CN109613559A - The flood boundaries floating material discriminating gear and method of view-based access control model and laser radar - Google Patents
The flood boundaries floating material discriminating gear and method of view-based access control model and laser radar Download PDFInfo
- Publication number
- CN109613559A CN109613559A CN201811547930.3A CN201811547930A CN109613559A CN 109613559 A CN109613559 A CN 109613559A CN 201811547930 A CN201811547930 A CN 201811547930A CN 109613559 A CN109613559 A CN 109613559A
- Authority
- CN
- China
- Prior art keywords
- module
- laser radar
- unmanned boat
- image
- riverbank
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 19
- 238000007667 floating Methods 0.000 title claims abstract description 13
- 239000000463 material Substances 0.000 title claims abstract description 12
- 238000012549 training Methods 0.000 claims abstract description 30
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 30
- 238000012545 processing Methods 0.000 claims abstract description 28
- 238000004891 communication Methods 0.000 claims abstract description 26
- 230000000007 visual effect Effects 0.000 claims abstract description 24
- 238000005259 measurement Methods 0.000 claims abstract description 22
- 238000010191 image analysis Methods 0.000 claims abstract description 19
- 238000013480 data collection Methods 0.000 claims abstract description 16
- 238000013528 artificial neural network Methods 0.000 claims abstract description 15
- 230000003993 interaction Effects 0.000 claims abstract description 13
- 230000008569 process Effects 0.000 claims abstract description 10
- 241000195493 Cryptophyta Species 0.000 claims description 9
- 238000005286 illumination Methods 0.000 claims description 6
- 238000009434 installation Methods 0.000 claims description 6
- 238000003062 neural network model Methods 0.000 claims description 6
- 230000002708 enhancing effect Effects 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 4
- 230000002068 genetic effect Effects 0.000 claims description 4
- 210000005036 nerve Anatomy 0.000 claims description 4
- 230000001537 neural effect Effects 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 230000001678 irradiating effect Effects 0.000 claims description 3
- 238000011897 real-time detection Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 230000001360 synchronised effect Effects 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract description 15
- 208000034699 Vitreous floaters Diseases 0.000 description 10
- 238000010586 diagram Methods 0.000 description 5
- 230000006872 improvement Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000002002 slurry Substances 0.000 description 1
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
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/89—Lidar systems specially adapted for specific applications for mapping or imaging
-
- 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
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/86—Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Remote Sensing (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Evolutionary Biology (AREA)
- Software Systems (AREA)
- Radar, Positioning & Navigation (AREA)
- Electromagnetism (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Multimedia (AREA)
- Optical Radar Systems And Details Thereof (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses the detection device of the floater and land boundary of a kind of view-based access control model and laser radar, described device includes data collection layer, processing diagnostic horizon and communication interface layer;The data collection layer: including a laser radar, a vision system and a visual processes SOC;The processing diagnostic horizon includes: MCU, human-computer interaction module, pose measurement module, image analysis processing module and deep neural network training module;Above-mentioned communication interface layer includes Ethernet SOC, Powerlink module and CAN module.The present invention provides the floater of a kind of view-based access control model and laser radar and the detection device and method of land boundary, the boundary on the water surface for having floating material and land or riverbank can accurately be differentiated by making unmanned boat both, the moment hull bottom and riverbed distance can be detected again, avoid stranded equal dangerous generation in time.
Description
Technical field
The present invention relates to the discriminating gear of the floater and land boundary of a kind of view-based access control model and laser radar and sides
Method belongs to the Condition Monitoring Technology field of industrial intelligent equipment.
Background technique
Refuse on water surface unmanned boat is that one kind does not need Manpower operating, by its independent navigation, detection, positioning, monitoring in
One, the special equipment of collecting refuse from open water prune job is carried out, due to Chinese Urbanization and industrialized development, to river
Pollution is produced, the floaters large area such as rubbish and floating algae covers the water surface, causes aquatic environment complicated, unmanned boat is in the water surface
On can not accurately differentiate flood boundaries, be possible to cause in this way unmanned boat in water operation when too close to riverbank, make nobody
Ship is stranded, or even causes unmanned boat hull damage.So this detection differentiation is to be badly in need of and necessary, in order to improve unmanned boat
Fluency and safety when operation.
