CN103512579B - A kind of map constructing method based on thermal infrared video camera and laser range finder - Google Patents
A kind of map constructing method based on thermal infrared video camera and laser range finder Download PDFInfo
- Publication number
- CN103512579B CN103512579B CN201310499858.2A CN201310499858A CN103512579B CN 103512579 B CN103512579 B CN 103512579B CN 201310499858 A CN201310499858 A CN 201310499858A CN 103512579 B CN103512579 B CN 103512579B
- Authority
- CN
- China
- Prior art keywords
- thermal infrared
- dimensional
- laser range
- video camera
- point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/005—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 with correlation of navigation data from several sources, e.g. map or contour matching
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B29/00—Maps; Plans; Charts; Diagrams, e.g. route diagram
- G09B29/003—Maps
- G09B29/005—Map projections or methods associated specifically therewith
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Automation & Control Theory (AREA)
- Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Image Processing (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The present invention relates to a kind of map constructing method based on thermal infrared video camera and laser range finder, it is characterized in that the thermal infrared images by obtaining target replaces prior art to obtain the visible images of target, effectively solving that prior art is poor at illumination condition, having shelter to deposit in case cannot the problem of correct map structuring; Utilize variance weighted information entropy to do region of interesting extraction, obtain the rectangle frame comprising target, reduce solution space, eliminate a large amount of noise; Euclidean distance of the present invention and Temperature Matching corresponding point reliability high, with RANSAC algorithm filter corresponding point, at utmost improve the reliability of corresponding point, fast based on ICP algorithmic match computing velocity.
Description
Technical field
The present invention relates to mobile robot immediately to locate and map structuring field, particularly relate to mobile robot in visibility very low and there is shelter map structuring.It can be used for mobile robot at zone of ignorance by optional position, and the perception data according to laser range finder and thermal infrared video camera estimates robot pose and constructing environment map.
Background technology
Along with the development of Robotics, the intelligent mobile robot with the function that is movably walking, environment sensing ability and trajectory planning ability is more and more subject to the attention of various countries researchist.Realizing instant location and map structuring (SimultaneousLocalizationandMapping, SLAM) is one of the most basic function of intelligent robot, is also that it completes the important prerequisite of many tasks.
At present in the application of two-dimentional or three-dimensional map structuring, mainly adopt based on Scale invariant features transform algorithm (Scale-invariantfeaturetransform, SIFT).SIFT algorithm is a kind of based on metric space, to image scaling, rotates the Feature Correspondence Algorithm that even affined transformation maintains the invariance.This algorithmic match ability is comparatively strong, can extract stable feature, can process the matching problem occurred between two width images in translation, rotation, affined transformation, view transformation, light change situation.But the shortcoming of this method has very strong dependence to ambient brightness and the random road sign occurred.And iterative closest point algorithms (IterativeClosestPoint, ICP), by iteration optimization matrix, in each iterative process, to each point in target point set, concentrate in reference point and find closest approach, and utilize such corresponding point, calculate corresponding rotation matrix and translation vector, use it in target point set, obtain new target point set, then enter next iterative process.Finally obtain best transition matrix, realize the accuracy registration of two point sets.
Usually use depth camera or other sensors to gather the visible images of target in map structuring, obtain target information.Visible images is reflected image, and radio-frequency component is many, can reflect the details of scene under certain illumination, but the contrast of visible images when illumination is not good is lower, and poor quality, accurately cannot obtain target information; Thermal infrared images is radiation image, and gray scale is determined by the temperature difference of object and background, and in dark or have in the environment such as cigarette, cloud, mist, visible images is second-rate, and the target in infrared image is but still clear and legible.And thermal infrared possesses certain penetration capacity, though having shelter to exist still more clearly can to obtain target image, be conducive to when hiding, pretending and blocking sooner, the detection of a target more accurately.
Summary of the invention
The technical problem to be solved in the present invention is: provide a kind of map constructing method based on thermal infrared video camera and laser range finder and device, solve very low in visibility and there is shelter map structuring problem.
