CN105059506B - intelligent underwater robot based on laser imaging detection - Google Patents
intelligent underwater robot based on laser imaging detection Download PDFInfo
- Publication number
- CN105059506B CN105059506B CN201510443651.2A CN201510443651A CN105059506B CN 105059506 B CN105059506 B CN 105059506B CN 201510443651 A CN201510443651 A CN 201510443651A CN 105059506 B CN105059506 B CN 105059506B
- Authority
- CN
- China
- Prior art keywords
- subset
- underwater
- image
- human body
- laser
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Studio Devices (AREA)
Abstract
The present invention relates to a kind of intelligent underwater robot based on laser imaging detection, including underwater human agent, laser imaging apparatus, feature extraction identification equipment, described laser imaging apparatus and described feature extraction identification equipment are all located on described underwater human agent, described laser imaging apparatus is used for shooting underwater laser image, described feature extraction identification equipment is connected with described laser imaging apparatus, for extracting characteristics of human body determine human body type under water from described underwater laser image.By means of the invention it is possible to accurately carry out underwater laser images, and remains under water can be automatically detected.
Description
Technical field
The present invention relates to image processing field, particularly relate to a kind of intellectuality based on laser imaging detection
Underwater robot.
Background technology
In prior art, diver carry electronic equipment, be used for using technique of laser imaging under water
Target shoots, and uses image processing techniques that the laser image of shooting is carried out human body target identification afterwards,
It it is the conventional means of human body target detection under water.
There is following defect in above-mentioned means: 1, diver's life is on the hazard；2, laser imaging effect
Difference；3, underwater picture identification technology targetedly is lacked.For these reasons, existing water is caused
Lower human body target recognition reliability and safety are the highest.
For this reason, it may be necessary to a kind of new human body target identifying schemes under water based on laser imaging detection, energy
Enough use machine detection mode to substitute artificial detection mode, improve laser imaging effect, and can carry
Hi-vision accuracy of identification.
Summary of the invention
In order to solve the technical problem that prior art exists, the invention provides a kind of based on laser imaging
The intelligent underwater robot of detection, utilizes distinctive underwater robot structure for carrier, introduces high-precision
The laser imaging of degree controls technology, and uses neural network recognization mode to carry out image procossing, thus more
Detect human body target under water exactly, improve the intelligent level rescued under water.
According to an aspect of the present invention, it is provided that a kind of intellectuality machine under water based on laser imaging detection
Device people, described underwater robot includes that underwater human agent, laser imaging apparatus, feature extraction are known
Other equipment, described laser imaging apparatus and described feature extraction identification equipment are all located at described underwater
On human agent, described laser imaging apparatus is used for shooting underwater laser image, described feature extraction identification
Equipment is connected with described laser imaging apparatus, for extracting human body under water from described underwater laser image
Feature also determines human body type.
More specifically, in described intelligent underwater robot based on laser imaging detection, also include:
Described underwater human agent includes support, left pressure gram transparent tube, right pressure gram transparent tube, connection
Hoop, storage platform, mechanical arm, mechanical hand, water proof sealing drum, transverse propeller, vertical propeller,
Longitudinal spiral oar and three direct current generators, described support is for being fixed on described underwater human agent
Under water, described connecting hoop is fixing with described support to be connected, and described storage platform and described mechanical arm are with described
Connecting hoop connects respectively, and described mechanical hand is connected with described mechanical arm, described mechanical arm include large arm and
The forearm being connected with large arm, described three direct current generators drive described transverse propeller, described perpendicular respectively
To propeller and described longitudinal spiral oar, with by the rotating of propeller, for underwater human agent
The thrust power of 6 degree of freedom is provided；Portable hard drive, is positioned on described underwater human agent, uses
In having prestored the luminance threshold upper limit and luminance threshold lower limit；Sonar, be positioned at described in machine under water
On device human agent, adopt for the submarine target in described underwater human agent front is performed sonar image
Collection, to obtain sonar image；Sonar image processing equipment, hard with described sonar and described movement
Dish connects respectively, sets including the first detection subset, the second detection subset and object range detection
Standby, described first detection subset is connected respectively with described sonar and described portable hard drive, is used for
Use luminance threshold upper limit traversal sonar image to be partitioned into core objective region；Described second detection
Equipment is connected respectively with described first detection subset and described portable hard drive, for described core mesh
The marginal point in mark region, as seed points, utilizes the luminance threshold lower limit picture to core objective areas adjacent
Vegetarian refreshments carries out brightness judgement, to obtain and to be partitioned into final goal region；Described object range detection
Equipment is connected with described second detection subset, calculates the central point in final goal region to sonar image
Detect the distance of initial point and export as target range；Described laser imaging apparatus, including laser instrument,
Detector and microcontroller, the submarine target in described underwater human agent front is sent out by described laser instrument
Go out laser beam, with when described laser beam is reflexed to described detector by submarine target, it is simple to described spy
Survey the shooting of device, described microcontroller and described sonar image processing equipment, described laser instrument and described
Detector connects respectively, determines that described detector is fast based on target range and laser spread speed under water
The gating time of door, and when gating time arrives, gate the shutter of described detector, trigger described
Submarine target is shot by detector, to obtain underwater laser image；Described feature extraction identification sets
For including pretreatment subset, feature extraction subset and human body type identification subset；Described pre-place
Reason subset is connected with described laser imaging apparatus, sets including medium filtering subset, low pass filtered marble
Standby and homomorphic filtering subset；Described medium filtering subset is connected with described detector, for institute
State underwater laser image and perform medium filtering, to filter the spot noise in described underwater laser image, obtain
Obtain the first filtering image；Described low-pass filtering subset is connected with described medium filtering subset, is used for
Remove the random noise in described first filtering image, it is thus achieved that the second filtering image；Described homomorphic filtering
Subset is connected with described low-pass filtering subset, increases for described second filtering image is performed image
By force, underwater picture is strengthened to obtain；Described feature extraction subset is connected with described pretreatment subset,
Including image segmentation unit and eigenvector recognition unit, described image segmentation unit is based on human body image
Human body target in described enhancing underwater picture is identified to obtain people under water by gray threshold scope
Body image；Described eigenvector recognition unit is connected with described image segmentation unit, based on described under water
Human body image determines 8 geometric properties of human body target under water: Euler's hole count, circularity, angle point number,
Convex-concave degree, smoothness, draw ratio, compactness and main shaft angle, and by described 8 geometric properties groups
Become characteristic vector；Described human body type identification subset is connected with described feature extraction subset, uses
Single hidden layer BP neutral nets of 8 input 4 outputs, using 8 geometric properties of human body target under water as
Input layer, output layer is human body type under water, and the described type of human body under water includes remains, youngster
Virgin visitor, old man visitor and adult visitor；Main control device, is arranged on described underwater human agent,
It is connected with described human body type identification subset, when described in receiving, human body type is remains under water,
Send remains alarm signal, described in receive under water human body type be child visitor, old man visitor or
During adult visitor, send visitor's alarm signal；Submerged cable, is used for described main control device with waterborne
Rescue center connects, and is sent to described waterborne by described remains alarm signal or described visitor's alarm signal
Rescue center.
More specifically, in described intelligent underwater robot based on laser imaging detection: in described
Value filtering subset, described low-pass filtering subset and described homomorphic filtering subset are respectively adopted difference
Fpga chip realize.
More specifically, in described intelligent underwater robot based on laser imaging detection: in described
Value filtering subset, described low-pass filtering subset and described homomorphic filtering subset are integrated in one piece
On surface-mounted integrated circuit.
More specifically, in described intelligent underwater robot based on laser imaging detection: described master
Control equipment is digital signal processor.
More specifically, in described intelligent underwater robot based on laser imaging detection: described master
Control equipment is when sending described remains alarm signal or described visitor's alarm signal, also by described people under water
Described water life-saving center it is sent to after body compression of images.
Accompanying drawing explanation
Below with reference to accompanying drawing, embodiment of the present invention are described, wherein:
Fig. 1 is according to the intellectuality machine under water based on laser imaging detection shown in embodiment of the present invention
The block diagram of device people.
Reference: 1 underwater human agent；2 laser imaging apparatus；3 feature extraction identifications set
Standby
Detailed description of the invention
Intelligent underwater robot based on laser imaging detection to the present invention below with reference to accompanying drawings
Embodiment be described in detail.
In prior art, the identification to personnel under water depends on manual type partially, and safety is the highest, and
Testing mechanism is the most coarse, and recognition efficiency is relatively low.
In order to overcome above-mentioned deficiency, the present invention has built a kind of intelligent water based on laser imaging detection
Lower robot, uses intelligent underwater robot to analyze submarine target type accurately and efficiently, carries
Height rescues speed under water.
Fig. 1 is according to the intellectuality machine under water based on laser imaging detection shown in embodiment of the present invention
The block diagram of device people, described underwater robot include underwater human agent, laser imaging apparatus,
Feature extraction identification equipment, described laser imaging apparatus and described feature extraction identification equipment are all located at institute
Stating on underwater human agent, described laser imaging apparatus is used for shooting underwater laser image, described spy
Levy extraction identification equipment to be connected with described laser imaging apparatus, for carrying from described underwater laser image
The lower characteristics of human body of water intaking also determines human body type.
Then, the concrete of the intelligent underwater robot based on laser imaging detection to the present invention is continued
Structure is further detailed.
Described underwater robot also includes: described underwater human agent includes that support, left pressure gram are saturating
Placket, right pressure gram transparent tube, connecting hoop, storage platform, mechanical arm, mechanical hand, water proof sealing drum,
Transverse propeller, vertical propeller, longitudinal spiral oar and three direct current generators, described support is used for will
Described underwater human agent is fixed under water, and described connecting hoop is fixing with described support to be connected, described
Storage platform and described mechanical arm are connected respectively with described connecting hoop, and described mechanical hand is with described mechanical arm even
Connecing, described mechanical arm includes that large arm and the forearm being connected with large arm, described three direct current generators carry respectively
Dynamic described transverse propeller, described vertical propeller and described longitudinal spiral oar, with by propeller
Rotating, provides the thrust power of 6 degree of freedom for underwater human agent.
Described underwater robot also includes: portable hard drive, is positioned on described underwater human agent, uses
In having prestored the luminance threshold upper limit and luminance threshold lower limit.
Described underwater robot also includes: sonar, is positioned on described underwater human agent, uses
In the submarine target execution sonar image collection to described underwater human agent front, to obtain sonar
Image.
Described underwater robot also includes: sonar image processing equipment, with described sonar and described
Portable hard drive connects respectively, including the first detection subset, the second detection subset and target range inspection
Surveying subset, described first detection subset connects respectively with described sonar and described portable hard drive
Connect, be used for using luminance threshold upper limit traversal sonar image to be partitioned into core objective region.
Described second detection subset connects respectively with described first detection subset and described portable hard drive
Connect, for the marginal point using described core objective region as seed points, utilize luminance threshold lower limit pair
The pixel of core objective areas adjacent carries out brightness judgement, to obtain and to be partitioned into final goal district
Territory；Described object range detection subset is connected with described second detection subset, calculates final goal
The central point in region is to the distance of sonar image detection initial point and as target range output.
Described laser imaging apparatus, including laser instrument, detector and microcontroller, described laser instrument pair
The submarine target in described underwater human agent front sends laser beam, with at described laser beam by under water
When target reflection is to described detector, it is simple to the shooting of described detector, described microcontroller is with described
Sonar image processing equipment, described laser instrument and described detector connect respectively, based on target range and
Laser spread speed under water determines the gating time of described detector shutter, and arrives in gating time
Time, gate the shutter of described detector, trigger described detector and submarine target is shot, to obtain
Obtain underwater laser image.
Described feature extraction identification equipment includes pretreatment subset, feature extraction subset and human body class
Type identification subset；Described pretreatment subset is connected with described laser imaging apparatus, filters including intermediate value
Marble equipment, low-pass filtering subset and homomorphic filtering subset；Described medium filtering subset and institute
State detector to connect, for described underwater laser image is performed medium filtering, with described in filtering under water
Spot noise in laser image, it is thus achieved that the first filtering image；Described low-pass filtering subset with described in
Value filtering subset connects, for removing the random noise in described first filtering image, it is thus achieved that second
Filtering image；Described homomorphic filtering subset is connected with described low-pass filtering subset, for described
Second filtering image performs image enhaucament, strengthens underwater picture to obtain；Described feature extraction subset
It is connected with described pretreatment subset, including image segmentation unit and eigenvector recognition unit, described
Image segmentation unit based on human body image gray threshold scope by the human body in described enhancing underwater picture
Target recognition is out to obtain human body image under water；Described eigenvector recognition unit divides with described image
Cut unit to connect, determine 8 geometric properties of human body target under water based on described human body image under water:
Euler's hole count, circularity, angle point number, convex-concave degree, smoothness, draw ratio, compactness and main shaft angle,
And by described 8 geometric properties composition characteristics vector.
Described human body type identification subset is connected with described feature extraction subset, uses 8 inputs 4
Single hidden layer BP neutral net of output, using 8 geometric properties of human body target under water as input layer
Neuron, output layer is human body type under water, the described type of human body under water include remains, child visitor,
Old man visitor and adult visitor.
Described underwater robot also includes: main control device, is arranged on described underwater human agent,
It is connected with described human body type identification subset, when described in receiving, human body type is remains under water,
Send remains alarm signal, described in receive under water human body type be child visitor, old man visitor or
During adult visitor, send visitor's alarm signal；Submerged cable, is used for described main control device with waterborne
Rescue center connects, and is sent to described waterborne by described remains alarm signal or described visitor's alarm signal
Rescue center.
Alternatively, in described intelligent underwater robot based on laser imaging detection: described intermediate value
Filtering subset, described low-pass filtering subset and described homomorphic filtering subset are respectively adopted different
Fpga chip realizes；Described medium filtering subset, described low-pass filtering subset and described with
State filtering subset is integrated on one piece of surface-mounted integrated circuit；Described main control device is Digital Signal Processing
Device；Described main control device, when sending described remains alarm signal or described visitor's alarm signal, also will
It is sent to described water life-saving center after the compression of described human body image under water.
It addition, FPGA (Field-Programmable Gate Array), i.e. field-programmable gate array
Row, he is the product of development further on the basis of the programming devices such as PAL, GAL, CPLD.
He is to occur as a kind of semi-custom circuit in special IC (ASIC) field, both solves
Determine the deficiency of custom circuit, overcome again the shortcoming that original programming device gate circuit number is limited.
The circuit design completed with hardware description language (Verilog or VHDL), can be through letter
Single comprehensive and layout, is quickly burned onto on FPGA and tests, and is modern IC designs checking
Technology main flow.These can be edited element and can be used to realize some basic logic gates (ratio
Such as AND, OR, XOR, NOT) or more more complicated combination function such as decoder or number
Learn equation.Inside most FPGA, in these editable elements, also comprise memory cell
Such as trigger (Flip-flop) or other more complete block of memory.System designer can root
By editable connection, the logical block within FPGA is coupled together according to needing, just look like an electricity
Road bread board has been placed in a chip.One dispatch from the factory after the logical block of finished product FPGA and connection
Can change according to designer, so FPGA can complete required logic function.
FPGA in general speed than ASIC (special IC) is slow, it is achieved same merit
Can be bigger than ASIC circuit area.But they also have a lot of advantages such as can quick finished product,
The mistake in correction program and less expensive cost can be modified to.Manufacturer is likely to provide cheap
But edit capability difference FPGA.Because these chips have poor can edit capability, so
The exploitation of these designs is to complete on common FPGA, then design is transferred to one and is similar to
On the chip of ASIC.Another method is with CPLD (Complex Programmable Logic
Device, CPLD).The exploitation of FPGA is relative to tradition PC, main control device
Exploitation is very different.FPGA, based on concurrent operation, realizes with hardware description language；Compare
Order in PC or main control device (either von Neumann structure or Harvard structure) operates to be had very
Big difference.
As far back as 1980 mid-nineties 90s, FPGA takes root in PLD equipment.CPLD and FPGA
Include the Programmadle logic unit of some relatively large amount.The density of CPLD gate arrives thousand of
Between several ten thousand logical blocks, and FPGA is typically several ten thousand to millions of.CPLD and FPGA
The main distinction be their system structure.CPLD is a somewhat restrictive structure.This knot
Structure is arranged by the logical groups of one or more editable result sum and the locking of some relatively small amounts
Depositor composition.Such result be a lack of edit motility, but but have it is anticipated that delay
Time and the logical block advantage to connecting unit height ratio.And FPGA is to have a lot of connection lists
Unit, although so allowing him edit more flexibly, but structure is complicated many.
Use the intelligent underwater robot based on laser imaging detection of the present invention, for prior art
In under water human bioequivalence system optimize not and cause Detection results difference technical problem, use sonar
Optimizing laser imaging with sonar image processing equipment to control, being simultaneously introduced neural network recognization technology has
Tell human body target under water pointedly, thus improve the response speed rescued under water.
Although it is understood that the present invention discloses as above with preferred embodiment, but above-mentioned enforcement
Example is not limited to the present invention.For any those of ordinary skill in the art, without departing from
Under technical solution of the present invention ambit, all may utilize the technology contents of the disclosure above to the technology of the present invention
Scheme makes many possible variations and modification, or is revised as the Equivalent embodiments of equivalent variations.Therefore,
Every content without departing from technical solution of the present invention, the technical spirit of the foundation present invention is to above example
Any simple modification, equivalent variations and the modification done, all still falls within technical solution of the present invention protection
In the range of.
Claims (1)
1. an intelligent underwater robot based on laser imaging detection, described underwater robot bag
Including underwater human agent, laser imaging apparatus, feature extraction identification equipment, described laser imaging sets
Standby and described feature extraction identification equipment is all located on described underwater human agent, described laser imaging
Equipment is used for shooting underwater laser image, described feature extraction identification equipment and described laser imaging apparatus
Connect, for extracting characteristics of human body determine human body type under water from described underwater laser image；
It is characterized in that, described underwater robot also includes:
Described underwater human agent include support, left pressure gram transparent tube, right pressure gram transparent tube,
Connecting hoop, storage platform, mechanical arm, mechanical hand, water proof sealing drum, transverse propeller, vertical spiral
Oar, longitudinal spiral oar and three direct current generators, described support is for solid by described underwater human agent
Being scheduled under water, described connecting hoop and described support are fixing to be connected, described storage platform and described mechanical arm and
Described connecting hoop connects respectively, and described mechanical hand is connected with described mechanical arm, and described mechanical arm includes greatly
Arm and the forearm being connected with large arm, described three direct current generators drive described transverse propeller, institute respectively
State vertical propeller and described longitudinal spiral oar, with by the rotating of propeller, for underwater robot
Main body provides the thrust power of 6 degree of freedom；
Portable hard drive, is positioned on described underwater human agent, is used for having prestored luminance threshold
Limit and luminance threshold lower limit；
Sonar, is positioned on described underwater human agent, for described underwater human agent
The submarine target in front performs sonar image collection, to obtain sonar image；
Sonar image processing equipment, is connected respectively with described sonar and described portable hard drive, including
First detection subset, the second detection subset and object range detection subset, described first detection
Subset is connected respectively with described sonar and described portable hard drive, is used for using the luminance threshold upper limit
Traversal sonar image is to be partitioned into core objective region；Described second detection subset and described first inspection
Survey subset and described portable hard drive connects respectively, make for the marginal point with described core objective region
For seed points, utilize luminance threshold lower limit that the pixel of core objective areas adjacent is carried out brightness and sentence
Disconnected, to obtain and to be partitioned into final goal region；Described object range detection subset and described second
Detection subset connects, and calculates the central point distance to sonar image detection initial point in final goal region
And export as target range；
Described laser imaging apparatus, including laser instrument, detector and microcontroller, described laser instrument pair
The submarine target in described underwater human agent front sends laser beam, with at described laser beam by under water
When target reflection is to described detector, it is simple to the shooting of described detector, described microcontroller is with described
Sonar image processing equipment, described laser instrument and described detector connect respectively, based on target range and
Laser spread speed under water determines the gating time of described detector shutter, and arrives in gating time
Time, gate the shutter of described detector, trigger described detector and submarine target is shot, to obtain
Obtain underwater laser image；
Described feature extraction identification equipment includes pretreatment subset, feature extraction subset and human body class
Type identification subset；
Described pretreatment subset is connected with described laser imaging apparatus, including medium filtering subset,
Low-pass filtering subset and homomorphic filtering subset；Described medium filtering subset is with described detector even
Connect, for described underwater laser image is performed medium filtering, to filter in described underwater laser image
Spot noise, it is thus achieved that the first filtering image；Described low-pass filtering subset sets with described medium filtering
Standby connection, for removing the random noise in described first filtering image, it is thus achieved that the second filtering image；
Described homomorphic filtering subset is connected with described low-pass filtering subset, for described second filtering figure
As performing image enhaucament, strengthen underwater picture to obtain；
Described feature extraction subset is connected with described pretreatment subset, including image segmentation unit and
Eigenvector recognition unit, described image segmentation unit based on human body image gray threshold scope by described
The human body target strengthened in underwater picture identifies to obtain human body image under water；Described characteristic vector
Recognition unit is connected with described image segmentation unit, determines human body under water based on described human body image under water
8 geometric properties of target: Euler's hole count, circularity, angle point number, convex-concave degree, smoothness, major diameter
Ratio, compactness and main shaft angle, and by described 8 geometric properties composition characteristics vector；
Described human body type identification subset is connected with described feature extraction subset, uses 8 inputs 4
Single hidden layer BP neutral net of output, using 8 geometric properties of human body target under water as input layer
Neuron, output layer is human body type under water, the described type of human body under water include remains, child visitor,
Old man visitor and adult visitor；
Main control device, is arranged on described underwater human agent, sets with described human body type identification
Standby connection, when human body type is remains under water described in receiving, sends remains alarm signal, when connecing
When human body type is child visitor, old man visitor or adult visitor under water described in receiving, send visitor's report
Alert signal；
Submerged cable, for being connected described main control device with water life-saving center, by described remains report
Alert signal or described visitor's alarm signal are sent to described water life-saving center.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510443651.2A CN105059506B (en) | 2015-07-24 | 2015-07-24 | intelligent underwater robot based on laser imaging detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510443651.2A CN105059506B (en) | 2015-07-24 | 2015-07-24 | intelligent underwater robot based on laser imaging detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105059506A CN105059506A (en) | 2015-11-18 |
| CN105059506B true CN105059506B (en) | 2016-09-14 |
Family
ID=54489105
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510443651.2A Active CN105059506B (en) | 2015-07-24 | 2015-07-24 | intelligent underwater robot based on laser imaging detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105059506B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105963875A (en) * | 2016-05-24 | 2016-09-28 | 杨燕 | High-altitude work safety belt suspension device for power plant |
| WO2018104786A1 (en) | 2016-12-07 | 2018-06-14 | Abb Schweiz Ag | Submersible inspection vehicle with navigation and mapping capabilities |
| CN115032946B (en) * | 2022-06-21 | 2022-12-06 | 浙江同发塑机有限公司 | Blow molding control method and system of blow molding machine |
-
2015
- 2015-07-24 CN CN201510443651.2A patent/CN105059506B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN105059506A (en) | 2015-11-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104967832B (en) | A kind of area detecting method that launches a ship based on image procossing | |
| Zhang et al. | Target detection of forward-looking sonar image based on improved YOLOv5 | |
| CN109117876A (en) | A kind of dense small target deteection model building method, model and detection method | |
| CN105059506B (en) | intelligent underwater robot based on laser imaging detection | |
| CN109359519A (en) | A kind of video anomaly detection method based on deep learning | |
| CN105574550A (en) | Vehicle identification method and device | |
| CN112528782B (en) | Underwater fish target detection method and device | |
| CN113378763B (en) | SAR image-oriented target automatic detection method and system | |
| CN110245642A (en) | A kind of radar spectrum recognition method and system based on deep learning | |
| CN105046888A (en) | Water tourist identification monitoring platform | |
| CN110321944A (en) | A kind of construction method of the deep neural network model based on contact net image quality evaluation | |
| CN103761526A (en) | Urban area detecting method based on feature position optimization and integration | |
| CN113627257A (en) | Detection method, detection system, device and storage medium | |
| CN105136808A (en) | Underwater robot underwater equipment damage detection platform | |
| CN105096325B (en) | Underwater equipment detection system based on laser image | |
| CN116012336B (en) | Tunnel intelligent geological sketch and surrounding rock grade identification device and method | |
| CN104991259A (en) | Laser imaging detection method | |
| CN104999164B (en) | Underwater robot based on multiple filter treatment | |
| CN105000156A (en) | Submarine rescue platform for human-body detection | |
| CN112129778A (en) | Rail train maintenance detection system based on computer vision | |
| CN105010276A (en) | Automatic fish catching method | |
| CN105123636A (en) | Fish body identifying system based on laser image detection | |
| CN105068077A (en) | Submarine underwater searching method based on data communication | |
| Yasser et al. | Egyart_classify: an approach to classify outpainted Egyptian monuments images using GAN and ResNet | |
| CN104999201B (en) | A kind of method using underwater robot to carry out automatic welding under water |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C41 | Transfer of patent application or patent right or utility model | ||
| CB03 | Change of inventor or designer information |
Inventor after: Chen Yanyi Inventor after: Zhang Xiang Inventor before: Wang Lin |
|
| COR | Change of bibliographic data | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20160803 Address after: 361000 Fujian City, Xiamen Software Park, the three phase of the main street, Yi Cheng, unit 366, 0006 Applicant after: Ropt (Xiamen) Technology Group Co., Ltd. Address before: 256600 No. five, No. 99, the Yellow River Road, Shandong, Binzhou Applicant before: Wang Lin |
|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 361000, Xiamen Software Park, Fujian Province, three, 0006, Yi Cheng street, unit 366 Patentee after: ROPT TECHNOLOGY GROUP Co.,Ltd. Address before: 361000, Xiamen Software Park, Fujian Province, three, 0006, Yi Cheng street, unit 366 Patentee before: Roput (Xiamen) Technology Group Co.,Ltd. |