CN113895575A - Water surface cleaning robot fishing system based on Aliyun and convolutional neural network algorithm - Google Patents
Water surface cleaning robot fishing system based on Aliyun and convolutional neural network algorithm Download PDFInfo
- Publication number
- CN113895575A CN113895575A CN202111347219.5A CN202111347219A CN113895575A CN 113895575 A CN113895575 A CN 113895575A CN 202111347219 A CN202111347219 A CN 202111347219A CN 113895575 A CN113895575 A CN 113895575A
- Authority
- CN
- China
- Prior art keywords
- hull
- ship body
- neural network
- garbage
- water surface
- 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
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B63—SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
- B63B—SHIPS OR OTHER WATERBORNE VESSELS; EQUIPMENT FOR SHIPPING
- B63B35/00—Vessels or similar floating structures specially adapted for specific purposes and not otherwise provided for
- B63B35/32—Vessels or similar floating structures specially adapted for specific purposes and not otherwise provided for for collecting pollution from open water
-
- E—FIXED CONSTRUCTIONS
- E02—HYDRAULIC ENGINEERING; FOUNDATIONS; SOIL SHIFTING
- E02B—HYDRAULIC ENGINEERING
- E02B15/00—Cleaning or keeping clear the surface of open water; Apparatus therefor
- E02B15/04—Devices for cleaning or keeping clear the surface of open water from oil or like floating materials by separating or removing these materials
- E02B15/10—Devices for removing the material from the surface
- E02B15/104—Conveyors; Paddle wheels; Endless belts
Abstract
The invention discloses a water surface cleaning robot salvage system based on Aliyun and a convolutional neural network algorithm, which comprises a ship body, wherein a propeller is arranged on the rear side of the ship body, the propeller is driven to rotate by a propeller motor arranged at the bottom of the ship body, a garbage transfer belt driven by a power system arranged on the ship body is arranged on the front side of the ship body, a garbage collection box is arranged in the middle of the ship body, the garbage transfer belt is obliquely arranged, the lower end of the garbage transfer belt is positioned below the water surface, and the upper end of the garbage transfer belt is arranged in the garbage collection box. The invention can efficiently salvage in a severe water area with more waterweeds by arranging the stopping device and the air pumps arranged on the two sides of the ship body, can improve the garbage collection amount each time by matching with the left and right collection expansion nets, and prevents the garbage from being incapable of being successfully salvaged due to the outward water flow generated during the advancing process. Secondly, set up robot system on the hull, debris such as rubbish on can the quick discernment surface of water, pasture and water are close to fast and are realized salvaging.
Description
Technical Field
The invention relates to the technical field of water surface garbage cleaning, in particular to a water surface cleaning robot fishing system based on Aliyun and a convolutional neural network algorithm.
Background
With the increasing living standard of people, the environmental problem is also increasingly serious, especially the water pollution problem, has been carried through to every field, makes the protection and the cleanness in waters become more important, at this moment, needs a device to help people to accomplish the protection of water resource. At present, manual salvage is mainly adopted in the market, and the traditional salvage mode has high risk, low efficiency and poor working environment; secondly, salvage ship salvage, reply adverse waters area environment work efficiency low, if the hull removes when being close to rubbish, produce outside rivers, lead to rubbish to appear keeping away from the hull and float and be difficult for salvaging. Secondly, in the waters with more aquatic weeds, the aquatic weeds can be continuously gathered and wound when the ship is driven into the waters due to the connection of the aquatic weeds, so that the problem of dead locking of a paddle is easy to occur, and finally the fishing efficiency is low.
In order to solve the problems, the scheme is developed accordingly.
Disclosure of Invention
Technical problem to be solved
Aiming at the defects of the prior art, the invention provides a water surface cleaning robot fishing system based on Aliyun and a convolutional neural network algorithm, and solves the problems in the background technology.