Summary of the invention
To solve the above-mentioned problems, the present invention provides floater and the land side of a kind of view-based access control model and laser radar
The detection device and method on boundary, the boundary on the water surface for having floating material and land or riverbank can accurately be differentiated by making unmanned boat both,
The moment hull bottom and riverbed distance can be detected again, avoid stranded equal dangerous generation in time.Detection device of the present invention and nobody
Ship, come control flaps slurry, maintains easily maintenance and programming of the personnel to unmanned boat ontology and detection device by interface connection, and
Fault detection, analysis and replacement to laser radar and vision system and detection device.
Technical scheme is as follows:
The detection device of the floater and land boundary of a kind of view-based access control model and laser radar, described device includes that data are adopted
Collect layer, processing diagnostic horizon and communication interface layer;
The data collection layer: including a laser radar, a vision system and a visual processes SOC;The vision SOC
By broadcasting network absolute time and relative time, the image data of vision system and the point cloud data of laser radar scanning are realized
At the time of it is synchronous;The vision system and the laser radar simultaneously to same riverbank and water surface juncture area row scanning shoot,
Acquire riverbank, algae and rubbish point cloud data and visual pattern;The vision SOC Built-in Image preprocessor, passes through addition
Anisotropic diffusion filtering carries out smooth and image border to image and retains, this is existing ripe algorithm;
The processing diagnostic horizon includes: MCU, human-computer interaction module, pose measurement module, image analysis processing module and depth mind
Through network training module;By SPI communication bus communication, MCU passes through with human-computer interaction module for MCU and pose measurement module
RS485 is communicated, and the deep neural network training module and image analysis processing module directly pass through DMA in MCU memory
Carry out data exchange;
The human-computer interaction module is for providing manual remote control, display and audio output function, part when for initially installing
It is arranged, shows the harbor work's work that pulls in shore back of unmanned boat when work and work are completed;
The pose measurement module establishes station heart rectangular coordinate system by origin of laser radar, by the output for recording navigation software
Data record unmanned ship's head deflection information, the riverbank point cloud coordinate acquired by the space coordinates and laser radar,
The approximation space plane equation on the moment riverbank is fitted by principle of least square method, then range formula can obtain ship and arrive from point to surface
The vertical range on riverbank, it is stranded because of too close riverbank to avoid unmanned boat, and the data of the pose measurement module are also used for depth
Spend neural metwork training module training pattern;
Described image analysis and processing module can carry out characteristic point acquisition by image of the existing SIFT algorithm to data collection layer,
And feature point description vector is generated to all characteristic points, the above visual pattern, visual pattern characteristic point are transmitted to depth nerve
Network training model;
The deep neural network training module is by existing genetic algorithm, with visual pattern, visual pattern characteristic parameter
Input carries out evolutionary training to it to be output with the course deflection information of input data mutually in the same time;
The communication interface layer provides the communication interface of data transmission for device;Communication interface layer include Ethernet SOC,
Powerlink module and CAN module.