For solving the problems of the technologies described above, the technical solution used in the present invention is as follows:
Based on a map constructing method for thermal infrared video camera and laser range finder, it is characterized in that comprising the steps:
Step one, the cooperation of employing laser range finder rotate freely motor and build three-dimensional laser range finding platform, realize the scanning to three-dimensional scenic;
Step 2, three-dimensional laser range finding platform step one built and thermal infrared video camera are installed on mobile robot, build and can obtain the thermal infrared images of target and the scanister of three-dimensional laser point point set simultaneously; Demarcate thermal infrared video camera, obtain thermal infrared intrinsic parameters of the camera and external parameter; The position of adjustment thermal infrared video camera, makes thermal infrared video camera consistent with the focus of laser range finder and does not stop scanning area each other; By calculating the global coordinate system being converted to device;
Step 3, the scanister scanning utilizing step 2 to build obtain the initial three-dimensional laser spots data of environment, then record the range data of service robot that ultrasonic sensor records and preceding object thing, the two-dimensional grid map of establishing target environment;
Step 4, use thermal infrared video camera obtain several thermal infrared imagess of environment and carry out preliminary filtering noise reduction process to several thermal infrared imagess obtained; In two steps lens distortion correction is carried out to image according to horizontal direction and vertical direction; Mobile robot's thermal infrared imaging mapping method is expanded to traverse measurement system, calculates the analyzing spot of three-dimensional laser stadimeter and the mathematics transformational relation of corresponding thermal infrared images pixel;
Step 5, carry out based on the process of variance weighted information entropy to thermal infrared images, realize detecting and extraction process the target of area-of-interest under complex background, extract several thermal infrared images temperature information unique points and Euclidean distance unique point;
Step 6, determine coupling corresponding point after, adopt RANSAC Algorithm for Solving basis matrix, then adopt basis matrix to reject the corresponding point of matching error;
Step 7, by two-dimensional grid map with gather the temperature information unique point of several thermal infrared imagess at diverse location and visual angle and Euclidean distance unique point carries out repeatedly ICP Iterative matching, realize the reconstruct to unknown scene 3 d grid map.
By technique scheme, adopt the electric rotating air connector contacted by mercury in step one, laser range finder can rotate freely and can not cause cable distortion; Three-dimensional laser range measurement system freely can obtain three-dimensional laser data around 0 ° ~ 360 ° rotations of laser scanning plane.
By technique scheme, three-dimensional laser stadimeter is first set with 1 millisecond for the sampling period gathers environmental data carry out analog to digital conversion in step 3, obtain initial three-dimensional environmental data, then record the range data of service robot that ultrasonic sensor records and preceding object thing; The three-dimensional laser point point set of obtained initial three-dimensional environmental data is carried out triangular grid, to form multiple plane, and obtains and each the corresponding normal vector in multiple plane; Merge close normal vector normal vector list to be mated with each vector in described environmental characteristic vector table to vector list with forming method; Normal vector in the normal vector table of failing to mate is added to upgrade environmental characteristic vector table in environmental characteristic vector table, utilizes the vector of coupling mutually, build local two-dimensional grid map;
Then, utilize odometer to obtain displacement and the translational speed of mobile robot's left and right wheels, employing track recursion pushes away the pose that the method obtained obtains current robot; The Throw ratio of the current pose of calculating robot in grating map; By the location algorithm of EKF by the prediction of local two-dimensional grid map by robustness, after the coupling fusion treatment of each time point environment detail, generate overall two-dimensional grid map.
Of the present inventionly to focus on: by obtaining thermal infrared images and the three-dimensional laser point set of target, then based on variance weighted information entropy, the target of area-of-interest under complex background is detected and extraction process, and use repeatedly ICP Iterative matching, reach the object of the three-dimensional map building circumstances not known.
Relative to prior art, beneficial effect of the present invention is:
The present invention replaces prior art to obtain the visible images of target by the thermal infrared images obtaining target, effectively solves that prior art is poor at illumination condition, having shelter to deposit in case cannot the problem of correct map structuring; Utilize variance weighted information entropy to do region of interesting extraction, obtain the rectangle frame comprising target, reduce solution space, eliminate a large amount of noise; Euclidean distance of the present invention and Temperature Matching corresponding point reliability high, with RANSAC algorithm filter corresponding point, at utmost improve the reliability of corresponding point, fast based on ICP algorithmic match computing velocity.
The present invention has good versatility and practicality, effectively can promote the widespread use of infrared image, have good economic benefit.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of a kind of map constructing method based on thermal infrared video camera and laser range finder of the present invention.
Fig. 2 is that in the present invention, laser range finder coordinates the coordinate system figure rotating freely motor structure three-dimensional laser range finding platform.
Fig. 3 is the coordinate system figure of the experiment porch that in the present invention, three-dimensional laser range finding platform and thermal infrared video camera build.