(II) technical scheme
In order to achieve the purpose, the invention is realized by the following technical scheme: a water surface cleaning robot fishing system based on Aliyun and a convolutional neural network algorithm comprises a ship body, wherein a propeller is arranged on the rear side of the ship body, the propeller is driven to rotate by a propeller motor arranged at the bottom of the ship body, a garbage transfer belt driven by a power system arranged on the ship body is arranged on the front side of the ship body, a garbage collection box is arranged in the middle of the ship body, the garbage transfer belt is obliquely arranged, the lower end of the garbage transfer belt is positioned below the water surface, the upper end of the garbage transfer belt is arranged in the garbage collection box, a sealing sleeve is arranged between a rotating shaft connected with the propeller to rotate and a motor driving the rotating shaft to rotate, the left side and the right side of the ship body are respectively provided with a first air pump, the bottom of the rear side of the ship body is provided with a second air pump, a collecting and gathering device is arranged on the ship body and comprises a left collecting expansion net and a right collecting blocking device arranged on the front side of the ship body and a bottom, wherein the left collecting expansion net and right collecting expansion net are used for gathering garbage on the front side of the ship body, the blocking device is matched with the air pump to be used so as to collect garbage at the bottom and the side edges of the ship body when the ship turns.
Preferably, the left and right collecting expansion nets carry steering engines and realize 0-45-degree rotation control.
Preferably, the arresting device is including locating the arresting plate of hull bottom both sides, and two arresting plates are at vertical direction staggered arrangement, and the upper end is connected with tooth dental lamina respectively, two tooth dental lamina interval staggered arrangement respectively, and be equipped with the gear with it meshing at the middle part, the axial lead coincidence of two gears, and overlap in a pivot, the pivot drives the rotation through the motor of arranging the hull outer wall in for two tooth dental laminas are the cross operation of one on the other, and wherein the fishing operation when the use of tooth dental lamina is for cooperating the hull to turn to.
Preferably, the hull bottom is equipped with the slurcam, and the both ends of slurcam link up with the inboard of arresting barrier mutually, the slurcam passes through the cylinder and drives flexible, and then can promote along hull length direction.
Preferably, the garbage transfer belt is provided with a blocking strip, and the outer side end of the blocking strip is connected with a barb.
Preferably, the garbage collection box is arranged in the middle of the ship body, two carrying rods are arranged on the upper side of the garbage collection box, symmetrical supporting blocks are arranged on the side edges of the garbage collection box, and the supporting blocks are arranged on the upper surface of the ship body.
Wherein surface of water cleaning machines people based on Aliskiu and convolution neural network algorithm, including microprocessor control system, vision processing system, power control system, interactive system, power and all kinds of sensors, microprocessor control system uses the STM32 singlechip as the core board, vision processing system includes camera and industrial computer, power control system includes the actuating system board, the screw motor, the air pump propeller, the sensor includes GPS big dipper navigation orientation module, MPU6050 attitude sensor, the place ahead ultrasonic sensor, left side ultrasonic sensor, right side ultrasonic sensor, interactive system includes NB-IOT module, Aliskiu thing networking platform and PC end are mutual, terminal cloud platform promptly.
The visual processing system is combined with a yoloV3 target recognition platform built on a pytorch platform, a Darknet53 main feature extraction network is used, the network depth is properly increased by using a Residual error network Residual to improve the accuracy, and a rule connection is performed on an internal Residual block to solve the problem of gradient disappearance; the method comprises the steps of performing reinforced feature extraction by constructing an FPN feature pyramid, predicting three effective feature layers by using a Yolo Head, obtaining prediction results of the three feature layers from the feature layers, dividing the whole picture into grids corresponding to the length and the width of the whole picture by the three feature layers, establishing a check box in each grid, and judging whether an object exists in each grid and the type of the object; decoding the prediction result, adding x _ offset and y _ offset to each grid to obtain the center of the prediction frame, then calculating the width and height of the prediction frame by using the check frame and h, w, and performing score sorting and non-maximum inhibition screening on the obtained result to obtain the position of the prediction frame on the original image; and drawing the screened inhibition frame on an original image to obtain a recognition result.
(III) advantageous effects
After adopting the technical scheme, compared with the prior art, the invention has the following advantages: the invention can efficiently salvage in a severe water area with more waterweeds by arranging the stopping device and the air pumps arranged on the two sides of the ship body, can improve the garbage collection amount each time by matching with the left and right collection expansion nets, and prevents the garbage from being incapable of being successfully salvaged due to the outward water flow generated during the advancing process. Secondly, set up robot system on the hull, debris such as rubbish on can the quick discernment surface of water, pasture and water are close to fast and are realized salvaging.
Drawings
FIG. 1 is a schematic view of the present invention;
FIG. 2 is a schematic view of the present invention from above;
FIG. 3 is a partial structure diagram of the rear side of the hull of the present invention;
FIG. 4 is a schematic view of a stopping device according to the present invention;
FIG. 5 is a schematic view of the garbage collection bin of the present invention;
FIG. 6 is a schematic view of a waste transport belt according to the present invention;
FIG. 7 is a schematic diagram of a control system according to the present invention;
FIG. 8 is a flow chart of the garbage recognition control of the present invention.
In the figure: 1. a hull; 2. a propeller; 3. a propeller motor; 4. a waste transfer belt; 5. a garbage collection box; 6. sealing sleeves; 7. a first air pump; 8. a second air pump; 9. a stopping device; 91. a damming board; 92. a tooth plate; 93. a gear; 94. a rotating shaft; 95. a motor; 10. collecting and expanding nets left and right; 11. a push plate; 12. a cylinder; 13. a barrier strip; 14. a barb; 15. a carrying rod; 16. a support block; 17. a terminal cloud platform; 18. a camera; 19. a GPS/Beidou positioning module; 20. MPU6050 attitude sensor; 21. STM32 single-chip microcomputer; 22. front ultrasonic waves; 23. left side ultrasonic wave; 24. right side ultrasonic wave; 25. a drive system; 26. a propeller motor; 27. an air pump propeller; 28. an NB-IOT module; 29. and an industrial personal computer.
Detailed Description
The invention is explained in more detail below with reference to the figures and examples.
As shown in fig. 1-8: a water surface cleaning robot fishing system based on Aliyun and a convolutional neural network algorithm is characterized in that an ultrasonic module is installed at the front end of a ship body 1 and used for avoiding obstacles in the front, a camera 18 is further installed above the ship body and used for collecting images in the front, and objects in the front are identified and processed.
The rear side of the ship body 1 is provided with control devices such as a control panel of the ship body 1, the rear side is provided with two symmetrical mounting holes and is connected with a propeller 2, a propeller motor 3 in the propeller 2 is connected with the control panel, and the propeller 2 is always in a vertical state, so that the balance controlled by the ship body 1 is ensured.
A sealing sleeve 6 is arranged between the rotating shaft 94 connected with the rotation of the propeller 2 and the motor 95 driving the rotating shaft 94 to rotate, so that the winding and the rotation blockage of garbage and aquatic plants are avoided.
The garbage collection box 5 is arranged in a notch in the middle of the ship body 1, the garbage collection box 5 is provided with two carrying rods 15 and symmetrical supporting blocks 16, and the supporting blocks 16 are arranged on the upper surface of the ship body 1 and used for being carried on the ship body 1 and being capable of being taken down quickly, so that the garbage is cleaned and transferred.
The front end of the ship body 1 is provided with a garbage transfer belt 4 which is driven and transmitted by a power system. The garbage transfer belt 4 is obliquely arranged, the lower end of the garbage transfer belt is positioned below the water surface, and the upper end of the garbage transfer belt is arranged in the garbage collection box 5. The surface of the garbage transfer belt 4 is provided with barrier strips at intervals, so that the problem that garbage slips off is avoided (a conventional chain belt type conveyor belt is adopted, and a power system adopts a structure of a gear 93 and a motor 95).
The hull 1 is equipped with air pump 7 respectively in the left and right sides, and air pump 7 of both sides is used for supplementary hull 1's the propulsion that turns to through producing thrust, and the diversion controllability of the relative oar of propelling force of air pump 7 is higher, promotes the operation through the air pump and drives hull 1 and slowly rotate constantly and change the orientation, and the cooperation is collected and is gathered together the device and make hull 1 circumference even the pasture and water of bottom constantly be gathered together and collect to transport through rubbish transmission area 4 and salvage, salvage efficiency is higher.
Secondly, an air pump II 8 is arranged at the bottom of the rear side of the ship body 1 and is used for assisting the ship body 1 to slowly propel forwards when the propeller 2 stops working. Simultaneously, the setting of air pump two 8 can be with the basin of screw 2 periphery towards scattering, avoids further appearing pasture and water winding problem, can deal with the waters of pasture and water gathering and carry out the operation.
The collecting and gathering device is arranged on the ship body 1 and comprises a left collecting expansion net 10 and a right collecting expansion net 10 which are arranged on the front side of the ship body 1, wherein the left collecting expansion net 10 and the right collecting expansion net 10 carry steering engines to realize 0-45-degree rotation control, so that a garbage cleaning area is widened, and the cleaning efficiency is improved.
Further, the collecting and gathering device further comprises blocking plates 91 arranged on two sides of the bottom of the ship body 1, the two blocking plates 91 are arranged in a staggered mode in the vertical direction, the upper ends of the two blocking plates are respectively connected with tooth plates 92, the two tooth plates 92 are arranged in a staggered mode at intervals, gears 93 meshed with the two tooth plates are arranged in the middle of the two blocking plates, axial leads of the two gears 93 are overlapped and sleeved on a rotating shaft 94, and the rotating shaft 94 is driven to rotate through a motor 95 arranged on the outer wall of the ship body 1, so that the two tooth plates 92 can perform cross operation one on the other.
The bottom of the arresting plate 91 can be provided with a cutting edge, and particularly, when the aquatic weeds are more, the aquatic weeds can be cut off so as to be conveniently and quickly salvaged.
The blocking plate 91 is mainly matched with the air pump 7 to be used, when the ship turns to, the waterweeds or sundry garbage on the lower side and the side are gathered under the ship body 1 by the blocking plate 91 on the corresponding side, therefore, the scheme further provides the push plate 11, the push plate 11 is arranged under the ship body 1 and can push along the length direction of the ship body 1 (can be driven by the air cylinder 12), and the waterweeds or sundry garbage on the bottom of the ship body 1 are pushed to be close to the garbage transfer belt 4 to be gathered. Secondly, connect barb 14 at the stop strip outside end for can catch the rubbish that is close to and collect, also can be collected and salvage the rubbish of rubbish transfer belt 4 rear side contact part promptly, the clearance efficiency is higher.
As shown in fig. 7-8, the robot system includes microprocessor control system, vision processing system, power control system, interactive system, power and sensor, microprocessor control system uses STM32 singlechip 21 as the core board, vision processing system includes camera 18 and industrial computer 29, power control system includes actuating system 25 board, screw motor 26, air pump propeller 27, the sensor includes GPS big dipper navigation orientation module, MPU6050 attitude sensor 20, the place ahead ultrasonic wave 22 sensor, left side ultrasonic wave 23 sensor, right side ultrasonic wave 24 sensor, interactive system includes NB-IOT module 28, the interaction of the thing networking platform of the cloud of an arii and PC end, terminal cloud platform 17 promptly. The power supply is a 12V/24V direct current storage power supply.
The control system comprises an STM32 single chip microcomputer 21, an NB-IOT module, a camera 18, an industrial personal computer 29, an ultrasonic module, an air pump, a propeller motor and electric regulation module, a GPS positioning module and an attitude identification module. Air pump and ultrasonic wave are connected with STM32 singlechip 21, and the screw motor is connected with the electricity accent, and the electricity accent is connected with STM32 singlechip 21, and GPS and gesture recognition module, NB-IOT module all are connected with STM32 singlechip 21. The camera 18 is connected with the industrial personal computer 29 and is connected with the STM32 single chip microcomputer 21 after being processed by the industrial personal computer. The STM32 singlechip 21, the industrial personal computer 29, the NB-IOT module, the electric regulation module, the GPS positioning module and the attitude identification module are all installed inside the rear side hull 1.
The invention incorporates, in a visual processing system, the yoloV3 target recognition platform built on a pytorech platform. The method uses Darknet53 backbone feature extraction network, uses Residual error network Residual to increase network depth properly to improve accuracy, and uses contract connection to internal Residual block to solve the problem of gradient disappearance. The method comprises the steps of constructing an FPN feature pyramid to extract enhanced features, predicting three effective feature layers by using a Yolo Head to obtain prediction results of the three feature layers from the feature layers, dividing the whole picture into grids corresponding to the length and the width of the picture by the three feature layers, establishing check boxes in the grids, and judging whether objects exist and the types of the objects. Decoding the prediction result, adding x _ offset and y _ offset to each grid to obtain the center of the prediction frame, then calculating the width and height of the prediction frame by using the check frames h and w, and performing score sorting and non-maximum inhibition screening on the obtained result to obtain the position of the prediction frame on the original image. And drawing the screened inhibition frame on an original image to obtain a recognition result.
The system of the ship body 1 works as follows: the camera 18 collects image data and transmits the image data to the industrial personal computer 29, the industrial personal computer 29 identifies garbage in pictures by using a trained CNN neural network model, garbage center coordinates are sent to the STM32 single chip microcomputer 21 through serial ports in processing, the STM32 single chip microcomputer 21 drives the propeller 2 to reach a coordinate specified position according to instructions and a PID algorithm, cleaning is carried out in sequence according to the distance between the coordinates and an original point (ship position), and if the garbage is not monitored in the front, the unmanned ship walks in a patrol state in a straight line.
In light of the foregoing, it will be apparent to those skilled in the art from this disclosure that various changes and modifications can be made without departing from the spirit and scope of the invention. The technical scope of the present invention is not limited to the content of the specification, and the protection scope must be determined by the scope of the claims.
Claims (8)
1. A water surface cleaning robot based on Aliskiu and a convolutional neural network algorithm is characterized in that: including microprocessor control system, vision processing system, power control system, interactive system, power and sensor, microprocessor control system uses the STM32 singlechip as nuclear core plate, vision processing system includes camera and industrial computer, power control system includes the actuating system board, the screw motor, the air pump propeller, the sensor includes GPS big dipper navigation orientation module, MPU6050 attitude sensor, the place ahead ultrasonic sensor, left side ultrasonic sensor, right side ultrasonic sensor, interactive system includes NB-IOT module, the thing networking platform of the A Li cloud and PC end are mutual, terminal cloud platform promptly.
2. The arroga and convolutional neural network algorithm-based water surface cleaning robot of claim 1, wherein: the visual processing system is combined with a yoloV3 target recognition platform built on a pytorech platform, a Darknet53 main feature extraction network is used, the network depth is properly increased by using a Residual error network Residual to improve the accuracy, and the problem of gradient disappearance is solved by carrying out rule connection on an internal Residual block; the method comprises the steps of performing reinforced feature extraction by constructing an FPN feature pyramid, predicting three effective feature layers by using a Yolo Head, obtaining prediction results of the three feature layers from the feature layers, dividing the whole picture into grids corresponding to the length and the width of the whole picture by the three feature layers, establishing a check box in each grid, and judging whether an object exists in each grid and the type of the object; decoding the prediction result, adding x _ offset and y _ offset to each grid to obtain the center of the prediction frame, then calculating the width and height of the prediction frame by using the check frame and h, w, and performing score sorting and non-maximum inhibition screening on the obtained result to obtain the position of the prediction frame on the original image; and drawing the screened inhibition frame on an original image to obtain a recognition result.
3. The utility model provides a surface of water cleaning machines people salvages system based on arrying and convolution neural network algorithm, includes the hull, and the rear side of hull is equipped with the screw, and the screw rotates through the screw motor drive of arranging the hull bottom in, and the front side of hull is equipped with the driving system driven rubbish transmission area through locating the hull, and the middle part of hull is equipped with garbage collection box, the slope of rubbish transmission area is arranged, and its lower extreme is located the surface of water below, and the rubbish collection box is arranged in to the upper end, its characterized in that: connect be equipped with the seal cover between screw pivoted pivot and the drive pivot pivoted motor, the hull is equipped with air pump one respectively in the left and right sides, and the bottom of hull rear side is equipped with air pump two, be equipped with on the hull and collect the device of gathering together, collect the device of gathering together including locating the hull front side collect the barrier device of expansion net and bottom about wherein, collect the rubbish that the expansion net is used for gathering together the hull front side, barrier device cooperation air pump one uses to collect the rubbish of hull bottom and side when turning to.
4. The arrestus and convolutional neural network algorithm-based water surface cleaning robot fishing system of claim 3, wherein: the left and right collecting expansion nets carry steering engines and realize rotation control of 0-45 degrees.
5. The arrestus and convolutional neural network algorithm-based water surface cleaning robot fishing system of claim 3, wherein: the arresting device is including locating the arresting plate of hull bottom both sides, and two arresting plates are at vertical direction staggered arrangement, and the upper end is connected with tooth dental lamina respectively, two tooth dental lamina interval staggered arrangement respectively, and be equipped with the gear with it meshing at the middle part, the axial lead coincidence of two gears, and overlap in a pivot, the pivot drives the rotation through the motor of arranging the hull outer wall in for two tooth dental lamina do the cross operation of one on the other, wherein the use of tooth dental lamina is for the fishing operation when the cooperation hull turns to.
6. The arrestus and convolutional neural network algorithm-based water surface cleaning robot fishing system of claim 5, wherein: the hull bottom is equipped with the slurcam, and the both ends of slurcam link up mutually with the inboard of arresting barrier, the slurcam passes through the cylinder and drives flexible, and then can follow hull length direction and promote.
7. The arrestus and convolutional neural network algorithm-based water surface cleaning robot fishing system of claim 3, wherein: and a blocking strip is arranged on the garbage transfer belt, and the outer side end of the blocking strip is connected with a barb.
8. The arrestus and convolutional neural network algorithm-based water surface cleaning robot fishing system of claim 3, wherein: the garbage collection box is arranged in the middle of the ship body, two carrying rods are arranged on the upper side of the garbage collection box, symmetrical supporting blocks are arranged on the side edges of the garbage collection box, and the supporting blocks are arranged on the upper surface of the ship body.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111347219.5A CN113895575B (en) | 2021-11-15 | 2021-11-15 | Water surface cleaning robot salvaging system based on Arian cloud and convolutional neural network algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111347219.5A CN113895575B (en) | 2021-11-15 | 2021-11-15 | Water surface cleaning robot salvaging system based on Arian cloud and convolutional neural network algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113895575A true CN113895575A (en) | 2022-01-07 |
| CN113895575B CN113895575B (en) | 2023-09-15 |
Family
ID=79194276
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111347219.5A Active CN113895575B (en) | 2021-11-15 | 2021-11-15 | Water surface cleaning robot salvaging system based on Arian cloud and convolutional neural network algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113895575B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023137601A1 (en) * | 2022-01-18 | 2023-07-27 | 广州工商学院 | Ai-based water surface garbage sorting and recycling platform system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107719593A (en) * | 2017-09-11 | 2018-02-23 | 上海电机学院 | A kind of Water surface refuse collecting boat for possessing floating type salvaging transport structure |
