CN108805063A - A kind of multiresolution visual perception method to object and environment - Google Patents
A kind of multiresolution visual perception method to object and environment Download PDFInfo
- Publication number
- CN108805063A CN108805063A CN201810546696.6A CN201810546696A CN108805063A CN 108805063 A CN108805063 A CN 108805063A CN 201810546696 A CN201810546696 A CN 201810546696A CN 108805063 A CN108805063 A CN 108805063A
- Authority
- CN
- China
- Prior art keywords
- covering
- point
- visual perception
- environment
- multiresolution
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
Abstract
The present invention is a kind of multiresolution visual perception method to object and environment, it is intended to illustrate how the form by multiresolution, object and environment around perceiving, more the description of fining ground understands object and environment, the big place of object surface shape Curvature varying selects the form of small resolution ratio to describe, it is similar with amplification sem observation it, the small place of object surface shape Curvature varying selects the form of big resolution ratio to describe, since in this way, using the method for multiresolution, both the surface shape for seeing object clearly that can be whole, the details for the subdivision object that can be refined again, not only it had taken into account whole but also had perceived part, this is a kind of universality visual perception method meeting biological vision mechanism.
Description
Technical field
In terms of the present invention relates to the technological concepts such as artificial intelligence, machine vision, especially gesture identification and object identification, push away
The development of the visual perception technology of dynamic generality object.
Background technology
With industrial machine man-based development in recent years, the gradual turn up of service robot industry has been driven, while from 2014
The Intelligent hardware field that year starts also begins to protrusion, according to the statistics of international alliance of robot, service robot sale in 2015
Volume will be up to 8,500,000,000 dollars, and higher 20%~30% growth rate is kept to be studied according to Ai Rui in Intelligent hardware field, and 2014
Year, global Intelligent hardware installation amount reached 6,000,000,000, it is contemplated that 2017 will be more than 14,000,000,000.
The behind of high speed development in market, problem is equally apparent, and the potentiality in one side market are also excavated far away, another
Aspect, robot and Intelligent hardware enter service industry, and there is also some technological difficulties.
In terms of the visual identity of object, though a big difficulty, also some it is technical attempt to tackle key problems toward this respect, such as specially
Profit《A kind of object global recognition method based on 3 d grid map》With《A kind of environmental characteristic based on 3 d grid map
Method for measuring similarity》In, mention how a kind of method is known object from " shape ", " color ", " material " etc.
Not.What we to be solved here is:Such as how the technology of multiresolution is refined identification to object.
Goal of the invention
The main object of the present invention be exactly solve vision be as the form of how multiresolution more refine perceptible
Body and environment.
Technical solution
The object of the present invention is achieved like this:By relevant device and algorithm, object or environment in real life are obtained
Point cloud information and gridding information, according to these information, come object analysis or environment, subsequent processing by way of multiresolution
Steps are as follows:
(1) multiresolution of visual perception is set;
(2) by the point cloud information and gridding information of environment or object, environment or object is calculated and covers collection accordingly;
(3) it calculates covering and concentrates the feature each covered.
System composition used in the present invention is as follows:Resolution setting system, covering collection dividing system, Cover Characteristics calculate
System.These three systems are the software systems according to function setting, and each subsystem concrete function is as follows:
* resolution setting system:The multiresolution of visual perception is set,
* covering collection dividing system:The covering collection of object or environment is divided,
* Cover Characteristics computing system:It calculates all coverings and concentrates the feature each covered.
Description of the drawings:
Fig. 1 is the method for the present invention system for use in carrying composition figure
Fig. 2 is the point cloud and gridding information figure of " hand " in practice
Fig. 3 is Cover Characteristics perspective view
Fig. 4 is Cover Characteristics pixel map
Specific implementation mode
Below in conjunction with the accompanying drawings, illustrate embodiments of the present invention.
Overall system architecture used in the method for the present invention can refer to attached drawing 1, and there are three subsystems to form for it, specific comprising such as
Lower step:
The first step
In resolution setting system, resolution ratio is set, is set to multistage resolution ratio r0,r1,r2,…,rn, different big
Small object can set the resolution ratio of different stage, and the corresponding covering of point of different curvature is come using the resolution ratio of different stage
Analyzed calculating.
Second step
In covering collects dividing system, the resolution ratio r of a certain rank is taken out0, carry out covering collection divide, here for the ease of
Illustrate, present implementation is collected using universal covering, collects equally applicable to sparse covering;For the purposes of being convenient for illustrating, this embodiment party
Method creates a covering collection using the resolution ratio of a rank;According to the gridding information of object or environment such as attached drawing 2, net is traversed
Lattice, during traversal, to every bit PiCalculate its corresponding coveringPoint PmWith point PiReachable and distance therebetween
Less than r0, obtain covering collectionIt similarly can also obtain the covering collection of other resolution ratio
Third walks
In Cover Characteristics computing system, its feature is sought in each covering concentrated to each covering, with point PiPlace
CoveringFor, seek featureSuch as attached drawing 3, to coveringInterior arbitrary different and point PiPoint Pm, same to PiThe normal of pointPerpendicular to point PiPlane be denoted as πi, point PmIn plane πiOn upright projection be denoted asAs shown in Fig. 4, point OπFor coordinate
Origin is in plane πiOn upright projection, in plane πiIt is interior, withDirection is X-direction, X-direction and Y direction, normalForm right-handed coordinate system, pixelThe value at place is km, the upright projection of all the points in the covering is calculated, obtains a resolution
Rate is the character pixel figure of 2r × 2rIt is all covering concentrate the character pixel figures all covered at setFor
The multiresolution visual perception digitized representations of corresponding object or environment.
To sum up, it will be seen that by the method for the invention, the multiresolution for successfully solving object or environment is fine
Change identification, solid theoretical foundation is laid to the motion-captured of object.
Claims (9)
1. a kind of multiresolution visual perception method to object and environment, this method is that object and environment are regarded as to be embedded into three
Two-dimensional manifold curved surface Surf in dimension Euclidean space passes through the surface points cloud and net got according to the feature of Surf itself
Lattice information, carries out the visual perception of multiresolution, and realization provides as follows:
(1) the point cloud information of curved surface Surf known to:The set of point(xi,yi,zi) it is point PiSeat
Mark,It is point PiNormal, kiIt is point PiAttributive character, kiBe Gaussian curvature or principal curvatures or average curvature or directional curvature or
Color or material are separately also known as the gridding information { f of curved surface Surfi, each fiIt is plane triangle or polygon, Surf is by fi
It is spliced by side;
(2) the covering collection of curved surface Surf, some point P are calculatediCovering Cover be labeled as Ci, Ci={ Pm|Pm∈ Surf }, Pi
∈CiAnd CiInterior any two points PsWith PjIt is reachable, that is to say, that PsWith PjExist between but several sides connection access, every
While belonging to one or more plane fiIt is interior, in addition, with some point PiDistance be r within the scope of covering Cover be labeled as
Wherein r is known as covering the resolution ratio of Cover, ifClaim setCollect for a covering of curved surface Surf, if bent
Each point P of face SurfiCovering Cover all concentrated in covering, just this covering collection be referred to as that universal covering collects, other situations
Referred to as sparse covering collection;
(3) feature that each covering is concentrated in covering is calculated, to a point PiCoveringItsFeature useIt marks,
To coveringInterior arbitrary different and point PiPoint Pm, same to PiThe normal of pointPerpendicular to point PiPlane be denoted as πi, point PmIn plane πi
On upright projection be denoted asSimilarly coveringInterior all point all upright projections are to plane πiOn, then in plane πiOn
From the point of view of, the pixel map that a resolution ratio is 2r × 2r is had, the value of each pixel is corresponding subpoint PmAttribute km, claim
This pixel map is exactly featureThen gatherMean that the visual perception of this object or environment.
2. a kind of multiresolution visual perception method to object and environment as described in claim 1, which is characterized in that universal
The visual perception under visual perception or sparse covering collection under covering collection.
3. a kind of multiresolution visual perception method to object and environment as described in claim 1, which is characterized in that use
Visual perception is indicated based on the Cover Characteristics collection of covering collection.
4. a kind of multiresolution visual perception method to object and environment as described in claim 1, which is characterized in that cover
Lid is characterized as input, carries out secondary operation processing, exports new data, and visual perception is indicated with this new data.
5. a kind of multiresolution visual perception method to object and environment as described in claim 1, which is characterized in that a certain
Covering is found out under the premise of specified resolution.
6. a kind of multiresolution visual perception method to object and environment as described in claim 1, which is characterized in that same
It is covered with identical or different resolution ratio in a covering collection.
7. a kind of multiresolution visual perception method to object and environment as described in claim 1, which is characterized in that a certain
Covering is the point cloud surrounded by the space sphere of rule or the point cloud surrounded by irregular space.
8. a kind of multiresolution visual perception method to object and environment as described in claim 1, which is characterized in that same
The visual perception of object or environment can be indicated with one or more covering collection.
9. a kind of multiresolution visual perception method to object and environment as described in claim 1, which is characterized in that object
Or the attributive character of environment is Gaussian curvature or principal curvatures or average curvature or directional curvature or color or material.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810546696.6A CN108805063A (en) | 2018-05-31 | 2018-05-31 | A kind of multiresolution visual perception method to object and environment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810546696.6A CN108805063A (en) | 2018-05-31 | 2018-05-31 | A kind of multiresolution visual perception method to object and environment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108805063A true CN108805063A (en) | 2018-11-13 |
Family
ID=64089664
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810546696.6A Pending CN108805063A (en) | 2018-05-31 | 2018-05-31 | A kind of multiresolution visual perception method to object and environment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108805063A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112765299A (en) * | 2021-01-26 | 2021-05-07 | 中国科学院西北生态环境资源研究院 | Visualization method and device for irregular raster data, electronic equipment and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1781111A (en) * | 2002-11-06 | 2006-05-31 | 几何信息学股份有限公司 | Analysis of geometric surfaces by comformal structure |
CN101807256A (en) * | 2010-03-29 | 2010-08-18 | 天津大学 | Object identification detection method based on multiresolution frame |
CN107194983A (en) * | 2017-05-16 | 2017-09-22 | 华中科技大学 | A kind of three-dimensional visualization method and system based on a cloud and image data |
US9858640B1 (en) * | 2015-07-15 | 2018-01-02 | Hrl Laboratories, Llc | Device and method for merging 3D point clouds from sparsely distributed viewpoints |
-
2018
- 2018-05-31 CN CN201810546696.6A patent/CN108805063A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1781111A (en) * | 2002-11-06 | 2006-05-31 | 几何信息学股份有限公司 | Analysis of geometric surfaces by comformal structure |
CN101807256A (en) * | 2010-03-29 | 2010-08-18 | 天津大学 | Object identification detection method based on multiresolution frame |
US9858640B1 (en) * | 2015-07-15 | 2018-01-02 | Hrl Laboratories, Llc | Device and method for merging 3D point clouds from sparsely distributed viewpoints |
CN107194983A (en) * | 2017-05-16 | 2017-09-22 | 华中科技大学 | A kind of three-dimensional visualization method and system based on a cloud and image data |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112765299A (en) * | 2021-01-26 | 2021-05-07 | 中国科学院西北生态环境资源研究院 | Visualization method and device for irregular raster data, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Hirschmuller | Stereo vision in structured environments by consistent semi-global matching | |
Borrmann et al. | The 3d hough transform for plane detection in point clouds: A review and a new accumulator design | |
Chen et al. | Urban building roof segmentation from airborne lidar point clouds | |
Xiao et al. | CAD mesh model segmentation by clustering | |
US20180122083A1 (en) | Method and device for straight line detection and image processing | |
CN104820991B (en) | A kind of multiple soft-constraint solid matching method based on cost matrix | |
CN107907124A (en) | The localization method known again based on scene, electronic equipment, storage medium, system | |
CN105678747B (en) | A kind of tooth mesh model automatic division method based on principal curvatures | |
CN107292234A (en) | It is a kind of that method of estimation is laid out based on information edge and the indoor scene of multi-modal feature | |
CN102136155A (en) | Object elevation vectorization method and system based on three dimensional laser scanning | |
CN113077476B (en) | Height measurement method, terminal device and computer storage medium | |
CN102999926B (en) | A kind of image vision significance computational methods merged based on low-level image feature | |
Reina et al. | 3D traversability awareness for rough terrain mobile robots | |
CN111488812A (en) | Obstacle position recognition method and device, computer equipment and storage medium | |
CN106484692A (en) | A kind of method for searching three-dimension model | |
Mörwald et al. | Geometric data abstraction using b-splines for range image segmentation | |
CN105550688A (en) | Method and device for point cloud data classification | |
Choi et al. | Robust ground plane detection from 3D point clouds | |
CN103714547A (en) | Image registration method combined with edge regions and cross-correlation | |
CN113436223B (en) | Point cloud data segmentation method and device, computer equipment and storage medium | |
CN108805063A (en) | A kind of multiresolution visual perception method to object and environment | |
CN102073848A (en) | Intelligent optimization-based road recognition system and method | |
Jin et al. | Depth image-based plane detection | |
Elkhrachy | Feature extraction of laser scan data based on geometric properties | |
CN116310843B (en) | Coal rock identification method, device, readable storage medium and heading machine |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20181113 |
|
WD01 | Invention patent application deemed withdrawn after publication |