CN105123635A - Fish body positioning method through neural network identification - Google Patents
Fish body positioning method through neural network identification Download PDFInfo
- Publication number
- CN105123635A CN105123635A CN201510445523.1A CN201510445523A CN105123635A CN 105123635 A CN105123635 A CN 105123635A CN 201510445523 A CN201510445523 A CN 201510445523A CN 105123635 A CN105123635 A CN 105123635A
- Authority
- CN
- China
- Prior art keywords
- fish body
- fishing net
- underwater
- human agent
- fish
- 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.)
- Withdrawn
Links
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 31
- 238000000034 method Methods 0.000 title claims abstract description 16
- 241000251468 Actinopterygii Species 0.000 claims abstract description 124
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 62
- 239000003795 chemical substances by application Substances 0.000 claims description 58
- 238000001914 filtration Methods 0.000 claims description 35
- DMBHHRLKUKUOEG-UHFFFAOYSA-N diphenylamine Chemical compound C=1C=CC=CC=1NC1=CC=CC=C1 DMBHHRLKUKUOEG-UHFFFAOYSA-N 0.000 claims description 21
- 238000001514 detection method Methods 0.000 claims description 18
- 230000004807 localization Effects 0.000 claims description 10
- 230000011218 segmentation Effects 0.000 claims description 9
- 230000008878 coupling Effects 0.000 claims description 7
- 238000010168 coupling process Methods 0.000 claims description 7
- 238000005859 coupling reaction Methods 0.000 claims description 7
- 230000002708 enhancing effect Effects 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000007789 sealing Methods 0.000 claims description 6
- 230000007935 neutral effect Effects 0.000 claims description 3
- 238000011084 recovery Methods 0.000 claims description 3
- 230000000630 rising effect Effects 0.000 claims description 3
- 230000007704 transition Effects 0.000 claims description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000005266 casting Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K79/00—Methods or means of catching fish in bulk not provided for in groups A01K69/00 - A01K77/00, e.g. fish pumps; Detection of fish; Whale fishery
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
- G01S15/88—Sonar systems specially adapted for specific applications
- G01S15/96—Sonar systems specially adapted for specific applications for locating fish
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Environmental Sciences (AREA)
- Physics & Mathematics (AREA)
- Marine Sciences & Fisheries (AREA)
- Animal Husbandry (AREA)
- Biodiversity & Conservation Biology (AREA)
- Acoustics & Sound (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
Abstract
The invention relates to a fish body positioning method through neural network identification. The method comprises the following steps of providing a fish body positioning system through neural network identification and positioning fish bodies via the positioning system. The fish body positioning system through neural network identification comprises an underwater robot main body, feature extracting equipment and fish body type identifying equipment, wherein the feature extracting equipment and the fish body type identifying equipment are both placed on the underwater robot main body to respectively extract underwater fish body features and determine fish body types and give alarm information when determining the fish body types as rare and valuable protection types. Fish bodies can be automatically caught and underwater valuable and rare protection type fish bodies can be determined by the use of the fish body positioning method through neural network identification.
Description
Technical field
The present invention relates to digital image arts, particularly relate to a kind of fish body localization method adopting neural network recognization.
Background technology
Fishing pattern of the prior art depends on manually partially, and cannot judge shoal of fish situation under water, more cannot carry out dynamically casting for fish adjustably according to fish school status under water adaptively.
For this reason, the invention provides a kind of fish body navigation system adopting neural network recognization, can directly with under water contact, identify fish body target, judge that fish body is dynamic under water, thus determine fish body position, control to cast net strategy, realize underwater fishing adaptively, substitute with machine fishing pattern and manually fish pattern, the sustainable time is more of a specified duration, and effect is higher, and fishing achievement is particularly remarkable.
Summary of the invention
In order to solve the technical problem that prior art exists, the invention provides a kind of fish body navigation system adopting neural network recognization, utilize the underwater robot of peculiar structure as fishing carrier, introduce medium filtering subset, LPF subset and homomorphic filtering subset and carry out underwater picture pretreatment, adopt the image technique of neural network recognization to adapt to underwater environment, also introduce Underwater Navigation equipment accurately to locate fish body position under water.
According to an aspect of the present invention, provide a kind of fish body localization method adopting neural network recognization, the method comprises: 1) provide a kind of fish body navigation system adopting neural network recognization, described navigation system comprises underwater human agent, feature extracting device and fish body type identification equipment, described feature extracting device and described fish body type identification equipment are all positioned on described underwater human agent, for extracting fish body characteristics and determine fish body type under water respectively, and send warning message when determining that fish body type is rare protect types; 2) use described navigation system to position.
More specifically, in the fish body navigation system of described employing neural network recognization, also comprise: fishing net container, be arranged on described underwater human agent, for holding fishing net under non-fishing state, described fishing net container comprises electronic snap close, relay and opening, when described electric lock is buckled in and receives fishing enabling signal, open described opening, when described electric lock is buckled in and receives recovery complete signal, close described opening, described relay is connected respectively with electronic snap close and power supply unit, for powering for described electronic snap close and controlling opening operation and the shutoff operation of described electronic snap close, fishing net release actuator, is arranged on described underwater human agent, is connected with described fishing net, for controlling the release of described fishing net according to described fishing net release dynamics and described fishing net release angle, fishing net reclaims driver, is arranged on described underwater human agent, is connected with described fishing net, for when receiving fishing end signal, controls described fishing net to be recovered to by described fishing net in described fishing net container, release motor, is arranged on described underwater human agent, is connected with described fishing net release actuator, for described fishing net release actuator provides power to the control that fishing net discharges, reclaim motor, be arranged on described underwater human agent, reclaim driver with described fishing net and be connected, provide power for described fishing net reclaims driver to the control that fishing net discharges, signal receiver waterborne, be arranged on described underwater human agent, reclaim driver with described electronic snap close and described fishing net to be connected respectively, be connected with described treatment facility waterborne by cable, for be fully retrieved to personnel on the water after in described fishing net container at described fishing net operation under provide and reclaim complete signal, also for providing fishing end signal under the operation of personnel on the water, described underwater human agent comprises driving arrangement and robotic's framework, described driving arrangement comprises driving governor, larboard DC speed-reducing, starboard DC speed-reducing, sink-float motor, right-handed screw oar, counterpropeller, subsidiary screw and shaft coupling, described larboard DC speed-reducing, described starboard DC speed-reducing and described sink-float motor are respectively by described shaft coupling and described right-handed screw oar, described counterpropeller is connected with described subsidiary screw, described driving governor receives the drive control signal that described treatment facility waterborne sends, with larboard DC speed-reducing according to the content driven of described drive control signal and described starboard DC speed-reducing to control described right-handed screw oar and described counterpropeller respectively, underwater human agent is driven to realize advancing, retreat and left and right action, also for the motor that rises and falls according to the content driven of described drive control signal to control described subsidiary screw, underwater human agent is driven to realize rising and dive action, underwater camera equipment, be arranged on described underwater human agent, comprise hemispherical watertight transparent cover, floor light subset and CMOS camera, described hemispherical watertight transparent cover is for holding described floor light subset and described CMOS camera, described floor light subset provides floor light for the underwater photograph technical of described CMOS camera, described CMOS camera to objects ahead shooting to obtain the underwater picture comprising objects ahead, pre-processing device, is arranged on described underwater human agent, is connected with described CMOS camera, comprises medium filtering subset, LPF subset and homomorphic filtering subset, described medium filtering subset is connected with described CMOS camera, for performing medium filtering to described underwater picture, with the spot noise in underwater picture described in filtering, obtains the first filtering image, described LPF subset is connected with described medium filtering subset, for removing the random noise in described first filtering image, obtains the second filtering image, described homomorphic filtering subset is connected with described LPF subset, for performing image enhaucament, to obtain enhancing underwater picture to described second filtering image, described feature extracting device, be arranged on described underwater human agent, be connected with described pre-processing device, comprise Iamge Segmentation subset and eigenvector recognition subset, the fish body target in described enhancing underwater picture is identified to obtain fish volume image under water based on fish volume image gray threshold scope by described Iamge Segmentation subset, described eigenvector recognition subset is connected with described Iamge Segmentation subset, 8 geometric properties of fish body target are under water determined: Euler's hole count, circularity, angle point number, convex-concave degree, smoothness, draw ratio, tight ness rating and main shaft angle based on the described volume image of fish under water, and by described 8 geometric properties composition characteristics vector, described fish body type identification equipment, be arranged on described underwater human agent, be connected with described feature extracting device, adopt single hidden layer BP neutral net that 8 inputs 4 export, using 8 geometric properties of fish body target under water as input layer, output layer is fish body type under water, the described body of fish under water type comprises rare protect types, hazard types, edible type and other types, when the body of the fish under water type exported is for edible type, calculate fish body deviation angle under water based on the relative position of the described volume image of fish under water in described underwater picture, buoy waterborne, is arranged on the top water surface of described underwater human agent, power supply unit, be arranged on described buoy waterborne, comprise waterproof sealing cover, solar powered device, accumulator, change-over switch and electric pressure converter, described waterproof sealing cover is for holding described solar powered device, described accumulator, described change-over switch and described electric pressure converter, described change-over switch is connected respectively with described solar powered device and described accumulator, dump energy according to accumulator determines whether be switched to described solar powered device to be powered by described solar powered device, described electric pressure converter is connected with described change-over switch, with the 5V voltage transitions will inputted by change-over switch for 3.3V voltage, the Big Dipper positioning equipment, is arranged on described buoy waterborne, provides supply of electric power by described power supply unit, for receiving the Big Dipper locator data that the Big Dipper satellite sends, sonar detection equipment, is arranged on described buoy waterborne, provides supply of electric power by described power supply unit, for detecting the relative distance of described submersible main body to described buoy waterborne, and to adjust the distance output as first-phase, ultrasonic ranging equipment, is arranged on described underwater human agent, for measuring the distance of described underwater human agent distance front fish body target, and to adjust the distance output as second-phase, single-chip microcomputer, be arranged on described underwater human agent, be connected respectively with described fish body type identification equipment, described the Big Dipper positioning equipment, described sonar detection equipment and described ultrasonic ranging equipment, when described in receiving, fish body type is rare protect types under water, send alarm signal, and to adjust the distance based on described the Big Dipper locator data, described first-phase and described second-phase is adjusted the distance and calculated fish body locator data, wherein, described single-chip microcomputer also reclaims driver with described electronic snap close, described fishing net release actuator and described fishing net and is connected respectively, when described in receiving, fish body type is for edible type under water, adjust the distance according to second-phase and fishing net weight determination fishing net release dynamics, according to the fishing net of fish body deviation angle determination under water release angle, and send described fishing enabling signal to described electric lock garnishment, described single-chip microcomputer is also connected with described signal receiver waterborne, described alarm signal and described fish body locator data are sent to described treatment facility waterborne by cable.
More specifically; in the fish body navigation system of described employing neural network recognization: described single-chip microcomputer, when fish body type is rare protect types described in receiving, starts described the Big Dipper positioning equipment, described sonar detection equipment and described ultrasonic ranging equipment under water.
More specifically, in the fish body navigation system of described employing neural network recognization: described single-chip microcomputer, when fish body type is hazard types, edible type or other types described in receiving, cuts out described the Big Dipper positioning equipment, described sonar detection equipment and described ultrasonic ranging equipment under water.
More specifically, in the fish body navigation system of described employing neural network recognization, also comprise: fishing net weight detection equipment, for detecting described fishing net weight.
More specifically, in the fish body navigation system of described employing neural network recognization: described fishing net weight detection equipment is connected with described single-chip microcomputer.
Accompanying drawing explanation
Below with reference to accompanying drawing, embodiment of the present invention are described, wherein:
Fig. 1 is the block diagram of the fish body navigation system of the employing neural network recognization illustrated according to an embodiment of the present invention.
Reference numeral: 1 underwater human agent; 2 feature extracting device; 3 fish body type identification equipment
Embodiment
Below with reference to accompanying drawings the embodiment of the fish body navigation system of employing neural network recognization of the present invention is described in detail.
In prior art, conventional fishing pattern mainly relies on the observation on the water surface, and fixed point is casted net, fishing inefficiency.
In order to overcome above-mentioned deficiency, the present invention has built a kind of fish body navigation system adopting neural network recognization, with the artificial main body of underwater, be integrated with the fish body identification of a series of applicable underwater environment, location and capture device, improve the gentle flying power of Automated water of underwater fishing.
Fig. 1 is the block diagram of the fish body navigation system of the employing neural network recognization illustrated according to an embodiment of the present invention; described navigation system comprises underwater human agent, feature extracting device and fish body type identification equipment; described feature extracting device and described fish body type identification equipment are all positioned on described underwater human agent; for extracting fish body characteristics and determine fish body type under water respectively, and send warning message when determining that fish body type is rare protect types.
Then, continue to be further detailed the concrete structure of the fish body navigation system of employing neural network recognization of the present invention.
Described navigation system also comprises: fishing net container, be arranged on described underwater human agent, for holding fishing net under non-fishing state, described fishing net container comprises electronic snap close, relay and opening, when described electric lock is buckled in and receives fishing enabling signal, open described opening, when described electric lock is buckled in and receives recovery complete signal, close described opening, described relay is connected respectively with electronic snap close and power supply unit, for powering for described electronic snap close and controlling opening operation and the shutoff operation of described electronic snap close.
Described navigation system also comprises: fishing net release actuator, is arranged on described underwater human agent, is connected with described fishing net, for controlling the release of described fishing net according to described fishing net release dynamics and described fishing net release angle.
Described navigation system also comprises: fishing net reclaims driver, is arranged on described underwater human agent, is connected with described fishing net, for when receiving fishing end signal, controls described fishing net to be recovered in described fishing net container by described fishing net.
Described navigation system also comprises: release motor, is arranged on described underwater human agent, is connected with described fishing net release actuator, for described fishing net release actuator provides power to the control that fishing net discharges.
Described navigation system also comprises: reclaim motor, be arranged on described underwater human agent, reclaim driver be connected with described fishing net, provides power for described fishing net reclaims driver to the control that fishing net discharges.
Described navigation system also comprises: signal receiver waterborne, be arranged on described underwater human agent, reclaim driver with described electronic snap close and described fishing net to be connected respectively, be connected with described treatment facility waterborne by cable, for be fully retrieved to personnel on the water after in described fishing net container at described fishing net operation under provide and reclaim complete signal, also for providing fishing end signal under the operation of personnel on the water.
Described underwater human agent comprises driving arrangement and robotic's framework, described driving arrangement comprises driving governor, larboard DC speed-reducing, starboard DC speed-reducing, sink-float motor, right-handed screw oar, counterpropeller, subsidiary screw and shaft coupling, described larboard DC speed-reducing, described starboard DC speed-reducing and described sink-float motor are respectively by described shaft coupling and described right-handed screw oar, described counterpropeller is connected with described subsidiary screw, described driving governor receives the drive control signal that described treatment facility waterborne sends, with larboard DC speed-reducing according to the content driven of described drive control signal and described starboard DC speed-reducing to control described right-handed screw oar and described counterpropeller respectively, underwater human agent is driven to realize advancing, retreat and left and right action, also for the motor that rises and falls according to the content driven of described drive control signal to control described subsidiary screw, underwater human agent is driven to realize rising and dive action.
Described navigation system also comprises: underwater camera equipment, be arranged on described underwater human agent, comprise hemispherical watertight transparent cover, floor light subset and CMOS camera, described hemispherical watertight transparent cover is for holding described floor light subset and described CMOS camera, described floor light subset provides floor light for the underwater photograph technical of described CMOS camera, described CMOS camera to objects ahead shooting to obtain the underwater picture comprising objects ahead.
Described navigation system also comprises: pre-processing device, is arranged on described underwater human agent, is connected with described CMOS camera, comprises medium filtering subset, LPF subset and homomorphic filtering subset; Described medium filtering subset is connected with described CMOS camera, for performing medium filtering to described underwater picture, with the spot noise in underwater picture described in filtering, obtains the first filtering image; Described LPF subset is connected with described medium filtering subset, for removing the random noise in described first filtering image, obtains the second filtering image; Described homomorphic filtering subset is connected with described LPF subset, for performing image enhaucament, to obtain enhancing underwater picture to described second filtering image.
Described feature extracting device, be arranged on described underwater human agent, be connected with described pre-processing device, comprise Iamge Segmentation subset and eigenvector recognition subset, the fish body target in described enhancing underwater picture is identified to obtain fish volume image under water based on fish volume image gray threshold scope by described Iamge Segmentation subset; Described eigenvector recognition subset is connected with described Iamge Segmentation subset, 8 geometric properties of fish body target are under water determined: Euler's hole count, circularity, angle point number, convex-concave degree, smoothness, draw ratio, tight ness rating and main shaft angle based on the described volume image of fish under water, and by described 8 geometric properties composition characteristics vector.
Described fish body type identification equipment; be arranged on described underwater human agent; be connected with described feature extracting device; adopt single hidden layer BP neutral net that 8 inputs 4 export; using 8 geometric properties of fish body target under water as input layer; output layer is fish body type under water; the described body of fish under water type comprises rare protect types, hazard types, edible type and other types; when the body of the fish under water type exported is for edible type, calculate fish body deviation angle under water based on the relative position of the described volume image of fish under water in described underwater picture.
Described navigation system also comprises: buoy waterborne, is arranged on the top water surface of described underwater human agent.
Described navigation system also comprises: power supply unit, be arranged on described buoy waterborne, comprise waterproof sealing cover, solar powered device, accumulator, change-over switch and electric pressure converter, described waterproof sealing cover is for holding described solar powered device, described accumulator, described change-over switch and described electric pressure converter, described change-over switch is connected respectively with described solar powered device and described accumulator, dump energy according to accumulator determines whether be switched to described solar powered device to be powered by described solar powered device, described electric pressure converter is connected with described change-over switch, with the 5V voltage transitions will inputted by change-over switch for 3.3V voltage.
Described navigation system also comprises: the Big Dipper positioning equipment, is arranged on described buoy waterborne, provides supply of electric power by described power supply unit, for receiving the Big Dipper locator data that the Big Dipper satellite sends.
Described navigation system also comprises: sonar detection equipment, is arranged on described buoy waterborne, provides supply of electric power by described power supply unit, for detecting the relative distance of described submersible main body to described buoy waterborne, and to adjust the distance output as first-phase.
Described navigation system also comprises: ultrasonic ranging equipment, is arranged on described underwater human agent, for measuring the distance of described underwater human agent distance front fish body target, and to adjust the distance output as second-phase.
Described navigation system also comprises: single-chip microcomputer, be arranged on described underwater human agent, be connected respectively with described fish body type identification equipment, described the Big Dipper positioning equipment, described sonar detection equipment and described ultrasonic ranging equipment, when described in receiving, fish body type is rare protect types under water, send alarm signal, and to adjust the distance based on described the Big Dipper locator data, described first-phase and described second-phase is adjusted the distance and calculated fish body locator data; Wherein, described single-chip microcomputer also reclaims driver with described electronic snap close, described fishing net release actuator and described fishing net and is connected respectively, when described in receiving, fish body type is for edible type under water, adjust the distance according to second-phase and fishing net weight determination fishing net release dynamics; According to the fishing net of fish body deviation angle determination under water release angle, and send described fishing enabling signal to described electric lock garnishment; Described single-chip microcomputer is also connected with described signal receiver waterborne, described alarm signal and described fish body locator data are sent to described treatment facility waterborne by cable.
Alternatively, in the fish body navigation system of described employing neural network recognization: described single-chip microcomputer, when fish body type is rare protect types described in receiving, starts described the Big Dipper positioning equipment, described sonar detection equipment and described ultrasonic ranging equipment under water; Described single-chip microcomputer, when fish body type is hazard types, edible type or other types described in receiving, cuts out described the Big Dipper positioning equipment, described sonar detection equipment and described ultrasonic ranging equipment under water; Described system also comprises fishing net weight detection equipment, for detecting described fishing net weight; Described fishing net weight detection equipment is connected with described single-chip microcomputer.
In addition, cmos sensor also can be subdivided into passive type element sensor (PassivePixelSensorCMOS) and active pixel sensor (ActivePixelSensorCMOS).
Passive type element sensor (PassivePixelSensor is called for short PPS), be again passive type element sensor, he is made up of a back-biased photodiode and a switching tube.Photodiode is a PN junction be made up of P-type semiconductor and N-type semiconductor in essence, and he can be equivalent to a back-biased diode and a mos capacitance parallel connection.When switching tube is opened, photodiode is communicated with vertical alignment (Columnbus).The charge integration amplifier reading circuit (Chargeintegratingamplifier) being positioned at alignment end keeps column line voltage to be a constant, when the signal charge of photodiode storage is read out, its voltage is reset to column line voltage level, meanwhile, the electric charge be directly proportional to optical signal is converted to electric charge by charge integration amplifier and exports.
Active pixel sensor (ActivePixelSensor is called for short APS), is again active element sensor.Almost while the invention of CMOSPPS dot structure, people recognize very soon in pixel, to introduce the performance that buffer or amplifier can improve pixel, have the amplifier of oneself in CMOSAPS in each pixel.The amplifier transistor being integrated in surface decreases the effective surface area of pixel element, reduces " packaging density ", the incident light of 40% ~ 50% is reflected.Another problem of this sensor is, how to make there is good coupling between the multi-channel amplifier of sensor, and this can be realized preferably by the fixed pattern noise reducing residual level.Because each amplifier in CMOSAPS pixel is only excited, so the power dissipation ratio ccd image sensor of CMOSAPS is also little during this reads.
Adopt the fish body navigation system of employing neural network recognization of the present invention, for the technical problem cannot carrying out self adaptation fishing under water in prior art, introduce underwater robot and a series of high-precision image procossing and target localization equipment, realize the intelligent underwater fishing of sustainability.
Be understandable that, although the present invention with preferred embodiment disclose as above, but above-described embodiment and be not used to limit the present invention.For any those of ordinary skill in the art, do not departing under technical solution of the present invention ambit, the technology contents of above-mentioned announcement all can be utilized to make many possible variations and modification to technical solution of the present invention, or be revised as the Equivalent embodiments of equivalent variations.Therefore, every content not departing from technical solution of the present invention, according to technical spirit of the present invention to any simple modification made for any of the above embodiments, equivalent variations and modification, all still belongs in the scope of technical solution of the present invention protection.
Claims (6)
1. adopt a fish body localization method for neural network recognization, the method comprises:
1) a kind of fish body navigation system adopting neural network recognization is provided, described navigation system comprises underwater human agent, feature extracting device and fish body type identification equipment, described feature extracting device and described fish body type identification equipment are all positioned on described underwater human agent, for extracting fish body characteristics and determine fish body type under water respectively, and send warning message when determining that fish body type is rare protect types;
2) use described navigation system to position.
2. the fish body localization method adopting neural network recognization as claimed in claim 1, it is characterized in that, described navigation system also comprises:
Fishing net container, be arranged on described underwater human agent, for holding fishing net under non-fishing state, described fishing net container comprises electronic snap close, relay and opening, when described electric lock is buckled in and receives fishing enabling signal, opens described opening, when described electric lock is buckled in and receives recovery complete signal, close described opening, described relay is connected respectively with electronic snap close and power supply unit, for powering for described electronic snap close and controlling opening operation and the shutoff operation of described electronic snap close;
Fishing net release actuator, is arranged on described underwater human agent, is connected with described fishing net, for controlling the release of described fishing net according to described fishing net release dynamics and described fishing net release angle;
Fishing net reclaims driver, is arranged on described underwater human agent, is connected with described fishing net, for when receiving fishing end signal, controls described fishing net to be recovered to by described fishing net in described fishing net container;
Release motor, is arranged on described underwater human agent, is connected with described fishing net release actuator, for described fishing net release actuator provides power to the control that fishing net discharges;
Reclaim motor, be arranged on described underwater human agent, reclaim driver with described fishing net and be connected, provide power for described fishing net reclaims driver to the control that fishing net discharges;
Signal receiver waterborne, be arranged on described underwater human agent, reclaim driver with described electronic snap close and described fishing net to be connected respectively, be connected with described treatment facility waterborne by cable, for be fully retrieved to personnel on the water after in described fishing net container at described fishing net operation under provide and reclaim complete signal, also for providing fishing end signal under the operation of personnel on the water;
Described underwater human agent comprises driving arrangement and robotic's framework, described driving arrangement comprises driving governor, larboard DC speed-reducing, starboard DC speed-reducing, sink-float motor, right-handed screw oar, counterpropeller, subsidiary screw and shaft coupling, described larboard DC speed-reducing, described starboard DC speed-reducing and described sink-float motor are respectively by described shaft coupling and described right-handed screw oar, described counterpropeller is connected with described subsidiary screw, described driving governor receives the drive control signal that described treatment facility waterborne sends, with larboard DC speed-reducing according to the content driven of described drive control signal and described starboard DC speed-reducing to control described right-handed screw oar and described counterpropeller respectively, underwater human agent is driven to realize advancing, retreat and left and right action, also for the motor that rises and falls according to the content driven of described drive control signal to control described subsidiary screw, underwater human agent is driven to realize rising and dive action,
Underwater camera equipment, be arranged on described underwater human agent, comprise hemispherical watertight transparent cover, floor light subset and CMOS camera, described hemispherical watertight transparent cover is for holding described floor light subset and described CMOS camera, described floor light subset provides floor light for the underwater photograph technical of described CMOS camera, described CMOS camera to objects ahead shooting to obtain the underwater picture comprising objects ahead;
Pre-processing device, is arranged on described underwater human agent, is connected with described CMOS camera, comprises medium filtering subset, LPF subset and homomorphic filtering subset; Described medium filtering subset is connected with described CMOS camera, for performing medium filtering to described underwater picture, with the spot noise in underwater picture described in filtering, obtains the first filtering image; Described LPF subset is connected with described medium filtering subset, for removing the random noise in described first filtering image, obtains the second filtering image; Described homomorphic filtering subset is connected with described LPF subset, for performing image enhaucament, to obtain enhancing underwater picture to described second filtering image;
Described feature extracting device, be arranged on described underwater human agent, be connected with described pre-processing device, comprise Iamge Segmentation subset and eigenvector recognition subset, the fish body target in described enhancing underwater picture is identified to obtain fish volume image under water based on fish volume image gray threshold scope by described Iamge Segmentation subset; Described eigenvector recognition subset is connected with described Iamge Segmentation subset, 8 geometric properties of fish body target are under water determined: Euler's hole count, circularity, angle point number, convex-concave degree, smoothness, draw ratio, tight ness rating and main shaft angle based on the described volume image of fish under water, and by described 8 geometric properties composition characteristics vector;
Described fish body type identification equipment, be arranged on described underwater human agent, be connected with described feature extracting device, adopt single hidden layer BP neutral net that 8 inputs 4 export, using 8 geometric properties of fish body target under water as input layer, output layer is fish body type under water, the described body of fish under water type comprises rare protect types, hazard types, edible type and other types, when the body of the fish under water type exported is for edible type, calculate fish body deviation angle under water based on the relative position of the described volume image of fish under water in described underwater picture;
Buoy waterborne, is arranged on the top water surface of described underwater human agent;
Power supply unit, be arranged on described buoy waterborne, comprise waterproof sealing cover, solar powered device, accumulator, change-over switch and electric pressure converter, described waterproof sealing cover is for holding described solar powered device, described accumulator, described change-over switch and described electric pressure converter, described change-over switch is connected respectively with described solar powered device and described accumulator, dump energy according to accumulator determines whether be switched to described solar powered device to be powered by described solar powered device, described electric pressure converter is connected with described change-over switch, with the 5V voltage transitions will inputted by change-over switch for 3.3V voltage,
The Big Dipper positioning equipment, is arranged on described buoy waterborne, provides supply of electric power by described power supply unit, for receiving the Big Dipper locator data that the Big Dipper satellite sends;
Sonar detection equipment, is arranged on described buoy waterborne, provides supply of electric power by described power supply unit, for detecting the relative distance of described submersible main body to described buoy waterborne, and to adjust the distance output as first-phase;
Ultrasonic ranging equipment, is arranged on described underwater human agent, for measuring the distance of described underwater human agent distance front fish body target, and to adjust the distance output as second-phase;
Single-chip microcomputer, be arranged on described underwater human agent, be connected respectively with described fish body type identification equipment, described the Big Dipper positioning equipment, described sonar detection equipment and described ultrasonic ranging equipment, when described in receiving, fish body type is rare protect types under water, send alarm signal, and to adjust the distance based on described the Big Dipper locator data, described first-phase and described second-phase is adjusted the distance and calculated fish body locator data;
Wherein, described single-chip microcomputer also reclaims driver with described electronic snap close, described fishing net release actuator and described fishing net and is connected respectively, when described in receiving, fish body type is for edible type under water, adjust the distance according to second-phase and fishing net weight determination fishing net release dynamics; According to the fishing net of fish body deviation angle determination under water release angle, and send described fishing enabling signal to described electric lock garnishment;
Wherein, described single-chip microcomputer is also connected with described signal receiver waterborne, described alarm signal and described fish body locator data are sent to described treatment facility waterborne by cable.
3. the fish body localization method adopting neural network recognization as claimed in claim 2; it is characterized in that: described single-chip microcomputer, when fish body type is rare protect types described in receiving, starts described the Big Dipper positioning equipment, described sonar detection equipment and described ultrasonic ranging equipment under water.
4. the fish body localization method adopting neural network recognization as claimed in claim 2, it is characterized in that: described single-chip microcomputer, when fish body type is hazard types, edible type or other types described in receiving, cuts out described the Big Dipper positioning equipment, described sonar detection equipment and described ultrasonic ranging equipment under water.
5. the fish body localization method adopting neural network recognization as claimed in claim 2, is characterized in that, also comprise: fishing net weight detection equipment, for detecting described fishing net weight.
6. the fish body localization method adopting neural network recognization as claimed in claim 5, is characterized in that: described fishing net weight detection equipment is connected with described single-chip microcomputer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510445523.1A CN105123635A (en) | 2015-07-25 | 2015-07-25 | Fish body positioning method through neural network identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510445523.1A CN105123635A (en) | 2015-07-25 | 2015-07-25 | Fish body positioning method through neural network identification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105123635A true CN105123635A (en) | 2015-12-09 |
Family
ID=54709530
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510445523.1A Withdrawn CN105123635A (en) | 2015-07-25 | 2015-07-25 | Fish body positioning method through neural network identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105123635A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106773889A (en) * | 2016-08-04 | 2017-05-31 | 浙江大丰实业股份有限公司 | Danger arenas control platform based on image detection |
| CN110678071A (en) * | 2017-06-30 | 2020-01-10 | 株式会社东和电机制作所 | Automatic fishing system and automatic fishing method |
| CN116819540A (en) * | 2023-05-09 | 2023-09-29 | 南京俊禄科技有限公司 | Method for intelligently calculating type and depth of fishing group |
-
2015
- 2015-07-25 CN CN201510445523.1A patent/CN105123635A/en not_active Withdrawn
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106773889A (en) * | 2016-08-04 | 2017-05-31 | 浙江大丰实业股份有限公司 | Danger arenas control platform based on image detection |
| CN106773889B (en) * | 2016-08-04 | 2018-11-20 | 浙江大丰实业股份有限公司 | Danger arenas control platform based on image detection |
| CN110678071A (en) * | 2017-06-30 | 2020-01-10 | 株式会社东和电机制作所 | Automatic fishing system and automatic fishing method |
| CN116819540A (en) * | 2023-05-09 | 2023-09-29 | 南京俊禄科技有限公司 | Method for intelligently calculating type and depth of fishing group |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105076076A (en) | Fish body positioning system using neural network recognition | |
| CN105046232A (en) | Image processing based system for searching fish body at bottom of ship | |
| CN107542073A (en) | A kind of mixed dynamic water surface cleaning of intelligence based on Raspberry Pi and water monitoring device and method | |
| CN105129052A (en) | Underwater human body searching method | |
| CN105123635A (en) | Fish body positioning method through neural network identification | |
| CN104967833B (en) | A kind of fishing method based on data communication | |
| KR102169701B1 (en) | System for colleting marine waste | |
| CN105076078A (en) | Automatic detection method based on feature extraction | |
| CN105007467B (en) | It is positioned at the human body search platform below hull bottom | |
| CN105005996A (en) | Image sharpening analysis system | |
| CN105046228A (en) | Data communication based fish body identification method | |
| CN105072395B (en) | A kind of diver's subaqueous rock preventing collision method based on data communication | |
| CN207571578U (en) | A kind of underwater automatic aircraft being imaged based on PSD rangings and CCD night visions | |
| CN105095875A (en) | Method for detecting fishes under ship based on image filtering | |
| CN105035287A (en) | Underwater remain exploring method based on data communication | |
| CN105068138A (en) | Automatic detecting instrument | |
| CN105005979A (en) | Detection platform based on image filtering | |
| CN104954766A (en) | Searching method for human body below bottom of ship | |
| CN105069417A (en) | Fish searching method based on image processing | |
| CN104996370A (en) | Underwater fish orientation capturing system based on data communication | |
| CN105160637A (en) | Image sharpening analysis method | |
| CN105057848A (en) | Underwater welding joint search platform capable of improving image processing accuracy | |
| CN105005050A (en) | Underwater rock detection method adopting neural network identification | |
| CN105069414A (en) | Diver special fish identification system based on data communication | |
| CN105138008A (en) | Multifunctional submersible for underwater submerged reef detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20151209 |
|
| WW01 | Invention patent application withdrawn after publication |