CN105841675A - Range finding method and system for intelligent robot - Google Patents
Range finding method and system for intelligent robot Download PDFInfo
- Publication number
- CN105841675A CN105841675A CN201610285713.6A CN201610285713A CN105841675A CN 105841675 A CN105841675 A CN 105841675A CN 201610285713 A CN201610285713 A CN 201610285713A CN 105841675 A CN105841675 A CN 105841675A
- Authority
- CN
- China
- Prior art keywords
- image
- distance
- measured object
- image information
- data
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
- G01C11/04—Interpretation of pictures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
- G01B11/022—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness by means of tv-camera scanning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Theoretical Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Image Analysis (AREA)
- Manipulator (AREA)
Abstract
The invention discloses a range finding method and system for an intelligent robot .The range finding method comprises the steps that image information data is obtained based on a current view point; the image information data is parsed to determine a target to be ranged; characteristic records matched with the target to be ranged are selected from a database; image characteristics of the target to be ranged are parsed from the image information data; the image characteristics are compared with the characteristic records, and the distance from the target to be ranged is calculated according to comparison results .By the adoption of the range finding method and the range finding system, the distance between the robot and the specified target to be ranged can be accurately measured .Compared with the prior art, the range finding process is simple, the required hardware standard is low, and the range finding method has a higher practical value and lower popularization difficulty .
Description
Technical field
The present invention relates to robot field, in particular relate to a kind of distance-finding method for intelligent robot and be
System.
Background technology
Along with development and the continuous progress of artificial intelligence technology of computer technology, small-sized in domestic environments
The application of intelligent robot is more extensive, towards the intelligent robot of domestic just in fast development.
In the robot interaction with user, robot is in order to judge that self location state often needs
Obtain the distance between self and certain objects.In the prior art, robot generally surveys by ultrasound wave etc.
Finding range away from sensor, the precision of its range measurement is restricted by the hardware attributes of sensor, if to improve
Precision, certainly will be greatly increased the cost of robot.
Further, ultrasonic ranging can only the naked object in orientation survey front, it is impossible to accomplish to survey flexibly
Amount specifies object.Block if existed between object and robot, then can have a strong impact on range measurement.
Such as, there is object A at robot dead ahead, after object A, there is object B, if needing Measuring Object
Distance between B and robot, then ranging process will be disturbed by object A, actual measure arrive for object
The distance of A.
To sum up, in the prior art, the range finding behavior of robot does not simply fail to accurately specify object, and surveys
It is easy to disturbed away from result.The order of accuarcy that this interbehavior leveraging robot exports, reduces
Consumer's Experience.Therefore, in order to improve the Consumer's Experience of robot, expand the range of application of robot, for intelligence
The distance-finding method of energy robot is needed badly and is enhanced.
Summary of the invention
In order to improve the Consumer's Experience of robot, expand the range of application of robot, the invention provides a kind of use
In the distance-finding method of intelligent robot, described method includes:
Image information data is obtained with current view point；
Resolve described image information data, determine measured object；
The feature record mated with described measured object is chosen from data base；
The characteristics of image of described measured object is parsed from described image information data；
Contrast described characteristics of image and described feature record, calculate and described measured object according to comparing result
Between distance.
In one embodiment, also include:
In conjunction with the distance between described measured object, export multi-modal data.
In one embodiment, resolve described image information data, determine measured object, including:
Resolve described external image information to judge whether described image information data exists face image data；
When there is described face image data using described face as described measured object.
In one embodiment, when using described face as described measured object, wherein:
Resolving described face image data to determine user property, described user property includes age and sex；
From described data base, the feature record of the face-image of coupling is chosen according to described user property.
In one embodiment, when there is not described face image data, also include:
Determine other objects to be measured；
Obtain the characteristic attribute of other measured objects described；
Characteristic attribute according to described measured object chooses the described feature note of coupling from described data base
Record.
In one embodiment, described feature is recorded as the image combining described measured object under setpoint distance
Size and described setpoint distance and the feature record that constructs；
The described characteristics of image parsing described measured object from described image information data, specifically wraps
Include:
The present image size of described measured object is parsed from described image information data；
The described characteristics of image of described contrast and described feature record, calculate and described measured mesh according to comparing result
Distance between mark thing, specifically includes:
Contrast described present image size and described image size under setpoint distance, calculate according to comparing result
And the distance between described measured object.
The invention allows for a kind of range-measurement system for intelligent robot, including:
Image collecting device, it is configured to obtain image information data with current view point；
Object determines device, and it is configured to resolve described image information data, determines measured object；
Data storage, it is configured to store multiple different feature record, each described feature record correspondence one
The most measured individual object；
Feature record acquisition device, it is configured to choose from data storage and current described measured target
The feature record of thing coupling；
Characteristics of image resolver, it is configured to parse described measured target from described image information data
The characteristics of image of thing；
Distance calculates device, and it is configured to contrast described characteristics of image and described feature record, according to comparing result
Calculate the distance between described measured object.
In one embodiment, described object determines that device is configured that
Resolve described external image information to judge whether described image information data exists face image data；
When there is described face image data using described face as described measured object.
In one embodiment:
Described characteristics of image resolver is additionally configured to: when using described face as described measured object,
Resolving described face image data to determine user property, described user property includes age and sex；
Described feature record acquisition device is configured that to be chosen from described data storage according to described user property
The feature record of the face-image of coupling.
In one embodiment:
Described data storage is configured to the figure storing the most described measured object under setpoint distance
As size and described setpoint distance；
Described characteristics of image resolver is configured to parse described measured mesh from described image information data
The present image size of mark thing；
Described distance calculates device and is configured to contrast described present image size and described figure under setpoint distance
As size, calculate the distance between described measured object according to comparing result.
The method and system of the present invention, can be accurately between robot measurement and the measured object specified
Distance.Compared to prior art, the system of the present invention can realize based on existing robot hardware, measures process
Simply, necessary hardware standard is low, has higher practical value and relatively low popularization difficulty.
The further feature of the present invention or advantage will illustrate in the following description.Further, the part of the present invention is special
Levy or advantage will be become apparent by description, or be appreciated that by implementing the present invention.The present invention
Purpose and certain advantages can be come by step specifically noted in description, claims and accompanying drawing
Realize or obtain.
Accompanying drawing explanation
Accompanying drawing is for providing a further understanding of the present invention, and constitutes a part for description, with the present invention
Embodiment be provided commonly for explain the present invention, be not intended that limitation of the present invention.In the accompanying drawings:
Fig. 1 and Fig. 3 is the method flow diagram according to different embodiments of the invention respectively；
Fig. 2 is Part Methods flow chart according to an embodiment of the invention；
Fig. 4 is system structure sketch according to an embodiment of the invention.
Detailed description of the invention
Embodiments of the present invention are described in detail, whereby the enforcement of the present invention below with reference to drawings and Examples
Personnel can fully understand how application technology means are to solve technical problem for the present invention, and reaches technique effect
Realize process and be embodied as the present invention according to the above-mentioned process that realizes.As long as it should be noted that do not constitute conflict,
Each embodiment in the present invention and each feature in each embodiment can be combined with each other, the technology formed
Scheme is all within protection scope of the present invention.
In the robot interaction with user, robot is in order to judge that self location state often needs
Obtain the distance between self and certain objects.In the prior art, robot generally surveys by ultrasound wave etc.
Finding range away from sensor, the precision of its range measurement is restricted by the hardware attributes of sensor, if to improve
Precision, certainly will be greatly increased the cost of robot.
Further, ultrasonic ranging can only the naked object in orientation survey front, it is impossible to accomplish to survey flexibly
Amount specifies object.Block if existed between object and robot, then can have a strong impact on range measurement.
Such as, there is object A at robot dead ahead, after object A, there is object B, if needing Measuring Object
Distance between B and robot, then ranging process will be disturbed by object A, actual measure arrive for object
The distance of A.
Accurately finding range in order to convenient, the present invention proposes a kind of range finding side for intelligent robot
Method.Current most of robot is all built with image collecting device, in order to reduce hardware cost as far as possible, and fall
Low distance measurement function realize difficulty, the method for the present invention is based primarily upon graphical analysis and finds range.
Robot is when carrying out image acquisition, owing to usual image collecting device is that structure is on robot body
, the image therefore collected is with robot current location as visual angle.Object is determined for one, its
The visual field (view data collected) of robot can present a series of can be with the state of quantization means
Attribute.And along with the distance between object and robot changes, it (is gathered in the visual field of robot
To view data) in the quantized value of status attribute that presents respective change also can occur.If that in advance
The status attribute that measurement acquisition object presents in the visual field (view data collected) of robot
The corresponding relation of the distance between quantized value and object and robot, then the most just can exist according to object
The quantized value of the status attribute presented in the visual field (view data collected) of robot calculates and obtains mesh
Distance between mark thing and robot.
Based on above-mentioned principle, in an embodiment of the present invention, first image information data is obtained with current view point；
Then resolve image information data, therefrom determine measured object；Then choose from data base with measured
The feature record of object coupling；Meanwhile, the image parsing measured object from image information data is special
Levying, characteristics of image records corresponding with feature；Finally, contrast images feature and feature record, according to contrast knot
Fruit calculates the distance between measured object.
In above-mentioned flow process, characteristics of image records corresponding with feature, one or more of its most corresponding object
Status attribute.The design parameter of characteristics of image is the current status attribute that object is presented in robot view field
Quantized value.Feature record then comprises the corresponding of the quantized value of this status attribute and object and robot spacing
Relation.
Concrete, in an embodiment of the present invention, characteristics of image object size the most corresponding with feature record,
Here size refers to that the relative size that in robot view field, object is presented (is not that actual size is measured
The ratio that value, such as object are occupied in robot view field, concrete example, such as robot view field are
1024*1024 pixel, object occupies a rectangular area of 50*50 pixel).Feature record comprises with special
The object relative size that set a distance (between object with robot) is corresponding is (such as, when object distance machine
During device people 5 meters, it occupies 100*100 pixel in robot view field) (feature record is actual in advance measurement
Obtain).
The relative size presented in robot view field due to object linearly closes with the distance away from robot
System's (distance robot is the most remote, and its ratio occupied in robot is unemployed is the least), therefore contrast object is worked as
Front relative size and the relative size in feature record, it is possible to according to comparing result by feature record
Specific range calculates the distance obtaining current goal thing apart from robot.
Said process may be summarized to be: combines measured object image size under setpoint distance and setting
Distance and construct the feature record of measured object；Measured object is parsed from image information data
Present image size；Contrast present image size and the image size under setpoint distance, according to comparing result meter
Calculate the distance between measured object.
Next describe in detail based on accompanying drawing and specifically perform flow process according to the multiple embodiment of the present invention.Accompanying drawing
Step shown in flow chart can be held in the robot system comprising such as one group of computer executable instructions
OK.Although showing the logical order of each step in flow charts, but in some cases, can be with difference
Step shown or described by performing in order herein.
As it is shown in figure 1, in an embodiment of the present invention, first robot system starts with S100.At this
In a bright embodiment, in the step s 100, robot receive distance measuring instruction and resolve distance measuring instruction obtain treat
The description of measuring distance of target thing.Distance measuring instruction can be directly from outside input, it is also possible to be robot based on
Current interactive environment generates.
Then perform step S110, obtain image information data, obtain the view data of robot current view point.
Perform step S120 after step silo, determine measured object.Concrete, at the present embodiment
In, step S120 mainly determines whether there is measured object in the current robot visual field.
In an embodiment of the present invention, the concrete flow process that performs of step S120 is as in figure 2 it is shown, obtaining figure
As performing step S221 after information data (step S110), it is determined whether need measuring distance of target thing.Specifically
, resolve the most whether image information data comprises the image that can mate range finding object factory with judgement.
When robot view field does not exist measured object, then it is probably the direction of visual lines mistake of robot, this
Shi Zhihang step S222, it determines whether exist the sight line that do not detects towards (in view of in actual environment, usual one
Secondary image acquisition will not gather the image of whole angle simultaneously, only can gather the image in certain angular field of view).
If there is the sight line not detected towards, then perform step S223, change sight line towards, control robot change
Image collecting device towards, and again perform step S210, obtain new image information data.Work as robot
All towards the visual field in the most there is not measured object and (step S222 do not exist the sight line court not detected
To) time, then it is performed without range operation.
When image information data comprises the image (measured object image) that can mate range finding object factory
Time, perform step S130, resolve characteristics of image, resolve the measured measured object of object Image Acquisition and exist
The characteristics of image presented in robot present viewing field.
Then perform step S140, obtain feature record, obtain the feature record that measured object prestores.?
The characteristics of image that the measured object of rear contrast is presented in robot present viewing field and the feature record prestored
Thus calculate the distance (step S150) obtaining measured object with the machine human world.
In an embodiment of the present invention, feature record is pre-stored in data base.According to the actual requirements, data base
In set up class entry for different objects (may be as the object of measured object).For each
Object carry out field survey obtain object feature description and for computed range concrete quantized value with
Object and the corresponding relation of robot spacing.In step S140, the range finding object according to getting is retouched
State and from data base, call the object feature description of coupling so that it is determined that object, and then recall the quantization of correspondence
Value and object and the corresponding relation of robot spacing.
Further, it is contemplated that the range finding object factory that parsing distance measuring instruction gets is the most concrete.According to range finding
Object factory well can not mate object feature description from data base so that it is determined that object.Such as,
Owing to the detailed features difference of different types of chair is that the biggest (such as folding seat and executive chair, its volume is big
Little differ greatly), data base is carry out (being such as divided into of class entry preservation according to the detailed kind of chair
Folding seat, executive chair etc.).When robot needs to obtain the distance between itself and front " chair ", resolve and survey
The range finding object factory arrived away from order or range finding Requirement Acquisition is " chair " this description, if can not more enter
One step distinguish that front needs the detailed kind of " chair " of range finding, then just cannot mesh in matching database
Mark thing feature description is so that it is determined that object.
Based on above-mentioned consideration, in an embodiment of the present invention, step S130 not only resolves acquisition to be used for contrasting
Feature record characteristics of image, also can resolve for coupling call feature record object describe in detail.Above
As a example by the chair that face describes, may determine that, after resolving image information data, the image wherein comprising chair, then enter
One step resolves chair image to differentiate the type of chair.
Further, after the step s 150, between robot is according to that get and measured object
Distance, exports corresponding multi-modal data.In the robot interaction with user, in order to obtain higher use
Family is experienced, and robot needs when carrying out the output of a lot of interbehavior to obtain the distance with user.Such as with
During user's talk, robot needs to control the spacing between user, during following user, machine
Device people needs to maintain the spacing between user.In these cases, hypotelorism or the most all can have influence on use
Family is experienced.
Therefore, in an embodiment of the present invention, by user, particularly, mainly user's head (face) is made
For measured object, (i.e. robot generates user's head (face) as measured mesh according to interactive environment
The distance measuring instruction of mark thing).Concrete, after getting external image information data, resolve external image information
To judge whether described image information data exists face image data；When there is face image data by people
Face is as measured object.
The execution flow process of one embodiment of the invention is as it is shown on figure 3, work as and get external image information data (step
S110), after, image information data is first resolved to determine whether to include humanoid (S321).Work as image information
When data comprise humanoid, by further analysis diagram picture to determine in image information data whether comprise facial image
(human facial image).Humanoid or when not comprising facial image when image information data does not comprise, conversion
Sight line towards, again perform step S110, obtain new image information data.
When image information data comprises facial image using user face as measured object, based on face
Image carries out range operation.Concrete, perform step S332, resolve facial image and obtain user property.At this
In embodiment, step S332 mainly resolves age and the sex obtaining user.
After resolving age and the sex of acquisition user in step S332, it is possible to perform step S340,
Obtain face characteristic record.In the present embodiment, data base prestores the mankind's of all ages and classes and sex
Area in preview picture in photographic head view-finder during face's distance photographic head distance to a declared goal.Such as: man, 28
Year, distance (D0) 18cm, face area (S1) 400*400 pixel.Above-mentioned data are for pass through in practice
Sampling obtains.Assume in step S332, determine that user is 28 years old male, then just can adjust from data base
Go out the feature record of coupling: apart from (D0) 18cm, face area (S1) 400*400 pixel.
It should be noted that in the present embodiment, pixel count is used to show the relative size of face area, wherein,
The acquiescence pixel size of monocular cam preview picture is (S0) 1080*1920 pixel.In other realities of the present invention
Execute in example, the relative size characterizing face area in other ways can be adopted.
Meanwhile, system resolves facial image based on image information data and obtains characteristics of image (step S331).Tool
Body, the picture (image information data) currently gathered by photographic head, as parameter, calls face recognition algorithms.
Face recognition algorithms returns the coordinates matrix information of face, such as apex coordinate in picture (image information data)
p0(x1,y1), and long (l0) and wide (w0).So area S of current face2For:
S2=l0*w0(formula 1)；
People and distance D of robot1Computing formula be:
D1=D0*(S2/S1) (formula 2).
Further, in the present embodiment, monocular cam is by the frequency acquisition (root with general 20 frames per second
Determine according to business) real-time image acquisition information data, thus robot obtain in real time between self and user away from
From.
Further, in other embodiments of the present invention, can be using other objects beyond user as measured
Object.Concrete range finding flow process comprises determining that other objects to be measured；Obtain other measured objects
Characteristic attribute；Characteristic attribute according to measured object chooses the feature record of coupling from data base.
To sum up, method according to the invention it is possible to accurate robot measurement and the measured object specified it
Between distance.Compared to prior art, measure process simple, there is higher practical value and relatively low pushing away
Wide difficulty.
Method based on the present invention, the invention allows for a kind of robot system.The robot system of the present invention
Can be analyzed by image acquisition and realize range finding.In an embodiment of the present invention, system basic structure such as Fig. 4
Shown in, system includes:
Range finding Requirement Acquisition device 400, it is right to obtain current range finding that it is configured to obtain and resolve distance measuring instruction
As describing；
Image collecting device 410, it is configured to obtain image information data with current view point；
Object determines device 420, and it is configured to resolve described image information data, right according to current range finding
Measured object is determined as describing；
Data storage 411, it is configured to store multiple different feature record, each feature record correspondence one
The most measured individual object；
Feature record acquisition device 440, it is configured to choose from data storage 441 measured with current
The feature record of object coupling；
Characteristics of image resolver 430, it is configured to parse measured object from image information data
Characteristics of image；
Distance calculates device 450, and it is configured to contrast images feature and feature record, calculates according to comparing result
And the distance between measured object.
Concrete, in an embodiment of the present invention:
Data storage 441 is configured to the image size storing the most measured object under setpoint distance
And setpoint distance；
Characteristics of image resolver 430 is configured to parse the current of measured object from image information data
Image size；
Distance calculates device 450 and is configured to contrast present image size and the image size under setpoint distance, root
The distance between measured object is calculated according to comparing result.
Further, in an embodiment of the present invention, object determines that device 420 is configured that
Resolve external image information to judge whether image information data exists face image data；Further, when
Using described face as measured object when there is face image data.
Accordingly, characteristics of image resolver 430 is additionally configured to: when using face as measured object,
Parsing face image data is to determine user property, and user property includes age and sex；Feature record obtains
Device 440 is configured that the feature of the face-image choosing coupling according to user property from data storage 441
Record.
To sum up, the system according to the present invention, can accurately robot measurement and the measured object specified it
Between distance.Compared to prior art, the system of the present invention can realize based on existing robot hardware, measures
Process is simple, and necessary hardware standard is low, has higher practical value and relatively low popularization difficulty.
While it is disclosed that embodiment as above, but described content is only to facilitate understand the present invention
And the embodiment used, it is not limited to the present invention.System of the present invention also can have other multiple realities
Execute example.Without departing from the spirit of the present invention, those of ordinary skill in the art are when making according to the present invention
Go out various corresponding change or deformation, but these change accordingly or deform the claim that all should belong to the present invention
Protection domain.
Claims (10)
1. the distance-finding method for intelligent robot, it is characterised in that described method includes:
Image information data is obtained with current view point；
Resolve described image information data, determine measured object；
The feature record mated with described measured object is chosen from data base；
The characteristics of image of described measured object is parsed from described image information data；
Contrast described characteristics of image and described feature record, calculate and described measured object according to comparing result
Between distance.
Method the most according to claim 1, it is characterised in that also include:
In conjunction with the distance between described measured object, export multi-modal data.
Method the most according to claim 1, it is characterised in that resolve described image information data, really
Fixed measured object, including:
Resolve described external image information to judge whether described image information data exists face image data；
When there is described face image data using described face as described measured object.
Method the most according to claim 3, it is characterised in that when using described face as described to be measured
When object, wherein:
Resolving described face image data to determine user property, described user property includes age and sex；
From described data base, the feature record of the face-image of coupling is chosen according to described user property.
Method the most according to claim 3, it is characterised in that when there is not described face image data
Time, also include:
Determine other objects to be measured；
Obtain the characteristic attribute of other measured objects described；
Characteristic attribute according to described measured object chooses the described feature note of coupling from described data base
Record.
6. according to the method according to any one of claim 1-5, it is characterised in that described feature is recorded as knot
The feature closing described measured object image size under setpoint distance and described setpoint distance and construct
Record；
The described characteristics of image parsing described measured object from described image information data, specifically wraps
Include:
The present image size of described measured object is parsed from described image information data；
The described characteristics of image of described contrast and described feature record, calculate and described measured mesh according to comparing result
Distance between mark thing, specifically includes:
Contrast described present image size and described image size under setpoint distance, calculate according to comparing result
And the distance between described measured object.
7. the range-measurement system for intelligent robot, it is characterised in that including:
Image collecting device, it is configured to obtain image information data with current view point；
Object determines device, and it is configured to resolve described image information data, determines measured object；
Data storage, it is configured to store multiple different feature record, each described feature record correspondence one
The most measured individual object；
Feature record acquisition device, it is configured to choose from data storage and current described measured target
The feature record of thing coupling；
Characteristics of image resolver, it is configured to parse described measured target from described image information data
The characteristics of image of thing；
Distance calculates device, and it is configured to contrast described characteristics of image and described feature record, according to comparing result
Calculate the distance between described measured object.
System the most according to claim 7, it is characterised in that described object determines that device is configured that
Resolve described external image information to judge whether described image information data exists face image data；
When there is described face image data using described face as described measured object.
System the most according to claim 8, it is characterised in that:
Described characteristics of image resolver is additionally configured to: when using described face as described measured object,
Resolving described face image data to determine user property, described user property includes age and sex；
Described feature record acquisition device is configured that to be chosen from described data storage according to described user property
The feature record of the face-image of coupling.
10. according to the system according to any one of claim 7-9, it is characterised in that:
Described data storage is configured to the figure storing the most described measured object under setpoint distance
As size and described setpoint distance；
Described characteristics of image resolver is configured to parse described measured mesh from described image information data
The present image size of mark thing；
Described distance calculates device and is configured to contrast described present image size and described figure under setpoint distance
As size, calculate the distance between described measured object according to comparing result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610285713.6A CN105841675B (en) | 2016-05-03 | 2016-05-03 | A kind of distance measuring method and system for intelligent robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610285713.6A CN105841675B (en) | 2016-05-03 | 2016-05-03 | A kind of distance measuring method and system for intelligent robot |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105841675A true CN105841675A (en) | 2016-08-10 |
| CN105841675B CN105841675B (en) | 2019-09-13 |
Family
ID=56590618
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610285713.6A Active CN105841675B (en) | 2016-05-03 | 2016-05-03 | A kind of distance measuring method and system for intelligent robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105841675B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109781008A (en) * | 2018-12-30 | 2019-05-21 | 北京猎户星空科技有限公司 | A kind of distance measurement method, device, equipment and medium |
| CN110989688A (en) * | 2019-12-09 | 2020-04-10 | 台州学院 | Automatic following system and method based on AprilTag code recognition |
| CN111006583A (en) * | 2019-10-25 | 2020-04-14 | 盟立自动化(昆山)有限公司 | Method for acquiring depth of goods yard box body through 2D vision |
| CN111168722A (en) * | 2019-12-12 | 2020-05-19 | 中国科学院深圳先进技术研究院 | Robot following system and method based on monocular camera ranging |
| CN111398968A (en) * | 2018-12-28 | 2020-07-10 | 浙江舜宇智能光学技术有限公司 | TOF precision detection system and precision detection method thereof |
| CN112666572A (en) * | 2019-09-30 | 2021-04-16 | 北京声智科技有限公司 | Wake-up method based on radar, wake-up device, electronic device and storage medium |
| CN113029089A (en) * | 2021-03-17 | 2021-06-25 | 国网安徽省电力有限公司铜陵供电公司 | Video image inner target distance estimation method based on electric power field auxiliary information |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101324430A (en) * | 2007-06-12 | 2008-12-17 | 北京航空航天大学 | Binocular odometry based on similarity principle |
| CN101337536A (en) * | 2008-08-11 | 2009-01-07 | 北京中星微电子有限公司 | Vehicle device and method for determining vehicle-distance |
| CN202915911U (en) * | 2012-10-19 | 2013-05-01 | 广州市盛光微电子有限公司 | Shooting device for distance measurement |
| CN105182983A (en) * | 2015-10-22 | 2015-12-23 | 深圳创想未来机器人有限公司 | Face real-time tracking method and face real-time tracking system based on mobile robot |
-
2016
- 2016-05-03 CN CN201610285713.6A patent/CN105841675B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101324430A (en) * | 2007-06-12 | 2008-12-17 | 北京航空航天大学 | Binocular odometry based on similarity principle |
| CN101337536A (en) * | 2008-08-11 | 2009-01-07 | 北京中星微电子有限公司 | Vehicle device and method for determining vehicle-distance |
| CN202915911U (en) * | 2012-10-19 | 2013-05-01 | 广州市盛光微电子有限公司 | Shooting device for distance measurement |
| CN105182983A (en) * | 2015-10-22 | 2015-12-23 | 深圳创想未来机器人有限公司 | Face real-time tracking method and face real-time tracking system based on mobile robot |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111398968A (en) * | 2018-12-28 | 2020-07-10 | 浙江舜宇智能光学技术有限公司 | TOF precision detection system and precision detection method thereof |
| CN111398968B (en) * | 2018-12-28 | 2022-10-18 | 浙江舜宇智能光学技术有限公司 | TOF precision detection system and precision detection method thereof |
| CN109781008A (en) * | 2018-12-30 | 2019-05-21 | 北京猎户星空科技有限公司 | A kind of distance measurement method, device, equipment and medium |
| CN109781008B (en) * | 2018-12-30 | 2021-05-25 | 北京猎户星空科技有限公司 | Distance measuring method, device, equipment and medium |
| CN112666572A (en) * | 2019-09-30 | 2021-04-16 | 北京声智科技有限公司 | Wake-up method based on radar, wake-up device, electronic device and storage medium |
| CN111006583A (en) * | 2019-10-25 | 2020-04-14 | 盟立自动化(昆山)有限公司 | Method for acquiring depth of goods yard box body through 2D vision |
| CN110989688A (en) * | 2019-12-09 | 2020-04-10 | 台州学院 | Automatic following system and method based on AprilTag code recognition |
| CN111168722A (en) * | 2019-12-12 | 2020-05-19 | 中国科学院深圳先进技术研究院 | Robot following system and method based on monocular camera ranging |
| CN113029089A (en) * | 2021-03-17 | 2021-06-25 | 国网安徽省电力有限公司铜陵供电公司 | Video image inner target distance estimation method based on electric power field auxiliary information |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105841675B (en) | 2019-09-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105841675A (en) | Range finding method and system for intelligent robot | |
| US10068344B2 (en) | Method and system for 3D capture based on structure from motion with simplified pose detection | |
| US10515259B2 (en) | Method and system for determining 3D object poses and landmark points using surface patches | |
| US8081818B2 (en) | Locating a feature in a digital image | |
| CN103383731B (en) | A kind of projection interactive method based on finger tip location, system and the equipment of calculating | |
| Wu et al. | Online empirical evaluation of tracking algorithms | |
| CN106037651A (en) | Heart rate detection method and system | |
| CN109035579A (en) | A kind of commodity recognition method, self-service machine and computer readable storage medium | |
| CN106355197A (en) | Navigation image matching filtering method based on K-means clustering algorithm | |
| CN102915545A (en) | OpenCV(open source computer vision library)-based video target tracking algorithm | |
| CN108961547A (en) | A kind of commodity recognition method, self-service machine and computer readable storage medium | |
| CN111652838B (en) | Thyroid nodule positioning and ultrasonic report error correction method based on target detection network | |
| CN105103164A (en) | View classification-based model initialization | |
| JP5027758B2 (en) | Image monitoring device | |
| CN111429515A (en) | Learning method of robot obstacle avoidance behavior based on deep learning | |
| CN109620293A (en) | A kind of image-recognizing method, device and storage medium | |
| CN110307903A (en) | A kind of method of the contactless temperature dynamic measurement of poultry privileged site | |
| Sreevalsan-Nair et al. | Contour extraction in buildings in airborne lidar point clouds using multiscale local geometric descriptors and visual analytics | |
| CN109544632A (en) | A kind of semantic SLAM method of mapping based on hierarchical subject model | |
| Cociaş et al. | Multiple-superquadrics based object surface estimation for grasping in service robotics | |
| CN112097742B (en) | Pose determination method and device | |
| CN112414444A (en) | Data calibration method, computer equipment and storage medium | |
| CN115546829A (en) | Pedestrian spatial information sensing method and device based on ZED (zero-energy-dimension) stereo camera | |
| US20230186477A1 (en) | System and methods for segmenting images | |
| CN113808256B (en) | High-precision holographic human body reconstruction method combined with identity recognition |
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 |