| CN109466725A (en) * | 2018-10-11 | 2019-03-15 | 重庆邮电大学 | It is a kind of that system is salvaged based on the intelligent floater of neural network and image recognition |
| EP3643594A1 (en) * | 2018-10-23 | 2020-04-29 | Dec N.V. (Deme Environmental Contractors) | Method and system for removing floating waste from water |
| CN211223788U (en) * | 2019-12-12 | 2020-08-11 | 泰山学院 | Full-automatic intelligent surface garbage salvage ship |
| CN112613425A (en) * | 2020-12-24 | 2021-04-06 | 山东船舶技术研究院 | Target identification method and system for small sample underwater image |
| CN113006027A (en) * | 2021-04-08 | 2021-06-22 | 武汉理工大学 | Water surface garbage treatment device |
| CN113134683A (en) * | 2021-05-13 | 2021-07-20 | 兰州理工大学 | Laser marking method and device based on machine learning |
-
2021
- 2021-11-15 CN CN202111347219.5A patent/CN113895575B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107719593A (en) * | 2017-09-11 | 2018-02-23 | 上海电机学院 | A kind of Water surface refuse collecting boat for possessing floating type salvaging transport structure |
| CN109466725A (en) * | 2018-10-11 | 2019-03-15 | 重庆邮电大学 | It is a kind of that system is salvaged based on the intelligent floater of neural network and image recognition |
| EP3643594A1 (en) * | 2018-10-23 | 2020-04-29 | Dec N.V. (Deme Environmental Contractors) | Method and system for removing floating waste from water |
| CN211223788U (en) * | 2019-12-12 | 2020-08-11 | 泰山学院 | Full-automatic intelligent surface garbage salvage ship |
| CN112613425A (en) * | 2020-12-24 | 2021-04-06 | 山东船舶技术研究院 | Target identification method and system for small sample underwater image |
| CN113006027A (en) * | 2021-04-08 | 2021-06-22 | 武汉理工大学 | Water surface garbage treatment device |
| CN113134683A (en) * | 2021-05-13 | 2021-07-20 | 兰州理工大学 | Laser marking method and device based on machine learning |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023137601A1 (en) * | 2022-01-18 | 2023-07-27 | 广州工商学院 | Ai-based water surface garbage sorting and recycling platform system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113895575B (en) | 2023-09-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101792013B (en) | Method and device for collecting garbage floating on water surface | |
| CN103714683B (en) | Marine oil overflow collecting platform based on catamaran | |
| CN109501974B (en) | Water surface garbage cleaning ship | |
| CN213594481U (en) | Water surface garbage salvage ship | |
| CN207076743U (en) | A kind of net cage purging system based on unmanned boat | |
| CN208021681U (en) | Garbage cleaning robot waterborne | |
| CN112937811B (en) | Crawler-type cleans intelligent robot of discarded object under water | |
| CN110185013A (en) | Water surface cleaning ship device and water surface clean method based on Machine Vision Recognition | |
| CN109703707B (en) | Aquatic weed salvage ship based on vision system and aquatic weed salvage method | |
| CN113895575A (en) | Water surface cleaning robot fishing system based on Aliyun and convolutional neural network algorithm | |
| WO2023019942A1 (en) | Pollutant cleaning boat for cleaning greasy dirt and floating object on water surface, pollutant cleaning control system and pollutant cleaning control method | |
| CN108617603A (en) | A kind of crawler type shellfish harvester tool of submersible operation | |
| CN207089643U (en) | A kind of marine float garbage-cleaning unmanned plane | |
| CN114991298B (en) | Urban drainage pipeline detection and dredging intelligent robot and working method | |
| CN115387306A (en) | Intelligent floating garbage collecting and sorting robot | |
| CN203735090U (en) | Full-automatic aquatic plant clearing machine boat used for river crab culture | |
| CN114352084A (en) | Swimming pool water surface cleaning method and cleaning robot | |
| CN111441384A (en) | Intelligent floating house control method and system based on big data processing and analysis | |
| CN112937812B (en) | Floated intelligent robot that cleans discarded object under water | |
| CN110758657A (en) | Novel automatic retrieve surface of water rubbish twinhull vessel | |
| CN212556706U (en) | Solar water surface garbage cleaning robot | |
| CN108782483A (en) | A kind of drag harrow formula shellfish harvester tool of submersible operation | |
| CN212685865U (en) | Automatic cleaning robot for garbage on water surface | |
| CN215405957U (en) | Unmanned garbage collection device on water | |
| CN210395297U (en) | Amphibious garbage cleaning robot |
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 |