Fig. 4 is the projection model of thermal infrared video camera in the present invention.
Embodiment
For making technical scheme of the present invention and advantage clearly understand, with reference to accompanying drawing, the present invention is described in further detail, the restriction not to its protection domain.
Fig. 1 gives the implementing procedure figure of a present system.As shown in Figure 1, generally speaking, method of the present invention comprises the steps:
Step one, utilize German SICK company LMS200 laser range finder to coordinate to rotate freely motor and build three-dimensional laser scanner, realize the scanning to three-dimensional scenic by laser range finder.Three-dimensional laser range measurement system is made up of the small-sized The Cloud Terrace of built-in motor and LMS200 laser range finder, inclination mounting means, and the built-in motor of The Cloud Terrace drives laser.The present invention adopts the electric rotating air connector contacted by mercury, and stadimeter can rotate freely and can not cause cable distortion.Three-dimensional laser range measurement system freely can obtain three-dimensional laser data around 0D ~ 360D rotation of laser scanning plane, and scan mode is perpendicular to surface level.This laser scanner is arranged on the Ying Ji Si company MT-R Autonomic Mobile Robot System platform of Shanghai.Coordinate the motor that rotates freely of The Cloud Terrace to select permanent type heavy duty magnetic-synchro motor, can ensure the serviceable life that three-dimensional laser range measurement system is longer, and have stable operating function, its rotational speed is similar to uniform motion.
Due to when mechanical erection in actual case study on implementation, spatially there is certain deviation in rotation center and the radiating laser beams center of The Cloud Terrace, its location parameter relation can be represented by Fig. 2 structural representation.Assuming that two-dimentional stadimeter LMS200 coordinate system is Σ
l, the coordinate of initial point ο is positioned at plane of scanning motion center, and X ' axle corresponds to the two-dimentional stadimeter plane of scanning motion, does is Y ' axle perpendicular to scanning plane (face or axle?), Z ' axle is corresponding right-handed coordinate system.Coordinate system Σ
srepresent three-dimensional laser stadimeter, origin ο is the rotation platform being positioned at a specific distance center.X-axis corresponds to the front of the three-dimensional laser stadimeter in front, and the surface of the corresponding rotation axis of Y-axis, Z axis is for meeting right-handed coordinate system.This scanning laser range finder setting angle is for being β with horizontal plane angle, and the rotational scan rate of the The Cloud Terrace plane of scanning motion is
Homogeneous transform matrix
st
lwith coordinate system Σ
l, Σ
sbetween relationship between expression be:
In the present invention
sr
lwith
st
ltwo-dimentional stadimeter coordinate system Σ respectively
lrelative to three-dimensional laser range finding coordinate system Σ
srotation matrix and transition matrix.
Measurement point L
prelative to Σ
lbe expressed as:
R represents measuring distance, and θ represents scanning angle.
Measurement point coordinate
sp is about three-dimensional laser range measurement system coordinate system Σ
smathematical relation be:
Sp=
ST
L Lp
Real case is acquisition measurement point in implementing
sthe accurate three-dimensional Cartesian coordinates of p, the anglec of rotation γ that the is synchronous and plane of scanning motion of scan-data is extremely important.
Step 2, thermal infrared video camera and three-dimensional laser range-finding system to be arranged on robot MT-R in the lump.For building a three dimensional temperature record figure, we need full width thermal infrared images.Because the visual angle of traditional infrared camera is usually less, for reaching the mapping of three dimensional temperature record figure, camera also should be arranged on the rotary head of robot.Parameter calibration is carried out to thermal infrared video camera, obtains its inner parameter and external parameter.The position of adjustment thermal infrared video camera, makes thermal infrared video camera consistent with the focus of laser range finder and does not stop scanning area each other.As the coordinate system figure of the experiment porch that Fig. 3 three-dimensional laser range finding platform and thermal infrared video camera build.By single analyzing spot
sp and corresponding thermal infrared images pixel
cp mates.The coordinate system of thermal infrared video camera is Σ
c, Σ
ctrue origin 0
//the position of the camera focus be positioned at, x-axis X
//for optic axis, the z-axis Z of camera
//for the vertical coordinate of camera, y-axis Y
//for meeting the axis of right-handed coordinate system.
