CN108012143A - Binocular camera scaling method and device - Google Patents
Binocular camera scaling method and device Download PDFInfo
- Publication number
- CN108012143A CN108012143A CN201711260448.7A CN201711260448A CN108012143A CN 108012143 A CN108012143 A CN 108012143A CN 201711260448 A CN201711260448 A CN 201711260448A CN 108012143 A CN108012143 A CN 108012143A
- Authority
- CN
- China
- Prior art keywords
- binocular camera
- cameras
- image information
- specified target
- distance
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N17/00—Diagnosis, testing or measuring for television systems or their details
- H04N17/002—Diagnosis, testing or measuring for television systems or their details for television cameras
-
- 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
- G01B11/22—Measuring arrangements characterised by the use of optical techniques for measuring depth
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
- G01S17/06—Systems determining position data of a target
- G01S17/08—Systems determining position data of a target for measuring distance only
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
- G06T7/55—Depth or shape recovery from multiple images
- G06T7/593—Depth or shape recovery from multiple images from stereo images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
- G06T7/85—Stereo camera calibration
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Computer Networks & Wireless Communication (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The present invention provides a kind of binocular camera scaling method and device, terminal measures laser range sensor and the actual range D of specified target by being located at the laser range sensor of same depth plane with binocular camera;Gather the image information of specified target, and the image information of the specified target according to collection respectively by binocular camera, calculate the scale value t of distance between binocular camera transition matrix R in rotary moving and two cameras;Gather the infrared light spot image information that laser range sensor is radiated in the specified target respectively by binocular camera, and the matching relationship in image information calculates the depth value d between laser range sensor and infrared light spot;The actual range T between two cameras is calculated according to the scale value t of distance between the actual range D, depth value d and two cameras;Binocular camera demarcated with this.
Description
Technical field
The present invention relates to the technical field of camera calibration, more particularly to a kind of binocular camera scaling method and device.
Background technology
Binocular camera is powerful because slam (positioning and map structuring immediately) stability of its binocular vision is good, by
Gradually it is used for various sweeping robots.
At present, binocular camera generally requires artificial calibration and obtains outer ginseng before use.In order to save manpower, dispatch from the factory previous
As can use acquiescence calibrating parameters, but because its is complicated, not easy to install, two camera installation sites are if there is larger
Offset, acquiescence calibrating parameters cannot be suitable for actual use, easily influence after positioning and navigation.
The content of the invention
The main object of the present invention is provides a kind of binocular camera scaling method and device, to binocular camera into rower
It is fixed.
The present invention proposes a kind of binocular camera scaling method, comprises the following steps:
Terminal measures laser ranging sensing by being located at the laser range sensor of same depth plane with binocular camera
Device and the actual range D of specified target;
Gather the image information of specified target respectively by binocular camera, and believed according to the image of the specified target of collection
Breath, calculates the scale value t of distance between binocular camera transition matrix R in rotary moving and two cameras;
Gather the infrared light point diagram that laser range sensor is radiated in the specified target respectively by binocular camera
As information, and the matching relationship in image information calculates the depth value d between laser range sensor and infrared light spot;
Two are calculated according to the scale value t of distance between the actual range D, depth value d and two cameras to take the photograph
As the actual range T between head.
Further, the image information of the specified target according to collection, it is in rotary moving to calculate binocular camera
Between transition matrix R and two cameras the step of the scale value t of distance, including:
Feature extraction is carried out to the image information of the specified target of collection, extracts and is matched in the image of two camera collections
Characteristic point;
According to matched characteristic point, calculate between binocular camera transition matrix R and two cameras in rotary moving
The scale value t of distance.
Further, the quantity for extracting matched characteristic point in the image of two camera collections is eight, the basis
Matched characteristic point, calculates the scale value t of distance between binocular camera transition matrix R and two cameras in rotary moving
The step of, specifically include:
According to matched eight characteristic points, binocular camera transition matrix in rotary moving is calculated using 8 methods of normalization
The scale value t of distance between R and two camera.
Further, it is described gather specified target respectively by binocular camera image information the step of after, also wrap
Include:
Denoising is carried out to the image information of the specified target of collection.
Further, the matching relationship in image information is calculated between laser range sensor and infrared light spot
Depth value d the step of, including:
According to matching relationship of the infrared light spot in the image that two cameras gather, trigonometric calculations laser is utilized
Depth value d between distance measuring sensor and infrared light spot.