The detection method of the floater and land boundary of a kind of view-based access control model and laser radar, utilizes above-mentioned dress
It sets, it is characterised in that include the following steps:
(1) according to unmanned boat structure and draft, determine that laser radar irradiation area should be at a distance from fore holding, according to nothing
People's ship draft and river structure determine the early warning distance at ship and land and water boundary;
(2) by human-computer interaction module, Current vision system and laser radar direction of illumination and irradiating angle, radar illumination are set
Direction, vision system shooting direction, the direction of advance of fore direction and unmanned boat are answered coplanar;
(3) unmanned boat after the installation is completed, is placed in water by device, into device calibration phase;
(4) following special water surface visual signature image and radar scanning point cloud data: city are first acquired by manual operation unmanned boat
River riverbank texture, algae and rubbish waterborne and other floating materials;
(5) device obtains the data of vision system and laser radar by data collection layer, adds anisotropy to expand by vision SOC
The image that filtering shoots video camera is dissipated to pre-process, to image noise reduction and enhancing, meanwhile, pass through the communication of communication interface layer
Module is communicated with unmanned boat propeller control, and device receives the signal from propeller control, provides current spiral
Paddle direction of propulsion information;
(6) image analysis processing module utilizes the pretreatment image of data collection layer, establishes the time slip-window of image sequence simultaneously
Comparison front and back image changes, the characteristic parameter and invariant features parameter changed in real-time detection image, finally according to characteristic parameter
Establish floating material and riverbank characteristic model;
(7) pose measurement module real-time perfoming unmanned boat course deflection information acquires, and course deflection information is transmitted to depth
Neural training module;According to known river width and using radar as 3, any riverbank coordinate of space coordinates origin, nothing
People's ship calculates the depth of water and offshore distance of unmanned boat real time position, according to the early warning distance set, judges whether to occur
It is stranded;
(8) genetic algorithm is utilized, depth nerve training module is using image analysis processing modular character result as neural network mould
Type input, the course deflection information of pose measurement module is that output is trained, and stores network model, when the school of finishing device
Quasi- work;
(9) it if device does not complete calibration, repeats step (4) to step (8) and is calibrated;If device has been completed to calibrate, weight
Multiple step (4) and step (7), and enter step (10);
(10) stored neural network model is utilized, image analysis processing module is recorded a demerit defeated as neural network model
Enter, the information of pose measurement module is the operation at sea that output instruct unmanned boat;
(11) step (9) are repeated and step (10) starts to carry out the online real-time working process of unmanned boat.
Advantageous effects of the invention:
The floater and land boundary method of discrimination of view-based access control model and laser radar provided by the invention, can judge land and water side
Boundary and floating material, the generation for the safety accidents such as avoid unmanned boat stranded, can also measure the real-time unmanned ship position depth of water and offshore
Distance.In addition, discriminating gear of the present invention can also be used directly as third party's discriminating gear, facilitate unmanned boat or unmanned boat
Other work.
Detailed description of the invention
Fig. 1 is the hardware architecture diagram of apparatus of the present invention;
Fig. 2 is the installation site schematic diagram of apparatus of the present invention;
Fig. 3 is the detection principle diagram of apparatus of the present invention.
Specific embodiment
The invention will be further described below in conjunction with the accompanying drawings.Following embodiment is only used for clearly illustrating the present invention
Technical solution, and not intended to limit the protection scope of the present invention.
As shown in Figure 1, the detection device of the floater and land boundary of a kind of view-based access control model and laser radar, described
Device includes data collection layer, processing diagnostic horizon and communication interface layer;
The data collection layer: including a laser radar, a vision system and a visual processes SOC;The vision SOC
By broadcasting network absolute time and relative time, the image data of vision system and the point cloud data of laser radar scanning are realized
At the time of it is synchronous;The vision system and the laser radar simultaneously to same riverbank and water surface juncture area row scanning shoot,
Acquire riverbank, algae and rubbish point cloud data and visual pattern;The vision SOC Built-in Image preprocessor, i.e., by adding
Entering anisotropic filtering may be implemented vision system image real-time de-noising and enhancing;
The processing diagnostic horizon includes: MCU, human-computer interaction module, pose measurement module, image analysis processing module and depth mind
Through network training module;By SPI communication bus communication, MCU passes through with human-computer interaction module for MCU and pose measurement module
RS485 is communicated, and the deep neural network training module and image analysis processing module directly pass through DMA in MCU memory
Carry out data exchange;
The human-computer interaction module is for providing manual remote control, display and audio output function, part when for initially installing
It is arranged, shows the harbor work's work that pulls in shore back of unmanned boat when work and work are completed;
The pose measurement module is by establishing the dynamic space coordinate fixed as origin, three axes direction using laser radar
System, determines the real-time course deflection of unmanned boat, and acquires the information, passes through the space coordinates, it may be determined that laser radar acquisition
Riverbank point cloud coordinate can calculate the approximation space plane equation and Vertical Square on the moment riverbank using space geometry vector
To the unmanned boat real time position depth of water, unmanned boat is avoided because the depth of water is too shallow and stranded, the data of the pose measurement module are also used
In deep neural network training module training pattern;
Described image analysis and processing module carries out characteristic point acquisition by image of the SIFT algorithm to data collection layer, acquires city
River riverbank texture image, algae and rubbish floater waterborne as visual pattern characteristic parameter, and match synchronization,
The radar scanning point cloud chart of the same area, and the above visual pattern, visual pattern characteristic parameter and radar scanning point cloud chart are passed
Transport to deep neural network training pattern;
The deep neural network training module, with visual pattern, visual pattern characteristic parameter and matched radar points in the same time
Cloud atlas picture is input, to be output with the course deflection information of input data mutually in the same time, carries out evolutionary training;
The communication interface layer provides the communication interface of data transmission for device;Communication interface layer include Ethernet SOC,
Powerlink module and CAN module.
It is illustrated in figure 2 the installation site schematic diagram of apparatus of the present invention, laser radar and the vision system peace of apparatus of the present invention
Vision system and radar are mounted on the close ship in hull line of symmetry at unmanned boat ceiling, and it can be seen from top view
Head position guarantees unmanned boat balance when installation as far as possible.
It is illustrated in figure 3 the detection principle diagram of apparatus of the present invention, water surface information is acquired by vision system and radar, depending on
Feel SOC and handle the data processing of diagnostic horizon, vision system can be detected floater and riverbank, pass through deep neural network
The training result model of training module, can differentiate floating material and land boundary, in addition the early warning distance concurrently set, that is, can refer to
Lead work of the unmanned boat on the water surface.
The detection method of the floater and land boundary of a kind of view-based access control model and laser radar, utilizes above-mentioned dress
It sets, it is characterised in that include the following steps:
(1) according to unmanned boat structure and draft, determine that laser radar irradiation area should be at a distance from fore holding, according to nothing
People's ship draft and river structure determine the early warning distance at ship and land and water boundary;
(2) by human-computer interaction module, Current vision system and laser radar direction of illumination and irradiating angle, radar illumination are set
Direction, vision system shooting direction, the direction of advance of fore direction and unmanned boat are answered coplanar;
(3) unmanned boat after the installation is completed, is placed in water by device, into device calibration phase;
(4) following special water surface visual signature image and radar scanning point cloud data: city are first acquired by manual operation unmanned boat
River riverbank texture, algae and rubbish waterborne and other floating materials;
(5) device obtains the data of vision system and laser radar by data collection layer, adds anisotropy to filter by vision SOC
The image that wave shoots video camera pre-processes, to image noise reduction and enhancing, meanwhile, pass through the communication module of communication interface layer
It is communicated with unmanned boat propeller control, device receives the signal from propeller control, provides when front propeller pushes away
Into directional information;
(6) image analysis processing module utilizes the pretreatment image of data collection layer, establishes the time slip-window of image sequence simultaneously
Comparison front and back image changes, the characteristic parameter and invariant features parameter changed in real-time detection image, finally according to characteristic parameter
Establish floating material and riverbank characteristic model;
(7) pose measurement module real-time perfoming unmanned boat course deflection information acquires, and course deflection information is transmitted to depth
Neural training module;According to known river width and using radar as 3, any riverbank coordinate of space coordinates origin, nothing
People's ship calculates the depth of water and offshore distance of unmanned boat real time position, according to the early warning distance set, judges whether to occur
It is stranded;
(8) genetic algorithm is utilized, depth nerve training module is using image analysis processing modular character result as neural network mould
Type input, the course deflection information of pose measurement module is that output is trained, and stores network model, when the school of finishing device
Quasi- work;
(9) it if device does not complete calibration, repeats step (4) to step (8) and is calibrated;If device has been completed to calibrate, weight
Multiple step (4) and step (7), and enter step (10);
(10) stored neural network model is utilized, image analysis processing module is recorded a demerit defeated as neural network model
Enter, the information of pose measurement module is the operation at sea that output instruct unmanned boat;
(11) step (9) are repeated and step (10) starts to carry out the online real-time working process of unmanned boat.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, without departing from the technical principles of the invention, several improvement and deformations can also be made, these improvement and deformations
Also it should be regarded as protection scope of the present invention.
Claims (2)
1. the discriminating gear of the floater and land boundary of a kind of view-based access control model and laser radar, it is characterised in that: described
Device includes data collection layer, processing diagnostic horizon and communication interface layer;
The data collection layer: including a laser radar, a vision system and a visual processes SOC;The vision SOC
By broadcasting network absolute time and relative time, the image data of vision system and the point cloud data of laser radar scanning are realized
At the time of it is synchronous;The vision system and the laser radar simultaneously to same riverbank and water surface juncture area row scanning shoot,
Acquire riverbank, algae and rubbish point cloud data and visual pattern;The vision SOC Built-in Image preprocessor, i.e., by adding
Entering anisotropic filtering may be implemented vision system image real-time de-noising and enhancing;
The processing diagnostic horizon includes: MCU, human-computer interaction module, pose measurement module, image analysis processing module and depth mind
Through network training module;By SPI communication bus communication, MCU passes through with human-computer interaction module for MCU and pose measurement module
RS485 is communicated, and the deep neural network training module and image analysis processing module directly pass through DMA in MCU memory
Carry out data exchange;
The human-computer interaction module is for providing manual remote control, display and audio output function, part when for initially installing
It is arranged, shows the harbor work's work that pulls in shore back of unmanned boat when work and work are completed;
The pose measurement module is by establishing the dynamic space coordinate fixed as origin, three axes direction using laser radar
System, determines the real-time course deflection of unmanned boat, and acquires the information, passes through the space coordinates, it may be determined that laser radar acquisition
Riverbank point cloud coordinate can calculate the approximation space plane equation and Vertical Square on the moment riverbank using space geometry vector
To the unmanned boat real time position depth of water, unmanned boat is avoided because the depth of water is too shallow and stranded, the data of the pose measurement module are also used
In deep neural network training module training pattern;
Described image analysis and processing module carries out characteristic point acquisition by image of the SIFT algorithm to data collection layer, acquires city
River riverbank texture image, algae and rubbish floater waterborne as visual pattern characteristic parameter, and match synchronization,
The radar scanning point cloud chart of the same area, and the above visual pattern, visual pattern characteristic parameter and radar scanning point cloud chart are passed
Transport to deep neural network training pattern;
The deep neural network training module, with visual pattern, visual pattern characteristic parameter and matched radar points in the same time
Cloud atlas picture is input, to be output with the course deflection information of input data mutually in the same time, carries out evolutionary training;
The communication interface layer provides the communication interface of data transmission for device;Communication interface layer include Ethernet SOC,
Powerlink module and CAN module.
2. the method for discrimination of the floater and land boundary of a kind of view-based access control model and laser radar utilizes claim 1 institute
The device stated, it is characterised in that include the following steps:
(1) according to unmanned boat structure and draft, determine that laser radar irradiation area should be at a distance from fore holding, according to nothing
People's ship draft and river structure determine the early warning distance at ship and land and water boundary;
(2) by human-computer interaction module, Current vision system and laser radar direction of illumination and irradiating angle, radar illumination are set
Direction, vision system shooting direction, the direction of advance of fore direction and unmanned boat are answered coplanar;
(3) unmanned boat after the installation is completed, is placed in water by device, into device calibration phase;
(4) following special water surface visual signature image and radar scanning point cloud data: city are first acquired by manual operation unmanned boat
River riverbank texture, algae and rubbish waterborne and other floating materials;
(5) device obtains the data of vision system and laser radar by data collection layer, adds anisotropy to filter by vision SOC
The image that wave shoots video camera pre-processes, to image noise reduction and enhancing, meanwhile, pass through the communication module of communication interface layer
It is communicated with unmanned boat propeller control, device receives the signal from propeller control, provides when front propeller pushes away
Into directional information;
(6) image analysis processing module utilizes the pretreatment image of data collection layer, establishes the time slip-window of image sequence simultaneously
Comparison front and back image changes, the characteristic parameter and invariant features parameter changed in real-time detection image, finally according to characteristic parameter
Establish floating material and riverbank characteristic model;
(7) pose measurement module real-time perfoming unmanned boat course deflection information acquires, and course deflection information is transmitted to depth
Neural training module;According to known river width and using radar as 3, any riverbank coordinate of space coordinates origin, nothing
People's ship calculates the depth of water and offshore distance of unmanned boat real time position, according to the early warning distance set, judges whether to occur
It is stranded;
(8) genetic algorithm is utilized, depth nerve training module is using image analysis processing modular character result as neural network mould
Type input, the course deflection information of pose measurement module is that output is trained, and stores network model, when the school of finishing device
Quasi- work;
(9) it if device does not complete calibration, repeats step (4) to step (8) and is calibrated;If device has been completed to calibrate, weight
Multiple step (4) and step (7), and enter step (10);
(10) stored neural network model is utilized, image analysis processing module is recorded a demerit defeated as neural network model
Enter, the information of pose measurement module is the operation at sea that output instruct unmanned boat;
(11) step (9) are repeated and step (10) starts to carry out the online real-time working process of unmanned boat.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811547930.3A CN109613559B (en) | 2018-12-18 | 2018-12-18 | Device and method for distinguishing water-land boundary floaters based on vision and laser radar |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811547930.3A CN109613559B (en) | 2018-12-18 | 2018-12-18 | Device and method for distinguishing water-land boundary floaters based on vision and laser radar |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109613559A true CN109613559A (en) | 2019-04-12 |
CN109613559B CN109613559B (en) | 2022-04-22 |
Family
ID=66009464
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811547930.3A Expired - Fee Related CN109613559B (en) | 2018-12-18 | 2018-12-18 | Device and method for distinguishing water-land boundary floaters based on vision and laser radar |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109613559B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110371259A (en) * | 2019-07-29 | 2019-10-25 | 河海大学常州校区 | A kind of offshore colleting garbage floated on water device and method |
CN110414396A (en) * | 2019-07-19 | 2019-11-05 | 中国人民解放军海军工程大学 | A kind of unmanned boat perception blending algorithm based on deep learning |
CN110632920A (en) * | 2019-08-29 | 2019-12-31 | 上海海事大学 | Unmanned ship control method |
CN115202370A (en) * | 2022-09-15 | 2022-10-18 | 泰山学院 | Navigation control method and system for unmanned ship and readable storage medium |
CN116642536A (en) * | 2023-05-31 | 2023-08-25 | 交通运输部天津水运工程科学研究所 | Breakwater structure safety monitoring and early warning system based on multi-source data |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101125233B1 (en) * | 2010-11-25 | 2012-03-21 | 재단법인대구경북과학기술원 | Fusion technology-based security method and security system thereof |
CN102975826A (en) * | 2012-12-03 | 2013-03-20 | 上海海事大学 | Portable ship water gauge automatic detection and identification method based on machine vision |
CN103927751A (en) * | 2014-04-18 | 2014-07-16 | 哈尔滨工程大学 | Water surface optical visual image target area detection method based on gradient information fusion |
CN108731788A (en) * | 2018-05-22 | 2018-11-02 | 河海大学常州校区 | A kind of working at height arm low-frequency vibration vision inspection apparatus and method |
-
2018
- 2018-12-18 CN CN201811547930.3A patent/CN109613559B/en not_active Expired - Fee Related
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101125233B1 (en) * | 2010-11-25 | 2012-03-21 | 재단법인대구경북과학기술원 | Fusion technology-based security method and security system thereof |
CN102975826A (en) * | 2012-12-03 | 2013-03-20 | 上海海事大学 | Portable ship water gauge automatic detection and identification method based on machine vision |
CN103927751A (en) * | 2014-04-18 | 2014-07-16 | 哈尔滨工程大学 | Water surface optical visual image target area detection method based on gradient information fusion |
CN108731788A (en) * | 2018-05-22 | 2018-11-02 | 河海大学常州校区 | A kind of working at height arm low-frequency vibration vision inspection apparatus and method |
Non-Patent Citations (1)
Title |
---|
周华: "红外视觉检测技术和数字信号处理器在内河船舶助航***中的应用研究", 《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110414396A (en) * | 2019-07-19 | 2019-11-05 | 中国人民解放军海军工程大学 | A kind of unmanned boat perception blending algorithm based on deep learning |
CN110414396B (en) * | 2019-07-19 | 2021-07-16 | 中国人民解放军海军工程大学 | Unmanned ship perception fusion algorithm based on deep learning |
CN110371259A (en) * | 2019-07-29 | 2019-10-25 | 河海大学常州校区 | A kind of offshore colleting garbage floated on water device and method |
CN110371259B (en) * | 2019-07-29 | 2021-06-01 | 河海大学常州校区 | Near-shore water surface floater cleaning device and method |
CN110632920A (en) * | 2019-08-29 | 2019-12-31 | 上海海事大学 | Unmanned ship control method |
CN115202370A (en) * | 2022-09-15 | 2022-10-18 | 泰山学院 | Navigation control method and system for unmanned ship and readable storage medium |
CN116642536A (en) * | 2023-05-31 | 2023-08-25 | 交通运输部天津水运工程科学研究所 | Breakwater structure safety monitoring and early warning system based on multi-source data |
Also Published As
Publication number | Publication date |
---|---|
CN109613559B (en) | 2022-04-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109613559A (en) | The flood boundaries floating material discriminating gear and method of view-based access control model and laser radar | |
CN109670411B (en) | Ship point cloud depth image processing method and system based on generation countermeasure network | |
CN110414396B (en) | Unmanned ship perception fusion algorithm based on deep learning | |
CN103139482B (en) | Vision Builder for Automated Inspection is searched and rescued in the perils of the sea | |
CN106741683B (en) | A kind of water area refuse automated cleaning ship and automatic cleaning method based on machine vision | |
CN105184816A (en) | Visual inspection and water surface target tracking system based on USV and detection tracking method thereof | |
CN109283538A (en) | A kind of naval target size detection method of view-based access control model and laser sensor data fusion | |
CN110580044A (en) | unmanned ship full-automatic navigation heterogeneous system based on intelligent sensing | |
CN104297758B (en) | A kind of auxiliary berthing device and its method based on 2D pulse type laser radars | |
KR102339465B1 (en) | Autonomous navigation ship system for removing sea waste based on deep learning-vision recognition | |
CN114782905B (en) | Ship draft detection method based on video monitoring | |
CN101214851A (en) | Intelligent all-weather actively safety early warning system and early warning method thereof for ship running | |
CN113436258A (en) | Offshore pontoon detection method and system based on fusion of vision and laser radar | |
CN109835441A (en) | The automatic Pilot method and its system of water quality monitoring intelligence canoe | |
Papadopoulos et al. | 3D-surface reconstruction for partially submerged marine structures using an autonomous surface vehicle | |
CN108871409A (en) | A kind of fault detection method and system | |
CN114926739A (en) | Unmanned collaborative acquisition and processing method for underwater and overwater geographic spatial information of inland waterway | |
CN111746728A (en) | Novel overwater cleaning robot based on reinforcement learning and control method | |
CN105824024B (en) | A kind of anti-frogman's solid early warning identifying system of new submerged gate | |
CN109982044A (en) | A kind of tracking of the target localization and tracking system based on CCTV Sensor Network | |
CN115060343A (en) | Point cloud-based river water level detection system, detection method and program product | |
CN106096617A (en) | A kind of based on the panorama sea horizon extracting method improving active contour model | |
CN116343551A (en) | Intelligent ship control simulation system and method | |
Susanto et al. | Development of underwater object detection method base on color feature | |
CN114046777A (en) | Underwater optical imaging system and method suitable for large-range shallow sea coral reef drawing |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20220422 |