Thermal infrared picture point
cp and coordinate system Σ
cmathematical relation be:
Cp=
CT
L Cp(1)
In the present invention
ct
scoordinate system Σ
sand Σ
cbetween homogeneous transformation, and
wt
swith Σ
scoordinate system and Σ
wbetween coordinate system (global coordinate system), position relationship is known,
wt
cwith Σ
ccoordinate system and Σ
wthe relation of coordinate system is calculated by camera position and camera rotation angle.Therefore,
We can obtain global coordinate system Σ thus
wbe transformed into robot coordinate system Σ
rS, when analyzing spot model extension also can move to robot by an analyzing spot when robot is static.
The scanning of scanister that step 3, utilization (step 2) build obtains the initial three-dimensional laser spots data of environment, then records the range data of service robot that ultrasonic sensor records and preceding object thing, the two-dimensional grid map of establishing target environment.
1) three-dimensional laser stadimeter is set with 1 millisecond for the sampling period gathers environmental data carry out analog to digital conversion, obtains initial three-dimensional environmental data, then record the range data of service robot that ultrasonic sensor records and preceding object thing.Obtained three-dimensional laser point point set is carried out triangular grid, to form multiple plane, and obtains and each the corresponding normal vector in multiple plane.Due to determine that the normal vector of plane orthogonal is unique, therefore can all represent a plane by each normal vector, that namely perpendicular plane.Merge close normal vector normal vector list to be mated with each vector in described environmental characteristic vector table to vector list with forming method.Normal vector in the normal vector table of failing to mate is added to upgrade environmental characteristic vector table in environmental characteristic vector table, utilizes the vector of coupling mutually, build local two-dimensional grid map.
2) utilize odometer to obtain displacement and the translational speed of mobile robot's left and right wheels, employing track recursion pushes away the pose that the method obtained obtains current robot.The Throw ratio of the current pose of calculating robot in grating map.By the location algorithm of EKF by the prediction of local two-dimensional grid map by robustness, after the coupling fusion treatment of each time point environment detail, generate overall two-dimensional grid map.
Step 4, obtain thermal infrared images corresponding to scanning coordinate point by thermal infrared video camera.As the video camera projection model of Fig. 4 display.
Pass through homogeneous equation
and equation
Three-dimensional coordinate point Q=(X, Y, Z) is transformed into a pixel q=(x, y) to homogeneous.Wherein M is the inner parameter matrix of thermal infrared video camera, f
xand f
ythe focal length of representative, c
xand c
yit is the side-play amount of projection centre.The condition that equation (3) meets does not have lens distortion, therefore the distortion correction of thermal infrared video camera is required.The view data obtained from thermal infrared camera lens is carried out to the correction of horizontal direction, by carry out horizontal direction correction after view data write dynamic storage.Then the view data in dynamic storage is carried out to the correction of vertical direction.Carry out lens distortion correction in two steps according to horizontal direction and vertical direction, the lens distortion realizing image rapidly corrects.
In order to can map structuring fast, mobile robot's thermal infrared imaging mapping method be expanded to traverse measurement system by us.The method is that formula (3) basis obtains in three-dimensional range finding.Make Σ
rSthe data that in robot coordinate system, laser range finder is caught, Σ
rCit is the image that in robot coordinate system, thermal infrared camera is caught.
rSt
srepresent scanner coordinate relative to robot coordinate homogeneous transform matrix,
rSt
crepresent that camera coordinates is relative to robot coordinate homogeneous transform matrix.Therefore homogeneous transform matrix
ct
s(represent Σ
sabout Σ
c) can be analyzed to:
CT
S=
CT
RC RCT
W WT
RS RST
S
When tentatively specifically being implemented during moveable robot movement, the mathematics transformational relation of the thermal infrared images pixel corresponding to the analyzing spot of three-dimensional laser stadimeter.
Step 5, carry out based on the process of variance weighted information entropy to thermal infrared images, under complex background based on the target detection of area-of-interest and extraction.Region of interesting extraction step wherein based on variance weighted information entropy is:
1) the initial frame Iamge Segmentation of M*N size is become the subimage block of m*n size, obtain subimage block set F=(u, v), wherein: m=2
k, n=2
i, 1≤K≤4,1≤I≤4,0≤u≤M/m-1,0≤v≤N/n-1;
2) every width image F=(i, j) in antithetical phrase image block set F=(u, v), adopts formula:
Calculate its variance weighted information entropy H=(i, j), obtain the entropy diagram picture of M/ (m-1) * N/ (n-1) size, and the average μ of computing information entropy diagram picture and variances sigma; Wherein: 0≤i≤M/m-1,0≤v≤N/n-1, s represents gray-scale value, p
srepresent the probability that often kind of gray level is corresponding,
represent the average gray of infrared image, work as p
swhen=0, make p
s* log (p
s)=0;
3) when step 2) entropy H (t, r)>=H maximum in the entropy diagram picture that obtains
ttime, the subimage F (t, r) that H (t, r) is corresponding is seed; As H (t, r) <H
ttime, get m=m/2, n=n/2, repeat step (1) and (2), until entropy maximum in entropy diagram picture meets H (t, r)>=H
tor m=2, n=2; Wherein (t, r) represents the position of the image block that entropy is maximum.
