CN102278977B - Infrared visual positioning system of robotic fish - Google Patents
Infrared visual positioning system of robotic fish Download PDFInfo
- Publication number
- CN102278977B CN102278977B CN2011102235722A CN201110223572A CN102278977B CN 102278977 B CN102278977 B CN 102278977B CN 2011102235722 A CN2011102235722 A CN 2011102235722A CN 201110223572 A CN201110223572 A CN 201110223572A CN 102278977 B CN102278977 B CN 102278977B
- Authority
- CN
- China
- Prior art keywords
- infrared
- image
- beacon light
- machine fish
- light beacon
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 241000251468 Actinopterygii Species 0.000 title claims abstract description 75
- 230000000007 visual effect Effects 0.000 title abstract description 5
- 239000011159 matrix material Substances 0.000 claims abstract description 28
- 238000000034 method Methods 0.000 claims abstract description 17
- 238000004891 communication Methods 0.000 claims abstract description 4
- 230000008569 process Effects 0.000 claims abstract description 4
- 230000004807 localization Effects 0.000 claims description 12
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 3
- 238000013341 scale-up Methods 0.000 claims description 2
- 238000000926 separation method Methods 0.000 claims description 2
- 230000003595 spectral effect Effects 0.000 claims description 2
- 238000001514 detection method Methods 0.000 abstract description 8
- 238000010191 image analysis Methods 0.000 abstract 1
- 238000004519 manufacturing process Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 8
- 238000011161 development Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 239000011148 porous material Substances 0.000 description 3
- 206010034960 Photophobia Diseases 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 208000013469 light sensitivity Diseases 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 206010070834 Sensitisation Diseases 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000007630 basic procedure Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000005352 clarification Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 210000001624 hip Anatomy 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000011664 nicotinic acid Substances 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
- 230000008313 sensitization Effects 0.000 description 1
- 239000007921 spray Substances 0.000 description 1
- 230000009182 swimming Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 239000003643 water by type Substances 0.000 description 1
- 238000003466 welding Methods 0.000 description 1
Images
Landscapes
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an infrared visual positioning system of robotic fish. The system comprises an infrared light beacon, a camera, an image acquisition card, an image analysis unit, a light beacon detection unit and a visual positioning unit, wherein the infrared light beacon consists of infrared points which are arranged on the back of the robotic fish; the camera is used for capturing the image information of the infrared light beacon; the image acquisition card is used for acquiring an image which is shot by the camera in real time; the image acquisition unit pre-processes the image which is acquired by the image acquisition card, separates the background of the image from infrared point pixels and gathers the infrared point pixels into a communication point field; for each communication point field, the light beacon detection unit detects an image point field of a single infrared point, detects a light beacon which consists of a plurality of infrared points on the back of each robotic fish by using a hierarchical clustering method, compares the detected light beacon with a preset light beacon mode, and records image coordinates of the detected light beacon if the detected light beacon corresponds to the preset light beacon mode; and the visual positioning unit calculates world coordinates of the light beacon according to a homography matrix and the image coordinates. The system is simple in structure, convenient to manufacture and low in cost.
Description
Technical field
The present invention belongs to computer vision and field of photoelectric technology, is specifically related to the infrared vision positioning system of a kind of machine fish.
Background technology
Along with the development of Robotics, bionic machine fish more and more receives the lot of domestic and foreign research organizations pay much.Development machine fishing gear has realistic meaning widely, utilizes them can survey ocean water quality, exploration waters landform or the like.The machine fish also has bright development prospect aspect amusement, and for example in the exhibition of the machine fish in science and technology center, aquarium: many machine fishes such as chase, push the ball, head a ball, tour around at various programs at aquacade.
In order to control machine fish autonomous swimming in the water, must detect the posture information of machine fish in real time, so the location of machine fish is very basis, also very crucial technology to accomplish each task.At present numerous patents of invention relevant with the machine fish all only lay particular emphasis on electromechanical structure and the control method of machine fish, and the description that the machine fish is located seldom.The machine fish employing GPS realization location navigation that is used to survey water quality of BJ University of Aeronautics & Astronautics's development, for the amusement type machine fish in the indoor environment, the GPS localization method is then infeasible.The autonomous machine fish of Peking University's development relies on the CMOS camera that is positioned at fish head top that environmental data is gathered, and this scheme can be followed the tracks of colored water polo, but can't realize the accurate location of machine fish.The machine fish of Institute of Automation Research of CAS's complication system laboratory development attaches the color block mark at the machine fish dorsal, detects the color lump mark through overall video camera and carries out vision localization.Color block has changed the original outward appearance of machine fish, influences its sight.Owing to disturbed by the water surface glistening light of waves, the color block characteristic can not accurately detect in addition, so this localization method is stable and adaptability is very poor.
Summary of the invention
The objective of the invention is for avoiding above-mentioned existing in prior technology weak point, a kind of new infrared vision positioning system that is applied to the machine fish is provided, realize real-time, accurate location the machine fish.
The infrared vision positioning system of machine fish of the present invention comprises: infrared beacon light, form by the infrared point that is installed in the machine fish dorsal; Video camera is lifted on above the pond at machine fish place, is used to catch infrared lamp target image information; Image pick-up card is used for obtaining in real time the image that video camera is taken; Image analyzing unit, the image that image pick-up card is obtained carries out pre-service, with the background and the infrared point pixel separation of image, and the infrared point pixel is gathered into a connectivity points territory; The beacon light detecting unit; Detect the wherein picture point territory of single infrared point to each connectivity points territory; The beacon light that a plurality of infrared point that adopt the hierarchical clustering method to detect every machine fish back are formed; Detected beacon light and predetermined beacon light pattern are compared,, then write down the image coordinate of this detected beacon light if can be corresponding with predetermined beacon light pattern; The vision localization unit calculates the world coordinates of beacon light according to homography matrix and said image coordinate.
Utilize system and method for the present invention that the machine fish is carried out vision localization; Make the simple in structure, easy to make, with low cost of system; The infrared beacon light that the present invention adopts is very little; Influence the original outward appearance of machine fish hardly, location Calculation of the present invention is not disturbed by surround lighting and ripples accurately, fast.
Description of drawings
Fig. 1 is the infrared vision positioning system structural representation of machine fish of the present invention;
Fig. 2 installs the synoptic diagram of SMD infrared-emitting diode for the machine fish dorsal in the infrared vision positioning system of machine fish of the present invention;
Fig. 3 is for confirming the process flow diagram of homography matrix in the infrared vision positioning system of machine fish of the present invention;
The three kind infrared beacon light pattern diagram of Fig. 4 for adopting in the infrared vision positioning system of machine fish of the present invention;
Fig. 5 is the workflow diagram of the infrared vision positioning system of machine fish of the present invention;
The synoptic diagram of Fig. 6 after for infrared image processing captured in the infrared vision positioning system of machine fish of the present invention;
Fig. 7 is detection and Identification infrared lamp target process flow diagram in the infrared vision positioning system of machine fish of the present invention.
Embodiment
Below, the present invention is described further in conjunction with accompanying drawing through specific embodiment.
Fig. 1 is a system architecture synoptic diagram of the present invention, and the main body of system consists of machine fish 1, thermal camera 3, computing machine 5 and is installed in the infrared beacon light 2 on the machine fish 1.
Machine fish 1 moves about in the pond.Infrared beacon light 2 can be installed in the machine fish dorsal, is made up of several SMD infrared-emitting diodes.The spectral centroid wavelength of infrared-emitting diode is 850nm.With reference to Fig. 1, the beacon light 2 that three pores of the above-head of machine fish 1 constitute for the paster infrared-emitting diode, its wavelength is 850nm.Can evoke a lot of sprays when machine fish 1 moves about in water, glistening light of waves flicker is selected with infrared light as clarification of objective just for fear of the interference of these visible lights.Because SMD infrared-emitting diode volume is very little, being attached to the machine fish dorsal as infrared light supply influences its original outward appearance hardly; And the light wave emission angle of SMD infrared-emitting diode is very big, near 180 degree, thereby utilizes the video camera that is lifted on the top to catch the image information of beacon light.The wavelength of normally used infrared-emitting diode comprises two kinds of 850nm and 940nm, because video camera CCD is higher than the light sensitivity to the 940nm infrared light to the light sensitivity of 850nm infrared light, so the present invention preferably uses the 850nm infrared lamp to make beacon light.
IMAQ card connection on video camera 3 and the computing machine 5; Image pick-up card obtains the image of shot by camera in real time, and image analyzing unit, beacon light detecting unit, the infrared lamp target vision localization unit of passing to computing machine calculate to carry out graphical analysis, beacon light detection and vision localization.Location Calculation result passes to control module again; Control module calculates controlled quentity controlled variable according to the posture information of mission requirements and machine fish, and the mode through radio communication sends to electromechanical module in the machine fish body to realize the effective control to the machine fish with control information then.
Fig. 2 has provided the concrete scheme of installation of beacon light, passes machine fish 1 shell with rigidity pin 6, in machine fish shell, with lead 7 the rigidity pin is connected into closed circuit.SMD infrared-emitting diode 2 is welded on the rigidity pin that exposes shell.Three infrared lamps all on machine fish ridge line, constitute a kind of beacon light pattern.
World coordinates is based upon on the water surface of pond.Because the stationkeeping of video camera 3; And dried up height is much larger than the depth variable quantity of machine fish 1 when the water surface moves about; Therefore the position of infrared beacon light 2 on the water surface is the projective rejection of plane to the plane with the projection relation of video camera 3 imaging planes formation; Be the homography matrix transformation relation, formulae express is suc as formula shown in 1.
In the following formula, H is a homography matrix, m
i(i=1,2 ..., 9) be the matrix element of homography matrix, s
iBe scale-up factor, (u
i, v
i) be the coordinate of beacon light in image, (x
i, y
i) be the world coordinates of beacon light at the water surface.In case camera position confirms that homography matrix is just confirmed, the just image coordinate and the world coordinates of beacon light of change.The scaling method of homography matrix is following: after installing video camera 3, through four definite gauge points of artificial layout on the limit, pond, utilize formula 1 calculated off-line to go out homography matrix.Fig. 3 has provided the basic procedure of demarcating homography matrix, specifically comprises: S301 detects four gauge points arranging in advance in image; The world coordinates of four gauge points of the artificial input of S302; S303 utilizes the homography matrix formula to go out homography matrix by the image coordinate data and the world coordinates data computation of four pairs of known points then, and the result is stored in the corresponding document.Concrete steps are following: formula (1) is expanded into three equations,
Divided by the 3rd equation, second equation is divided by the 3rd equation with first equation, and s disappears
iObtain two equations:
If the n on the known object plane point known their volume coordinate (x
i, y
i) (i=1,2 ..., n), and known their picture point coordinate (u
i, v
i) (i=1,2 ..., n), then we have 2n the linear equation about the homography matrix element, write out these equations with matrix form below:
Can make m
9=1, make that equation coefficient is a matrix K, variable is M, is worth to be U, and then equation can be written as KM=U, and the least square solution of equation is:
M＝(K
TK)
-1K
TU (5)
There are 8 unknown numbers, can pass through four pairs of some solving equations, thereby obtain each matrix element value of homography matrix.
Fig. 4 is the vertical view of machine fish, has provided three kinds of beacon light patterns.Three kinds of public parts of pattern all have an infrared lamp point at machine fish head front end exactly, the counting and distribute of other infrared lamps of different is back.Pattern 8 is a collinear three points, and pattern 9 is for constituting 3 points of isosceles triangle, and pattern 10 respectively has more a bit on two waists of isosceles triangle.
Because infrared beacon light 2 is fixed on one's body the machine fish 1, so the detection of infrared beacon light 2 just is equal to detection and the location to machine fish 1 with the location.As shown in Figure 5; When machine fish 1 was carried out vision localization, computing machine 5 was carried out following steps: S501, from the homography matrix document, the homography matrix data of video camera 3 is read in internal memory earlier; S502 obtains new image and carries out image pre-service work such as filtering, image binaryzation, morphology processing from video camera 3 through image pick-up card then; S503 adopts clustering algorithm and algorithm for pattern recognition to detect and discern infrared beacon light then, judges whether detect beacon light and whether match set beacon light pattern, if do not have; Then get back to S501, get into the next round circulation; If have, then carry out the S505 operation, promptly calculate the world coordinates of infrared beacon light (machine fish) and deposit result of calculation in document, get back to S501 then, get into the next round circulation.
Describe detection of infrared lamp target and identifying in detail below in conjunction with Fig. 6 and Fig. 7.Synoptic diagram after the Infrared images pre-processing that Fig. 6 photographs for video camera, Fig. 7 are that infrared beacon light detects the particular flow sheet with identification (step S503).
With reference to Fig. 7; The idiographic flow of step S503: S701 adopts the nearest neighbor classifier method to detect the luminous point of each infrared lamp, corresponds among Fig. 6; Promptly realize detecting the image coordinate location and the shared pixel size of pore of each pore, and store in the linked list data structure; S702, the infrared lamp that adopts the hierarchical clustering method will belong to same fish gathers into one type, in Fig. 6, the comparison that comprises by ellipse near the just corresponding machine fish of stain; S703, according to the infrared lamp quantity and the distribution cancelling noise point of beacon light, the stain that ellipse 11 comprises among Fig. 6 is exactly a noise spot; S704 carries out beacon light identification according to beacon light pattern (relative position of infrared signature point in the beacon light), and Fig. 4 has provided three kinds of patterns of beacon light, and three kinds of beacon light patterns have all occurred among Fig. 6, utilize its geometric properties that it is discerned one by one.
Among the S505, the world coordinates of machine fish is confirmed according to following mode: three kinds of beacon light patterns as shown in Figure 4, machine fish head front end all has an infrared lamp point, with the image coordinate of this infrared lamp point image coordinate (u as this machine fish
i, v
i), combine homography matrix to solve the world coordinates (x of machine fish through formula 1 then
i, y
i).
Utilize system and method for the present invention that the machine fish is carried out vision localization; Make the simple in structure, easy to make, with low cost of system; The infrared beacon light that the present invention adopts is very little; Influence the original outward appearance of machine fish hardly, location Calculation of the present invention is not disturbed by surround lighting and ripples accurately, fast.
Above-described specific embodiment; The object of the invention, technical scheme and beneficial effect have been carried out further explain, and institute it should be understood that the above is merely specific embodiment of the present invention; Be not limited to the present invention; All within spirit of the present invention and principle, any modification of being made, be equal to replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (7)
1. the infrared vision positioning system of a machine fish, this system comprises:
Infrared beacon light is made up of the infrared point that is installed in the machine fish dorsal;
Video camera is lifted on above the pond at machine fish place, is used to catch infrared lamp target image information;
Image pick-up card is used for obtaining in real time the image that video camera is taken;
Image analyzing unit; The image that image pick-up card is obtained carries out pre-service; With background and infrared point pixel separation, the infrared point pixel is gathered into a connectivity points territory through image binaryzation, morphology processing and infrared image binaryzation through the morphology expansion process;
The beacon light detecting unit; Adopt the nearest neighbor classifier method to detect the wherein picture point territory of single infrared point to each connectivity points territory; The beacon light that a plurality of infrared point that adopt the hierarchical clustering method to detect every machine fish back are formed; Detected beacon light and predetermined beacon light pattern are compared,, then write down the image coordinate of this detected beacon light if can be corresponding with predetermined beacon light pattern;
The vision localization unit calculates the world coordinates of beacon light according to homography matrix and said image coordinate, and wherein said world coordinates is confirmed through following formula:
Wherein, H is a homography matrix, m
1, m
2, m
3, m
4, m
5, m
6, m
7, m
8, m
9Be the matrix element of homography matrix, s
iBe scale-up factor, (u
i, v
i) be the coordinate of beacon light in image, (x
i, y
i) be the world coordinates of beacon light at the water surface.
2. the system of claim 1 is characterized in that, this system also comprises control module, is used to produce control information, and the mode through radio communication sends to electromechanical module in the machine fish body to realize the effective control to machine fish pose with control information.
3. the system of claim 1 is characterized in that, said infrared point is an infrared-emitting diode.
4. system as claimed in claim 3 is characterized in that, the spectral centroid wavelength of said infrared-emitting diode is 850nm.
5. system as claimed in claim 4 is characterized in that, the mounting center wavelength is the narrow bandpass filter plate of 850nm in the camera lens front of video camera.
6. system as claimed in claim 5; It is characterized in that said homography matrix confirms that under off-line state a plurality of gauge points are arranged in manual work in advance on the pond; Utilize the known image coordinate and the world coordinates of these gauge points, find the solution the matrix element of homography matrix through least square method.
7. system as claimed in claim 6 is characterized in that, said image pick-up card, image analyzing unit, beacon light detecting unit, vision localization unit are included in the computing machine.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011102235722A CN102278977B (en) | 2011-08-05 | 2011-08-05 | Infrared visual positioning system of robotic fish |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011102235722A CN102278977B (en) | 2011-08-05 | 2011-08-05 | Infrared visual positioning system of robotic fish |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102278977A CN102278977A (en) | 2011-12-14 |
| CN102278977B true CN102278977B (en) | 2012-11-28 |
Family
ID=45104564
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011102235722A Active CN102278977B (en) | 2011-08-05 | 2011-08-05 | Infrared visual positioning system of robotic fish |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102278977B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103208437A (en) * | 2013-04-28 | 2013-07-17 | 苏州工业园区高登威科技有限公司 | Resin clamp state detection device |
| CN104236944A (en) * | 2014-09-12 | 2014-12-24 | 北京卫星环境工程研究所 | Application of stroboscopic target recognition on lunar surface gravity simulation system |
| CN104966072B (en) * | 2015-07-08 | 2018-02-23 | 河海大学常州校区 | It is a kind of based on shape without colour code machine fish pose recognizer |
| CN105678749B (en) * | 2015-12-30 | 2018-03-30 | 中国水产科学研究院渔业机械仪器研究所 | A kind of fresh fish discriminating direction method of view-based access control model |
| CN112697127B (en) * | 2020-11-26 | 2024-06-11 | 佛山科学技术学院 | Indoor positioning system and method |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008044545A (en) * | 2006-08-18 | 2008-02-28 | Mhi Solution Technologies Co Ltd | Fish-shaped robot |
| CN101348165A (en) * | 2007-07-18 | 2009-01-21 | 中国科学院自动化研究所 | Three-dimensional motion bionic machine fish |
| US20100005700A1 (en) * | 2008-07-11 | 2010-01-14 | Kenneth Dale Thomas | Robotic fishing lure |
-
2011
- 2011-08-05 CN CN2011102235722A patent/CN102278977B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN102278977A (en) | 2011-12-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102278977B (en) | Infrared visual positioning system of robotic fish | |
| CN104217439B (en) | Indoor visual positioning system and method | |
| CN102419178B (en) | Mobile robot positioning system and method based on infrared road sign | |
| CN110142785A (en) | A kind of crusing robot visual servo method based on target detection | |
| CN101918980B (en) | Runway surveillance system and method | |
| CA3087370A1 (en) | Fish measurement station keeping | |
| CN106335646A (en) | Interference-type anti-UAV (Unmanned Aerial Vehicle) system | |
| CN106878687A (en) | A kind of vehicle environment identifying system and omni-directional visual module based on multisensor | |
| CN103733234A (en) | A surveillance system and a method for detecting a foreign object, debris, or damage in an airfield | |
| CN207115193U (en) | A kind of mobile electronic device for being used to handle the task of mission area | |
| CN110244314A (en) | One kind " low slow small " target acquisition identifying system and method | |
| CN107977018A (en) | Crop straw burning monitoring method based on binocular stereo vision and unmanned plane | |
| CN206611521U (en) | A kind of vehicle environment identifying system and omni-directional visual module based on multisensor | |
| CN108459597A (en) | A kind of mobile electronic device and method for handling the task of mission area | |
| CN101866006A (en) | Rotary multi-sensor photoelectric radar | |
| CN107976685B (en) | Indoor human target tracking system of infrared sensor based on thing networking | |
| CN108919811A (en) | A kind of indoor mobile robot SLAM method based on tag label | |
| CN105405126A (en) | Multi-scale air-ground parameter automatic calibration method based on monocular vision system | |
| CN105608417A (en) | Traffic signal lamp detection method and device | |
| CN104535047A (en) | Multi-agent target tracking global positioning system and method based on video stitching | |
| CN105136108A (en) | High-accuracy wave height measuring method based on stereoscopic vision | |
| CN110889327A (en) | Intelligent detection method for sewage draining exit around water area based on thermal infrared image | |
| CN106934402A (en) | Indoor moving video tracking positions auxiliary shooting method and device | |
| CN111028378A (en) | Unmanned aerial vehicle inspection system and inspection method for fishing complementary photovoltaic power station | |
| CN108140066A (en) | Drawing producing device and drawing production method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |