CN105425806A - Human body detection and tracking method and device of mobile robot - Google Patents
Human body detection and tracking method and device of mobile robot Download PDFInfo
- Publication number
- CN105425806A CN105425806A CN201510992646.7A CN201510992646A CN105425806A CN 105425806 A CN105425806 A CN 105425806A CN 201510992646 A CN201510992646 A CN 201510992646A CN 105425806 A CN105425806 A CN 105425806A
- Authority
- CN
- China
- Prior art keywords
- human body
- human
- mobile robot
- induction switch
- azimuth coverage
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 31
- 238000000034 method Methods 0.000 title claims abstract description 27
- 230000006698 induction Effects 0.000 claims abstract description 90
- 230000033001 locomotion Effects 0.000 claims abstract description 29
- 230000001143 conditioned effect Effects 0.000 claims description 11
- 238000010586 diagram Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 5
- 238000009434 installation Methods 0.000 description 4
- 241000222712 Kinetoplastida Species 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000003238 somatosensory effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
- G05D1/0251—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means extracting 3D information from a plurality of images taken from different locations, e.g. stereo vision
Abstract
The invention is suitable for the technical field of mobile robots, and provides a human body detection and tracking method and device of a mobile robot. The method comprises the steps that the azimuth range of a human body relative to the mobile robot is acquired via a human body induction switch array; the human body is searched in the azimuth range via a motion-sensing camera, and a horizontal holder is controlled to rotate so as to drive the motion-sensing camera to track the human body after the human body is found; the concrete azimuth of the human body relative to the mobile robot and the distance between the human body and the mobile robot are determined according to the rotating angle of the horizontal holder and the position of the human body in an image acquired by the motion-sensing camera; and movement of three omnidirectional driving wheels of the mobile robot is controlled according to the concrete azimuth and the distance. Dynamic detection is realized via the human body induction switch array, the horizontal holder and the motion-sensing camera so that positioning accuracy is enhanced; and three omnidirectional driving wheels are controlled to perform 360-degree omnidirectional movement so that rapid tracking of movement of the human body can be realized, and lost of tracking of the detected human body can be avoided.
Description
Technical field
The invention belongs to mobile robot technology field, particularly relate to the human body detection of mobile robot and tracking and device.
Background technology
In recent years, mobile robot technology development is ripe, and mobile robot is applied in the indoor scenes such as factory, exhibition, airport and museum, has welcome, leads the way, goes on patrol and the various function such as security protection.Human body detection and tracking technique are the important component parts of mobile robot technology, are the necessary technologies enabling mobile robot realize the function such as security protection and food delivery.
At present, the human body detection of mobile robot realizes mainly through following several method: first method by camera collection image, then is detected by Feature extraction and recognition and locates human body.Second method adopts passive type infrared camera, and this camera can detect the thermal objects such as human body well, is applicable to field scene, is usually used in military use, but due to expensive, conditional request is higher, therefore less in civilian middle application.The third method adopts human induction switch, and this switch can detect the mobile human body of (such as, maximum detection angles 120 degree, maximum detecting distance 10 meters) in certain limit.Although human induction switch detection sensitivity is higher, can only detects with or without human body in a big way, and accurate location can not be realized, often be used to the scene such as automatically-controlled door and corridor lamp.4th kind of method adopts the body sense equipment such as Kinect, and this equipment has the ability of sampling depth image, by related algorithm, can detect the human body in 1 ~ 4 meter, 53 degree angular ranges in real time, and determines position and the posture of human body.Existing mobile robot adopts the driven universal wheel of the differential cooperation of two-wheeled to realize driving mostly.
Realizing in process of the present invention, inventor finds that in prior art, at least there are the following problems: can detect human body based on infrared and human body detection that is microwave and report to the police, but can not realize dynamically carrying out human body tracking; The robot of two-wheel drive, when human body moves more quickly, easily with losing detected human body, causes human body tracking failure.
Summary of the invention
Given this, embodiments provide the human body detection of a kind of mobile robot and tracking and device, to solve existing mobile robot, to carry out the accuracy of human body detection lower, is difficult to realize dynamic tracking, easily with the problem of losing detected human body.
First aspect, embodiments provides human body detection and the tracking of a kind of mobile robot, comprising:
The azimuth coverage of human body relative to described mobile robot is obtained by human induction switch array;
In described azimuth coverage, human body is found by body sense camera, described body sense camera is driven by horizontal The Cloud Terrace, and after the described human body of discovery, control described horizontal cloud platform rotation and follow the tracks of described human body to drive described body sense camera, to ensure that described human body is in the image of described body sense camera acquisition;
Position in the image obtained at described body sense camera according to the rotational angle of described horizontal The Cloud Terrace and described human body, determine the concrete position angle of described human body relative to described mobile robot, and obtain the distance between described human body and described mobile robot by described body sense camera;
Three omnidirectional driving wheel motions of mobile robot according to described concrete position angle and described distance controlling.