4) on entropy diagram picture, with the factor that step (3) obtains, adopt the region growing methods based on eight neighborhood to increase, obtain the region of interest ROI (centerx comprising target, centery, w, h) as infrared small target in complex background detect result, wherein: centerx is regional center horizontal ordinate, centery is regional center ordinate, w is the width in region, is h region height, is integer; Described based on the similarity α ∈ (0,1) in the region growing methods of eight neighborhood.
Step 6, extract several thermal infrared images temperature information unique points and Euclidean distance unique point.After match point is chosen, error matching points is rejected to match point RANSAC algorithm, improves matching efficiency.RANSAC (randomsampleconsensus) algorithm is a kind of iterative algorithm estimating mathematical model parameter, and main thought is by the strategy of sampling and verify, solves the parameter of the mathematical model that most of sample characteristics point can meet.The present invention uses the concrete steps of RANSAC algorithm as follows:
1) randomly draw 4 pairs of thermal infrared images temperature information unique points and Euclidean distance unique point as characteristic matching point (this sentence has an ambiguity, needs clarify and revise), as some set in initial, calculate transformation matrix H by this interior point set total.
2) judge the point outside interior some set successively, calculate the distance between X and HX ', if be less than the I value of setting, then point front to " i " is joined interior set successively.
3) repeat (1) and (2) N time, choose that maximum group of interior some number as qualified coupling point set.In new, put set, use least square method to upgrade transformation matrix H.
Suppose that the ratio that the point of correct coupling accounts for sum is p, then 4 couple randomly drawed match point is not the probability of correct coupling is entirely 1-p, extracts that all to take out for N time less than 4 the probability being entirely correct match point be (1-p)
4, in practice, as long as can ensure (1-p)
4<0.05 just can meet the needs of practical application.
Step 7, two-dimensional grid map is carried out repeatedly ICP with the temperature information unique point and Euclidean distance unique point that gather several thermal infrared imagess at diverse location and visual angle mate, realize the structure to scene 3 d grid map.ICP coupling in the present invention not only uses Euclidean distance but also finds corresponding point according to the temperature difference.The use of this algorithm of evaluation function not only recently iteration point quadratic sum but also consider the corresponding point calorific value difference of two squares.In each iterative step, the immediate corresponding point of ICP algorithms selection also calculate its rotation matrix R and transformed matrix t and minimize ICP algorithm equation:
Wherein N
mand N
dbeing M place reference point quantity and D place match point quantity respectively, is the weight of K temperature; h
mia m
iplace's temperature value, h
dja d
jplace's temperature value.When
time,
functional value minimizes.ICP iteration is carried out always, until E
t(R, t) restrains, and now arrives iteration optimum value.Finally obtain surrounding three-dimensional grating map.
The implementation case is with the advantage of map constructing method compared with domestic and international prior art of laser range finder based on thermal infrared video camera: first extract region of interest ROI, can effectively reduce map match region, reduces data calculated amount; Secondly error matching points is rejected to match point RANSAC algorithm, reduce data analysis quantity, improve map match efficiency, shorten match time; Again by the 3 d grid map of constructing environment, environmental information can be embodied better, contribute to the application of three-dimensional map in real work.
The implementation case is based on the map constructing method of thermal infrared video camera and laser range finder, realize the low and targeted environment in intensity of illumination to there is shelter and deposit in case, establishing target surrounding three-dimensional map, improves laser robot under circumstances not known to the detectivity of environment and work efficiency.The present invention can be applied to the working environment such as field detection, earthquake search and rescue equally, has good economic and social benefit.
Above-described specific embodiment, further describes object of the present invention, technical scheme and beneficial effect, it should be understood that and the foregoing is only specific embodiments of the invention, be not limited to the present invention.Within the spirit and principles in the present invention all, any amendment made, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (3)
1., based on a map constructing method for thermal infrared video camera and laser range finder, it is characterized in that comprising the steps:
Step one, the cooperation of employing laser range finder rotate freely motor and build three-dimensional laser range finding platform, realize the scanning to three-dimensional scenic;
Step 2, three-dimensional laser range finding platform step one built and thermal infrared video camera are installed on mobile robot, build and can obtain the thermal infrared images of target and the scanister of three-dimensional laser point point set simultaneously; Demarcate thermal infrared video camera, obtain thermal infrared intrinsic parameters of the camera and external parameter; The position of adjustment thermal infrared video camera, makes the find range focus of platform laser range finder of thermal infrared video camera and three-dimensional laser consistent and do not stop scanning area each other; By calculating the global coordinate system being converted to device;
Step 3, the scanister scanning utilizing step 2 to build obtain the initial three-dimensional laser spots data of environment, then record the range data of mobile robot that ultrasonic sensor records and preceding object thing, the two-dimensional grid map of establishing target environment;
Step 4, use thermal infrared video camera obtain several thermal infrared imagess of environment and carry out preliminary filtering noise reduction process to several thermal infrared imagess obtained; In two steps lens distortion correction is carried out to image according to horizontal direction and vertical direction; Mobile robot's thermal infrared imaging mapping method is expanded to three-dimensional laser range finding platform, calculate the three-dimensional laser range finding analyzing spot of platform and the mathematics transformational relation of corresponding thermal infrared images pixel;
Step 5, carry out based on the process of variance weighted information entropy to thermal infrared images, realize detecting and extraction process the target of area-of-interest under complex background, extract several thermal infrared images temperature information unique points and Euclidean distance unique point;
Step 6, determine coupling corresponding point after, adopt RANSAC Algorithm for Solving basis matrix, then adopt basis matrix to reject the corresponding point of matching error;
Step 7, by two-dimensional grid map with gather the temperature information unique point of several thermal infrared imagess at diverse location and visual angle and Euclidean distance unique point carries out repeatedly ICP Iterative matching, realize the reconstruct to unknown scene 3 d grid map.
2. according to claim 1 based on the map constructing method of thermal infrared video camera and laser range finder, it is characterized in that: adopt the electric rotating air connector contacted by mercury in step one, three-dimensional laser range finding platform can rotate freely and can not cause cable distortion; Three-dimensional laser range finding platform freely can obtain three-dimensional laser data around 0 ° ~ 360 ° rotations of laser scanning plane.
3., according to claim 1 based on the map constructing method of thermal infrared video camera and laser range finder, it is characterized in that:
Three-dimensional laser range finding platform is first set with 1 millisecond for the sampling period gathers environmental data carry out analog to digital conversion in step 3, obtains initial three-dimensional environmental data, then record the range data of mobile robot that ultrasonic sensor records and preceding object thing; The three-dimensional laser point point set of obtained initial three-dimensional environmental data is carried out triangular grid, to form multiple plane, and obtains and each the corresponding normal vector in multiple plane; Merge close normal vector normal vector list to be mated with each vector in described environmental characteristic vector table to vector list with forming method; Normal vector in the normal vector table of failing to mate is added to upgrade environmental characteristic vector table in environmental characteristic vector table, utilizes the vector of coupling mutually, build local two-dimensional grid map;
Then, utilize odometer to obtain displacement and the translational speed of mobile robot's left and right wheels, employing track recursion pushes away the pose that the method obtained obtains current robot; The Throw ratio of the current pose of calculating robot in grating map; By the location algorithm of EKF by the prediction of local two-dimensional grid map by robustness, after the coupling fusion treatment of each time point environment detail, generate overall two-dimensional grid map.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310499858.2A CN103512579B (en) | 2013-10-22 | 2013-10-22 | A kind of map constructing method based on thermal infrared video camera and laser range finder |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310499858.2A CN103512579B (en) | 2013-10-22 | 2013-10-22 | A kind of map constructing method based on thermal infrared video camera and laser range finder |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103512579A CN103512579A (en) | 2014-01-15 |
CN103512579B true CN103512579B (en) | 2016-02-10 |
Family
ID=49895683
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310499858.2A Active CN103512579B (en) | 2013-10-22 | 2013-10-22 | A kind of map constructing method based on thermal infrared video camera and laser range finder |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103512579B (en) |
Families Citing this family (30)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103837138B (en) * | 2014-03-25 | 2014-12-17 | 许凯华 | Precise photogrammetry robot |
CN104536009B (en) | 2014-12-30 | 2016-12-28 | 华中科技大学 | Above ground structure identification that a kind of laser infrared is compound and air navigation aid |
CN104932494B (en) * | 2015-04-27 | 2018-04-13 | 广州大学 | The build mechanism of distribution of obstacles figure in a kind of probabilistic type room |
CN105987693B (en) * | 2015-05-19 | 2019-04-30 | 北京蚁视科技有限公司 | A kind of vision positioning device and three-dimensional mapping system and method based on the device |
CN105222789A (en) * | 2015-10-23 | 2016-01-06 | 哈尔滨工业大学 | A kind of building indoor plane figure method for building up based on laser range sensor |
CN105216905B (en) * | 2015-10-27 | 2018-01-02 | 北京林业大学 | Immediately positioning and map building exploration search and rescue robot |
CN105444681A (en) * | 2015-11-16 | 2016-03-30 | 安徽省道一电子科技有限公司 | High-precision rail crawling measurement method based on single camera calibration and coding points |
CN105467994B (en) * | 2015-11-27 | 2019-01-18 | 长春瑶光科技有限公司 | The meal delivery robot indoor orientation method that vision is merged with ranging |
CN105953787A (en) * | 2016-04-27 | 2016-09-21 | 河北德普电器有限公司 | Robot navigation map generation system |
CN105866132B (en) * | 2016-05-27 | 2018-08-24 | 中国铁道科学研究院 | A kind of cab signal machine appearance detecting system and method |
CN106227218A (en) * | 2016-09-27 | 2016-12-14 | 深圳乐行天下科技有限公司 | The navigation barrier-avoiding method of a kind of Intelligent mobile equipment and device |
CN106909149B (en) * | 2017-03-14 | 2020-09-22 | 深圳蓝因机器人科技有限公司 | Method and device for avoiding obstacles by depth camera |
CN106872963B (en) * | 2017-03-31 | 2019-08-27 | 厦门大学 | A kind of automatic Calibration algorithm of multiple groups multi-line laser radar |
CN107315426A (en) * | 2017-08-31 | 2017-11-03 | 珠海市微半导体有限公司 | One kind rotation ranging sensing device and robot |
CN107767465B (en) * | 2017-10-25 | 2021-03-23 | 深圳市万德建设集团股份有限公司 | Intelligent construction method for decoration design scheme |
CN109959935B (en) * | 2017-12-14 | 2020-10-23 | 北京欣奕华科技有限公司 | Map establishing method, map establishing device and robot |
WO2019148311A1 (en) * | 2018-01-30 | 2019-08-08 | 深圳前海达闼云端智能科技有限公司 | Information processing method and system, cloud processing device and computer program product |
CN108759844B (en) * | 2018-06-07 | 2021-11-16 | 科沃斯商用机器人有限公司 | Robot repositioning and environment map constructing method, robot and storage medium |
CN110850856B (en) * | 2018-07-25 | 2022-11-25 | 北京欣奕华科技有限公司 | Data processing method and device and robot |
CN109682385A (en) * | 2018-11-05 | 2019-04-26 | 天津大学 | A method of instant positioning and map structuring based on ORB feature |
CN110044963B (en) * | 2019-04-22 | 2021-01-19 | 西安交通大学 | Thermal grid scanning thermal imaging nondestructive testing method |
CN110764096A (en) * | 2019-09-24 | 2020-02-07 | 浙江华消科技有限公司 | Three-dimensional map construction method for disaster area, robot and robot control method |
CN110782506B (en) * | 2019-11-21 | 2021-04-20 | 大连理工大学 | Method for constructing grid map by fusing infrared camera and depth camera |
CN111489391B (en) * | 2020-03-02 | 2022-09-16 | 天地科技股份有限公司 | Advanced hydraulic support positioning system and method based on laser point cloud |
CN112486171B (en) * | 2020-11-30 | 2022-08-30 | 中科院软件研究所南京软件技术研究院 | Robot obstacle avoidance method based on vision |
CN112950696A (en) * | 2021-02-03 | 2021-06-11 | 珠海格力智能装备有限公司 | Navigation map generation method and generation device and electronic equipment |
CN112936348B (en) * | 2021-03-04 | 2022-11-18 | 哈尔滨工业大学 | Sensor integration device for sensing RGB-D-T information of intelligent robot |
CN113759355B (en) * | 2021-09-09 | 2023-04-28 | 四川虹美智能科技有限公司 | Distance measuring method and device based on infrared data |
CN114972970A (en) * | 2022-05-25 | 2022-08-30 | 中煤科工集团重庆研究院有限公司 | Coal mine mechanical arm scanning observation system |
CN117870653B (en) * | 2024-03-13 | 2024-05-14 | 中国科学技术大学 | Method for establishing and updating two-dimensional differential Euclidean symbol distance field map |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101769754A (en) * | 2010-01-19 | 2010-07-07 | 湖南大学 | Quasi three-dimensional map-based mobile robot global path planning method |
CN102654577A (en) * | 2011-03-03 | 2012-09-05 | 黎亮 | High-precision mobile robot two-dimensional map data fusion method |
CN103154666A (en) * | 2011-06-14 | 2013-06-12 | 日产自动车株式会社 | Distance measurement device and environment map generation apparatus |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2003302470A (en) * | 2002-04-05 | 2003-10-24 | Sogo Jidosha Anzen Kogai Gijutsu Kenkyu Kumiai | Pedestrian detection device and pedestrian detection method |
AU2003256435A1 (en) * | 2002-08-16 | 2004-03-03 | Evolution Robotics, Inc. | Systems and methods for the automated sensing of motion in a mobile robot using visual data |
JP4262196B2 (en) * | 2004-12-14 | 2009-05-13 | 本田技研工業株式会社 | Autonomous mobile robot |
-
2013
- 2013-10-22 CN CN201310499858.2A patent/CN103512579B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101769754A (en) * | 2010-01-19 | 2010-07-07 | 湖南大学 | Quasi three-dimensional map-based mobile robot global path planning method |
CN102654577A (en) * | 2011-03-03 | 2012-09-05 | 黎亮 | High-precision mobile robot two-dimensional map data fusion method |
CN103154666A (en) * | 2011-06-14 | 2013-06-12 | 日产自动车株式会社 | Distance measurement device and environment map generation apparatus |
Also Published As
Publication number | Publication date |
---|---|
CN103512579A (en) | 2014-01-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103512579B (en) | A kind of map constructing method based on thermal infrared video camera and laser range finder | |
US20180268239A1 (en) | Method and System of Image-Based Change Detection | |
CN101916437B (en) | Method and system for positioning target based on multi-visual information | |
Borrmann et al. | Thermal 3D mapping of building façades | |
CN106908040B (en) | A kind of binocular panorama visual robot autonomous localization method based on SURF algorithm | |
Abuhadrous et al. | Digitizing and 3D modeling of urban environments and roads using vehicle-borne laser scanner system | |
McManus et al. | Towards appearance-based methods for lidar sensors | |
Moussa | Integration of digital photogrammetry and terrestrial laser scanning for cultural heritage data recording | |
Yue et al. | Fast 3D modeling in complex environments using a single Kinect sensor | |
Zhang et al. | Background filtering and vehicle detection with roadside lidar based on point association | |
Fang et al. | A Real‐Time 3D Perception and Reconstruction System Based on a 2D Laser Scanner | |
Mi et al. | A vision-based displacement measurement system for foundation pit | |
Nagy et al. | Online targetless end-to-end camera-LiDAR self-calibration | |
Özdemir et al. | A multi-purpose benchmark for photogrammetric urban 3D reconstruction in a controlled environment | |
Sakai et al. | Large-scale 3D outdoor mapping and on-line localization using 3D-2D matching | |
Jiang et al. | Bridge Deformation Measurement Using Unmanned Aerial Dual Camera and Learning‐Based Tracking Method | |
Gracias | Mosaic-based visual navigation for autonomous underwater vehicles | |
Sen et al. | SceneCalib: Automatic targetless calibration of cameras and LiDARs in autonomous driving | |
CN113240755B (en) | City scene composition method and system based on street view image and vehicle-mounted laser fusion | |
Jacobs et al. | Two cloud-based cues for estimating scene structure and camera calibration | |
Al-Durgham | The registration and segmentation of heterogeneous Laser scanning data | |
Zhang et al. | 3D point cloud registration for multiple roadside LiDARs with retroreflective reference | |
Li et al. | 3D semantic map construction based on point cloud and image fusion | |
Lyu et al. | Multi-sensor fusion based obstacle localization technology | |
Park et al. | Localization of an unmanned ground vehicle based on hybrid 3D registration of 360 degree range data and DSM |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant |