CN105005050A - Underwater rock detection method adopting neural network identification - Google Patents
Underwater rock detection method adopting neural network identification Download PDFInfo
- Publication number
- CN105005050A CN105005050A CN201510470430.4A CN201510470430A CN105005050A CN 105005050 A CN105005050 A CN 105005050A CN 201510470430 A CN201510470430 A CN 201510470430A CN 105005050 A CN105005050 A CN 105005050A
- Authority
- CN
- China
- Prior art keywords
- rock
- subaqueous
- underwater vehicle
- equipment
- underwater
- 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
Classifications
-
- 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
- G01S15/93—Sonar systems specially adapted for specific applications for anti-collision purposes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V8/00—Prospecting or detecting by optical means
- G01V8/10—Detecting, e.g. by using light barriers
Abstract
The invention relates to an underwater rock detection method adopting neural network identification. The method comprises the following steps: (1) providing an underwater rock detection platform adopting neural network identification, wherein the underwater rock detection platform includes a submersible body, a feature extraction device and a rock type identification device, and the feature extraction device and the rock type identification device are disposed on the submersible body and are respectively used for extracting the features of underwater rocks and determining the type of rocks; and (2) running the platform. By adopting the method, a submersible can avoid underground rocks intelligently without the need for manual operation underwater.
Description
Technical field
The present invention relates to field of image recognition, particularly relate to a kind of subaqueous rock detection method adopting neural network recognization.
Background technology
At present, conventional underwater vehicle carries out underwater operation to realize the purposes such as underwater prospecting, under water rescue.In underwater vehicle under water walking process, if be in shoal water zone or subaqueous rock is too high, if hide too late, be easy to collide with subaqueous rock, cause underwater vehicle impaired, and due to particular surroundings under water, service capsule cost is very high under water, to the great economic loss of the fractal one-tenth of underwater vehicle operational department, and waste a lot of time costs.
Because subaqueous rock shape size differs, distributing position does not also possess regularity, adds particular surroundings under water, causes subaqueous rock shape recognition abnormal difficult, can not solve the scheme of this difficult problem in prior art.
For this reason, the present invention proposes a kind of subaqueous rock detection platform adopting neural network recognization, can for special circumstances under water, the rock checkout equipment of applicable underwater environment is used effectively to detect subaqueous rock, correspondingly formulate different processing modes, avoid underwater vehicle and rock directly to bump against.
Summary of the invention
In order to solve the technical matters that prior art exists, the invention provides a kind of subaqueous rock detection platform adopting neural network recognization, the concrete structure of transformation underwater vehicle, adopt the petrologic analysis equipment comprising medium filtering subset, low-pass filtering subset and homomorphic filtering subset to carry out accurate analysis to subaqueous rock situation simultaneously, based on the rock height identified, formulate different processing policies, improve the security performance of underwater vehicle.
According to an aspect of the present invention, provide a kind of subaqueous rock detection method adopting neural network recognization, the method comprises: 1) provide a kind of subaqueous rock detection platform adopting neural network recognization, described detection platform comprises underwater vehicle main body, feature extracting device and rock type identification equipment, described feature extracting device and described rock type identification equipment are all positioned in described underwater vehicle main body, for extracting subaqueous rock characteristic sum determination rock type respectively; 2) described platform is run.
More specifically, in the subaqueous rock detection platform of described employing neural network recognization, also comprise: excavating equipment, be arranged in described underwater vehicle main body, comprise digging motor and excavate driver, described excavation driver is connected with described digging motor, for excavating front rock, ultrasonic ranging equipment, is arranged in described underwater vehicle main body, for measuring the distance of described underwater vehicle main body distance front rock target, and to adjust the distance output as second-phase, static storage device, rock area threshold, rock height threshold and rock width threshold value are prestored, described rock area threshold is directly proportional to excavating equipment output power, described rock height threshold is directly proportional to the instantaneous output power of climbing of underwater vehicle driving arrangement, and described rock width threshold value is directly proportional to the instantaneous output power that detours of described underwater vehicle driving arrangement, described underwater vehicle main body comprises driving arrangement and underwater vehicle mechanical framework, described driving arrangement comprises driving governor, larboard DC speed-reducing, starboard DC speed-reducing, sink-float motor, right-handed screw oar, counter propeller, subsidiary screw propeller 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 counter propeller is connected with described subsidiary screw propeller, 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 counter propeller respectively, underwater vehicle main body 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 propeller, underwater vehicle main body is driven to realize rising and dive action, underwater camera equipment, be arranged in described underwater vehicle main body, comprise semisphere watertight transparent cover, floor light subset and CMOS camera, described semisphere 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 in described underwater vehicle main body, is connected with described CMOS camera, comprises medium filtering subset, low-pass filtering 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 low-pass filtering 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 low-pass filtering subset, for performing image enhaucament, to obtain enhancing underwater picture to described second filtering image, feature extracting device, be arranged in described underwater vehicle main body, be connected with described pre-processing device, comprise Iamge Segmentation subset and eigenvector recognition subset, the rock target in described enhancing underwater picture identifies to obtain subaqueous rock image based on rock gradation of image threshold range by described Iamge Segmentation subset, described eigenvector recognition subset is connected with described Iamge Segmentation subset, 8 geometric properties based on described subaqueous rock image determination subaqueous rock target: Euler's hole count, circularity, angle point number, convex-concave degree, smoothness, length-diameter ratio, tight ness rating and main shaft angle, and by described 8 geometric properties composition characteristics vector, rock type identification equipment, be arranged in described underwater vehicle main body, be connected with described feature extracting device, adopt single hidden layer BP neural network that 8 inputs 2 export, using 8 of subaqueous rock target geometric properties as input layer, output layer is subaqueous rock type, and described subaqueous rock type comprises unsafe rock and conventional rock, rock conditions analytical equipment, be connected respectively with described feature extracting device and described ultrasonic ranging equipment, when receiving described subaqueous rock type, to adjust the distance based on described second-phase and area percentage that described subaqueous rock image occupies described enhancing underwater picture calculates subaqueous rock horizontal area, adjust the distance based on described second-phase and the longitudinal height percent calculating subaqueous rock height highly occupying the longitudinal height of described enhancing underwater picture of described subaqueous rock image, to adjust the distance based on described second-phase and width percentage that described subaqueous rock image transverse width occupies described enhancing underwater picture transverse width calculates subaqueous rock width, buoy waterborne, is arranged on the top water surface of described underwater vehicle main body, 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 electric power supply 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 electric power supply by described power-supply unit, for detecting the relative distance of described underwater vehicle main body to described buoy waterborne, and to adjust the distance output as first-phase, single-chip microcomputer, be arranged in described underwater vehicle main body, be connected respectively with described rock type identification equipment, described the Big Dipper positioning equipment, described sonar detection equipment and described ultrasonic ranging equipment, when to receive described subaqueous rock type be unsafe rock, send alerting 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 rock locator data, wherein, described single-chip microcomputer is also connected respectively with described rock conditions analytical equipment, described rock type identification equipment and described static storage device, when receiving described subaqueous rock type, described subaqueous rock horizontal area is compared with described rock area threshold, described subaqueous rock horizontal area is less than or equal to described rock area threshold and then sends excavation drive singal, and described subaqueous rock horizontal area is greater than described rock area threshold and then enters leadswinging pattern, described single-chip microcomputer operates below performing in described leadswinging pattern: then send rising drive singal when described subaqueous rock height is less than or equal to described rock height threshold, when described subaqueous rock height is greater than described rock height threshold, the comparative result of further judgement described subaqueous rock width and described rock width threshold value: detour about then sending when described subaqueous rock width is less than or equal to described rock width threshold value drive singal, otherwise, send retrogressing drive singal, described single-chip microcomputer is also connected with described driving arrangement, to be detoured in described rising drive singal, described left and right drive singal or retreat drive singal and be sent to described driving arrangement, described single-chip microcomputer is also connected with described excavation driver, so that described excavation drive singal is sent to described excavation driver.
More specifically, in the subaqueous rock detection platform of described employing neural network recognization, described detection platform also comprises: underwater cable, for being connected with water life-saving center by described single-chip microcomputer, described alerting signal and described rock locator data is sent to described water life-saving center.
More specifically, in the subaqueous rock detection platform of described employing neural network recognization: described single-chip microcomputer, when to receive described subaqueous rock type be unsafe rock, starts described the Big Dipper positioning equipment, described sonar detection equipment and described ultrasonic ranging equipment.
More specifically, in the subaqueous rock detection platform of described employing neural network recognization: described single-chip microcomputer, when to receive described subaqueous rock type be conventional rock, cuts out described the Big Dipper positioning equipment, described sonar detection equipment and described ultrasonic ranging equipment.
More specifically, in the subaqueous rock detection platform of described employing neural network recognization: described single-chip microcomputer is AT89C51.
More specifically, in the subaqueous rock detection platform of described employing neural network recognization: described underwater vehicle mechanical framework comprises support, left pressure gram transparent tube, right pressure gram transparent tube, connecting hoop, storage platform, mechanical arm, mechanical arm and water proof sealing bore.
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 subaqueous rock detection platform of the employing neural network recognization illustrated according to an embodiment of the present invention.
Reference numeral: 1 underwater vehicle main body; 2 feature extracting device; 3 rock type identification equipments
Embodiment
Below with reference to accompanying drawings the embodiment of the subaqueous rock detection platform of employing neural network recognization of the present invention is described in detail.
Underwater vehicle is higher due to intelligent level, usually involves great expense, but subaqueous rock situation is complicated, cannot anticipation to carry out reasonably avoiding, once there is underwater vehicle and rock collides, consequence is hardly imaginable.The underwater vehicle scheme of subaqueous rock is not still effectively hidden in prior art.
In order to overcome above-mentioned deficiency, the present invention has built a kind of subaqueous rock detection platform adopting neural network recognization, and the concrete condition based on subaqueous rock formulates different processing policies, avoids rock operator to be subject to economic loss.
Fig. 1 is the block diagram of the subaqueous rock detection platform of the employing neural network recognization illustrated according to an embodiment of the present invention, described detection platform comprises underwater vehicle main body, feature extracting device and rock type identification equipment, described feature extracting device and described rock type identification equipment are all positioned in described underwater vehicle main body, for extracting subaqueous rock characteristic sum determination rock type respectively.
Then, continue to be further detailed the concrete structure of the subaqueous rock detection platform of employing neural network recognization of the present invention.
Described detection platform also comprises: excavating equipment, is arranged in described underwater vehicle main body, and comprise digging motor and excavate driver, described excavation driver is connected with described digging motor, for excavating front rock.
Described detection platform also comprises: ultrasonic ranging equipment, is arranged in described underwater vehicle main body, for measuring the distance of described underwater vehicle main body distance front rock target, and to adjust the distance output as second-phase.
Described detection platform also comprises: static storage device, rock area threshold, rock height threshold and rock width threshold value are prestored, described rock area threshold is directly proportional to excavating equipment output power, described rock height threshold is directly proportional to the instantaneous output power of climbing of underwater vehicle driving arrangement, and described rock width threshold value is directly proportional to the instantaneous output power that detours of described underwater vehicle driving arrangement.
Described underwater vehicle main body comprises driving arrangement and underwater vehicle mechanical framework, described driving arrangement comprises driving governor, larboard DC speed-reducing, starboard DC speed-reducing, sink-float motor, right-handed screw oar, counter propeller, subsidiary screw propeller 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 counter propeller is connected with described subsidiary screw propeller, 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 counter propeller respectively, underwater vehicle main body 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 propeller, underwater vehicle main body is driven to realize rising and dive action.
Described detection platform also comprises: underwater camera equipment, be arranged in described underwater vehicle main body, comprise semisphere watertight transparent cover, floor light subset and CMOS camera, described semisphere 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 detection platform also comprises: pre-processing device, is arranged in described underwater vehicle main body, is connected with described CMOS camera, comprises medium filtering subset, low-pass filtering 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 low-pass filtering 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 low-pass filtering subset, for performing image enhaucament, to obtain enhancing underwater picture to described second filtering image.
Described feature extracting device, be arranged in described underwater vehicle main body, be connected with described pre-processing device, comprise Iamge Segmentation subset and eigenvector recognition subset, the rock target in described enhancing underwater picture identifies to obtain subaqueous rock image based on rock gradation of image threshold range by described Iamge Segmentation subset; Described eigenvector recognition subset is connected with described Iamge Segmentation subset, 8 geometric properties based on described subaqueous rock image determination subaqueous rock target: Euler's hole count, circularity, angle point number, convex-concave degree, smoothness, length-diameter ratio, tight ness rating and main shaft angle, and by described 8 geometric properties composition characteristics vector.
Described rock type identification equipment, be arranged in described underwater vehicle main body, be connected with described feature extracting device, adopt single hidden layer BP neural network that 8 inputs 2 export, using 8 of subaqueous rock target geometric properties as input layer, output layer is subaqueous rock type, and described subaqueous rock type comprises unsafe rock and conventional rock, rock conditions analytical equipment, be connected respectively with described feature extracting device and described ultrasonic ranging equipment, when receiving described subaqueous rock type, to adjust the distance based on described second-phase and area percentage that described subaqueous rock image occupies described enhancing underwater picture calculates subaqueous rock horizontal area, adjust the distance based on described second-phase and the longitudinal height percent calculating subaqueous rock height highly occupying the longitudinal height of described enhancing underwater picture of described subaqueous rock image, to adjust the distance based on described second-phase and width percentage that described subaqueous rock image transverse width occupies described enhancing underwater picture transverse width calculates subaqueous rock width.
Described detection platform also comprises: buoy waterborne, is arranged on the top water surface of described underwater vehicle main body.
Described detection platform 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 detection platform also comprises: the Big Dipper positioning equipment, is arranged on described buoy waterborne, provides electric power supply by described power-supply unit, for receiving the Big Dipper locator data that the Big Dipper satellite sends.
Described detection platform also comprises: sonar detection equipment, is arranged on described buoy waterborne, provides electric power supply by described power-supply unit, for detecting the relative distance of described underwater vehicle main body to described buoy waterborne, and to adjust the distance output as first-phase.
Described detection platform also comprises: single-chip microcomputer, be arranged in described underwater vehicle main body, be connected respectively with described rock type identification equipment, described the Big Dipper positioning equipment, described sonar detection equipment and described ultrasonic ranging equipment, when to receive described subaqueous rock type be unsafe rock, send alerting 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 rock locator data.
Described single-chip microcomputer is also connected respectively with described rock conditions analytical equipment, described rock type identification equipment and described static storage device, when receiving described subaqueous rock type, described subaqueous rock horizontal area is compared with described rock area threshold, described subaqueous rock horizontal area is less than or equal to described rock area threshold and then sends excavation drive singal, and described subaqueous rock horizontal area is greater than described rock area threshold and then enters leadswinging pattern.
Described single-chip microcomputer operates below performing in described leadswinging pattern: then send rising drive singal when described subaqueous rock height is less than or equal to described rock height threshold, when described subaqueous rock height is greater than described rock height threshold, the comparative result of further judgement described subaqueous rock width and described rock width threshold value: detour about then sending when described subaqueous rock width is less than or equal to described rock width threshold value drive singal, otherwise, send retrogressing drive singal.
Described single-chip microcomputer is also connected with described driving arrangement, to be detoured in described rising drive singal, described left and right drive singal or retreat drive singal and be sent to described driving arrangement; Described single-chip microcomputer is also connected with described excavation driver, so that described excavation drive singal is sent to described excavation driver.
Alternatively, in the subaqueous rock detection platform of described employing neural network recognization, described detection platform also comprises: underwater cable, for being connected with water life-saving center by described single-chip microcomputer, described alerting signal and described rock locator data is sent to described water life-saving center; Described single-chip microcomputer, when to receive described subaqueous rock type be unsafe rock, starts described the Big Dipper positioning equipment, described sonar detection equipment and described ultrasonic ranging equipment; Described single-chip microcomputer, when to receive described subaqueous rock type be conventional rock, cuts out described the Big Dipper positioning equipment, described sonar detection equipment and described ultrasonic ranging equipment; Described single-chip microcomputer is AT89C51; And described underwater vehicle mechanical framework comprises support, left pressure gram transparent tube, right pressure gram transparent tube, connecting hoop, storage platform, mechanical arm, mechanical arm and water proof sealing bore.
In addition, cmos sensor also can be subdivided into passive type element sensor (Passive PixelSensor CMOS) and active pixel sensor (Active Pixel Sensor CMOS).
Passive type element sensor (Passive Pixel Sensor 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 (Column bus).The charge integration amplifier sensing circuit (Charge integrating amplifier) 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 light signal is converted to electric charge by charge integration amplifier and exports.
Active pixel sensor (Active Pixel Sensor is called for short APS), is again active element sensor.Almost while the invention of CMOS PPS dot structure, people recognize very soon in pixel, to introduce the performance that impact damper or amplifier can improve pixel, have the amplifier of oneself in CMOS APS 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 multichannel amplifier of sensor, and this can be realized preferably by the fixed pattern noise reducing residual level.Because each amplifier in CMOS APS pixel is only excited, so the power dissipation ratio ccd image sensor of CMOS APS is also little during this reads.
Adopt the subaqueous rock detection platform of employing neural network recognization of the present invention, for lacking the intelligent technical matters hidden of underwater vehicle rock in prior art, transform existing underwater vehicle structure, underwater vehicle main body increases the rock identification equipment adapting to underwater environment and rock conditions analytical equipment, various subaqueous rock state can be detected, and carry out self-adaptation and hide, thus improve the automatization level of underwater vehicle, avoid collision accident under water to occur.
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 (7)
1. adopt a subaqueous rock detection method for neural network recognization, the method comprises:
1) a kind of subaqueous rock detection platform adopting neural network recognization is provided, described detection platform comprises underwater vehicle main body, feature extracting device and rock type identification equipment, described feature extracting device and described rock type identification equipment are all positioned in described underwater vehicle main body, for extracting subaqueous rock characteristic sum determination rock type respectively;
2) described platform is run.
2. the method for claim 1, is characterized in that, described detection platform also comprises:
Excavating equipment, is arranged in described underwater vehicle main body, and comprise digging motor and excavate driver, described excavation driver is connected with described digging motor, for excavating front rock;
Ultrasonic ranging equipment, is arranged in described underwater vehicle main body, for measuring the distance of described underwater vehicle main body distance front rock target, and to adjust the distance output as second-phase;
Static storage device, rock area threshold, rock height threshold and rock width threshold value are prestored, described rock area threshold is directly proportional to excavating equipment output power, described rock height threshold is directly proportional to the instantaneous output power of climbing of underwater vehicle driving arrangement, and described rock width threshold value is directly proportional to the instantaneous output power that detours of described underwater vehicle driving arrangement;
Described underwater vehicle main body comprises driving arrangement and underwater vehicle mechanical framework, described driving arrangement comprises driving governor, larboard DC speed-reducing, starboard DC speed-reducing, sink-float motor, right-handed screw oar, counter propeller, subsidiary screw propeller 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 counter propeller is connected with described subsidiary screw propeller, 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 counter propeller respectively, underwater vehicle main body 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 propeller, underwater vehicle main body is driven to realize rising and dive action,
Underwater camera equipment, be arranged in described underwater vehicle main body, comprise semisphere watertight transparent cover, floor light subset and CMOS camera, described semisphere 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 in described underwater vehicle main body, is connected with described CMOS camera, comprises medium filtering subset, low-pass filtering 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 low-pass filtering 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 low-pass filtering subset, for performing image enhaucament, to obtain enhancing underwater picture to described second filtering image;
Feature extracting device, be arranged in described underwater vehicle main body, be connected with described pre-processing device, comprise Iamge Segmentation subset and eigenvector recognition subset, the rock target in described enhancing underwater picture identifies to obtain subaqueous rock image based on rock gradation of image threshold range by described Iamge Segmentation subset; Described eigenvector recognition subset is connected with described Iamge Segmentation subset, 8 geometric properties based on described subaqueous rock image determination subaqueous rock target: Euler's hole count, circularity, angle point number, convex-concave degree, smoothness, length-diameter ratio, tight ness rating and main shaft angle, and by described 8 geometric properties composition characteristics vector;
Rock type identification equipment, be arranged in described underwater vehicle main body, be connected with described feature extracting device, adopt single hidden layer BP neural network that 8 inputs 2 export, using 8 of subaqueous rock target geometric properties as input layer, output layer is subaqueous rock type, and described subaqueous rock type comprises unsafe rock and conventional rock;
Rock conditions analytical equipment, be connected respectively with described feature extracting device and described ultrasonic ranging equipment, when receiving described subaqueous rock type, to adjust the distance based on described second-phase and area percentage that described subaqueous rock image occupies described enhancing underwater picture calculates subaqueous rock horizontal area, adjust the distance based on described second-phase and the longitudinal height percent calculating subaqueous rock height highly occupying the longitudinal height of described enhancing underwater picture of described subaqueous rock image, to adjust the distance based on described second-phase and width percentage that described subaqueous rock image transverse width occupies described enhancing underwater picture transverse width calculates subaqueous rock width,
Buoy waterborne, is arranged on the top water surface of described underwater vehicle main body;
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 electric power supply 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 electric power supply by described power-supply unit, for detecting the relative distance of described underwater vehicle main body to described buoy waterborne, and to adjust the distance output as first-phase;
Single-chip microcomputer, be arranged in described underwater vehicle main body, be connected respectively with described rock type identification equipment, described the Big Dipper positioning equipment, described sonar detection equipment and described ultrasonic ranging equipment, when to receive described subaqueous rock type be unsafe rock, send alerting 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 rock locator data;
Wherein, described single-chip microcomputer is also connected respectively with described rock conditions analytical equipment, described rock type identification equipment and described static storage device, when receiving described subaqueous rock type, described subaqueous rock horizontal area is compared with described rock area threshold, described subaqueous rock horizontal area is less than or equal to described rock area threshold and then sends excavation drive singal, and described subaqueous rock horizontal area is greater than described rock area threshold and then enters leadswinging pattern;
Wherein, described single-chip microcomputer operates below performing in described leadswinging pattern: then send rising drive singal when described subaqueous rock height is less than or equal to described rock height threshold, when described subaqueous rock height is greater than described rock height threshold, the comparative result of further judgement described subaqueous rock width and described rock width threshold value: detour about then sending when described subaqueous rock width is less than or equal to described rock width threshold value drive singal, otherwise, send retrogressing drive singal;
Wherein, described single-chip microcomputer is also connected with described driving arrangement, to be detoured in described rising drive singal, described left and right drive singal or retreat drive singal and be sent to described driving arrangement;
Wherein, described single-chip microcomputer is also connected with described excavation driver, so that described excavation drive singal is sent to described excavation driver.
3. method as claimed in claim 2, it is characterized in that, described detection platform also comprises:
Underwater cable, for being connected with water life-saving center by described single-chip microcomputer, is sent to described water life-saving center by described alerting signal and described rock locator data.
4. method as claimed in claim 2, is characterized in that:
Described single-chip microcomputer, when to receive described subaqueous rock type be unsafe rock, starts described the Big Dipper positioning equipment, described sonar detection equipment and described ultrasonic ranging equipment.
5. method as claimed in claim 2, is characterized in that:
Described single-chip microcomputer, when to receive described subaqueous rock type be conventional rock, cuts out described the Big Dipper positioning equipment, described sonar detection equipment and described ultrasonic ranging equipment.
6. method as claimed in claim 2, is characterized in that:
Described single-chip microcomputer is AT89C51.
7. method as claimed in claim 2, is characterized in that:
Described underwater vehicle mechanical framework comprises support, left pressure gram transparent tube, right pressure gram transparent tube, connecting hoop, storage platform, mechanical arm, mechanical arm and water proof sealing bore.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510470430.4A CN105005050A (en) | 2015-08-04 | 2015-08-04 | Underwater rock detection method adopting neural network identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510470430.4A CN105005050A (en) | 2015-08-04 | 2015-08-04 | Underwater rock detection method adopting neural network identification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105005050A true CN105005050A (en) | 2015-10-28 |
Family
ID=54377785
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510470430.4A Pending CN105005050A (en) | 2015-08-04 | 2015-08-04 | Underwater rock detection method adopting neural network identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105005050A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111381233A (en) * | 2018-12-28 | 2020-07-07 | 中国船舶重工集团公司第七一九研究所 | Underwater confrontation situation display and control method and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11337641A (en) * | 1998-05-27 | 1999-12-10 | Nec Corp | Sonar device for detecting obstacle and underwater navigating body |
| CN102495420A (en) * | 2011-12-13 | 2012-06-13 | 大连海事大学 | Underwater object precision positioning system and method |
| CN202763840U (en) * | 2012-08-18 | 2013-03-06 | 郑州大学 | Autonomous control underwater robot based on image processing |
| CN104567820A (en) * | 2015-01-24 | 2015-04-29 | 无锡桑尼安科技有限公司 | Underwater target central position searching system |
| CN104679001A (en) * | 2015-01-25 | 2015-06-03 | 无锡桑尼安科技有限公司 | Rectangular target detection method |
-
2015
- 2015-08-04 CN CN201510470430.4A patent/CN105005050A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11337641A (en) * | 1998-05-27 | 1999-12-10 | Nec Corp | Sonar device for detecting obstacle and underwater navigating body |
| CN102495420A (en) * | 2011-12-13 | 2012-06-13 | 大连海事大学 | Underwater object precision positioning system and method |
| CN202763840U (en) * | 2012-08-18 | 2013-03-06 | 郑州大学 | Autonomous control underwater robot based on image processing |
| CN104567820A (en) * | 2015-01-24 | 2015-04-29 | 无锡桑尼安科技有限公司 | Underwater target central position searching system |
| CN104679001A (en) * | 2015-01-25 | 2015-06-03 | 无锡桑尼安科技有限公司 | Rectangular target detection method |
Non-Patent Citations (1)
| Title |
|---|
| 王猛 等: "基于区域分割的水下目标实时识别系统", 《计算机仿真》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111381233A (en) * | 2018-12-28 | 2020-07-07 | 中国船舶重工集团公司第七一九研究所 | Underwater confrontation situation display and control method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102566724B1 (en) | Harbor monitoring device and harbor monitoring method | |
| CN102879786B (en) | Detecting and positioning method and system for aiming at underwater obstacles | |
| CN105129052A (en) | Underwater human body searching method | |
| US20220351523A1 (en) | Method and device for monitoring port and ship in consideration of sea level | |
| CN105005996A (en) | Image sharpening analysis system | |
| CN111332288A (en) | Vehicle and pedestrian collision avoidance method based on vision system | |
| CN110371259A (en) | A kind of offshore colleting garbage floated on water device and method | |
| CN105173038A (en) | Below-ship submerged reef recognition device combining wavelet filters with median filters | |
| CN105076076A (en) | Fish body positioning system using neural network recognition | |
| CN105072395A (en) | Diver underwater rock avoiding method based on data communication | |
| CN105005050A (en) | Underwater rock detection method adopting neural network identification | |
| CN105004670A (en) | Underwater rock detection platform with neural network recognition adopted | |
| CN105007467B (en) | It is positioned at the human body search platform below hull bottom | |
| CN105123635A (en) | Fish body positioning method through neural network identification | |
| CN105095875A (en) | Method for detecting fishes under ship based on image filtering | |
| CN105070103A (en) | Data communication based ship underwater submerged rock avoiding system | |
| CN105068145A (en) | Sharpness analyzing platform for image of human body | |
| CN105035287A (en) | Underwater remain exploring method based on data communication | |
| CN105138008A (en) | Multifunctional submersible for underwater submerged reef detection | |
| CN105160637A (en) | Image sharpening analysis method | |
| CN105005979A (en) | Detection platform based on image filtering | |
| CN105184769A (en) | Sharp-image-processing-based underwater equipment defect identification system | |
| CN105069405A (en) | Sharpness analyzing method for image of human body | |
| CN105187775B (en) | Diver's subaqueous rock avoidance system based on data communication | |
| CN105057848A (en) | Underwater welding joint search platform capable of improving image processing accuracy |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20151028 |