CN107608342A - A kind of robotic vision system and its control method for mine rescue - Google Patents
A kind of robotic vision system and its control method for mine rescue Download PDFInfo
- Publication number
- CN107608342A CN107608342A CN201710609547.5A CN201710609547A CN107608342A CN 107608342 A CN107608342 A CN 107608342A CN 201710609547 A CN201710609547 A CN 201710609547A CN 107608342 A CN107608342 A CN 107608342A
- Authority
- CN
- China
- Prior art keywords
- image
- controller
- angle
- steering wheel
- rescue
- 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
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000006243 chemical reaction Methods 0.000 claims description 12
- 239000000463 material Substances 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 5
- 230000011218 segmentation Effects 0.000 description 3
- 230000000903 blocking effect Effects 0.000 description 2
- 230000034994 death Effects 0.000 description 2
- 231100000517 death Toxicity 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000015654 memory Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000000505 pernicious effect Effects 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
Abstract
A kind of robotic vision system and its control method for mine rescue, including rescue robot and corresponding vision and control system;Rescue robot is provided with environment information acquisition unit, driver element, connection and the auxiliary unit of collection site image, control process unit;Environment information acquisition unit includes camera, LED light source;Driver element includes direct current generator, steering wheel, driving wheel and crawler belt;Connection and auxiliary unit include axle sleeve, power supply, large U type frame, small U-shaped frame, case lid, controller box, emergency aid articles casing, relief supplies, cover latch and case lid rotating shaft;Control process unit includes controller;Vision and control system on controller include image capture module, image processing module, motor and servo driving module.The present invention can independently, quickly and accurately carry out the efficient identification of mine working scene, and can provide corresponding medical treatment and material relief.
Description
Technical field
The present invention relates to a kind of robotic vision system of mine rescue and its control method, belongs to mine safety appliance skill
Art field.
Background technology
The generation of coal mining accident not only causes huge property loss, and threat to life.How to carry out and efficiently rescue
It is always the major issue that we study to help work.Therefore, robot serves very big important, people in rescue work
Research to robot is also more and more deep, is continually striving to develop New function, new technology, it would be desirable to develop more work(
Rescue personnel can be replaced to complete dangerous and hardships rescue tasks.Mine emergency rescue robot can not only can be in narrow and small environment
Walking, and can substitute rescue personnel's entrance has landslide danger, high temperature, anoxic, full of smoke, pernicious gas to spread at any time
Deng adverse circumstances in carry out shooting to disaster scene environment.Therefore, there is an urgent need to a kind of rescuing machine for installing vision system
Device people, solve road and obstacle recognition under the poor environment of light, and blocked by image information transmission understanding ore deposit hole,
The problems such as deposit state, wrecked personnel amount in danger and distribution, so as to which rapid development most preferably rescues route and rescue mode.
The content of the invention
Based on problem above, the invention provides a kind of robotic vision system of mine rescue, solves in the prior art
Rescue that automaticity is low, and manual rescue's efficiency is low and the problems such as threat to life and solve existing mine emergency rescue robot and exist
Road and obstacle recognition under the poor environment of light, and transmitted by image information and understand the blocking of ore deposit hole, deposit shape
The problems such as state, wrecked personnel amount in danger and distribution;By the way that the methods of machine vision is applied on rescue robot, effectively
Ground avoids rescue personnel's injures and deaths, improves the automaticity and rescue efficiency of rescue, meets the needs of actual conditions.
The technical scheme is that:A kind of robotic vision system of mine rescue, including rescue robot and corresponding
Vision and control system;Rescue robot is provided with the environment information acquisition unit, driver element, company of collection site image
Connect and auxiliary unit, control process unit;Environment information acquisition unit includes two cameras, 2, two LED light sources 13;Driving is single
Member includes eight 14, four, direct current generator driving wheels 11 of steering wheel 8, eight and four crawler belts 12;Connection and auxiliary unit include eight
It is 4, four small U-shaped 7, two case lids 3 of frame of individual 10, two, axle sleeve power supply 17, four large U type frame, controller box 1, anxious
Rescue article casing 5, relief supplies 16, two play cover latch 9 and two case lid rotating shafts 6;Control process unit includes controller
15;Vision and control system on controller 15 include image capture module, image processing module, motor and servo driving mould
Block;
Center on the upside of the front end of the controller box 1 and emergency aid articles casing 5 is separately installed with camera 2, often
The underface of individual camera 2 is mounted on a LED light source 13;Two case lids 3 by two case lid rotating shafts 6 respectively with controller
Casing 1 and emergency aid articles casing 5 connect;Four large U type framves 4 and four small U-shaped frame 7 are used for fixing four steering wheels 8 and four
Ensure the adjustment of angle when individual steering wheel 8 is rotated;
Eight direct current generators 14 are connected by four axles and eight axle sleeves 10 with eight driving wheels 11;Four crawler belts 12
It is connected by gearing relationships with eight driving wheels 11;
Described two cover latches 9 are arranged on the outside of two case lids 3;Controller 15 and relief supplies 16 are respectively placed at
In controller box 1 and emergency aid articles casing 5;The back side that power supply 17 is placed in controller box 1 is used to power.
