CN113047249A - Automatic greasy dirt clearing device and visual identification system thereof - Google Patents
Automatic greasy dirt clearing device and visual identification system thereof Download PDFInfo
- Publication number
- CN113047249A CN113047249A CN202110331585.5A CN202110331585A CN113047249A CN 113047249 A CN113047249 A CN 113047249A CN 202110331585 A CN202110331585 A CN 202110331585A CN 113047249 A CN113047249 A CN 113047249A
- Authority
- CN
- China
- Prior art keywords
- oil
- oil stain
- removing device
- automatic
- greasy dirt
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- 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
-
- 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
- E02B15/108—Ejection means
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A20/00—Water conservation; Efficient water supply; Efficient water use
- Y02A20/20—Controlling water pollution; Waste water treatment
- Y02A20/204—Keeping clear the surface of open water from oil spills
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mechanical Engineering (AREA)
- Environmental & Geological Engineering (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Structural Engineering (AREA)
- Civil Engineering (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Public Health (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Computing Systems (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Biomedical Technology (AREA)
- Ocean & Marine Engineering (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses an automatic oil stain removing device and a visual identification system thereof, which comprise an unmanned ship, wherein the unmanned ship is fixedly provided with the visual identification system, the unmanned ship is also fixedly provided with a spraying system, the bottom of the unmanned ship is fixedly provided with a water quality monitoring sensor, the spraying system is fixedly connected with the oil stain removing device, the oil stain removing device comprises an oil storage tank, an oil pipeline, an atomizer and an oil pump, and the spraying system comprises a spray head and an adjusting seat, so that the automatic oil stain removing device has the beneficial effects that: the accurate sea greasy dirt quantity of calculating, then open greasy dirt clearing device and spray the oil dispersant that corresponds quantity to the oil film surface, realize the accurate of greasy dirt and clear away to can not produce because of the oil dispersant sprays the secondary pollution that too much brought.
Description
Technical Field
The invention relates to the technical field of marine environment protection, in particular to an automatic oil stain removing device and a visual identification system thereof.
Background
The common removing method of sea surface oil spill comprises the methods of oil containment boom enclosure, sea surface combustion, oil dispersant spraying, manual recovery and the like, wherein the oil containment boom enclosure method has long oil spill treatment time, great harm to marine organisms and environmental pollution easily caused by the sea surface combustion method, so the oil dispersant spraying is the most practical method for solving the sea surface oil spill.
The traditional manual oil elimination agent spraying method has the advantages that the oil spraying pressure of each time cannot be accurately controlled, and the efficiency is low; when the pressure of the spray head is too high, the oil dispersant breaks through an oil film and falls into water when falling, and the oil dispersant cannot react with oil spilling on the water surface and causes secondary pollution; when the pressure of the spray head is too low, the oil dispersing agent can be blown away by sea wind in the falling process and can not fall on the surface of oil spill, the effect of removing the oil spill can not be achieved, and the manual recovery method is not suitable for the sea area far away from the sea shore line.
Disclosure of Invention
The invention aims to provide an automatic oil stain removing device to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme: the utility model provides an automatic greasy dirt clearing device, includes unmanned naval vessel, fixed mounting has visual identification system on the unmanned naval vessel, still fixed mounting has spray system on the unmanned naval vessel, the bottom fixed mounting of unmanned naval vessel has the water quality monitoring sensor, spray system fixed connection greasy dirt clearing device, greasy dirt clearing device includes oil storage tank, oil pipeline, atomizer and oil pump, spray system includes the shower nozzle and adjusts the seat.
As a further scheme of the invention: and a plurality of solar cell panels are fixedly installed on the deck of the unmanned ship.
As a further scheme of the invention: the vision recognition system comprises a camera and a recognition analysis system.
As a further scheme of the invention: the oil storage tank is fixed on a deck of the unmanned ship, and the atomizer is arranged on an oil conveying pipeline between the spraying system and the oil storage tank.
As a further scheme of the invention: the adjusting seat is an adjusting socket capable of rotating around a shaft, and the spray head is movably arranged on the adjusting seat.
A visual identification system based on an automatic oil stain removing device comprises the following steps:
the first step is as follows: carrying out full scene analysis on the water surface and simultaneously realizing real-time perception of the traffic situation of the water surface and detection of an oil stain area;
the second step is that: extracting a target mask, extracting the re-identification characteristics of the target ship, and associating the re-identification characteristics with the motion information by using the appearance characteristics in a high-level tracking process to form a stable track;
the third step: and (4) detecting a polluted area by aiming at the practical YOLO on the water surface, and calculating the spraying amount of the degreasing agent to be sent to an actuating mechanism.
In the aspect of traffic situation perception, scene semantic segmentation is firstly carried out through a full convolution network to distinguish moving targets and obstacles of a background and a foreground, a specific target detection algorithm is yolov3 algorithm, an operating environment is keras, tensoflow-gpu, and the algorithm is used for firstly adjusting an input picture into pictures with the size of 416 x 416 and then dividing the pictures into grids with different sizes of 13 x 13, 26 x 26 and 52 x 52 through yolo3 algorithm.
Since the image is likely to disappear after being convolved many times, the grid 52 x 52 is used to detect small objects, the grid 13 x 13 is used to detect large objects, and the oil stain is detected by the grid 13 x 13 because it is a relatively large object.
In the second step, each grid point is responsible for detecting the lower right corner of the oil stain, and when the center point of the oil stain is located in the area, the position of the oil stain is determined by the grid point.
Compared with the prior art, the invention has the beneficial effects that: the accurate sea greasy dirt quantity of calculating, then open greasy dirt clearing device and spray the oil dispersant that corresponds quantity to the oil film surface, realize the accurate of greasy dirt and clear away to can not produce because of the oil dispersant sprays the secondary pollution that too much brought.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic view of the structure of the present invention.
In the figure: the system comprises an unmanned ship 1, a visual identification system 2, a spraying system 3, a spray nozzle 301, an adjusting seat 302, a water quality monitoring sensor 4, an oil stain removing device 5, an oil storage tank 501, an oil pipeline 502, an atomizer 503 and an oil pump 504.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, in the embodiment of the present invention, an automatic oil contamination removing device includes an unmanned ship 1, a plurality of solar cell panels are fixedly installed on a deck of the unmanned ship 1, a visual recognition system 2 is fixedly installed on the unmanned ship 1, the visual recognition system 2 includes a camera and a recognition analysis system, a spraying system 3 is further fixedly installed on the unmanned ship 1, a water quality monitoring sensor 4 is fixedly installed at the bottom of the unmanned ship 1, the spraying system 3 is fixedly connected with an oil contamination removing device 5, the oil contamination removing device 5 includes an oil storage tank 501, an oil delivery pipeline 502, an atomizer 503 and an oil pump 504, the spraying system 3 includes a nozzle 301 and an adjusting seat 302, the oil storage tank 501 is fixed on the deck of the unmanned ship 1, the atomizer 503 is arranged on the oil delivery pipeline 502 between the spraying system 3 and the oil storage tank 501, the adjusting seat 302 is specifically an adjusting socket capable of rotating around a shaft, the spray head 301 is movably mounted on the adjusting seat 302.
A visual identification system based on an automatic oil stain removing device comprises the following steps:
the first step is as follows: carrying out full scene analysis on the water surface and simultaneously realizing real-time perception of the traffic situation of the water surface and detection of an oil stain area;
the second step is that: extracting a target mask, extracting the re-identification characteristics of the target ship, and associating the re-identification characteristics with the motion information by using the appearance characteristics in a high-level tracking process to form a stable track;
the third step: and (4) detecting a polluted area by aiming at the practical YOLO on the water surface, and calculating the spraying amount of the degreasing agent to be sent to an actuating mechanism.
The working principle is as follows:
the visual perception and recognition subsystem is based on a deep learning technology, carries out full scene analysis on the water surface, simultaneously realizes two functions of real-time perception of the traffic situation of the water surface and detection of an oil stain area, and firstly carries out scene semantic segmentation through a full convolution network in the aspect of traffic situation perception to distinguish moving targets and barriers of a background and a foreground; in the aspect of traffic situation perception, scene semantic segmentation is firstly carried out through a full convolution network, moving targets and obstacles of a background and a foreground are distinguished, a specific target detection algorithm is yolov3 algorithm, an operating environment is keras, tenserflow-gpu, and the method is used for firstly adjusting an input picture into a picture with the size of 416 x 416 and then dividing the picture into grids with different sizes of 13, 26 and 52 x 52 through yolo3 algorithm; the method comprises the steps that after images are convoluted for many times, the characteristics of small objects are easy to disappear, so 52-by-52 grids are used for detecting the small objects, 13-by-13 grids are used for detecting the large objects, oil stains are a large object and are detected by the 13-by-13 grids, in the second step, each grid point is responsible for detecting the lower right corner of each grid point, when the center point of the oil stains is located in the area, the position of the oil stains is determined by the grid point, the detection and example segmentation tasks are further executed for foreground targets and obstacles, target masks are extracted, the re-identification characteristics of target ships are extracted, and appearance characteristics and motion information are simultaneously used for correlation in a high-level tracking process to form stable tracks; and (4) detecting a polluted area by aiming at practical YOLO on the water surface, calculating the spraying amount of the degreasing agent, and spraying the degreasing agent through a spraying system.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.