Further, the scale value t according to distance between the actual range D, depth value d and two cameras
The step of calculating the actual range T between two cameras includes:
According to the actual range D, depth value d, scale s is calculated;
According to the scale value t of distance between the scale s and two cameras, the reality between two cameras is calculated
Distance T.
Further, the calculation formula of the scale s is s=D/d;The calculation formula of the actual range T for T=s ×
t。
Further, the laser range sensor is located at the midpoint of two camera lines in the binocular camera
On;The terminal is binocular vision sweeping robot.
Present invention also offers a kind of binocular camera caliberating device, including:
Measuring unit, laser is measured for the laser range sensor by being located at same depth plane with binocular camera
Distance measuring sensor and the actual range D of specified target;
First computing unit, for gathering the image information of specified target respectively by binocular camera, and according to collection
Specified target image information, calculate the spacing of binocular camera transition matrix R in rotary moving and two cameras
From scale value t;
Second computing unit, the specified mesh is radiated at for gathering laser range sensor respectively by binocular camera
The infrared light spot image information put on, and the matching relationship in image information calculates laser range sensor and infrared light spot
Between depth value d;
3rd computing unit, for the contracting according to distance between the actual range D, depth value d and two cameras
Put value t and calculate actual range T between two cameras.
Further, first computing unit includes:
Subelement is extracted, the image information for the specified target to collection carries out feature extraction, extracts two cameras
Matched characteristic point in the image of collection;
First computation subunit, for according to matched characteristic point, calculating binocular camera transition matrix R in rotary moving
And between two cameras distance scale value t.
Further, first computation subunit is specifically used for:
According to matched characteristic point, using 8 methods of normalization calculate binocular cameras transition matrix R in rotary moving with
And between two cameras distance scale value t.
Further, further include:
Denoising unit, the image information for the specified target to collection carry out denoising.
Further, second computing unit is specifically used for:
According to matching relationship of the infrared light spot in the image that two cameras gather, trigonometric calculations laser is utilized
Depth value d between distance measuring sensor and infrared light spot.
Further, the 3rd computing unit includes:
Second computation subunit, for according to the actual range D, depth value d, calculating scale s;
3rd computation subunit, for the scale value t according to distance between the scale s and two cameras, calculates
Actual range T between two cameras.
Further, the calculation formula of the scale s is s=D/d;The calculation formula of the actual range T for T=s ×
t。
Further, the laser range sensor is located at the midpoint of two camera lines in the binocular camera
On;The terminal is binocular vision sweeping robot.
The binocular camera scaling method and device provided in the present invention, has the advantages that:
The binocular camera scaling method and device provided in the present invention, terminal with binocular camera by being located at same depth
Spend the laser range sensor measurement laser range sensor and the actual range D of specified target of plane;Pass through binocular camera
The image information for specifying target, and the image information of the specified target according to collection are gathered respectively, calculate binocular camera rotation
The scale value t of distance between transfer dynamic transition matrix R and two cameras;Laser Measuring is gathered by binocular camera respectively
The infrared light spot image information in the specified target is radiated at away from sensor, and the matching relationship in image information calculates
Depth value d between laser range sensor and infrared light spot;According to the actual range D, depth value d and two cameras
Between the scale value t of distance calculate actual range T between two cameras;Binocular camera demarcated with this.
Brief description of the drawings
Fig. 1 is the step schematic diagram of binocular camera scaling method in one embodiment of the invention;
Fig. 2 is step S2 specific steps schematic diagrames in one embodiment of the invention;
Fig. 3 is step S4 specific steps schematic diagrames in one embodiment of the invention;
Fig. 4 is the structure diagram of binocular camera caliberating device in one embodiment of the invention;
Fig. 5 is the first computing unit structure diagram in one embodiment of the invention;
Fig. 6 is the 3rd computing unit structure diagram in one embodiment of the invention.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
Those skilled in the art of the present technique are appreciated that unless expressly stated, singulative " one " used herein, " one
It is a ", " described " " above-mentioned " and "the" may also comprise plural form.It is to be further understood that make in the specification of the present invention
Wording " comprising " refers to there are the feature, integer, step, operation, element, unit, module and/or component, but simultaneously
Do not preclude the presence or addition of other one or more features, integer, step, operation, element, unit, module, component and/or it
Group.It should be understood that when we claim element to be " connected " or during " coupled " to another element, it can be directly connected to or couple
To other elements, or there may also be intermediary element.In addition, " connection " used herein or " coupling " can include wirelessly connecting
Connect or wirelessly couple.Wording "and/or" used herein includes the whole or any of one or more associated list items
Unit and all combination.
Those skilled in the art of the present technique are appreciated that unless otherwise defined, all terms used herein (including technology art
Language and scientific terminology), there is the meaning identical with the general understanding of the those of ordinary skill in fields of the present invention.Should also
Understand, those terms such as defined in the general dictionary, it should be understood that have with the context of the prior art
The consistent meaning of meaning, and unless by specific definitions, otherwise will not be explained with the implication of idealization or overly formal.
With reference to Fig. 1, for the step schematic diagram of binocular camera scaling method in one embodiment of the invention.
A kind of binocular camera scaling method is proposed in one embodiment of the invention, is comprised the following steps:
Step S1, terminal measure Laser Measuring by being located at the laser range sensor of same depth plane with binocular camera
Actual range D away from sensor Yu specified target;
Step S2, the image information of specified target is gathered by binocular camera respectively, and according to the specified target of collection
Image information, calculate the scale value of distance between binocular camera transition matrix R in rotary moving and two cameras
t;
Step S3, gathered respectively by binocular camera laser range sensor be radiated at it is infrared in the specified target
Dot pattern picture information, and the matching relationship in image information calculates the depth between laser range sensor and infrared light spot
Value d;
Step S4, calculates according to the scale value t of distance between the actual range D, depth value d and two cameras
Actual range T between two cameras.
In the present embodiment, binocular camera can be applied on the terminal device that needs image, such as mobile phone, sweeper
Device people etc..Terminal in the present embodiment is illustrated by taking binocular vision sweeping robot as an example.
For two cameras that binocular camera includes because the terminal device of installation is different, its corresponding outer ginseng is also different.
Therefore, should when binocular camera to be installed in terminal to (such as binocular vision sweeping robot), it is necessary to demarcated to it
Calibration is to calculate the outer ginseng of the binocular camera, and outer ginseng includes the actual range T between binocular camera, and binocular is taken the photograph
As a transition matrix R in rotary moving.
In the present embodiment, before calibration, laser range sensor is arranged on mounted binocular camera same
In depth plane (same perpendicular), it is preferable that the laser range sensor is located in the binocular camera two and takes the photograph
As head line midpoint on.Laser range sensor can measure the actual range D with specified target, this specifies what target referred to
It is the target of texture-rich, such as a countermure picture on wall, photo frame etc., the specified target of texture-rich are easy to the knowledge of characteristic point
Not.Laser range sensor launches infrared light and is radiated at one infrared light spot of formation in specified target, two cameras point
The image information of the infrared light spot in the specified target is not gathered, and according to image information mid-infrared light point in two field pictures
Matching relationship calculate depth value d between laser range sensor and infrared light spot, depth value d is a scale value, its
What is represented is to have how many a scales between infrared light spot and laser range sensor.It is understood that according to above-mentioned reality
Distance D and depth value d, can calculate the distance value of scale s, i.e. each scale.
Further, the image information of specified target is gathered respectively by two cameras, and according to the specified mesh of collection
Target image information, calculates the scaling of distance between binocular camera transition matrix R in rotary moving and two cameras
Value t, scale value t are not an actual distance values, and what it was represented is to have how many a scales between two cameras.Due to upper
Measurement (i.e. holding laser range sensor and two-sided camera position are constant) under same state is stated to measure, because
This, scale s is identical, and the actual range T between two cameras can be calculated according to above-mentioned scale s and scale value t.
In conclusion just calculate the reality between two-sided camera transition matrix R in rotary moving and two cameras
Border distance T, completes the outer ginseng calibration to two-sided camera.Accurate to obtain outer ginseng and simple and convenient, operand is few, without artificial
Calibration.
With reference to Fig. 2, in one embodiment, the image information of the specified target according to collection, calculates binocular camera shooting
The step S2 of the scale value t of distance between transition matrix R in rotary moving and two cameras, including:
Step S21, carries out feature extraction to the image information of the specified target of collection, extracts the figure of two camera collections
The matched characteristic point as in;
Step S22, according to matched characteristic point, calculates binocular camera transition matrix R in rotary moving and two is taken the photograph
As the scale value t of distance between head.
In the present embodiment, two cameras carry out feature extraction to specifying target to carry out Image Acquisition, and to image information,
Identical characteristic point is matched in extraction two field pictures, further according to matched eight characteristic points, utilizes 8 method meters of normalization
Calculate the scale value t of distance between binocular camera transition matrix R and two cameras in rotary moving.Scale value t is not
One actual distance value, what it was represented is to have how many a scales between two cameras.
In the present embodiment, it is described gather specified target respectively by binocular camera image information the step of after,
Further include:
Denoising is carried out to the image information of the specified target of collection.Specifically, gaussian filtering, intermediate value can be used to filter
Ripple or morphological operation etc. carry out denoising.
In another embodiment, the matching relationship in image information calculates laser range sensor and infrared light
The step S2 of depth value d between point, specifically includes:
According to matching relationship of the infrared light spot in the image that two cameras gather, trigonometric calculations laser is utilized
Depth value d between distance measuring sensor and infrared light spot.
In the present embodiment, the image of each one frame infrared light spot of collection of two cameras, in the picture according to infrared light spot this
One identical characteristic point is matched, and utilizes the depth value d between trigonometric calculations laser range sensor and infrared light spot;
Depth value d is a scale value, and what it was represented is to have how many a scales between infrared light spot and laser range sensor.
With reference to Fig. 3, in the above-described embodiments, it is described according to the actual range D, depth value d and two cameras it
Between the scale value t of distance calculate the step S4 of the actual range T between two cameras and include:
Step S41, according to the actual range D, depth value d, calculates scale s;
Step S42, according to the scale value t of distance between the scale s and two cameras, calculate two cameras it
Between actual range T.
In the present embodiment, it is D to specify actual range between target and laser range sensor, laser range sensor
Depth value between infrared light spot is d, therefore, can calculate the scale s under current measuring state.Scale s is
The scale-value of distance between two cameras, therefore according to the scale value t of distance between the scale s and two cameras,
The actual range T between two cameras can be calculated.
Specifically, the calculation formula of the scale s is s=D/d;The calculation formula of the actual range T is T=s × t.
In conclusion being the binocular camera scaling method provided in the embodiment of the present invention, two shootings are accurately calculated
Actual range T and binocular camera transition matrix R in rotary moving between head, the outer ginseng to two-sided camera is completed with this
Calibration, and it is simple and convenient, operand is few, without artificial calibration.
With reference to Fig. 4, a kind of binocular camera caliberating device is additionally provided in one embodiment of the invention, including:
Measuring unit 10, swashs for the laser range sensor measurement by being located at same depth plane with binocular camera
Ligh-ranging sensor and the actual range D of specified target;
First computing unit 20, for gathering the image information of specified target respectively by binocular camera, and according to adopting
The image information of the specified target of collection, calculates between binocular camera transition matrix R in rotary moving and two cameras
The scale value t of distance;
Second computing unit 30, described specify is radiated at for gathering laser range sensor respectively by binocular camera
Infrared light spot image information in target, and the matching relationship in image information calculates laser range sensor and infrared light
Depth value d between point;
3rd computing unit 40, for according to distance between the actual range D, depth value d and two cameras
Scale value t calculates the actual range T between two cameras.
In the present embodiment, binocular camera can be applied on the terminal device that needs image, such as mobile phone, sweeper
Device people etc..Terminal in the present embodiment is illustrated by taking binocular vision sweeping robot as an example.
For two cameras that binocular camera includes because the terminal device of installation is different, its corresponding outer ginseng is also different.
Therefore, should when binocular camera to be installed in terminal to (such as binocular vision sweeping robot), it is necessary to demarcated to it
Calibration is to calculate the outer ginseng of the binocular camera, and outer ginseng includes the actual range T between binocular camera, and binocular is taken the photograph
As a transition matrix R in rotary moving.
In the present embodiment, before calibration, laser range sensor is arranged on mounted binocular camera same
In depth plane (same perpendicular), it is preferable that the laser range sensor is located in the binocular camera two and takes the photograph
As head line midpoint on.Measuring unit 10 can measure the actual range D with specified target by laser range sensor,
This specifies target to refer to the target of texture-rich, such as a countermure picture on wall, photo frame etc., the specified target of texture-rich
Easy to the identification of characteristic point.Laser range sensor launches infrared light and is radiated at one infrared light of formation in specified target
Point, two cameras gather the infrared light spot image information in the specified target respectively;Second computing unit 30 is according to image
Matching relationship of the information mid-infrared light point in two field pictures calculates the depth value between laser range sensor and infrared light spot
D, depth value d are a scale values, and what it was represented is to have how many a scales between infrared light spot and laser range sensor.
It is understood that according to above-mentioned actual range D and depth value d, scale s can be calculated, i.e., each scale away from
From value.
Further, the first computing unit 20 gathers the image information of specified target, and root by two cameras respectively
According to the image information of the specified target of collection, binocular camera transition matrix R in rotary moving and two cameras are calculated
Between distance scale value t, scale value t is not an actual distance value, what it was represented be have between two cameras it is more
Few scale.Since above-mentioned measurement (keeps laser range sensor and two-sided camera position not under same state
Become) measure, therefore, scale s is identical.Finally, the 3rd computing unit 40 can be according to above-mentioned scale s and scale value t
Calculate the actual range T between two cameras.
In conclusion just calculate the reality between two-sided camera transition matrix R in rotary moving and two cameras
Border distance T, completes the outer ginseng calibration to two-sided camera.Accurate to obtain outer ginseng and simple and convenient, operand is few, without artificial
Calibration.
With reference to Fig. 5, in one embodiment, first computing unit 20 includes:
Subelement 201 is extracted, the image information for the specified target to collection carries out feature extraction, extracts two shootings
Matched characteristic point in the image of head collection;
First computation subunit 202, for according to matched characteristic point, calculating binocular camera conversion square in rotary moving
The scale value t of distance between R and two camera of battle array.
In the present embodiment, by two cameras to specifying target to carry out Image Acquisition, extraction subelement 201 believes image
Breath carries out feature extraction, extracts characteristic point identical in two field pictures and is matched, in the image for extracting two camera collections
The quantity of matched characteristic point is eight, and the first computation subunit 202 utilizes 8 methods of normalization further according to matched characteristic point
Calculate the scale value t of distance between binocular camera transition matrix R and two cameras in rotary moving.Scale value t is not
It is an actual distance value, what it was represented is to have how many a scales between two cameras.
In another embodiment, above-mentioned two-sided camera calibration device further includes:
Denoising unit, the image information for the specified target to collection carry out denoising.Specifically, height can be used
This filtering, medium filtering or morphological operation etc. carry out denoising.
In another embodiment, second computing unit 30 is specifically used for:
According to matching relationship of the infrared light spot in the image that two cameras gather, trigonometric calculations laser is utilized
Depth value d between distance measuring sensor and infrared light spot.
In the present embodiment, the image of each one frame infrared light spot of collection of two cameras, in the picture according to infrared light spot this
One identical characteristic point is matched, the second computing unit 30 using trigonometric calculations laser range sensor and infrared light spot it
Between depth value d;Depth value d is a scale value, and what it was represented is had between infrared light spot and laser range sensor
How many a scales.
With reference to Fig. 6, in the above-described embodiments, the 3rd computing unit 40 includes:
Second computation subunit 401, for according to the actual range D, depth value d, calculating scale s;
3rd computation subunit 402, for the scale value t according to distance between the scale s and two cameras, meter
Calculate the actual range T between two cameras.
In the present embodiment, it is D to specify actual range between target and laser range sensor, laser range sensor
Depth value between infrared light spot is d, and therefore, the second computation subunit 401 can be calculated under current measuring state
Scale s.Scale s is the scale-value of distance between two cameras, thus according to the scale s and two cameras it
Between distance scale value t, the 3rd computation subunit 402 can calculate the actual range T between two cameras.
Specifically, the calculation formula of the scale s is s=D/d;The calculation formula of the actual range T is T=s × t.
In conclusion be the binocular camera scaling method and device that are provided in the embodiment of the present invention, terminal by with it is double
Mesh camera be located at laser range sensor measurement laser range sensor and the specified target of same depth plane it is actual away from
From D;Gather the infrared light spot image letter that laser range sensor is radiated in the specified target respectively by binocular camera
Breath, and the matching relationship in image information calculates the depth value d between laser range sensor and infrared light spot;By double
Mesh camera gathers the image information of specified target, and the image information of the specified target according to collection respectively, calculates binocular
The scale value t of distance between camera transition matrix R in rotary moving and two cameras;According to the actual range D, depth
The scale value t of distance calculates the actual range T between two cameras between angle value d and two cameras;Come pair with this
Binocular camera is demarcated;The accurate actual range T calculated between two cameras and binocular camera are in rotary moving
Transition matrix R, accurate to obtain outer ginseng and simple and convenient, operand is few, without artificial calibration.
Those skilled in the art of the present technique be appreciated that can with computer program instructions come realize these structure charts and/or
The combination of each frame and these structure charts and/or the frame in block diagram and/or flow graph in block diagram and/or flow graph.This technology is led
Field technique personnel be appreciated that these computer program instructions can be supplied to all-purpose computer, special purpose computer or other
The processor of programmable data processing method is realized, so that the processing by computer or other programmable data processing methods
Device performs the scheme specified in the frame of structure chart and/or block diagram and/or flow graph disclosed by the invention or multiple frames.