The control method of the described robotic vision system for mine rescue, methods described comprise the following steps that:
Step1, right case cover 3 is opened, relief supplies 16 are fitted into emergency aid articles casing 5;
Step2, left side case lid 3 is opened, open the start button of controller 15;
Step3, camera 2 and LED light source 13 proceed by image under the driving of image capture module in controller 15 and adopted
Collection and storage;
In the step Step3, it is as follows that image capture module carries out the step of IMAQ is with storage:
Step3.1, system initialization;
Step3.2, judge whether disk space is more than 1G:
If greater than 1G, then step Step3.3 is performed;Otherwise, return to step Step3.1;
Step3.3, judge whether remaining space is more than 0.5G:
If greater than 0.5G, then step Step3.4 is performed;Otherwise, return to step Step3.1;
Step3.4, open camera 2 and open LED light source 13;
Step3.5, the parameter for configuring camera 2 simultaneously adjust the brightness of LED light source 13;
Step3.6, the parameter configured using camera 2 shoot mine road image;The every width road image size collected
x1×y1All same;
Step3.7, with the name of the machine time of system the mine road image of shooting is stored.
Step4, the ore deposit collected using the image processing module in controller 15 to image capture module in controller 15
Mountain road image carries out path coordinate positioning;
In the step Step4, image processing module carry out path coordinate positioning the step of it is as follows:
Step4.1, road image is transformed to gray-scale map by cromogram;
Step4.2, histogram equalization is carried out to the gray level image after conversion;
Step4.3, image binaryzation processing is carried out to the image after histogram equalization;
Step4.4, the image progress image after binary conversion treatment is negated;
Step4.5, morphology opening operation is carried out to image of the inverted;
Step4.6, the calculating that connected domain size is carried out to the image after opening operation;
Step4.7, the area for asking for connected region and largest connected domain area index;
Step4.8, the processing result image for obtaining largest connected domain;
Step4.9, the centre coordinate (x for obtaining largest connected area image2, y2)。
The road elements of a fix that Step5, the image processing module in controller 15 determine, using in controller 15
Motor and servo driving module carry out the adjustment and driving of angle to direct current generator 14 and steering wheel 8;
In the step Step5, the step of motor and servo driving module carry out angle adjustment, is as follows:
Step5.1, by centre coordinate (x2, y2) centre coordinate (x obtained in X-axis is projected in image base X-axis2,
y1), and connect two coordinate points and form straight line l1;
Centre coordinate (x on Step5.2, acquisition entire image bottom X-axis1/ 2, y1), and connect (x1/ 2, y1) and (x2,
y2) form straight line l2;
Step5.3, obtain straight line l1With straight line l2Between angle theta;
Step5.4, judge x1Whether/2 be equal to x2:
If equal, step Step5.5 is performed;If unequal, step Step5.6 is performed;
Step5.5, four steering wheels (8) do not work;
Step5.6, judge x1Whether/2 be more than x2:
If it is greater, then perform step Step5.7;If it is not greater, then perform step Step5.8;
Step5.7, first, left side steering wheel 8 are turned left on the basis of angle, θ, and second, left side steering wheel 8 is with angle, θ/2
On the basis of turn left, the 3rd, left side steering wheel 8 is turned left on the basis of angle, θ/4, and the 4th, left side steering wheel 8 is with angle
Turned left on the basis of θ/8;
Step5.8, first, left side steering wheel 8 are turned right on the basis of angle, θ, and second, left side steering wheel 8 is with angle, θ/2
On the basis of turn right, the 3rd, left side steering wheel 8 is turned right on the basis of angle, θ/4, and the 4th, left side steering wheel 8 is with angle
Turned right on the basis of θ/8;
Step5.9, driving wheel 11 and crawler belt 12 are moved in the driving lower band mobile robot of direct current generator 14.
Step6, circulation perform step Step3~step Step5, until reaching scene of suing and labouring.
The beneficial effects of the invention are as follows:
(1) rescue robot is simple in construction, it is easy to accomplish.The use of multiple steering wheels, which can effectively be alleviated to bring in motion, shakes
It is dynamic;Caterpillar type of drive can realize steady obstacle detouring and pivot turn;The use of pulling type first aid casing can not only ensure
The stationarity of system operation, also can be that the more time is striven in rescue;
(2) solve to rescue that automaticity is low, and manual rescue's efficiency is low and the problems such as threat to life, passes through in the prior art
The methods of machine vision, is applied on rescue robot, is effectively prevented from rescue personnel's injures and deaths, improves the automation of rescue
Degree and rescue efficiency, meet the needs of actual conditions;
(3) road and obstacle recognition under the poor environment of light are solved, and is transmitted by image information and understands ore deposit hole
The problems such as blocking, deposit state, wrecked personnel amount in danger and distribution, so as to which rapid development most preferably rescues route and rescue
Method, the efficient identification of mine working scene can independently, be quickly and accurately carried out, and corresponding medical treatment and material can be provided
Relief.