Second aspect, embodiments provides human body detection and the tracking means of a kind of mobile robot, comprising:
Azimuth coverage acquiring unit, for obtaining the azimuth coverage of human body relative to described mobile robot by human induction switch array;
Human body finds unit, for finding human body by body sense camera in described azimuth coverage, described body sense camera is driven by horizontal The Cloud Terrace, and after the described human body of discovery, control described horizontal cloud platform rotation and follow the tracks of described human body to drive described body sense camera, to ensure that described human body is in the image of described body sense camera acquisition;
Concrete position angle and distance acquiring unit, for the position in the image that obtains at described body sense camera according to the rotational angle of described horizontal The Cloud Terrace and described human body, determine the concrete position angle of described human body relative to described mobile robot, and obtain the distance between described human body and described mobile robot by described body sense camera;
Tracking cell, for three omnidirectional driving wheel motions of mobile robot according to described concrete position angle and described distance controlling.
The beneficial effect that the embodiment of the present invention compared with prior art exists is: the embodiment of the present invention is by the azimuth coverage at human induction switch array preliminary quick detection human body place, accurately locate by horizontal The Cloud Terrace band kinetoplast sense camera and follow the tracks of human body again, thus achieve dynamic instrumentation, and improve the accuracy of human body location; Achieving 360 degree by three omnidirectional driving wheels to follow the tracks of without dead angle, achieve and follow human motion fast, avoiding with losing detected human body.
Accompanying drawing explanation
In order to be illustrated more clearly in the technical scheme in the embodiment of the present invention, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
Fig. 1 is the schematic diagram of the front elevation of the mobile robot that the embodiment of the present invention provides;
Fig. 2 is the installation site schematic diagram of the human induction switch 12 of the mobile robot that the embodiment of the present invention provides, horizontal The Cloud Terrace 13 and body sense camera 14 relative movement robot body 11;
Fig. 3 is the human body detection of the mobile robot that the embodiment of the present invention provides and the realization flow figure of tracking;
Fig. 4 is the angle schematic diagram of the omnidirectional driving wheel 15 of mobile robot in the human body detection of the mobile robot that the embodiment of the present invention provides and tracking, body sense camera 14 and human body 21;
Fig. 5 is the schematic diagram of coordinate system of machine and world coordinate system in the human body detection of the mobile robot that the embodiment of the present invention provides and tracking;
Fig. 6 is the human body detection of the mobile robot that the embodiment of the present invention provides and the structured flowchart of tracking means.
Embodiment
In order to make object of the present invention, technical scheme and advantage clearly understand, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein only in order to explain the present invention, be not intended to limit the present invention.
Fig. 1 shows the schematic diagram of the front elevation of the mobile robot that the embodiment of the present invention provides, and for convenience of explanation, illustrate only the part relevant to the embodiment of the present invention.With reference to Fig. 1, this mobile robot comprises mobile apparatus human body 11, is rotated around the equally distributed multiple human induction switch 12 of robot body 11, the horizontal The Cloud Terrace 13 be connected with mobile apparatus human body 11, the body sense camera 14 be connected with horizontal The Cloud Terrace 13; Mobile apparatus human body 11 comprises base 111, and mobile robot also comprises three omnidirectional driving wheels 15 be connected with base 111.
Fig. 2 shows the installation site schematic diagram of the human induction switch 12 of the mobile robot that the embodiment of the present invention provides, horizontal The Cloud Terrace 13 and body sense camera 14 relative movement robot body 11.
Fig. 3 shows the human body detection of the mobile robot that the embodiment of the present invention provides and the realization flow figure of tracking, and details are as follows:
In step S301, obtain the azimuth coverage of human body relative to described mobile robot by human induction switch array.
The embodiment of the present invention can be applicable in openr indoor environment or outdoor environment, in this no limit.
In embodiments of the present invention, human induction switch array is used for the azimuth coverage that preliminary quick detection human body occurs.
Preferably, described human induction switch array is made up of multiple human induction switch, and multiple described human induction switch is rotated around robot body and is uniformly distributed.
In embodiments of the present invention, multiple human induction switch is rotated around robot body 360 degree and is uniformly distributed installation.Such as, human induction switch array is made up of 4 human induction switchs, and 4 human induction switchs are rotated around robot body and are uniformly distributed, as shown in Figure 2.Suppose that the installation site of i-th human induction switch is α
i, search angle size is Δ, then the investigative range of this human induction switch is approximately
Preferably, described by human induction switch array obtain human body comprise relative to the azimuth coverage of described mobile robot: if having in human induction switch array described in current time and only have a described human induction switch described human body to be detected, then determine described azimuth coverage according to the investigative range of this human induction switch; If have in human induction switch array described in current time and only have two adjacent described human induction switchs described human body to be detected, then determine described azimuth coverage according to the common factor of the investigative range of these two adjacent described human induction switchs; If have at least three described human induction switchs described human body to be detected in human induction switch array described in current time, then described human body detected according to current time and a upper moment does not detect that the investigative range of the described human induction switch of described human body determines described azimuth coverage.
In embodiments of the present invention, the output signal of single human induction switch is 0 or 1, has people in the investigative range of 1 this human induction switch of expression, and 0 represents that the investigative range of this human induction switch is interior unmanned.Suppose that current time is t, a upper moment is t-1, human induction switch add up to n.The data that then current time human induction switch array reads in order are
the data that a upper moment human induction switch array reads in order are
consider the delay effect of human detection switch, judge the azimuth coverage of human body relative to mobile robot in the following manner: the first situation, if B
tin have and only have the switch value of a human induction switch to be 1, its residual value is 0, then think human body relative to the azimuth coverage of mobile robot to be switch value be 1 investigative range corresponding to human induction switch in, such as, the switch value of i-th human induction switch is 1, then azimuth coverage is θ ∈ [90 ° of i-60 °, 90 ° of i+60 °]; The second situation, if B
tin have and only have the switch value of two adjacent human induction switchs to be 1, its residual value is 0, then think human body relative to the azimuth coverage of mobile robot to be switch value be 1 the common factor of investigative range corresponding to two human induction switchs, such as, the switch value of i-th and the i-th+1 human induction switch is 1, then azimuth coverage is θ ∈ [90 ° of i+30 °, 90 ° of i+60 °]; The third situation, if B
tin have at least the switch value of three human induction switchs to be 1, then compare B
tand B
t-1, remove B
tin with B
t-1be the part of 1 simultaneously, then judge the azimuth coverage of human body relative to mobile robot according to the first situation and the second situation.When aforementioned three kinds of situations all do not meet, then think that azimuth coverage cannot directly judge, azimuth coverage is θ ∈ [0,360 °].
In step s 302, in described azimuth coverage, human body is found by body sense camera, described body sense camera is driven by horizontal The Cloud Terrace, and after the described human body of discovery, control described horizontal cloud platform rotation and follow the tracks of described human body to drive described body sense camera, to ensure that described human body is in the image of described body sense camera acquisition.
In embodiments of the present invention, body sense camera is connected with mobile apparatus human body by horizontal The Cloud Terrace, and horizontal The Cloud Terrace is used for control volume sense camera and rotates.Horizontal The Cloud Terrace is fixed on directly over mobile apparatus human body, distance ground certain altitude.By horizontal The Cloud Terrace carrying body sense camera, horizontal The Cloud Terrace can rotate independent of mobile apparatus human body by control volume sense camera, and horizontal The Cloud Terrace can control volume sense camera 360 degree rotation.In embodiments of the present invention, body sense camera is used for accurately locating human body, is rotated by horizontal The Cloud Terrace driving body sense camera, can control the center of the image that human body obtains at body sense camera all the time.Such as, the height on body sense camera distance ground can be 1.3 meters, and the shooting angle of body sense camera can be level, can the depth image of acquisition angles scope about 53 degree and coloured image, and effective shooting distance can be 0.5 ~ 4 meter, in this no limit.
Human detection and gesture recognition can be realized based on body sense camera.When specific implementation, Kinect somatosensory camera can be adopted to carry SDK (SoftwareDevelopmentKnit, SDK (Software Development Kit)) in the human posture recognition method that provides, or OpenNI increases income the human posture recognition method provided in function library.Said method can determine the three-dimensional space position of the relative body sense in each joint camera of multiple human body, gets the human body that distance mobile robot is nearest.Suppose with in the three-dimensional system of coordinate of the artificial initial point of mobile apparatus, the corresponding left and right directions of x-axis, the corresponding fore-and-aft direction of z-axis, the corresponding above-below direction of y-axis.The belly center of nearest human body is (x, y, z) relative to the volume coordinate of mobile robot, then the concrete position angle of human body relative movement robot is
the distance of human body relative movement robot is D=z.Wherein, the concrete position angle of human body relative movement robot can be the angle in human body relative movement robot dead ahead.
Preferably, in described azimuth coverage, human body is found by body sense camera, described body sense camera is driven by horizontal The Cloud Terrace and comprises: if described azimuth coverage meets first pre-conditioned, then control described body sense camera to rotate to the center position of described azimuth coverage, and control described horizontal cloud platform rotation and find described human body to drive described body sense camera; If described azimuth coverage does not meet described first pre-conditioned, then control described horizontal cloud platform rotation and find human body to drive described body sense camera in one week.
In embodiments of the present invention, it is the investigative range that certain human induction switch is corresponding that azimuth coverage meets the first pre-conditioned azimuth coverage that refers to, or azimuth coverage is the common factor of the investigative range that certain two adjacent human induction switchs are corresponding.If azimuth coverage meets first pre-conditioned, then control volume sense camera directly rotates the center position to azimuth coverage; If azimuth coverage does not meet first pre-conditioned, then the azimuth coverage that human body may exist is 0 ~ 360 degree, and therefore control volume sense camera rotates a circle.In the process that body sense camera rotates, the rotation speed constant of body sense camera.
As one embodiment of the present of invention, if obtain human body by human induction switch array to be greater than preset value relative to the execution time of the azimuth coverage of mobile robot or by the execution time of body sense camera searching human body, then think and exist extremely, mobile robot can send warning to Surveillance center.
In step 303, position in the image obtained at described body sense camera according to the rotational angle of described horizontal The Cloud Terrace and described human body, determine the concrete position angle of described human body relative to described mobile robot, and obtain the distance between described human body and described mobile robot by described body sense camera.
In step 304, according to described concrete position angle and described distance controlling, three omnidirectional driving wheels of mobile robot move.
Preferably, described according to described concrete position angle and described distance controlling three omnidirectional driving wheels motion of mobile robot be specially: three omnidirectional driving wheels motions according to described concrete position angle and described distance controlling, make moving to described concrete azimuthal direction of described mobile robot, and the distance controlled between described mobile robot and described human body is in pre-set interval.Wherein, pre-set interval can be 0.4 to 0.8 meter, in this no limit.
In embodiments of the present invention, adopt three omnidirectional driving wheels, three omnidirectional driving wheels are according to 120 degree of equidistantly distributions, give each omnidirectional driving wheel independently to drive simultaneously, mobile robot can be moved to any direction, achieving and follow the tracks of without dead angle, guaranteeing mobile robot not with losing detected human body.When specific implementation, mobile robot can be controlled and continue to follow the tracks of human body, until mobile robot is contracted to 0.8 meter with the distance of the human body detected, in this no limit.Fig. 4 shows the angle schematic diagram of the omnidirectional driving wheel 15 of mobile robot in the human body detection of the mobile robot that the embodiment of the present invention provides and tracking, body sense camera 14 and human body 21, and Fig. 4 also show mobile apparatus human body 11 and horizontal The Cloud Terrace 13.In the diagram, body sense camera 14 towards being positioned in the middle of two omnidirectional driving wheels, the angle of the line of the line of body sense camera 14 and human body 21 and two omnidirectional driving wheels 15 and human body 21 is respectively β
1and β
2.
Fig. 5 shows the schematic diagram of coordinate system of machine and world coordinate system in the human body detection of the mobile robot that the embodiment of the present invention provides and tracking.With reference to Fig. 5, in embodiments of the present invention, except world coordinate system (X
w, Y
w), set up an independently robot coordinate system (X in addition
m, Y
m).Robot coordinate system is parallel to surface level, and initial point is mobile robot center R.Motion model being presented as in robot coordinate system of mobile robot:
Wherein, the velocity vector of mobile robot is v
r=[x
r, y
r, ω
r]
t, x
r, y
rthe point-to-point speed of mobile robot, ω
rfor mobile robot's angular velocity of rotation, q is the omnidirectional driving wheel speed [q of mobile robot
1, q
2, q
3]
t, q
ifor the linear velocity of omnidirectional driving wheel, d is the distance of center to mobile robot center of omnidirectional driving wheel.The transformation matrix that robot coordinate is tied to world coordinate system is
Wherein, θ is the angle between world coordinate system and robot coordinate system's positive dirction.Therefore the motion model of mobile robot is in world coordinate system
Wherein, v
w=[x
w, y
w, ω
w]
tthe velocity vector of mobile robot in world coordinate system.Motion model based on above-mentioned mobile robot can distinguish the mode of motion of mobile robot: along the rectilinear motion of any direction, i.e. ω
r=0; Mobile robot rotates around its center position, i.e. x
r=y
r=0, ω
r≠ 0; The arcuate motion of robot can be divided into again translation circular arc (spin velocity is 0) and rotation circular arc (spin velocity is not 0).In Fig. 5,
for the angle of mobile robot's working direction and robot coordinate system, δ is the actual working direction of one of them omnidirectional driving wheel and the angle of its sense of rotation.
Should be understood that in embodiments of the present invention, the size of the sequence number of above-mentioned each process does not also mean that the priority of execution sequence, and the execution sequence of each process should be determined with its function and internal logic, and should not form any restriction to the implementation process of the embodiment of the present invention.
The embodiment of the present invention is by the azimuth coverage at human induction switch array preliminary quick detection human body place, accurately locate by horizontal The Cloud Terrace band kinetoplast sense camera and follow the tracks of human body again, combine the large-scale feature of human induction switch high sensitivity and the high-precision feature of body sense camera thus, achieve dynamic instrumentation, and improve the accuracy of human body location, accuracy is not less than 98%; Achieve 360 degree by three omnidirectional driving wheels to follow the tracks of without dead angle, the human body for faster movement also can realize 360 degree and follow the tracks of without dead angle, avoids with losing detected human body.
Fig. 6 shows the human body detection of the mobile robot that the embodiment of the present invention provides and the structured flowchart of tracking means, and this device can be mobile robot, also can for being built in the device in mobile robot.This device may be used for human body detection and the tracking of the mobile robot shown in service chart 1 to Fig. 5.For convenience of explanation, illustrate only the part relevant to the embodiment of the present invention.
With reference to Fig. 6, this device comprises:
Azimuth coverage acquiring unit 61, for obtaining the azimuth coverage of human body relative to described mobile robot by human induction switch array;
Human body finds unit 62, for finding human body by body sense camera in described azimuth coverage, described body sense camera is driven by horizontal The Cloud Terrace, and after the described human body of discovery, control described horizontal cloud platform rotation and follow the tracks of described human body to drive described body sense camera, to ensure that described human body is in the image of described body sense camera acquisition;
Concrete position angle and distance acquiring unit 63, for the position in the image that obtains at described body sense camera according to the rotational angle of described horizontal The Cloud Terrace and described human body, determine the concrete position angle of described human body relative to described mobile robot, and obtain the distance between described human body and described mobile robot by described body sense camera;
Tracking cell 64, for three omnidirectional driving wheel motions of mobile robot according to described concrete position angle and described distance controlling.
Preferably, described human induction switch array is made up of multiple human induction switch, and multiple described human induction switch is rotated around robot body and is uniformly distributed.
Preferably, described azimuth coverage acquiring unit 61 comprises:
First orientation angular region obtains subelement 611, if for having in human induction switch array described in current time and only having a described human induction switch described human body to be detected, then determine described azimuth coverage according to the investigative range of this human induction switch;
Second orientation angular region obtains subelement 612, if for having in human induction switch array described in current time and only having two adjacent described human induction switchs described human body to be detected, then determine described azimuth coverage according to the common factor of the investigative range of these two adjacent described human induction switchs;
Third party's parallactic angle scope obtains subelement 613, if for having at least three described human induction switchs described human body to be detected in human induction switch array described in current time, then described human body detected according to current time and a upper moment does not detect that the investigative range of the described human induction switch of described human body determines described azimuth coverage.
Preferably, described human body searching unit 62 comprises:
First finds subelement 621, if meet first pre-conditioned for described azimuth coverage, then control described body sense camera to rotate to the center position of described azimuth coverage, and control described horizontal cloud platform rotation and find described human body to drive described body sense camera;
Second finds subelement 622, if do not meet for described azimuth coverage described first pre-conditioned, then controls described horizontal cloud platform rotation and finds human body to drive described body sense camera in one week.
Preferably, described tracking cell 64 specifically for:
Three omnidirectional driving wheel motions according to described concrete position angle and described distance controlling, make moving to described concrete azimuthal direction of described mobile robot, and the distance controlled between described mobile robot and described human body are in pre-set interval.
The embodiment of the present invention by the azimuth coverage at human induction switch array preliminary quick detection human body place, is more accurately located by horizontal The Cloud Terrace band kinetoplast sense camera and is followed the tracks of human body, thus achieves dynamic instrumentation, and improves the accuracy of human body location; Achieving 360 degree by three omnidirectional driving wheels to follow the tracks of without dead angle, achieve and follow human motion fast, avoiding with losing detected human body.
Those of ordinary skill in the art can recognize, in conjunction with unit and the algorithm steps of each example of embodiment disclosed herein description, can realize with the combination of electronic hardware or computer software and electronic hardware.These functions perform with hardware or software mode actually, depend on application-specific and the design constraint of technical scheme.Professional and technical personnel can use distinct methods to realize described function to each specifically should being used for, but this realization should not thought and exceeds scope of the present invention.
Those skilled in the art can be well understood to, and for convenience and simplicity of description, the device of foregoing description and the specific works process of unit, with reference to the corresponding process in preceding method embodiment, can not repeat them here.
In several embodiments that the application provides, should be understood that disclosed apparatus and method can realize by another way.Such as, device embodiment described above is only schematic, such as, the division of described unit, be only a kind of logic function to divide, actual can have other dividing mode when realizing, such as multiple unit can in conjunction with or another system can be integrated into, or some features can be ignored, or do not perform.Another point, shown or discussed coupling each other or direct-coupling or communication connection can be by some interfaces, and the indirect coupling of unit or communication connection can be electrical, machinery or other form.
The described unit illustrated as separating component or can may not be and physically separates, and the parts as unit display can be or may not be physical location, namely can be positioned at a place, or also can be distributed in multiple network element.Some or all of unit wherein can be selected according to the actual needs to realize the object of the present embodiment scheme.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, also can be that the independent physics of unit exists, also can two or more unit in a unit integrated.
If described function using the form of SFU software functional unit realize and as independently production marketing or use time, can be stored in a computer read/write memory medium.Based on such understanding, the part of the part that technical scheme of the present invention contributes to prior art in essence in other words or this technical scheme can embody with the form of software product, this computer software product is stored in a storage medium, comprising some instructions in order to make a computer equipment (can be personal computer, server, or the network equipment etc.) perform all or part of step of method described in each embodiment of the present invention.And aforesaid storage medium comprises: USB flash disk, portable hard drive, ROM (read-only memory) (ROM, Read-OnlyMemory), random access memory (RAM, RandomAccessMemory), magnetic disc or CD etc. various can be program code stored medium.
The above; be only the specific embodiment of the present invention, but protection scope of the present invention is not limited thereto, is anyly familiar with those skilled in the art in the technical scope that the present invention discloses; change can be expected easily or replace, all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should described be as the criterion with the protection domain of claim.
Claims (10)
1. the human body detection of mobile robot and a tracking, is characterized in that, comprising:
The azimuth coverage of human body relative to described mobile robot is obtained by human induction switch array;
In described azimuth coverage, human body is found by body sense camera, described body sense camera is driven by horizontal The Cloud Terrace, and after the described human body of discovery, control described horizontal cloud platform rotation and follow the tracks of described human body to drive described body sense camera, to ensure that described human body is in the image of described body sense camera acquisition;
Position in the image obtained at described body sense camera according to the rotational angle of described horizontal The Cloud Terrace and described human body, determine the concrete position angle of described human body relative to described mobile robot, and obtain the distance between described human body and described mobile robot by described body sense camera;
Three omnidirectional driving wheel motions of mobile robot according to described concrete position angle and described distance controlling.
2. the method for claim 1, is characterized in that, described human induction switch array is made up of multiple human induction switch, and multiple described human induction switch is rotated around robot body and is uniformly distributed.
3. method as claimed in claim 1 or 2, is characterized in that, describedly obtains human body by human induction switch array and comprises relative to the azimuth coverage of described mobile robot:
If have in human induction switch array described in current time and only have a described human induction switch described human body to be detected, then determine described azimuth coverage according to the investigative range of this human induction switch;
If have in human induction switch array described in current time and only have two adjacent described human induction switchs described human body to be detected, then determine described azimuth coverage according to the common factor of the investigative range of these two adjacent described human induction switchs;
If have at least three described human induction switchs described human body to be detected in human induction switch array described in current time, then described human body detected according to current time and a upper moment does not detect that the investigative range of the described human induction switch of described human body determines described azimuth coverage.
4. the method for claim 1, is characterized in that, describedly in described azimuth coverage, finds human body by body sense camera, and described body sense camera is driven by horizontal The Cloud Terrace and comprises:
If described azimuth coverage meets first pre-conditioned, then control described body sense camera and rotate center position to described azimuth coverage, and control described horizontal cloud platform rotation and find described human body to drive described body sense camera;
If described azimuth coverage does not meet described first pre-conditioned, then control described horizontal cloud platform rotation and find human body to drive described body sense camera in one week.
5. the method for claim 1, is characterized in that, described according to described concrete position angle and described distance controlling three omnidirectional driving wheels motion of mobile robot be specially:
Three omnidirectional driving wheel motions according to described concrete position angle and described distance controlling, make moving to described concrete azimuthal direction of described mobile robot, and the distance controlled between described mobile robot and described human body are in pre-set interval.
6. the human body detection of mobile robot and a tracking means, is characterized in that, comprising:
Azimuth coverage acquiring unit, for obtaining the azimuth coverage of human body relative to described mobile robot by human induction switch array;
Human body finds unit, for finding human body by body sense camera in described azimuth coverage, described body sense camera is driven by horizontal The Cloud Terrace, and after the described human body of discovery, control described horizontal cloud platform rotation and follow the tracks of described human body to drive described body sense camera, to ensure that described human body is in the image of described body sense camera acquisition;
Concrete position angle and distance acquiring unit, for the position in the image that obtains at described body sense camera according to the rotational angle of described horizontal The Cloud Terrace and described human body, determine the concrete position angle of described human body relative to described mobile robot, and obtain the distance between described human body and described mobile robot by described body sense camera;
Tracking cell, for three omnidirectional driving wheel motions of mobile robot according to described concrete position angle and described distance controlling.
7. device as claimed in claim 6, it is characterized in that, described human induction switch array is made up of multiple human induction switch, and multiple described human induction switch is rotated around robot body and is uniformly distributed.
8. device as claimed in claims 6 or 7, it is characterized in that, described azimuth coverage acquiring unit comprises:
First orientation angular region obtains subelement, if for having in human induction switch array described in current time and only having a described human induction switch described human body to be detected, then determine described azimuth coverage according to the investigative range of this human induction switch;
Second orientation angular region obtains subelement, if for having in human induction switch array described in current time and only having two adjacent described human induction switchs described human body to be detected, then determine described azimuth coverage according to the common factor of the investigative range of these two adjacent described human induction switchs;
Third party's parallactic angle scope obtains subelement, if for having at least three described human induction switchs described human body to be detected in human induction switch array described in current time, then described human body detected according to current time and a upper moment does not detect that the investigative range of the described human induction switch of described human body determines described azimuth coverage.
9. device as claimed in claim 6, is characterized in that, described human body is found unit and comprised:
First finds subelement, if meet first pre-conditioned for described azimuth coverage, then controls described body sense camera and rotates center position to described azimuth coverage, and controls described horizontal cloud platform rotation and find described human body to drive described body sense camera;
Second finds subelement, if do not meet for described azimuth coverage described first pre-conditioned, then controls described horizontal cloud platform rotation and finds human body to drive described body sense camera in one week.
10. device as claimed in claim 6, is characterized in that, described tracking cell specifically for:
Three omnidirectional driving wheel motions according to described concrete position angle and described distance controlling, make moving to described concrete azimuthal direction of described mobile robot, and the distance controlled between described mobile robot and described human body are in pre-set interval.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510992646.7A CN105425806A (en) | 2015-12-25 | 2015-12-25 | Human body detection and tracking method and device of mobile robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510992646.7A CN105425806A (en) | 2015-12-25 | 2015-12-25 | Human body detection and tracking method and device of mobile robot |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105425806A true CN105425806A (en) | 2016-03-23 |
Family
ID=55504075
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510992646.7A Pending CN105425806A (en) | 2015-12-25 | 2015-12-25 | Human body detection and tracking method and device of mobile robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105425806A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105867371A (en) * | 2016-04-06 | 2016-08-17 | 北京小米移动软件有限公司 | Method and apparatus for controlling balance car to move |
| CN106054894A (en) * | 2016-07-05 | 2016-10-26 | 北京九星智元科技有限公司 | Robot accompanying system, robot accompanying method and robot trolley |
| CN106054897A (en) * | 2016-07-18 | 2016-10-26 | 旗瀚科技有限公司 | Robot capable of performing human body following |
| CN106155093A (en) * | 2016-07-22 | 2016-11-23 | 王威 | A kind of robot based on computer vision follows the system and method for human body |
| CN106335071A (en) * | 2016-11-14 | 2017-01-18 | 上海木爷机器人技术有限公司 | The robot and robot control method |
| CN108724177A (en) * | 2018-03-21 | 2018-11-02 | 北京猎户星空科技有限公司 | Task withdrawal control method, device, robot and storage medium |
| CN108733084A (en) * | 2018-03-21 | 2018-11-02 | 北京猎户星空科技有限公司 | Control method, device, robot and the storage medium of revolute |
| CN108733043A (en) * | 2017-09-01 | 2018-11-02 | 北京猎户星空科技有限公司 | robot movement control method and device |
| CN108737362A (en) * | 2018-03-21 | 2018-11-02 | 北京猎户星空科技有限公司 | Register method, device, equipment and storage medium |
| CN108942938A (en) * | 2018-07-27 | 2018-12-07 | 齐鲁工业大学 | A kind of four axis robotic arm motion control methods and system based on eeg signal |
| CN110045731A (en) * | 2019-03-26 | 2019-07-23 | 深圳先进技术研究院 | A kind of paths planning method, electronic device and computer readable storage medium |
| CN110312078A (en) * | 2019-08-02 | 2019-10-08 | 睿魔智能科技（深圳）有限公司 | A kind of automatic ring is around target image pickup method and system |
| CN110401799A (en) * | 2019-08-02 | 2019-11-01 | 睿魔智能科技（深圳）有限公司 | A kind of auto-tracking shooting method and system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2007015134A2 (en) * | 2005-08-01 | 2007-02-08 | Toyota Jidosha Kabushiki Kaisha | Moving body posture angle detecting apparatus |
| CN103646425A (en) * | 2013-11-20 | 2014-03-19 | 深圳先进技术研究院 | A method and a system for body feeling interaction |
| CN104102220A (en) * | 2014-07-11 | 2014-10-15 | 上海裕山信息科技有限公司 | Guide robot for monitoring human body position and control method thereof |
| CN104181926A (en) * | 2014-09-17 | 2014-12-03 | 上海畔慧信息技术有限公司 | Navigation control method of robot |
| CN104778726A (en) * | 2015-04-29 | 2015-07-15 | 深圳市保千里电子有限公司 | Motion trail tracing method and system based on human body characteristics |
| CN104977934A (en) * | 2015-07-09 | 2015-10-14 | 深圳中科智酷机器人科技有限公司 | Robot system and human body detection and tracking method based on robot system |
-
2015
- 2015-12-25 CN CN201510992646.7A patent/CN105425806A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2007015134A2 (en) * | 2005-08-01 | 2007-02-08 | Toyota Jidosha Kabushiki Kaisha | Moving body posture angle detecting apparatus |
| CN103646425A (en) * | 2013-11-20 | 2014-03-19 | 深圳先进技术研究院 | A method and a system for body feeling interaction |
| CN104102220A (en) * | 2014-07-11 | 2014-10-15 | 上海裕山信息科技有限公司 | Guide robot for monitoring human body position and control method thereof |
| CN104181926A (en) * | 2014-09-17 | 2014-12-03 | 上海畔慧信息技术有限公司 | Navigation control method of robot |
| CN104778726A (en) * | 2015-04-29 | 2015-07-15 | 深圳市保千里电子有限公司 | Motion trail tracing method and system based on human body characteristics |
| CN104977934A (en) * | 2015-07-09 | 2015-10-14 | 深圳中科智酷机器人科技有限公司 | Robot system and human body detection and tracking method based on robot system |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105867371A (en) * | 2016-04-06 | 2016-08-17 | 北京小米移动软件有限公司 | Method and apparatus for controlling balance car to move |
| CN105867371B (en) * | 2016-04-06 | 2019-05-21 | 北京小米移动软件有限公司 | Control the mobile method and device of balance car |
| CN106054894B (en) * | 2016-07-05 | 2019-04-09 | 北京九星智元科技有限公司 | A kind of robot adjoint system, adjoint method and robot car |
| CN106054894A (en) * | 2016-07-05 | 2016-10-26 | 北京九星智元科技有限公司 | Robot accompanying system, robot accompanying method and robot trolley |
| CN106054897A (en) * | 2016-07-18 | 2016-10-26 | 旗瀚科技有限公司 | Robot capable of performing human body following |
| CN106155093A (en) * | 2016-07-22 | 2016-11-23 | 王威 | A kind of robot based on computer vision follows the system and method for human body |
| CN106335071A (en) * | 2016-11-14 | 2017-01-18 | 上海木爷机器人技术有限公司 | The robot and robot control method |
| CN108733043B (en) * | 2017-09-01 | 2021-12-14 | 北京猎户星空科技有限公司 | Robot movement control method and device |
| CN108733043A (en) * | 2017-09-01 | 2018-11-02 | 北京猎户星空科技有限公司 | robot movement control method and device |
| CN108724177A (en) * | 2018-03-21 | 2018-11-02 | 北京猎户星空科技有限公司 | Task withdrawal control method, device, robot and storage medium |
| CN108737362A (en) * | 2018-03-21 | 2018-11-02 | 北京猎户星空科技有限公司 | Register method, device, equipment and storage medium |
| CN108733084A (en) * | 2018-03-21 | 2018-11-02 | 北京猎户星空科技有限公司 | Control method, device, robot and the storage medium of revolute |
| CN108942938A (en) * | 2018-07-27 | 2018-12-07 | 齐鲁工业大学 | A kind of four axis robotic arm motion control methods and system based on eeg signal |
| CN110045731A (en) * | 2019-03-26 | 2019-07-23 | 深圳先进技术研究院 | A kind of paths planning method, electronic device and computer readable storage medium |
| CN110045731B (en) * | 2019-03-26 | 2022-04-12 | 深圳市中科晟达互联智能科技有限公司 | Path planning method, electronic device and computer readable storage medium |
| CN110312078A (en) * | 2019-08-02 | 2019-10-08 | 睿魔智能科技（深圳）有限公司 | A kind of automatic ring is around target image pickup method and system |
| CN110401799A (en) * | 2019-08-02 | 2019-11-01 | 睿魔智能科技（深圳）有限公司 | A kind of auto-tracking shooting method and system |
| CN110401799B (en) * | 2019-08-02 | 2020-12-15 | 睿魔智能科技（深圳）有限公司 | Automatic tracking shooting method and system |
| WO2021022580A1 (en) * | 2019-08-02 | 2021-02-11 | 睿魔智能科技（深圳）有限公司 | Method and system for automatic tracking and photographing |
| WO2021022579A1 (en) * | 2019-08-02 | 2021-02-11 | 睿魔智能科技（深圳）有限公司 | Automatic surround photographing method and system for target |
| CN110312078B (en) * | 2019-08-02 | 2021-06-29 | 睿魔智能科技（深圳）有限公司 | Automatic surrounding target shooting method and system |
| US11622080B2 (en) | 2019-08-02 | 2023-04-04 | Remo Tech Co., Ltd. | Automatic surround photographing method and system for target |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105425806A (en) | Human body detection and tracking method and device of mobile robot | |
| CN110084272B (en) | Cluster map creation method and repositioning method based on cluster map and position descriptor matching | |
| TWI710798B (en) | Laser scanning system atteched on moving object, laser scanning method for laser scanner atteched on moving object, and laser scanning program | |
| CN102967305B (en) | Multi-rotor unmanned aerial vehicle pose acquisition method based on markers in shape of large and small square | |
| CN106092104A (en) | The method for relocating of a kind of Indoor Robot and device | |
| CN107846258A (en) | A kind of unmanned plane system of defense | |
| CN103324194B (en) | Based on the mobile robot positioning system of two-dimension code navigation band | |
| CN105865449A (en) | Laser and vision-based hybrid location method for mobile robot | |
| CN105184214A (en) | Sound source positioning and human face detection-based human body positioning method and system | |
| CN109737981B (en) | Unmanned vehicle target searching device and method based on multiple sensors | |
| CN103353758A (en) | Indoor robot navigation device and navigation technology thereof | |
| CN105844631A (en) | Method and device for positioning object | |
| CN103310442A (en) | Multi-frequency information fusion-based intelligent positioning system and method | |
| CN112085003A (en) | Automatic identification method and device for abnormal behaviors in public places and camera equipment | |
| CN111093907A (en) | Robust navigation of a robotic vehicle | |
| CN112928799A (en) | Automatic butt-joint charging method of mobile robot based on laser measurement | |
| CN111753694B (en) | Unmanned vehicle target searching system and method | |
| CN104199118A (en) | Searching and tracking integrated photoelectric detection system | |
| Deng et al. | Long-range binocular vision target geolocation using handheld electronic devices in outdoor environment | |
| CN106774295A (en) | A kind of distributed guided robot recharging system | |
| Brosh et al. | Accurate visual localization for automotive applications | |
| CN109116372B (en) | Target simulation method, system and device of infrared tracking device | |
| CN104330075A (en) | Rasterization polar coordinate system target positioning method | |
| Lv et al. | Absolute scale estimation of orb-slam algorithm based on laser ranging | |
| CN113358817A (en) | Gas source positioning device based on gas concentration gradient drive |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160323 |
|
| RJ01 | Rejection of invention patent application after publication |