Those skilled in the art of the present technique are appreciated that in the various operations discussed in the present invention, method, flow
Steps, measures, and schemes can be replaced, changed, combined or be deleted.Further, it is each with having been discussed in the present invention
Other steps, measures, and schemes in kind operation, method, flow may also be alternated, changed, rearranged, decomposed, combined or deleted.
Further, it is of the prior art to have and the step in the various operations disclosed in the present invention, method, flow, measure, scheme
It may also be alternated, changed, rearranged, decomposed, combined or deleted.
The foregoing is merely the preferred embodiment of the present invention, is not intended to limit the scope of the invention, every utilization
The equivalent structure or equivalent flow shift that description of the invention and accompanying drawing content are made, it is related to be directly or indirectly used in other
Technical field, be included within the scope of the present invention.
Claims (10)
1. a kind of binocular camera scaling method, it is characterised in that comprise the following steps:
Terminal by be located at binocular camera same depth plane laser range sensor measure laser range sensor with
Specify the actual range D of target;
Gather the image information of specified target, and the image information of the specified target according to collection respectively by binocular camera,
Calculate the scale value t of distance between binocular camera transition matrix R in rotary moving and two cameras;
Gather the infrared light spot image letter that laser range sensor is radiated in the specified target respectively by binocular camera
Breath, and the matching relationship in image information calculates the depth value d between laser range sensor and infrared light spot;
Two cameras are calculated according to the scale value t of distance between the actual range D, depth value d and two cameras
Between actual range T.
2. binocular camera scaling method according to claim 1, it is characterised in that the specified target according to collection
Image information, calculate the scale value t of distance between binocular camera transition matrix R in rotary moving and two cameras
The step of, including:
Feature extraction is carried out to the image information of the specified target of collection, extracts matched spy in the image of two camera collections
Sign point;
According to matched characteristic point, distance between binocular camera transition matrix R and two cameras in rotary moving is calculated
Scale value t.
3. binocular camera scaling method according to claim 2, it is characterised in that the figure of two camera collections of extraction
The quantity of matched characteristic point is eight as in, described according to matched characteristic point, calculates binocular camera turn in rotary moving
The step of changing the scale value t of distance between matrix R and two cameras, specifically includes:
According to matched eight characteristic points, using 8 methods of normalization calculate binocular cameras transition matrix R in rotary moving with
And between two cameras distance scale value t.
4. binocular camera scaling method according to claim 1, it is characterised in that described to be distinguished by binocular camera
After the step of image information of target is specified in collection, further include:
Denoising is carried out to the image information of the specified target of collection.
5. binocular camera scaling method according to claim 1, it is characterised in that in image information
The step of depth value d between laser range sensor and infrared light spot being calculated with relation, including:
According to matching relationship of the infrared light spot in the image that two cameras gather, trigonometric calculations laser ranging is utilized
Depth value d between sensor and infrared light spot.
A kind of 6. binocular camera caliberating device, it is characterised in that including:
Measuring unit, laser ranging is measured for the laser range sensor by being located at same depth plane with binocular camera
Sensor and the actual range D of specified target;
First computing unit, for gathering the image information of specified target respectively by binocular camera, and according to the finger of collection
The image information to set the goal, calculates distance between binocular camera transition matrix R in rotary moving and two cameras
Scale value t;
Second computing unit, the specified target is radiated at for gathering laser range sensor respectively by binocular camera
Infrared light spot image information, and matching relationship in image information is calculated between laser range sensor and infrared light spot
Depth value d;
3rd computing unit, for the scale value t according to distance between the actual range D, depth value d and two cameras
Calculate the actual range T between two cameras.
7. binocular camera caliberating device according to claim 6, it is characterised in that first computing unit includes:
Subelement is extracted, the image information for the specified target to collection carries out feature extraction, extracts two camera collections
Image in matched characteristic point;
First computation subunit, for according to matched characteristic point, calculate binocular camera transition matrix R in rotary moving and
The scale value t of distance between two cameras.
8. binocular camera caliberating device according to claim 7, it is characterised in that the figure of two camera collections of extraction
The quantity of matched characteristic point is eight as in, and first computation subunit is specifically used for:
According to matched eight characteristic points, using 8 methods of normalization calculate binocular cameras transition matrix R in rotary moving with
And between two cameras distance scale value t.
9. binocular camera caliberating device according to claim 6, it is characterised in that further include:
Denoising unit, the image information for the specified target to collection carry out denoising.
10. binocular camera caliberating device according to claim 6, it is characterised in that second computing unit is specific
For:
According to matching relationship of the infrared light spot in the image that two cameras gather, trigonometric calculations laser ranging is utilized
Depth value d between sensor and infrared light spot.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711260448.7A CN108012143B (en) | 2017-12-04 | 2017-12-04 | Binocular camera calibration method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711260448.7A CN108012143B (en) | 2017-12-04 | 2017-12-04 | Binocular camera calibration method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108012143A true CN108012143A (en) | 2018-05-08 |
CN108012143B CN108012143B (en) | 2021-02-09 |
Family
ID=62056525
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711260448.7A Active CN108012143B (en) | 2017-12-04 | 2017-12-04 | Binocular camera calibration method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108012143B (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108663681A (en) * | 2018-05-16 | 2018-10-16 | 华南理工大学 | Mobile Robotics Navigation method based on binocular camera Yu two-dimensional laser radar |
CN109451298A (en) * | 2018-10-26 | 2019-03-08 | 歌尔股份有限公司 | Angle of deviation detection method, device and the equipment of dual camera |
WO2019109226A1 (en) * | 2017-12-04 | 2019-06-13 | 深圳市沃特沃德股份有限公司 | Binocular camera calibration method and device |
CN109889820A (en) * | 2019-03-14 | 2019-06-14 | 深圳博时特科技有限公司 | Detection method, device, storage medium and the terminal of binocular camera mould group |
CN109917413A (en) * | 2019-01-21 | 2019-06-21 | 苏州雷泰医疗科技有限公司 | A kind of precision navigation localization method of intelligence transfer bed |
CN110058212A (en) * | 2019-05-15 | 2019-07-26 | 上海炬佑智能科技有限公司 | Target and TOF camera demarcate integrated system |
CN111736140A (en) * | 2020-06-15 | 2020-10-02 | 杭州海康微影传感科技有限公司 | Object detection method and camera equipment |
CN111753799A (en) * | 2020-07-03 | 2020-10-09 | 深圳市目心智能科技有限公司 | Based on initiative dual-purpose vision sensor and robot |
TWI725522B (en) * | 2018-08-28 | 2021-04-21 | 鈺立微電子股份有限公司 | Image capture system with calibration function |
WO2021174600A1 (en) * | 2020-03-05 | 2021-09-10 | 中国科学院上海微***与信息技术研究所 | Calibration and depth image processing method for multinocular stereo camera |
WO2021228266A1 (en) * | 2020-05-15 | 2021-11-18 | 奥动新能源汽车科技有限公司 | Visual positioning system, battery replacing device, and battery replacement control method |
US11587260B2 (en) * | 2020-10-05 | 2023-02-21 | Zebra Technologies Corporation | Method and apparatus for in-field stereo calibration |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102074015A (en) * | 2011-02-24 | 2011-05-25 | 哈尔滨工业大学 | Two-dimensional image sequence based three-dimensional reconstruction method of target |
CN102867304A (en) * | 2012-09-04 | 2013-01-09 | 南京航空航天大学 | Method for establishing relation between scene stereoscopic depth and vision difference in binocular stereoscopic vision system |
CN105716568A (en) * | 2016-01-28 | 2016-06-29 | 武汉光庭信息技术股份有限公司 | Binocular camera ranging method in automatic pilot system |
-
2017
- 2017-12-04 CN CN201711260448.7A patent/CN108012143B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102074015A (en) * | 2011-02-24 | 2011-05-25 | 哈尔滨工业大学 | Two-dimensional image sequence based three-dimensional reconstruction method of target |
CN102867304A (en) * | 2012-09-04 | 2013-01-09 | 南京航空航天大学 | Method for establishing relation between scene stereoscopic depth and vision difference in binocular stereoscopic vision system |
CN105716568A (en) * | 2016-01-28 | 2016-06-29 | 武汉光庭信息技术股份有限公司 | Binocular camera ranging method in automatic pilot system |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019109226A1 (en) * | 2017-12-04 | 2019-06-13 | 深圳市沃特沃德股份有限公司 | Binocular camera calibration method and device |
CN108663681A (en) * | 2018-05-16 | 2018-10-16 | 华南理工大学 | Mobile Robotics Navigation method based on binocular camera Yu two-dimensional laser radar |
CN108663681B (en) * | 2018-05-16 | 2021-01-19 | 华南理工大学 | Mobile robot navigation method based on binocular camera and two-dimensional laser radar |
TWI725522B (en) * | 2018-08-28 | 2021-04-21 | 鈺立微電子股份有限公司 | Image capture system with calibration function |
CN109451298B (en) * | 2018-10-26 | 2020-05-05 | 歌尔股份有限公司 | Deviation angle detection method, device and equipment for double cameras |
CN109451298A (en) * | 2018-10-26 | 2019-03-08 | 歌尔股份有限公司 | Angle of deviation detection method, device and the equipment of dual camera |
CN109917413A (en) * | 2019-01-21 | 2019-06-21 | 苏州雷泰医疗科技有限公司 | A kind of precision navigation localization method of intelligence transfer bed |
CN109917413B (en) * | 2019-01-21 | 2021-07-06 | 苏州雷泰医疗科技有限公司 | Accurate navigation positioning method of intelligent transfer bed |
CN109889820A (en) * | 2019-03-14 | 2019-06-14 | 深圳博时特科技有限公司 | Detection method, device, storage medium and the terminal of binocular camera mould group |
CN110058212A (en) * | 2019-05-15 | 2019-07-26 | 上海炬佑智能科技有限公司 | Target and TOF camera demarcate integrated system |
WO2021174600A1 (en) * | 2020-03-05 | 2021-09-10 | 中国科学院上海微***与信息技术研究所 | Calibration and depth image processing method for multinocular stereo camera |
WO2021228266A1 (en) * | 2020-05-15 | 2021-11-18 | 奥动新能源汽车科技有限公司 | Visual positioning system, battery replacing device, and battery replacement control method |
CN111736140A (en) * | 2020-06-15 | 2020-10-02 | 杭州海康微影传感科技有限公司 | Object detection method and camera equipment |
CN111753799A (en) * | 2020-07-03 | 2020-10-09 | 深圳市目心智能科技有限公司 | Based on initiative dual-purpose vision sensor and robot |
US11587260B2 (en) * | 2020-10-05 | 2023-02-21 | Zebra Technologies Corporation | Method and apparatus for in-field stereo calibration |
Also Published As
Publication number | Publication date |
---|---|
CN108012143B (en) | 2021-02-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108012143A (en) | Binocular camera scaling method and device | |
US8345953B2 (en) | Stereoscopic measurement system and method | |
US9454822B2 (en) | Stereoscopic measurement system and method | |
US9286506B2 (en) | Stereoscopic measurement system and method | |
CN104949617A (en) | Object dimension evaluation system and method used for packing object | |
CN202928571U (en) | Photographic measurement system for long-distance micro-deformation monitoring | |
CN110675455B (en) | Natural scene-based self-calibration method and system for vehicle body looking-around camera | |
EP2310799B1 (en) | Stereoscopic measurement system and method | |
CN107403447A (en) | Depth image acquisition method | |
CN105423975B (en) | The calibration system and method for a kind of large-scale workpiece | |
CN109087341B (en) | Fusion method of close-range hyperspectral camera and ranging sensor | |
Babapour et al. | A novel post-calibration method for digital cameras using image linear features | |
CN105078404B (en) | Fully automatic eye movement tracking distance measuring calibration instrument based on laser algorithm and use method of calibration instrument | |
EP2283314B1 (en) | Stereoscopic measurement system and method | |
EP2286297B1 (en) | Stereoscopic measurement system and method | |
Rakhmatulin et al. | Low-cost stereovision system (Disparity Map) for few dollars | |
CN107218918B (en) | A kind of single camera distance measuring method | |
WO2019109226A1 (en) | Binocular camera calibration method and device | |
CN116989825A (en) | Combined calibration method and system for road side laser radar-camera-UTM coordinate system | |
CN115457090A (en) | Registration fusion method and device for visible light image and infrared image | |
CN108051013A (en) | Use the system of sensor sensing chamber intrinsic displacement |
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 | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20190904 Address after: Room 402, 4th floor, Kanghe Sheng Building, New Energy Innovation Industrial Park, No. 1 Chuangsheng Road, Nanshan District, Shenzhen City, Guangdong Province, 518000 Applicant after: Shenzhen Infinite Power Development Co., Ltd. Address before: 518000 Nanshan District, Shenzhen, Guangdong Province, 1079 Nanhai Avenue, Shekou, Garden City Digital Building B Block 503, 602 Applicant before: SHENZHEN WOTE WODE CO., LTD. |
|
TA01 | Transfer of patent application right | ||
GR01 | Patent grant | ||
GR01 | Patent grant |