Brief description of the drawings
Fig. 1 is robot architecture's schematic perspective view of the present invention;
Fig. 2 is robot architecture's uncovered top view of the present invention;
Fig. 3 is robot architecture's upward view of the present invention;
Fig. 4 is image capture module flow chart of the present invention on vision and control system;
Fig. 5 is image processing module flow chart of the present invention on vision and control system;
Fig. 6 is motor and servo driving block flow diagram of the present invention on vision and control system;
Fig. 7 is the sample schematic diagram 1 that the present invention is obtained using image capture module;
Fig. 8 is the result figure that the present invention is handled Fig. 7 using image processing module;
Fig. 9 is artificial segmentation standard result figure of the present invention on Fig. 7;
Figure 10 is the angular dimension figure after the present invention is handled Fig. 8 using motor and servo driving module;
Figure 11 is the sample schematic diagram 2 that the present invention is obtained using image capture module;
Figure 12 is the result figure that the present invention is handled Figure 11 using image processing module;
Figure 13 is artificial segmentation standard result figure of the present invention on Figure 11;
Figure 14 is the angular dimension figure after the present invention is handled Figure 12 using motor and servo driving module;
Figure 15 is the sample schematic diagram 3 that the present invention is obtained using image capture module;
Figure 16 is the result figure that the present invention is handled Figure 15 using image processing module;
Figure 17 is artificial segmentation standard result figure of the present invention on Figure 15;
Figure 18 is the angular dimension figure after the present invention is handled Figure 16 using motor and servo driving module.
Each label in figure:1- controller box, 2- cameras, 3- case lids, 4- large U type framves, 5- emergency aid articles casings, 6- case lids
Rotating shaft, the small U-shaped framves of 7-, 8- steering wheels, 9- cover latches, 10- axle sleeves, 11- driving wheels, 12- crawler belts, 13-LED light sources, 14- are straight
Flow motor, 15- controllers, 16- relief supplies, 17- power supplies.
Embodiment
Embodiment 1:As represented in figures 1 through 14, a kind of robotic vision system for mine rescue, including rescue robot
With corresponding vision and control system;Rescue robot is provided with the environment information acquisition unit of collection site image, driving list
Member, connection and auxiliary unit, control process unit;Environment information acquisition unit includes two cameras, 2, two LED light sources 13;
Driver element includes eight 14, four, direct current generator driving wheels 11 of steering wheel 8, eight and four crawler belts 12;Connection and auxiliary unit
Including eight 10, two, axle sleeve large U type framves of power supply 17, four 4, four small U-shaped frame 7, two case lids 3, controller cases
Body 1, emergency aid articles casing 5, relief supplies 16, two play cover latch 9 and two case lid rotating shafts 6;Control process unit includes control
Device 15 processed;Vision and control system on controller 15 include image capture module, image processing module, motor and steering wheel and driven
Dynamic model block;
Center on the upside of the front end of the controller box 1 and emergency aid articles casing 5 is separately installed with camera 2, often
The underface of individual camera 2 is mounted on a LED light source 13;Two case lids 3 by two case lid rotating shafts 6 respectively with controller
Casing 1 and emergency aid articles casing 5 connect;Four large U type framves 4 and four small U-shaped frame 7 are used for fixing four steering wheels 8 and four
Ensure the adjustment of angle when individual steering wheel 8 is rotated;
Eight direct current generators 14 are connected by four axles and eight axle sleeves 10 with eight driving wheels 11;Four crawler belts 12
It is connected by gearing relationships with eight driving wheels 11;
Described two cover latches 9 are arranged on the outside of two case lids 3;Controller 15 and relief supplies 16 are respectively placed at
In controller box 1 and emergency aid articles casing 5;The back side that power supply 17 is placed in controller box 1 is used to power.
The control method of the robotic vision system for mine rescue comprises the following steps that:
Step1, right case cover 3 is opened, relief supplies 16 are fitted into emergency aid articles casing 5;
Step2, left side case lid 3 is opened, open the start button of controller 15;
Step3, two cameras 2 and two LED light sources 13 start in controller 15 under the driving of image capture module into
Row IMAQ and storage;
In the step Step3, it is as follows that image capture module carries out the step of IMAQ is with storage:
Step3.1, system initialization;
Step3.2, judge whether disk space is more than 1G:
If greater than 1G, then step Step3.3 is performed;Otherwise, return to step Step3.1;
Step3.3, judge whether remaining space is more than 0.5G:
If greater than 0.5G, then step Step3.4 is performed;Otherwise, return to step Step3.1;
Step3.4, open two cameras 2 and open two LED light sources 13;
Step3.5, the parameter for configuring two cameras 2 and the brightness for adjusting two LED light sources 13;
Step3.6, the parameter configured using two cameras 2 shoot mine road image;The every width road image collected
Size x1×y1All same;
Step3.7, with the name of the machine time of system the mine road image of shooting is stored;
Step4, the ore deposit collected using the image processing module in controller 15 to image capture module in controller 15
Mountain road image carries out path coordinate positioning;
In the step Step4, image processing module carry out path coordinate positioning the step of it is as follows:
Step4.1, road image is transformed to gray-scale map by cromogram;
Step4.2, histogram equalization is carried out to the gray level image after conversion;
Step4.3, image binaryzation processing is carried out to the image after histogram equalization;
Step4.4, the image progress image after binary conversion treatment is negated;
Step4.5, morphology opening operation is carried out to image of the inverted;
Step4.6, the calculating that connected domain size is carried out to the image after opening operation;
Step4.7, the area for asking for connected region and largest connected domain area index;
Step4.8, the processing result image for obtaining largest connected domain;
Step4.9, the centre coordinate (x for obtaining largest connected area image2, y2);
The road elements of a fix that Step5, the image processing module in controller 15 determine, using in controller 15
Motor and servo driving module carry out the adjustment and driving of angle to eight direct current generators 14 and four steering wheels 8;
In the step Step5, the step of motor and servo driving module carry out angle adjustment, is as follows:
Step5.1, by centre coordinate (x2, y2) centre coordinate (x obtained in X-axis is projected in image base X-axis2,
y1), and connect two coordinate points and form straight line l1;
Centre coordinate (x on Step5.2, acquisition entire image bottom X-axis1/ 2, y1), and connect (x1/ 2, y1) and (x2,
y2) form straight line l2;
Step5.3, obtain straight line l1With straight line l2Between angle theta;
Step5.4, judge x1Whether/2 be equal to x2:
If equal, step Step5.5 is performed;If unequal, step Step5.6 is performed;
Step5.5, four steering wheels 8 do not work;
Step5.6, judge x1Whether/2 be more than x2:
If it is greater, then perform step Step5.7;If it is not greater, then perform step Step5.8;
Step5.7, first, left side steering wheel 8 are turned left on the basis of angle, θ, and second, left side steering wheel 8 is with angle, θ/2
On the basis of turn left, the 3rd, left side steering wheel 8 is turned left on the basis of angle, θ/4, and the 4th, left side steering wheel 8 is with angle
Turned left on the basis of θ/8;
Step5.8, first, left side steering wheel 8 are turned right on the basis of angle, θ, and second, left side steering wheel 8 is with angle, θ/2
On the basis of turn right, the 3rd, left side steering wheel 8 is turned right on the basis of angle, θ/4, and the 4th, left side steering wheel 8 is with angle
Turned right on the basis of θ/8;
Step5.9, eight driving wheels 11 and four crawler belts 12 enter in the driving lower band mobile robot of eight direct current generators 14
Row motion.
Step6, circulation perform step Step3~step Step5, until reaching scene of suing and labouring.
Embodiment 2:As represented in figures 1 through 14, a kind of robotic vision system and its control method for mine rescue,
To make the objects, technical solutions and advantages of the present invention definitely, below in conjunction with drawings and Examples, to the present invention
It is described in further detail.It is mine emergency rescue robot vision system provided by the present invention to implement rescue equipment used
Unite (stereogram, uncovered top and bottom perspective views are as Figure 1-3), controller environment is PC (Intel (R) Core (TM) 2
Duo CPU T6570@2.10GHz, 2GB internal memories, realize on Windows7-32bit LabView2014 platforms.In the present invention
The picture format of collection is defined as JPG forms, and resolution ratio was 1280 × 960 (as seen in figs. 7 and 11), and the target in figure is
The road in mine.
The robotic vision system for mine rescue is identical with the system in embodiment 1;
The control method of the robotic vision system for mine rescue comprises the following steps that:
Step1, right case cover 3 is opened, relief supplies 16 are fitted into emergency aid articles casing 5;
Step2, left side case lid 3 is opened, open the start button of controller 15;
Circulation 1:
Step3, two cameras 2 and two LED light sources 13 start in controller 15 under the driving of image capture module into
Row IMAQ and storage;The image capture module flow chart of vision and control system is as shown in Figure 4;
In the step Step3, it is as follows that image capture module carries out the step of IMAQ is with storage:
Step3.1, system initialization;
Step3.2, judge whether disk space is more than 1G:
Disk space is 2G, then performs step Step3.3;
Step3.3, judge whether remaining space is more than 0.5G:
Remaining disk space is 2G, perform step Step3.4;
Step3.4, open two cameras 2 and open two LED light sources 13;
Step3.5, the parameter for configuring two cameras 2 and the brightness for adjusting two LED light sources 13;
Step3.6, the parameter configured using two cameras 2 shoot mine road image;The chi of the road image 1 collected
Very little is 960 × 1280, and the result figure of collection is as shown in Figure 7;
Step3.7, with the name of the machine time of system the mine road image of shooting is stored;
Step4, the ore deposit collected using the image processing module in controller 15 to image capture module in controller 15
Mountain road image carries out path coordinate positioning;The image processing module flow chart of vision and control system is as shown in Figure 5;
In the step Step4, image processing module carry out path coordinate positioning the step of it is as follows:
Step4.1, road image is transformed to gray-scale map by cromogram;
Step4.2, histogram equalization is carried out to the gray level image after conversion;
Step4.3, image binaryzation processing is carried out to the image after histogram equalization;
Step4.4, the image progress image after binary conversion treatment is negated;
Step4.5, morphology opening operation is carried out to image of the inverted;
Step4.6, the calculating that connected domain size is carried out to the image after opening operation;
Step4.7, the area for asking for connected region and largest connected domain area index;
Step4.8, the processing result image for obtaining largest connected domain;The processing result image in largest connected domain such as Fig. 8 institutes
Show, the result can be seen that compared with the standard results manually split in Fig. 9:Processing result image and figure in Fig. 8
Standard results in 9 have higher similarity;
Step4.9, the centre coordinate (548,1072) for obtaining largest connected area image;
The road elements of a fix that Step5, the image processing module in controller 15 determine, using in controller 15
Motor and servo driving module carry out the adjustment and driving of angle to eight direct current generators 14 and four steering wheels 8;Vision and control
The motor and servo driving block flow diagram of system are as shown in Figure 6;
In the step Step5, the step of motor and servo driving module carry out angle adjustment, is as follows:
Step5.1, centre coordinate (548,1072) is projected in image base X-axis to the centre coordinate obtained in X-axis
(548,1280), and connect two coordinate points and form straight line l1;
Step5.2, obtain centre coordinate (480,1280) in the X-axis of entire image bottom, and connect (480,1280) with
(548,1072) straight line l is formed2;
Step5.3, obtain straight line l1With straight line l2Between angle theta=28 °;Using motor and servo driving module to Fig. 8
Angular dimension figure after being handled is as shown in Figure 10;
Step5.4, judge x1Whether/2 be equal to x2:
It is unequal, then perform step Step5.6;
Step5.6, judge x1Whether/2 be more than x2:
It is not more than, then performs step Step5.8;
Step5.8, first, left side steering wheel 8 are turned right on the basis of 28 °, and second, left side steering wheel 8 is on the basis of 14 °
Turn right, the 3rd, left side steering wheel 8 is turned right on the basis of 7 °, the 4th, left side steering wheel 8 on the basis of 3.5 ° of angle to
Turn right dynamic;
Step5.9, eight driving wheels 11 and four crawler belts 12 enter in the driving lower band mobile robot of eight direct current generators 14
Row motion.
Circulation 2:
Step3, two cameras 2 and two LED light sources 13 start in controller 15 under the driving of image capture module into
Row IMAQ and storage;
In the step Step3, it is as follows that image capture module carries out the step of IMAQ is with storage:
Step3.1, system initialization;
Step3.2, judge whether disk space is more than 1G:
Disk space is 2G, then performs step Step3.3;
Step3.3, judge whether remaining space is more than 0.5G:
Remaining disk space is 1.53G, perform step Step3.4;
Step3.4, open two cameras 2 and open two LED light sources 13;
Step3.5, the parameter for configuring two cameras 2 and the brightness for adjusting two LED light sources 13;
Step3.6, the parameter configured using two cameras 2 shoot mine road image;The chi of the road image 2 collected
Very little is 960 × 1280, and the result figure of collection is as shown in figure 11;
Step3.7, with the name of the machine time of system the mine road image of shooting is stored;
Step4, the ore deposit collected using the image processing module in controller 15 to image capture module in controller 15
Mountain road image carries out path coordinate positioning;
In the step Step4, image processing module carry out path coordinate positioning the step of it is as follows:
Step4.1, road image is transformed to gray-scale map by cromogram;
Step4.2, histogram equalization is carried out to the gray level image after conversion;
Step4.3, image binaryzation processing is carried out to the image after histogram equalization;
Step4.4, the image progress image after binary conversion treatment is negated;
Step4.5, morphology opening operation is carried out to image of the inverted;
Step4.6, the calculating that connected domain size is carried out to the image after opening operation;
Step4.7, the area for asking for connected region and largest connected domain area index;
Step4.8, the processing result image for obtaining largest connected domain;The processing result image in largest connected domain such as Figure 12 institutes
Show, the result can be seen that compared with the standard results manually split in Figure 13:Processing result image in Figure 12 with
Standard results in Figure 13 have higher similarity;
Step4.9, the centre coordinate (417,943) for obtaining largest connected area image;
The road elements of a fix that Step5, the image processing module in controller 15 determine, using in controller (15)
Motor and servo driving module eight direct current generators 14 and four steering wheels 8 are carried out with the adjustment and driving of angles;
In the step Step5, the step of motor and servo driving module carry out angle adjustment, is as follows:
Step5.1, centre coordinate (417,943) is projected in image base X-axis to the centre coordinate obtained in X-axis
(417,1280), and connect two coordinate points and form straight line l1;
Step5.2, obtain centre coordinate (480,1280) in the X-axis of entire image bottom, and connect (480,1280) with
(417,943) straight line l is formed2;
Step5.3, obtain straight line l1With straight line l2Between angle theta=32 °;Using motor and servo driving module to figure
12 handled after angular dimension figure it is as shown in figure 14;
Step5.4, judge x1Whether/2 be equal to x2:
It is unequal, then perform step Step5.6;
Step5.6, judge x1Whether/2 be more than x2:
It is more than, then performs step Step5.7;
Step5.7, Step5.7, first, left side steering wheel 8 are turned left on the basis of 32 °, second, left side steering wheel 8 with
Turned left on the basis of 16 °, the 3rd, left side steering wheel 8 is turned left on the basis of 8 °, and the 4th, left side steering wheel 8 is with 4 ° for base
Standard turns left;
Step5.9, eight driving wheels 11 and four crawler belts 12 enter in the driving lower band mobile robot of eight direct current generators 14
Row motion.
Circulation 3:
Step3, two cameras 2 and two LED light sources 13 start in controller 15 under the driving of image capture module into
Row IMAQ and storage;
In the step Step3, it is as follows that image capture module carries out the step of IMAQ is with storage:
Step3.1, system initialization;
Step3.2, judge whether disk space is more than 1G:
Disk space is 2G, then performs step Step3.3;
Step3.3, judge whether remaining space is more than 0.5G:
Remaining disk space is 0.8G, perform step Step3.4;
Step3.4, open two cameras 2 and open two LED light sources 13;
Step3.5, the parameter for configuring two cameras 2 and the brightness for adjusting two LED light sources 13;
Step3.6, the parameter configured using two cameras 2 shoot mine road image;The chi of the road image 2 collected
Very little is 960 × 1280, and the result figure of collection is as shown in figure 15;
Step3.6, with the name of the machine time of system the mine road image of shooting is stored;
Step4, the ore deposit collected using the image processing module in controller 15 to image capture module in controller 15
Mountain road image carries out path coordinate positioning;
In the step Step4, image processing module carry out path coordinate positioning the step of it is as follows:
Step4.1, road image is transformed to gray-scale map by cromogram;
Step4.2, histogram equalization is carried out to the gray level image after conversion;
Step4.3, image binaryzation processing is carried out to the image after histogram equalization;
Step4.4, the image progress image after binary conversion treatment is negated;
Step4.5, morphology opening operation is carried out to image of the inverted;
Step4.6, the calculating that connected domain size is carried out to the image after opening operation;
Step4.7, the area for asking for connected region and largest connected domain area index;
Step4.8, the processing result image for obtaining largest connected domain;The processing result image in largest connected domain such as Figure 16 institutes
Show, the result can be seen that compared with the standard results manually split in Figure 17:Processing result image in Figure 16 with
Standard results in Figure 17 have higher similarity;
Step4.9, the centre coordinate (480,785) for obtaining largest connected area image;
The road elements of a fix that Step5, the image processing module in controller 15 determine, using in controller 15
Motor and servo driving module carry out the adjustment and driving of angle to eight direct current generators 14 and four steering wheels 8;
In the step Step5, the step of motor and servo driving module carry out angle adjustment, is as follows:
Step5.1, centre coordinate (480,785) is projected in image base X-axis to the centre coordinate obtained in X-axis
(480,1280), and connect two coordinate points and form straight line l1;
Step5.2, obtain centre coordinate (480,1280) in the X-axis of entire image bottom, and connect (480,1280) with
(417,785) straight line l is formed2;
Step5.3, obtain straight line l1With straight line l2Between angle theta=0 °;Using motor and servo driving module to Figure 16
Angular dimension figure after being handled is as shown in figure 18;
Step5.4, judge x1Whether/2 be equal to x2:
It is equal, then perform step Step5.5;
Step5.5, four steering wheels 8 do not work;
Step5.9, eight driving wheels 11 and four crawler belts 12 enter in the driving lower band mobile robot of eight direct current generators 14
Row motion.
Step6, circulation perform step Step3~step Step5, until reaching scene of suing and labouring.
The embodiment of the present invention is explained in detail above in conjunction with figure, but the present invention is not limited to above-mentioned reality
Mode is applied, in those of ordinary skill in the art's possessed knowledge, the premise of present inventive concept can also not departed from
It is lower that various changes can be made.
Claims (5)
- A kind of 1. robotic vision system for mine rescue, it is characterised in that:Including rescue robot and corresponding vision And control system;Rescue robot is provided with environment information acquisition unit, driver element, connection and the auxiliary of collection site image Unit, control process unit;Environment information acquisition unit includes two cameras (2), two LED light sources (13);Driver element bag Include eight direct current generators (14), four steering wheels (8), eight driving wheels (11) and four crawler belts (12);Connection and auxiliary unit bag Include eight axle sleeves (10), two power supplies (17), four large U type framves (4), four small U-shaped frame (7), two case lids (3), control Device casing (1) processed, emergency aid articles casing (5), relief supplies (16), two play cover latch (9) and two case lid rotating shafts (6);Control Processing unit processed includes controller (15);Vision and control system on controller (15) include image capture module, at image Manage module, motor and servo driving module;Center on the upside of the front end of the controller box (1) and emergency aid articles casing (5) is separately installed with camera (2), A LED light source (13) is mounted on immediately below each camera (2);Two case lids (3) pass through two case lid rotating shafts (6) difference It is connected with controller box (1) and emergency aid articles casing (5);Four large U type framves (4) and four small U-shaped frame (7) are used for fixing four Individual steering wheel (8) and the adjustment for ensureing angle when four steering wheels (8) are rotated;Eight direct current generators (14) are connected by four axles and eight axle sleeves (10) with eight driving wheels (11);Four crawler belts (12) it is connected by gearing relationships with eight driving wheels (11);Described two cover latches (9) are arranged on the outside of two case lids (3);Controller (15) and relief supplies (16) are pacified respectively It is placed in controller box (1) and emergency aid articles casing (5);Use at the back side that power supply (17) is placed in controller box (1) In power supply.
- A kind of 2. control method of the robotic vision system for mine rescue described in claim 1, it is characterised in that:Institute State comprising the following steps that for method:Step1, right case cover (3) is opened, relief supplies (16) are fitted into emergency aid articles casing (5);Step2, left side case lid (3) is opened, open the start button of controller (15);Step3, camera (2) and LED light source (13) proceed by image in controller (15) under the driving of image capture module Collection and storage;Step4, the ore deposit collected using the image processing module in controller (15) to image capture module in controller (15) Mountain road image carries out path coordinate positioning;The road elements of a fix that Step5, the image processing module in controller (15) determine, using in controller (15) Motor and servo driving module carry out the adjustment and driving of angle to direct current generator (14) and steering wheel (8);Step6, circulation perform step Step3~step Step5, until reaching scene of suing and labouring.
- 3. the control method of the robotic vision system according to claim 2 for mine rescue, it is characterised in that:Institute State in step Step3, it is as follows that image capture module carries out the step of IMAQ is with storage:Step3.1, system initialization;Step3.2, judge whether disk space is more than 1G:If greater than 1G, then step Step3.3 is performed;Otherwise, return to step Step3.1;Step3.3, judge whether remaining space is more than 0.5G:If greater than 0.5G, then step Step3.4 is performed;Otherwise, return to step Step3.1;Step3.4, open camera (2) and open LED light source (13);Step3.5, the parameter for configuring camera (2) simultaneously adjust the brightness of LED light source (13);Step3.6, the parameter shooting mine road image using camera (2) configuration;The every width road image size x collected1× y1All same;Step3.7, with the name of the machine time of system the mine road image of shooting is stored.
- 4. the robotic vision system and its control method according to claim 2 for mine rescue, it is characterised in that: In the step Step4, image processing module carry out path coordinate positioning the step of it is as follows:Step4.1, road image is transformed to gray-scale map by cromogram;Step4.2, histogram equalization is carried out to the gray level image after conversion;Step4.3, image binaryzation processing is carried out to the image after histogram equalization;Step4.4, the image progress image after binary conversion treatment is negated;Step4.5, morphology opening operation is carried out to image of the inverted;Step4.6, the calculating that connected domain size is carried out to the image after opening operation;Step4.7, the area for asking for connected region and largest connected domain area index;Step4.8, the processing result image for obtaining largest connected domain;Step4.9, the centre coordinate (x for obtaining largest connected area image2, y2)。
- 5. the robotic vision system and its control method according to claim 2 for mine rescue, it is characterised in that: In the step Step5, the step of motor and servo driving module carry out angle adjustment, is as follows:Step5.1, by centre coordinate (x2, y2) centre coordinate (x obtained in X-axis is projected in image base X-axis2, y1), and even Connect two coordinate points and form straight line l1;Centre coordinate (x on Step5.2, acquisition entire image bottom X-axis1/ 2, y1), and connect (x1/ 2, y1) and (x2, y2) shape Be in line l2;Step5.3, obtain straight line l1With straight line l2Between angle theta;Step5.4, judge x1Whether/2 be equal to x2:If equal, step Step5.5 is performed;If unequal, step Step5.6 is performed;Step5.5, four steering wheels (8) do not work;Step5.6, judge x1Whether/2 be more than x2:If it is greater, then perform step Step5.7;If it is not greater, then perform step Step5.8;Step5.7, first, left side steering wheel (8) are turned left on the basis of angle, θ, and second, left side steering wheel (8) is with angle, θ/2 On the basis of turn left, the 3rd, left side steering wheel (8) is turned left on the basis of angle, θ/4, and the 4th, left side steering wheel (8) is with angle Degree turns left on the basis of θ/8;Step5.8, first, left side steering wheel (8) are turned right on the basis of angle, θ, and second, left side steering wheel (8) is with angle, θ/2 On the basis of turn right, the 3rd, left side steering wheel (8) is turned right on the basis of angle, θ/4, and the 4th, left side steering wheel (8) is with angle Degree turns right on the basis of θ/8;Step5.9, driving wheel (11) and crawler belt (12) are moved in the driving lower band mobile robot of direct current generator (14).
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710609547.5A CN107608342A (en) | 2017-07-25 | 2017-07-25 | A kind of robotic vision system and its control method for mine rescue |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710609547.5A CN107608342A (en) | 2017-07-25 | 2017-07-25 | A kind of robotic vision system and its control method for mine rescue |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107608342A true CN107608342A (en) | 2018-01-19 |
Family
ID=61059617
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710609547.5A Pending CN107608342A (en) | 2017-07-25 | 2017-07-25 | A kind of robotic vision system and its control method for mine rescue |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107608342A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110162036A (en) * | 2019-04-09 | 2019-08-23 | 中国矿业大学 | A kind of development machine Camera calibration system and method |
CN112104976A (en) * | 2020-09-16 | 2020-12-18 | 威海腾罡智能科技有限公司 | Control system and control method of multifunctional first-aid robot |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020049530A1 (en) * | 1998-04-15 | 2002-04-25 | George Poropat | Method of tracking and sensing position of objects |
CN202264834U (en) * | 2011-10-24 | 2012-06-06 | 常熟理工学院 | Obstacle-surmounting rescue vehicle |
CN103147789A (en) * | 2013-03-07 | 2013-06-12 | 中国矿业大学 | System and method for controlling underground coal mine rescue robot |
CN103400392A (en) * | 2013-08-19 | 2013-11-20 | 山东鲁能智能技术有限公司 | Binocular vision navigation system and method based on inspection robot in transformer substation |
CN106909142A (en) * | 2016-11-29 | 2017-06-30 | 攀枝花市九鼎智远知识产权运营有限公司 | A kind of unmanned mine car system and method in underground based on image processing techniques |
-
2017
- 2017-07-25 CN CN201710609547.5A patent/CN107608342A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020049530A1 (en) * | 1998-04-15 | 2002-04-25 | George Poropat | Method of tracking and sensing position of objects |
CN202264834U (en) * | 2011-10-24 | 2012-06-06 | 常熟理工学院 | Obstacle-surmounting rescue vehicle |
CN103147789A (en) * | 2013-03-07 | 2013-06-12 | 中国矿业大学 | System and method for controlling underground coal mine rescue robot |
CN103400392A (en) * | 2013-08-19 | 2013-11-20 | 山东鲁能智能技术有限公司 | Binocular vision navigation system and method based on inspection robot in transformer substation |
CN106909142A (en) * | 2016-11-29 | 2017-06-30 | 攀枝花市九鼎智远知识产权运营有限公司 | A kind of unmanned mine car system and method in underground based on image processing techniques |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110162036A (en) * | 2019-04-09 | 2019-08-23 | 中国矿业大学 | A kind of development machine Camera calibration system and method |
CN112104976A (en) * | 2020-09-16 | 2020-12-18 | 威海腾罡智能科技有限公司 | Control system and control method of multifunctional first-aid robot |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106607907B (en) | A kind of moving-vision robot and its investigating method | |
CN104843176B (en) | Unmanned-gyroplane system used for automatic-inspection of bridges and tunnels and navigation method | |
CN106873566A (en) | A kind of unmanned logistic car based on deep learning | |
CN101774170B (en) | Nuclear power plant working robot and control system thereof | |
CN105955279B (en) | A kind of method for planning path for mobile robot and device based on image vision | |
CN107608342A (en) | A kind of robotic vision system and its control method for mine rescue | |
CN205075054U (en) | A robot for high -risk operation | |
CN106393049A (en) | Robot used for high risk operation | |
CN113821040A (en) | Robot with depth vision camera and laser radar integrated navigation | |
CN106170370A (en) | The robotic vehicle remotely controlled | |
CN207037466U (en) | A kind of visual detection robot system applied to underground coal mine | |
CN109324649A (en) | A kind of compound cruising inspection system of substation and method | |
CN106371442A (en) | Tensor-product-model-transformation-based mobile robot control method | |
CN116215697A (en) | Grain sampling system | |
CN108873895A (en) | Drop intelligent patrol detection vehicle in road surface | |
US10427534B2 (en) | Infrared automobile charging system | |
CN106054911A (en) | Quadrocopter capable of gesture identification operation and method thereof | |
CN114115282B (en) | Unmanned device of mine auxiliary transportation robot and application method thereof | |
CN106886758A (en) | Based on insect identifying device and method that 3 d pose is estimated | |
CN111470058B (en) | Unmanned aerial vehicle transfer station is patrolled and examined to battery electric power based on accurate descending of infrared dot matrix | |
CN107756402A (en) | A kind of intelligent avoidance grasping system based on deep learning | |
CN113101156A (en) | Blind guiding robot based on neural network | |
RU185354U1 (en) | Ultra-small mobile robotic platform | |
US20210031644A1 (en) | Charging system for transportation vehicles | |
Rivera et al. | Autonomous Control of an Electric Vehicle by Computer Vision Applied to the Teaching–Learning Process |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180119 |
|
RJ01 | Rejection of invention patent application after publication |