Claims (9)
1. The utility model provides an automatic greasy dirt clearing device, includes unmanned naval vessel (1), its characterized in that: fixed mounting has visual identification system (2) on unmanned naval vessel (1), still fixed mounting has spraying system (3) on unmanned naval vessel (1), the bottom fixed mounting of unmanned naval vessel (1) has water quality monitoring sensor (4), spraying system (3) fixed connection greasy dirt clearing device (5), greasy dirt clearing device (5) are including oil storage tank (501), oil pipeline (502), atomizer (503) and oil pump (504), spraying system (3) are including shower nozzle (301) and regulation seat (302).
2. The automatic oil stain removing device according to claim 1, characterized in that: a plurality of solar cell panels are fixedly installed on a deck of the unmanned ship (1).
3. The automatic oil stain removing device according to claim 1, characterized in that: the visual recognition system (2) comprises a camera and a recognition analysis system.
4. The automatic oil stain removing device according to claim 1, characterized in that: the oil storage tank (501) is fixed on a deck of the unmanned ship (1), and the atomizer (503) is arranged on an oil conveying pipeline (502) between the spraying system (3) and the oil storage tank (501).
5. The automatic oil stain removing device according to claim 1, characterized in that: the adjusting seat (302) is an adjusting socket capable of rotating around a shaft, and the spray head (301) is movably arranged on the adjusting seat (302).
6. The utility model provides a vision identification system based on automatic greasy dirt clearing device which characterized in that includes following step:
the first step is as follows: carrying out full scene analysis on the water surface and simultaneously realizing real-time perception of the traffic situation of the water surface and detection of an oil stain area;
the second step is that: extracting a target mask, extracting the re-identification characteristics of the target ship, and associating the re-identification characteristics with the motion information by using the appearance characteristics in a high-level tracking process to form a stable track;
the third step: and (4) detecting a polluted area by aiming at the practical YOLO on the water surface, and calculating the spraying amount of the degreasing agent to be sent to an actuating mechanism.
7. The visual identification system based on the automatic oil stain removing device according to claim 6, which is characterized in that: in the aspect of traffic situation perception, scene semantic segmentation is firstly carried out through a full convolution network to distinguish moving targets and obstacles of a background and a foreground, a specific target detection algorithm is yolov3 algorithm, an operating environment is keras, tensoflow-gpu, and the algorithm is used for firstly adjusting an input picture into pictures with the size of 416 x 416 and then dividing the pictures into grids with different sizes of 13 x 13, 26 x 26 and 52 x 52 through yolo3 algorithm.
8. The visual identification system based on the automatic oil stain removing device according to claim 7, characterized in that: since the image is likely to disappear after being convolved many times, the grid 52 x 52 is used to detect small objects, the grid 13 x 13 is used to detect large objects, and the oil stain is detected by the grid 13 x 13 because it is a relatively large object.
9. The visual identification system based on the automatic oil stain removing device according to claim 6, which is characterized in that: in the second step, each grid point is responsible for detecting the lower right corner of the oil stain, and when the center point of the oil stain is located in the area, the position of the oil stain is determined by the grid point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110331585.5A CN113047249A (en) | 2021-03-29 | 2021-03-29 | Automatic greasy dirt clearing device and visual identification system thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110331585.5A CN113047249A (en) | 2021-03-29 | 2021-03-29 | Automatic greasy dirt clearing device and visual identification system thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113047249A true CN113047249A (en) | 2021-06-29 |
Family
ID=76516291
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110331585.5A Pending CN113047249A (en) | 2021-03-29 | 2021-03-29 | Automatic greasy dirt clearing device and visual identification system thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113047249A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2772629Y (en) * | 2005-01-31 | 2006-04-19 | 深圳市龙善环保科技实业有限公司 | High-efficient spray tube of oil spilling dispersing agent |
| CN107021189A (en) * | 2017-05-27 | 2017-08-08 | 日照港达船舶重工有限公司 | A kind of binary overflow oil recovering ship |
| CN109083114A (en) * | 2018-08-10 | 2018-12-25 | 浙江海洋大学 | A kind of oil spilling monitoring and processing system based on remote sensing |
| CN211368633U (en) * | 2019-11-11 | 2020-08-28 | 海域海岛环境科技研究院(天津)有限公司 | Offshore oil spill emergency monitoring and disposal complex |
-
2021
- 2021-03-29 CN CN202110331585.5A patent/CN113047249A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2772629Y (en) * | 2005-01-31 | 2006-04-19 | 深圳市龙善环保科技实业有限公司 | High-efficient spray tube of oil spilling dispersing agent |
| CN107021189A (en) * | 2017-05-27 | 2017-08-08 | 日照港达船舶重工有限公司 | A kind of binary overflow oil recovering ship |
| CN109083114A (en) * | 2018-08-10 | 2018-12-25 | 浙江海洋大学 | A kind of oil spilling monitoring and processing system based on remote sensing |
| CN211368633U (en) * | 2019-11-11 | 2020-08-28 | 海域海岛环境科技研究院(天津)有限公司 | Offshore oil spill emergency monitoring and disposal complex |
Non-Patent Citations (1)
| Title |
|---|
| 张泽苗: "深层卷积神经网络的目标检测算法综述", 《小型微型计算机***》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021142902A1 (en) | Danet-based unmanned aerial vehicle coastline floating garbage inspection system | |
| CN107622231B (en) | A kind of intelligent floating material collection system of water day one and its collection method | |
| KR102339465B1 (en) | Autonomous navigation ship system for removing sea waste based on deep learning-vision recognition | |
| CN102289824B (en) | Method for positioning plane centroid of pipe orifice image of condenser | |
| CN112102369A (en) | Autonomous inspection method, device and equipment for water surface floating target and storage medium | |
| CN109978869A (en) | A kind of sea horizon detection method and system based on gray level co-occurrence matrixes and Hough transform | |
| CN110427873B (en) | Cleaning vehicle, intelligent pedestrian anti-splashing system and method applied to sanitation field | |
| CN106780598A (en) | A kind of floating on water object detecting method and unmanned plane based on unmanned plane | |
| CN109975759B (en) | Underwater unmanned aerial vehicle positioning method and device based on three-color laser | |
| CN111292371A (en) | Intelligent water level detection equipment, intelligent water level monitoring management device and detection method | |
| Zhang et al. | Vision-based system of AUV for an underwater pipeline tracker | |
| CN111079724A (en) | Unmanned aerial vehicle-based sea floating garbage identification method | |
| CN114220044B (en) | River course floater detection method based on AI algorithm | |
| CN115457297A (en) | Method and device for detecting oil leakage of aviation oil depot and aviation oil safety operation and maintenance system | |
| CN113792638B (en) | Thermal power plant rain exhaust pollutant identification method based on Parallelogram-YOLOv4 | |
| CN113047249A (en) | Automatic greasy dirt clearing device and visual identification system thereof | |
| CN211978876U (en) | Unmanned ship for monitoring and tracking oil pollution source in collaborative water environment | |
| Feng et al. | Real-time riverbank line detection for USV system | |
| CN116388669A (en) | Photovoltaic panel foreign matter detection and cleaning method based on Swin transducer | |
| CN116527850A (en) | Anti-drowning self-adaptive detection method based on video monitoring | |
| CN116310892A (en) | Marine rescue method based on improved YOLOV4 target detection | |
| CN111650960B (en) | Method for measuring ash coverage degree of photovoltaic panel of photovoltaic power station by using single unmanned aerial vehicle | |
| Krout et al. | Object tracking with imaging sonar | |
| CN113050665A (en) | Energy-saving underwater robot detection method and system based on SLAM framework | |
| CN114914843A (en) | Automatic identification and aiming algorithm for floating foreign matters in power transmission line and laser remote removal system |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210629 |