in face.
The weight each put is considered in the normal vector of Calculation Plane, obtained result emphasis can be made more prominent.
In the ideal case, obtain after N number of plane, each point in the three-dimensional point cloud should can be included into it
In a plane in.But it there may come a time when that having some points is not included into any one plane, if do not carried out to these points
Processing, some of which point will be missed when rendering, result also can be not accurate enough.Therefore, optionally, the present invention is implemented
In example, the normal vector of i-th of plane is determined in the normal vector of each point in i-th of plane, N number of plane is obtained
Normal vector after, can also include:
It is the integer from 1 to N to take i, is followed the steps below respectively:Judge whether be not belonging to wherein in the three-dimensional point cloud
The other point of any sort;If so, judge to be not belonging to normal vector and i-th of the plane of the point of any of which classification normal vector it
Between angle whether be less than the second default angle threshold value;
If the angle being not belonging between the normal vector of the point of any of which classification and the normal vector of wherein M plane is less than institute
The second predetermined threshold value is stated, determines to be not belonging to the distance between point and the M plane of any of which classification respectively, and determine not belong to
J-th of the plane belonged in the point of any of which classification in the M plane;Wherein, j-th of plane is:It is not belonging to this
The distance of the point of any of which classification most short plane;M is no more than N positive integer.
For example, it is determined that after the normal vector of N number of plane, if it is judged that there is a point in the three-dimensional point cloud
Any one plane therein is not belonging to, then be may determine that, in N number of plane, if has the normal vector of plane and the method for the point
Angle between vector is less than the described second default angle threshold value, if so, then determine to meet the quantity of the plane of the condition, if
Only one of which, then can directly determine that the point belongs to the plane, if multiple, then can determine that the point is put down with the plurality of respectively
The distance between face, it is determined that after multiple distances, it may be determined that the minimum distance of its intermediate value, then can determine that the point belongs to the value
Plane corresponding to minimum distance.
Optionally, in the embodiment of the present invention, it is determined that being not belonging to the jth that the point of any of which classification belongs in the M plane
Individual plane, including:Judge to be not belonging to whether the point of any of which classification is less than pre-determined distance with the distance of j-th of plane;
If less than the pre-determined distance, it is determined that the point for being not belonging to any of which classification belongs to j-th of plane.
In this embodiment, it is determined that after the normal vector of N number of plane, if it is judged that in the three-dimensional point cloud also
There is a point to be not belonging to any one plane therein, then may determine that, in N number of plane, if having the normal vector of plane with
Angle between the normal vector of the point is less than the described second default angle threshold value, if so, then determining to meet the plane of the condition
Quantity, if it is determined that the plane only one of which gone out, it is determined that the distance between the point and the plane whether be less than it is described it is default away from
From if being less than, it is determined that the point belongs to the plane.
If it is determined that plane have multiple, then the distance between the point and the plurality of plane can be determined respectively, true
After fixed multiple distances, it may be determined that the minimum distance of its intermediate value, and the plane corresponding to the minimum distance of the value is determined, it is determined that should
Whether the distance between point and the plane are less than the pre-determined distance, if being less than, and can determine that the point belongs to value minimum
Apart from corresponding plane.
Optionally, in the embodiment of the present invention, judge to be not belonging to the point of any of which classification and j-th of plane away from
From whether being less than after pre-determined distance, it can also include:If not less than the pre-determined distance, it is the integer from 1 to K to take k, respectively
Follow the steps below:Judge the angle being not belonging between the normal vector of the point of any of which classification and the normal vector of k-th of plane
Whether threeth default angle threshold value is less than;Described 3rd default angle threshold value is more than the described second default angle threshold value;If being less than,
It is determined that the point for being not belonging to any of which classification belongs to k-th of plane;Wherein, K is no more than N positive integer.
In the embodiment of the present invention, different default angle threshold values can be preset with, such as according to relation from small to large, point
Described second default angle threshold value, the 3rd angle threshold value, the 4th angle threshold value etc. is not preset with.But for each plane
For, the default angle threshold value limit that area difference can be born is also just different, and in general, area is bigger, then can be right
The upper limit for the default angle threshold value answered is also bigger.For example, having plane 1 and plane 2, the area of the plane 1 is more than described put down
The area in face 2, the then default angle threshold value that the plane 1 can be supported may just include the described second default angle threshold value, institute
The 3rd angle threshold value and the 4th angle threshold value are stated, and the default angle threshold value that the plane 2 can be supported just may be wrapped only
The described second default angle threshold value and the 3rd angle threshold value are included, and the 4th angle threshold value can not be supported.
Why between judgement is not belonging to the normal vector of the normal vector of the point of any of which classification and k-th of plane
Angle take k to be the integer from 1 to K when whether being less than the described 3rd default angle threshold value, rather than the integer from 1 to N, K is not
It is exactly because after default angle threshold value is improved, might have plane and do not support, then when judging naturally without sentencing again more than N
These disconnected planes.
For example, for first plane, if its corresponding default angle threshold value refer into the upper limit,
Such as upper limit is the described 4th default angle threshold value, and between the normal vector of the point and the normal vector of first plane
Angle is still not less than the described 4th default angle threshold value, then the corresponding default angle threshold value of first plane can not be again
Improve, can continue to judge the point and second plane therein, judgment mode and the judgment mode phase of first plane
Together.Because the default angle threshold value corresponding to each plane may be different, so as to bring different points into difference as far as possible
Plane in, it is to avoid omit.
It is whole come illustrate to handle a point for being not belonging to any plane below by way of a more detailed example
Individual process.
For example, after being clustered to the three-dimensional point cloud, obtaining 3 classifications, 3 classifications have also been obtained corresponding
Normal vector, area and central point.Afterwards, determine that also one point is not belonging to any of which classification, i.e. any one plane, then
It can judge whether the angle between the normal vector of the point and 3 normal vectors is less than the described second default angle threshold value respectively.
Such as angle between the normal vector of the point and 3 normal vectors is respectively less than the described second default angle threshold value, then
The distance between the point and 3 normal vectors can be determined respectively, after it is determined that finishing, therefrom select a value it is minimum away from
From the distance between normal vector and the point of such as the 3rd plane minimum.Then, continue to judge between the point and the 3rd plane
Distance whether be less than the pre-determined distance, if less than the pre-determined distance, can determine that the point belongs to the 3rd plane.
If not less than the pre-determined distance, described the than the described second high level of default angle threshold value can be determined
Three default angle threshold values, the described 3rd default angle threshold value is more than the described second default angle threshold value, while determining to support described
The plane of 3rd angle threshold value, such as 3 planes support the 3rd angle threshold value, then can continue to judge the point respectively
Normal vector and 3 normal vectors between angle whether be less than the normal vector of the described 3rd default angle threshold value, such as point
Angle between the normal vector of 3 planes can then determine that the point does not belong to not less than the described second default angle threshold value
In any of which plane.
In the embodiment of the present invention, it is determined that after N number of planes, multiple points being might have in the three-dimensional point cloud and are not belonged to
, then can be with identical to the processing mode of each point in any one plane therein, processing mode to a point above
It is illustrated, seldom repeats herein.
In the embodiment of the present invention, it is determined that be not belonging to after the point of any of which classification belongs to k-th of plane, also wrap
Include:The normal vector of each point in N number of plane determines the normal vector and area of N number of plane respectively again, also
The central point of each plane can be redefined.Preferably, only the plane that has newly-increased point can be redefined its normal vector,
Area and central point, workload can be reduced on the premise of the accuracy of result is ensured as far as possible.
Step 103:It is the integer from 1 to N to take i, is followed the steps below respectively:The point that i-th of plane is included
Normal vector according to i-th of plane is projected in a plane, and the plane is that the corresponding detection of i-th of plane is flat
Face;N number of detection plane is obtained.
After each point is included into N number of plane as far as possible, the point that can include i-th of plane is according to institute
Position where stating the direction of the normal vector of i-th of plane and the central point of i-th of plane is projected, and projects to one
In individual plane, the plane is properly termed as the corresponding detection plane of i-th of plane.Similar throwing is carried out to N number of plane
Shadow, can obtain N number of detection plane.
For N number of plane, this " plane " may be not necessarily substantially flat, may have certain " thickness
Degree ", i.e. for one of plane, point therein not exclusively may be located in a real plane.Therefore by institute
State N number of plane and re-start projection, spot projection therein into real plane, i.e. N number of detection plane is real meaning
Plane in justice.
Step 104:N number of detection plane is rendered, the corresponding 3-D view of the three dimensional object is obtained.
After N number of detection plane is obtained, N number of detection plane can be rendered.N number of detection plane
It is plane truly, this is the detection obtained on the basis of the structured features of the three-dimensional point cloud have been taken into full account
Plane, and each point in the three-dimensional point cloud has been put into N number of detection plane as far as possible, according to N number of inspection
Survey plane to be rendered, what is obtained is exactly the rendering result after denoising, effectively increases the accuracy of rendering result.
Fig. 2 is referred to, based on same inventive concept, the embodiment of the present invention provides a kind of electronic equipment, the electronic equipment
Cluster module 201, the first determining module 202, projection module 203 and rendering module 204 can be included.For example, the electronics is set
Standby can be the different equipment of mobile phone, PAD (tablet personal computer), PC (personal computer), intelligent television etc., or the electronics
Equipment can also be that, for carrying out equipment of professional image, etc., the present invention is not limited.
Cluster module 201 is used to be clustered for the three-dimensional point cloud of collection, obtains N number of classification, N is positive integer;Wherein
One plane of each classification correspondence, the three-dimensional point cloud is the three-dimensional point cloud obtained according to three dimensional object.
First determining module 202 is used to take i to be the integer from 1 to N, follows the steps below respectively:According in i-th of plane
The normal vector of each point determine the normal vector of i-th of plane, the normal vector of N number of plane is obtained.
Projection module 203 is used to take i to be the integer from 1 to N, follows the steps below respectively:It will be wrapped in i-th of plane
The point included is projected in a plane according to the normal vector of i-th of plane, and the plane is the corresponding inspection of i-th of plane
Survey plane;N number of detection plane is obtained.
Rendering module 204 is used to render N number of detection plane, obtains the corresponding graphics of the three dimensional object
Picture.
Optionally, in the embodiment of the present invention, the electronic equipment can also include the second determining module, be used for:For
The three-dimensional point cloud of collection is clustered, after obtaining N number of classification, according to the space measurement precision for the three dimensional object, really
The coordinate each put in the fixed three-dimensional point cloud, and, the locus of the point in wherein each classification, it is determined that each point exists
Weight in each self-corresponding classification.
Optionally, in the embodiment of the present invention, cluster module 201 specifically for:Determine that the three-dimensional point cloud includes every
The normal vector of individual point;According to the normal vector and coordinate each put in the three-dimensional point cloud, the point included to the three-dimensional point cloud
Clustered, obtain N number of classification.
Optionally, in the embodiment of the present invention, cluster module 201 specifically for:According to what is each put in the three-dimensional point cloud
Normal vector and coordinate, are clustered to the point that the three-dimensional point cloud includes, and obtain N number of classification, are specially:By normal vector
The point for being satisfied by same preparatory condition with coordinate is polymerized to a classification, obtains N number of classification;Wherein, the preparatory condition
For:Angle between normal vector and preset direction is located in the range of the first default angle threshold value, and coordinate is located at the first preset areas
In domain.
Optionally, in the embodiment of the present invention, the first determining module 202 specifically for:By each in i-th of plane
The normal vector of point is weighted averagely according to each corresponding weight of point, obtains the normal vector of i-th of plane.
Optionally, in the embodiment of the present invention, the first determining module 202 is additionally operable to:
The normal vector of i-th of plane is determined in the normal vector of each point in i-th of plane, is obtained N number of
After the normal vector of plane, it is the integer from 1 to N to take i, is followed the steps below respectively:Judge whether have in the three-dimensional point cloud
It is not belonging to the point of any of which classification;If so, judging to be not belonging to the normal vector of the point of any of which classification and i-th of plane
Normal vector between angle whether be less than the second default angle threshold value;
If the angle being not belonging between the normal vector of the point of any of which classification and the normal vector of wherein M plane is less than institute
The second predetermined threshold value is stated, determines to be not belonging to the distance between point and the M plane of any of which classification respectively, and determine not belong to
J-th of the plane belonged in the point of any of which classification in the M plane;Wherein, j-th of plane is:It is not belonging to this
The distance of the point of any of which classification most short plane;M is no more than N positive integer.
Optionally, in the embodiment of the present invention, the first determining module 202 is specifically for determining to be not belonging to any of which classification
J-th of plane that point belongs in the M plane, be specially:Judgement is not belonging to the point and j-th of plane of any of which classification
Distance whether be less than pre-determined distance;If less than the pre-determined distance, it is determined that the point for being not belonging to any of which classification belongs to described
J-th of plane.
Optionally, in the embodiment of the present invention, the first determining module 202 is additionally operable to:Judging to be not belonging to any of which classification
The distance of point and j-th of plane whether be less than after pre-determined distance, if not less than the pre-determined distance, take k be from 1 to
K integer, is followed the steps below respectively:
Judge whether the angle being not belonging between the normal vector of the point of any of which classification and the normal vector of k-th of plane is small
In the 3rd default angle threshold value;Described 3rd default angle threshold value is more than the described second default angle threshold value;
If being less than, it is determined that the point for being not belonging to any of which classification belongs to k-th of plane;Wherein, K is no more than N's
Positive integer.
Optionally, in the embodiment of the present invention, the first determining module 202 is additionally operable to:It is determined that being not belonging to any of which classification
Point belong to after k-th of plane, the normal vector of each point in N number of plane determines the N respectively again
The normal vector and area of individual plane.
The embodiment of the present invention provides a kind of three dimensional image processing method, including:Clustered for the three-dimensional point cloud of collection,
N number of classification is obtained, N is positive integer;Wherein each corresponding plane of classification, the three-dimensional point cloud is to be obtained according to three dimensional object
Three-dimensional point cloud;It is the integer from 1 to N to take i, is followed the steps below respectively:The normal vector of each point in i-th of plane
The normal vector of i-th of plane is determined, the normal vector of N number of plane is obtained;I is taken for integer from 1 to N, carry out respectively with
Lower step:The point that i-th of plane includes is projected in a plane according to the normal vector of i-th of plane, should
Plane is the corresponding detection plane of i-th of plane;N number of detection plane is obtained;Wash with watercolours is carried out to N number of detection plane
Dye, obtains the corresponding 3-D view of the three dimensional object
, can be by the spot projection in the three-dimensional point cloud of collection into different detection planes, finally in the embodiment of the present invention
Rendered according to detection plane, i.e., the structural information in 3-D view has been taken into full account in render process, has improved and renders
During noise removal capability, the result enabled to tries one's best accurately, ensures that obtained 3-D view will not distortion as far as possible.
It is apparent to those skilled in the art that, for convenience and simplicity of description, only with above-mentioned each function
The division progress of module is for example, in practical application, as needed can distribute above-mentioned functions by different function moulds
Block is completed, i.e., the internal structure of device is divided into different functional modules, to complete all or part of work(described above
Energy.The specific work process of the system, apparatus, and unit of foregoing description, may be referred to corresponding in preceding method embodiment
Journey, will not be repeated here.
In several embodiments provided herein, it should be understood that disclosed system, apparatus and method can be with
Realize by another way.For example, device embodiment described above is only schematical, for example, the module or
The division of unit, only a kind of division of logic function, can there is other dividing mode when actually realizing, such as multiple units
Or component can combine or be desirably integrated into another system, or some features can be ignored, or not perform.It is another, institute
Display or the coupling each other discussed or direct-coupling or communication connection can be by some interfaces, device or unit
INDIRECT COUPLING or communication connection, can be electrical, machinery or other forms.
The unit illustrated as separating component can be or may not be it is physically separate, it is aobvious as unit
The part shown can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be selected to realize the mesh of this embodiment scheme according to the actual needs
's.
In addition, each functional unit in the application each embodiment can be integrated in a processing unit, can also
That unit is individually physically present, can also two or more units it is integrated in a unit.Above-mentioned integrated list
Member can both be realized in the form of hardware, it would however also be possible to employ the form of SFU software functional unit is realized.
If the integrated unit is realized using in the form of SFU software functional unit and as independent production marketing or used
When, it can be stored in a computer read/write memory medium.Understood based on such, the technical scheme of the application is substantially
The part contributed in other words to prior art or all or part of the technical scheme can be in the form of software products
Embody, the computer software product is stored in a storage medium, including some instructions are to cause a computer
Equipment (can be personal computer, server, or network equipment etc.) or processor (processor) perform the application each
The all or part of step of embodiment methods described.And foregoing storage medium includes:USB flash disk, mobile hard disk, read-only storage
(ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disc or CD
Etc. it is various can be with the medium of store program codes.
Specifically, the corresponding computer program instructions of a kind of information processing method in the embodiment of the present application can be deposited
Store up in CD, hard disk, on the storage medium such as USB flash disk, calculated when corresponding with a kind of three dimensional image processing method in storage medium
When machine programmed instruction is read or is performed by an electronic equipment, comprise the following steps:
Clustered for the three-dimensional point cloud of collection, obtain N number of classification, N is positive integer;Wherein each classification correspondence one
Plane, the three-dimensional point cloud is the three-dimensional point cloud obtained according to three dimensional object;
It is the integer from 1 to N to take i, is followed the steps below respectively:The normal vector of each point in i-th of plane is true
The normal vector of fixed i-th of plane, is obtained the normal vector of N number of plane;
It is the integer from 1 to N to take i, is followed the steps below respectively:The point that i-th of plane is included is according to described
The normal vector of i-th of plane is projected in a plane, and the plane is the corresponding detection plane of i-th of plane;N is obtained
Individual detection plane;
N number of detection plane is rendered, the corresponding 3-D view of the three dimensional object is obtained.
Optionally, stored in the storage medium and step:Clustered in the three-dimensional point cloud for collection, obtain N
Individual classification, corresponding computer instruction after being performed, in addition to:
According to the space measurement precision for the three dimensional object, the coordinate each put in the three-dimensional point cloud is determined, and,
The locus of point in wherein each classification, it is determined that weight of each point in each self-corresponding classification.
Optionally, stored in the storage medium and step:Clustered, obtained N number of for the three-dimensional point cloud of collection
Classification, corresponding computer instruction is specifically included during specific be performed:
Determine the normal vector for each point that the three-dimensional point cloud includes;
According to the normal vector and coordinate each put in the three-dimensional point cloud, the point that the three-dimensional point cloud includes is gathered
Class, obtains N number of classification.
Optionally, stored in the storage medium and step:According to the normal vector each put in the three-dimensional point cloud and
Coordinate, is clustered to the point that the three-dimensional point cloud includes, and obtains N number of classification, corresponding computer instruction is specific
During being performed, specifically include:
The point that normal vector and coordinate are satisfied by into same preparatory condition is polymerized to a classification, obtains N number of classification;Its
In, the preparatory condition is:Angle between normal vector and preset direction is located in the range of the first default angle threshold value, and coordinate
In the first predeterminable area.
Optionally, stored in the storage medium and step:The normal vector of each point in i-th of plane is determined
The normal vector of i-th of plane, corresponding computer instruction it is specific be performed process during, including:
The normal vector of each point in i-th of plane is weighted averagely according to each corresponding weight of point, obtained
To the normal vector of i-th of plane.
Optionally, stored in the storage medium and step:The normal vector of each point in i-th of plane is determined
The normal vector of i-th of plane, is obtained the normal vector of N number of plane, corresponding computer instruction after specific be performed,
Also include:
It is the integer from 1 to N to take i, is followed the steps below respectively:Judge whether be not belonging to wherein in the three-dimensional point cloud
The other point of any sort;If so, judge to be not belonging to normal vector and i-th of the plane of the point of any of which classification normal vector it
Between angle whether be less than the second default angle threshold value;
If the angle being not belonging between the normal vector of the point of any of which classification and the normal vector of wherein M plane is less than institute
The second predetermined threshold value is stated, determines to be not belonging to the distance between point and the M plane of any of which classification respectively, and determine not belong to
J-th of the plane belonged in the point of any of which classification in the M plane;Wherein, j-th of plane is:It is not belonging to this
The distance of the point of any of which classification most short plane;M is no more than N positive integer.
Optionally, stored in the storage medium and step:It is determined that the point for being not belonging to any of which classification belongs to the M
J-th of plane in plane, corresponding computer instruction during specific be performed, including:
Judge to be not belonging to whether the point of any of which classification is less than pre-determined distance with the distance of j-th of plane;
If less than the pre-determined distance, it is determined that the point for being not belonging to any of which classification belongs to j-th of plane.
Optionally, stored in the storage medium and step:Judgement is not belonging to the point and the jth of any of which classification
Whether the distance of individual plane is less than pre-determined distance, corresponding computer instruction after specific be performed, in addition to:
If not less than the pre-determined distance, it is the integer from 1 to K to take k, is followed the steps below respectively:
Judge whether the angle being not belonging between the normal vector of the point of any of which classification and the normal vector of k-th of plane is small
In the 3rd default angle threshold value;Described 3rd default angle threshold value is more than the described second default angle threshold value;
If being less than, it is determined that the point for being not belonging to any of which classification belongs to k-th of plane;Wherein, K is no more than N's
Positive integer.
Optionally, stored in the storage medium and step:It is determined that the point for being not belonging to any of which classification belongs to described
K-th of plane, corresponding computer instruction after specific be performed, in addition to:
The normal vector of each point in N number of plane determines normal vector and the face of N number of plane respectively again
Product.
Described above, above example is only described in detail to the technical scheme to the application, but implements above
The explanation of example is only intended to the method and its core concept for helping to understand the present invention, should not be construed as limiting the invention.This
Those skilled in the art the invention discloses technical scope in, the change or replacement that can be readily occurred in should all be covered
Within protection scope of the present invention.
Claims (16)
1. a kind of three dimensional image processing method, comprises the following steps:
Clustered for the three-dimensional point cloud of collection, obtain N number of classification, N is positive integer;Wherein each classification correspondence one is put down
Face, the three-dimensional point cloud is the three-dimensional point cloud obtained according to three dimensional object;
It is the integer from 1 to N to take i, is followed the steps below respectively:The normal vector of each point in i-th of plane determines institute
The normal vector of i-th of plane is stated, the normal vector of N number of plane is obtained;
It is the integer from 1 to N to take i, is followed the steps below respectively:The point that i-th of plane is included is according to described i-th
The normal vector of plane is projected in a plane, and the plane is the corresponding detection plane of i-th of plane;N number of inspection is obtained
Survey plane;
N number of detection plane is rendered, the corresponding 3-D view of the three dimensional object is obtained;
Wherein, clustered for the three-dimensional point cloud of collection, obtain N number of classification, including:
Determine the normal vector for each point that the three-dimensional point cloud includes;
According to the normal vector and coordinate each put in the three-dimensional point cloud, the point that the three-dimensional point cloud includes is clustered,
Obtain N number of classification.
2. the method as described in claim 1, it is characterised in that clustered in the three-dimensional point cloud for collection, obtains N number of class
After not, in addition to:According to the space measurement precision for the three dimensional object, the seat each put in the three-dimensional point cloud is determined
Mark, and, the locus of the point in wherein each classification, it is determined that weight of each point in each self-corresponding classification.
3. method as claimed in claim 2, it is characterised in that according to the normal vector and seat each put in the three-dimensional point cloud
Mark, is clustered to the point that the three-dimensional point cloud includes, and obtains N number of classification, including:Normal vector and coordinate are satisfied by
The point of same preparatory condition is polymerized to a classification, obtains N number of classification;Wherein, the preparatory condition is:Normal vector with it is pre-
Angle between set direction is located in the range of the first default angle threshold value, and coordinate is located in the first predeterminable area.
4. the method as described in claim 2-3 is any, it is characterised in that the normal vector of each point in i-th of plane
The normal vector of i-th of plane is determined, including:By the normal vector of each point in i-th of plane according to each phase
The weight answered is weighted averagely, obtains the normal vector of i-th of plane.
5. method as claimed in claim 4, it is characterised in that determined in the normal vector of each point in i-th of plane
After the normal vector of i-th of plane, the normal vector that N number of plane is obtained, in addition to:
It is the integer from 1 to N to take i, is followed the steps below respectively:Judge whether be not belonging to any of which in the three-dimensional point cloud
The point of classification;If so, judging to be not belonging between the normal vector of the normal vector of the point of any of which classification and i-th of plane
Whether angle is less than the second default angle threshold value;
If the angle being not belonging between the normal vector of the point of any of which classification and the normal vector of wherein M plane is less than described the
Two predetermined threshold values, determine to be not belonging to the distance between point and the M plane of any of which classification respectively, and determine to be not belonging to it
J-th of plane that the middle other point of any sort belongs in the M plane;Wherein, j-th of plane is:It is not belonging to wherein with this
The distance of the other point of any sort most short plane;M is no more than N positive integer.
6. method as claimed in claim 5, it is characterised in that put down it is determined that the point for being not belonging to any of which classification belongs to the M
J-th of plane in face, including:
Judge to be not belonging to whether the point of any of which classification is less than pre-determined distance with the distance of j-th of plane;
If less than the pre-determined distance, it is determined that the point for being not belonging to any of which classification belongs to j-th of plane.
7. method as claimed in claim 6, it is characterised in that be not belonging to the point and the jth of any of which classification in judgement
Whether the distance of individual plane is less than after pre-determined distance, in addition to:If not less than the pre-determined distance, it is whole from 1 to K to take k
Number, is followed the steps below respectively:
Judge to be not belonging to whether angle between the normal vector of the point of any of which classification and the normal vector of k-th of plane is less than the
Three default angle threshold values;Described 3rd default angle threshold value is more than the described second default angle threshold value;
If being less than, it is determined that the point for being not belonging to any of which classification belongs to k-th of plane;Wherein, K is the just whole of no more than N
Number.
8. method as claimed in claim 7, it is characterised in that it is determined that the point for being not belonging to any of which classification belongs to described
After k plane, in addition to:The normal vector of each point in N number of plane determines N number of plane respectively again
Normal vector and area.
9. a kind of electronic equipment, including:
Cluster module, the normal vector for determining each point that three-dimensional point cloud includes;According to each point in the three-dimensional point cloud
Normal vector and coordinate, the point that the three-dimensional point cloud includes is clustered, N number of classification is obtained, N is positive integer;It is wherein every
One plane of individual classification correspondence, the three-dimensional point cloud is the three-dimensional point cloud obtained according to three dimensional object;
First determining module, for taking i to be the integer from 1 to N, is followed the steps below respectively:It is each in i-th of plane
The normal vector of point determines the normal vector of i-th of plane, and the normal vector of N number of plane is obtained;
Projection module, for taking i to be the integer from 1 to N, is followed the steps below respectively:The point that i-th of plane is included
Normal vector according to i-th of plane is projected in a plane, and the plane is that the corresponding detection of i-th of plane is flat
Face;N number of detection plane is obtained;
Rendering module, for being rendered to N number of detection plane, obtains the corresponding 3-D view of the three dimensional object.
10. electronic equipment as claimed in claim 9, it is characterised in that the electronic equipment also includes the second determining module, is used
In:Clustered in the three-dimensional point cloud for collection, obtain after N number of classification, surveyed according to the space for the three dimensional object
Accuracy of measurement, determines the coordinate each put in the three-dimensional point cloud, and, the locus of the point in wherein each classification, really
Weight of the fixed each point in each self-corresponding classification.
11. electronic equipment as claimed in claim 10, it is characterised in that the cluster module specifically for:According to described three
The normal vector and coordinate each put in dimension point cloud, cluster to the point that the three-dimensional point cloud includes, obtain N number of class
Not, it is specially:The point that normal vector and coordinate are satisfied by into same preparatory condition is polymerized to a classification, obtains N number of classification;
Wherein, the preparatory condition is:Angle between normal vector and preset direction is located in the range of the first default angle threshold value, and sits
Mark is in the first predeterminable area.
12. the electronic equipment as described in claim 10-11 is any, it is characterised in that first determining module specifically for:
The normal vector of each point in i-th of plane is weighted averagely according to each corresponding weight of point, described i-th is obtained
The normal vector of individual plane.
13. electronic equipment as claimed in claim 12, it is characterised in that first determining module is additionally operable to:
The normal vector of i-th of plane is determined in the normal vector of each point in i-th of plane, N number of plane is obtained
Normal vector after, take i for integer from 1 to N, follow the steps below respectively:Judge whether to have in the three-dimensional point cloud and do not belong to
In the point of any of which classification;If so, judging to be not belonging to method of the normal vector with i-th of plane of the point of any of which classification
Whether the angle between vector is less than the second default angle threshold value;
If the angle being not belonging between the normal vector of the point of any of which classification and the normal vector of wherein M plane is less than described the
Two predetermined threshold values, determine to be not belonging to the distance between point and the M plane of any of which classification respectively, and determine to be not belonging to it
J-th of plane that the middle other point of any sort belongs in the M plane;Wherein, j-th of plane is:It is not belonging to wherein with this
The distance of the other point of any sort most short plane;M is no more than N positive integer.
14. electronic equipment as claimed in claim 13, it is characterised in that first determining module is specifically for determining not belong to
J-th of the plane belonged in the point of any of which classification in the M plane, be specially:Judgement is not belonging to any of which classification
Whether point and the distance of j-th of plane are less than pre-determined distance;If less than the pre-determined distance, it is determined that being not belonging to any of which
The point of classification belongs to j-th of plane.
15. electronic equipment as claimed in claim 14, it is characterised in that first determining module is additionally operable to:Judging not
Belong to whether the point of any of which classification is less than after pre-determined distance with the distance of j-th of plane, if not less than described pre-
If distance, it is the integer from 1 to K to take k, is followed the steps below respectively:
Judge to be not belonging to whether angle between the normal vector of the point of any of which classification and the normal vector of k-th of plane is less than the
Three default angle threshold values;Described 3rd default angle threshold value is more than the described second default angle threshold value;
If being less than, it is determined that the point for being not belonging to any of which classification belongs to k-th of plane;Wherein, K is the just whole of no more than N
Number.
16. electronic equipment as claimed in claim 15, it is characterised in that first determining module is additionally operable to:It is determined that not
The point for belonging to any of which classification belongs to after k-th of plane, the normal vector weight of each point in N number of plane
The new normal vector and area for determining N number of plane respectively.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410251325.7A CN104050709B (en) | 2014-06-06 | 2014-06-06 | A kind of three dimensional image processing method and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410251325.7A CN104050709B (en) | 2014-06-06 | 2014-06-06 | A kind of three dimensional image processing method and electronic equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104050709A CN104050709A (en) | 2014-09-17 |
CN104050709B true CN104050709B (en) | 2017-08-29 |
Family
ID=51503478
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410251325.7A Active CN104050709B (en) | 2014-06-06 | 2014-06-06 | A kind of three dimensional image processing method and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104050709B (en) |
Families Citing this family (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108876906A (en) * | 2018-06-06 | 2018-11-23 | 链家网(北京)科技有限公司 | The method and device of virtual three-dimensional model is established based on the global plane optimizing of cloud |
CN109035422B (en) * | 2018-06-06 | 2019-06-07 | 贝壳找房(北京)科技有限公司 | In a kind of extraction chamber in threedimensional model plane domain method and system |
CN110264481B (en) * | 2019-05-07 | 2022-05-20 | 熵智科技(深圳)有限公司 | Box-like point cloud segmentation method and device |
CN111967484A (en) * | 2019-05-20 | 2020-11-20 | 长沙智能驾驶研究院有限公司 | Point cloud clustering method and device, computer equipment and storage medium |
WO2021073562A1 (en) * | 2019-10-17 | 2021-04-22 | 贝壳找房(北京)科技有限公司 | Multipoint cloud plane fusion method and device |
CN110796671B (en) * | 2019-10-31 | 2022-08-26 | 深圳市商汤科技有限公司 | Data processing method and related device |
CN111145119B (en) * | 2019-12-25 | 2023-06-02 | 维沃移动通信(杭州)有限公司 | Image processing method and electronic equipment |
CN113129249B (en) * | 2019-12-26 | 2023-01-31 | 舜宇光学(浙江)研究院有限公司 | Depth video-based space plane detection method and system and electronic equipment |
US11321953B2 (en) * | 2020-03-25 | 2022-05-03 | Hong Kong Applied Science and Technology Research Institute Company Limited | Method and apparatus for posture, dimension and shape measurements of objects in 3D scenes |
CN113438463B (en) * | 2021-07-30 | 2022-08-19 | 贝壳找房(北京)科技有限公司 | Method and device for simulating orthogonal camera image, storage medium and electronic equipment |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9767598B2 (en) * | 2012-05-31 | 2017-09-19 | Microsoft Technology Licensing, Llc | Smoothing and robust normal estimation for 3D point clouds |
CN103345771B (en) * | 2013-06-28 | 2016-08-10 | 中国科学技术大学 | A kind of Efficient image rendering intent based on modeling |
-
2014
- 2014-06-06 CN CN201410251325.7A patent/CN104050709B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN104050709A (en) | 2014-09-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104050709B (en) | A kind of three dimensional image processing method and electronic equipment | |
CN108509848B (en) | The real-time detection method and system of three-dimension object | |
CN104778688B (en) | The method for registering and device of cloud data | |
CN106033621B (en) | A kind of method and device of three-dimensional modeling | |
CN109146943B (en) | Detection method, device and the electronic equipment of stationary object | |
CN104732587A (en) | Depth sensor-based method of establishing indoor 3D (three-dimensional) semantic map | |
CN109002039A (en) | Avoidance based reminding method, relevant apparatus and computer readable storage medium | |
CN110298370A (en) | Network model training method, device and object pose determine method, apparatus | |
CN109035330A (en) | Cabinet approximating method, equipment and computer readable storage medium | |
CN109816730A (en) | Workpiece grabbing method, apparatus, computer equipment and storage medium | |
CN104408055B (en) | The storage method and device of a kind of laser radar point cloud data | |
CN107704638A (en) | Elevator machine room figure generating means and method, modeling data generating means and method | |
CN105243662B (en) | The determination method and terminal device of a kind of terminal position | |
CN109874146A (en) | A kind of method and device for predicting path loss | |
CN110148147A (en) | Image detecting method, device, storage medium and electronic device | |
CN109579718A (en) | Detection method, device, computer equipment and the storage medium of weld seam parameter | |
CN110047133A (en) | A kind of train boundary extraction method towards point cloud data | |
CN109389649A (en) | The quick calibrating method and device of binocular camera | |
CN106327558A (en) | Point cloud facade extraction method and apparatus | |
CN105334497A (en) | Three-dimensional positioning method and device | |
CN107203962B (en) | Method for making pseudo-3D image by using 2D picture and electronic equipment | |
WO2015031855A1 (en) | Expanding a digital representation of a physical plane | |
CN109767391A (en) | Point cloud denoising method, image processing equipment and the device with store function | |
CN109934165A (en) | A kind of joint point detecting method, device, storage medium and electronic equipment | |
CN109583495B (en) | Display image treating method and apparatus |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |