CN105184816A - Visual inspection and water surface target tracking system based on USV and detection tracking method thereof - Google Patents
Visual inspection and water surface target tracking system based on USV and detection tracking method thereof Download PDFInfo
- Publication number
- CN105184816A CN105184816A CN201510509429.8A CN201510509429A CN105184816A CN 105184816 A CN105184816 A CN 105184816A CN 201510509429 A CN201510509429 A CN 201510509429A CN 105184816 A CN105184816 A CN 105184816A
- Authority
- CN
- China
- Prior art keywords
- target
- pixel
- image
- unmanned
- background
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
- G06T2207/10021—Stereoscopic video; Stereoscopic image sequence
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a visual inspection and water surface target tracking system based on an USV (unmanned surface vessel), comprising a command center, an unmanned surface vessel, and an exploration system. The command center is a control terminal of the unmanned surface vessel, and is connected with the unmanned surface vessel in a communication manner, and sends instructions to the unmanned surface vessel. The unmanned surface vessel receives information sent by the exploration system, and completes tasks of tracking water surface targets through a navigation system. The exploration system detects target objects on a water surface and locates to obtain position coordinates thereof, and sends information to the unmanned surface vessel, and waits for next step commands of the command center. The exploration system is integrated with a pan tilt camera and a millimeter-wave radar. Two kinds of sensors of the pan tilt camera and the millimeter-wave radar are used in the system to locate positions of targets on the water surface, so detection tracking results are more accurate, detection efficiency is improved, manpower and financial resources are greatly saved, and the system has wide market prospect.
Description
Technical field
The present invention relates to unmanned water surface ship airmanship, be specifically related to based on the vision-based detection of USV and waterborne target tracing system and detect method for tracing.
Background technology
Unmanned water surface ship (UnmannedSurfaceVessel is called for short USV), is recently emerging offshore work platform, can completes autonomous exploration target according to artificial setting program, keeps away the tasks such as barrier, search and rescue.Take place frequently in the perils of the sea at present and the fast development of naval equipment with under practical impact, various countries more and more pay attention to institute's control marine site internal object monitoring management, and this makes the automatic target recognition technology on sea obtain develop rapidly.Along with Activities of Ocean is more and more frequent and the perils of the sea is multiple, each coastal zone country particularly focuses on offshore activities monitoring, and the task with traditional of each coastal zone country of the world is especially searched in the scene of the accident of naval target particularly behind the detection of boats and ships and supervision and the perils of the sea.Target image is detected from the visual pattern such as naval vessel, ship, to in the supervision of the monitoring at the scene of the accident, bay, marine site, harbour and sea transport, fishing and military war, the useful information that further extraction is a large amount of, differentiates that there is application prospect very widely at dangerous place etc.
In the epoch that current intelligent high speed develops, maritime safety management and military strategy also move towards high-intelligentization gradually.Unmanned water surface ship is as a novel marine intelligent body, there is the features such as independence, reactivity, adaptability, comparatively some aerial and unmanned ground vehicles such as unmanned plane develop more late, mainly affected by two aspect factors, one is that maritime environment changes greatly, and light affects the environmental factors such as large by water-reflected; Two is that waterborne target is general comparatively near, higher to the requirement of vision system sensor.Independently can identify accurately and judge that object in its operating environment or barrier are one of main tasks of unmanned water surface ship, therefore have higher intelligent requirements to its vision and disposal system.Unmanned water surface ship carries out close-in target or the main view-based access control model system of obstacle recognition, and therefore, the identification of research unmanned boat waterborne target, measurement and tracking have very great meaning.
In existing technology, for moving object detection and tracking in complicated dynamic scene, the method for usual indirect labor's search detects specific moving target, and realizes moving target tracking in the picture with track algorithm, this belongs to a kind of half autonomous guidance mode, therefore has certain limitation.
Summary of the invention
Goal of the invention: the object of the invention is to solve the deficiencies in the prior art, provides based on the vision-based detection of USV and waterborne target tracing system and detects method for tracing.
Technical scheme: a kind of vision-based detection based on USV of the present invention and waterborne target tracing system, comprise command centre, unmanned surface vehicle and investigation system; Described command centre is the control terminal of unmanned surface vehicle, and water is ordered and to be communicated to connect between unmanned boat and to send instruction to unmanned surface vehicle; Described unmanned surface vehicle receives the information sent from investigation system, and completes tracking waterborne target task by navigational system; Described investigation system detects the target object on the water surface and locates knows its position coordinates, and information is sent to unmanned surface vehicle, waits for next step instruction of command centre simultaneously; Investigation system is integrated with monopod video camera and millimetre-wave radar.
The invention also discloses the detection method for tracing of a kind of vision-based detection based on USV and waterborne target tracing system, comprise the following steps:
(1) the 2D video image that monopod video camera photographs is processed;
(2) monopod video camera tracing control, the pitching deflection angle of adjustment monopod video camera, makes target remain on the central authorities of image in real time;
(3) utilize millimetre-wave radar to measure distance between unmanned water surface ship and moving target, integrating step (2) the data obtained further, the tracking that the 3D data obtaining moving target complete moving target with accurately locate;
(4) unmanned water surface ship navigational system carries out autonomous trackable surface moving target traveling.
Further, described step (1) comprises image sequence pre-service and (comprises image conversion, image denoising, image enhaucament etc., its object is to be convenient to follow-uply to process picture signal), carry out the detection of background modeling and moving target, the segmentation of moving target and motion target tracking four steps, detailed process is as follows:
(11) image sequence pre-service comprises image conversion, image denoising and image enhaucament etc.;
(12) detection of background modeling and dynamic object, the i.e. moving object detection of combined with texture and motion model: use local binary patterns to extract texture pattern; Traditional local binary patterns is extended to time-space domain from spatial domain, for extracting motor pattern, concrete grammar is simultaneously: for extracting texture pattern descriptor for (x in t image
t,c, y
t,c) the pixel g at place
t,cconsider its eight neighborhood territory pixel g
t,p, p=0 ... .7, carries out binaryzation by each neighborhood territory pixel and this pixel and compares, obtain the binary string of eight, be i.e. a code word LBP at this pixel place
t(x
t,c, y
t,c):
Wherein
This code word portrays pixel (x
t,c, y
t,c) a kind of texture pattern of being formed with its surrounding pixel, then respectively modeling is carried out to each pixel employing texture pattern in scene and motion model, then in sorter aspect, the background model based on texture pattern and motor pattern is merged;
(13) segmentation of moving target: by using based on gauss hybrid models and embedding the background modeling method of feature based on neighbour's image block and generate two width backgrounds and wipe out image, then this two width background is wiped out Images uniting one width background and wipe out image; Then extract the connected region of foreground pixel, by connected region and and surrounding neighbors in pixel be divided into foreground seeds pixel, background sub pixel and unmarked pixel; The stingy nomography based on closing form is finally adopted to carry out more meticulous segmentation to the connected region and surrounding neighbors thereof that comprise moving target;
(14) tracking of moving target: in the first two field picture, by artificial selected target rectangle frame, is divided into multiple little topography's block by target rectangle frame, and uses the technology of integrogram to extract their grey level histogram; All be used as divide the topography's block obtained in the first frame as foreground image block, use the background modeling method based on local space symbiosis to carry out modeling to the background around target rectangle frame simultaneously; In a new two field picture, first by the foreground image block that coupling is all, generate a target weight image collection; Then design the Statistical Operator of a robust, merge target weight image collection, thus determine target position in the current frame; Use local background's model after obtaining the position of target, the image block in target rectangle frame corresponding for target location is divided into foreground image block and background image block; Then upgrade the intensity histogram graph model of foreground image block, upgrade local background's model simultaneously; In each two field picture, all carry out successively by said process, terminate until follow the tracks of video.
Beneficial effect: compared with prior art, the present invention has the following advantages:
(1) the present invention had both had the target detection function of view-based access control model, acquisition of signal wide ranges, obtained target information complete;
(2) the present invention also has the target detection work function based on radar, derives from self, be affected by the external environment less to the perception information of object, and reliability in Depth Information Acquistion and accuracy higher;
(3) the present invention does not need participating in the overall process of staff, the detection to moving target, image trace can be completed voluntarily, cradle head controllor controls the shooting angle of monopod video camera, dynamic object is made to be presented on imaging plane central authorities all the time, measure the distance between unmanned water surface ship and dynamic object in real time by millimetre-wave radar, thus realize the location to dynamic object, in this, as feedback signal, form closed-loop control, guide the tracking of unmanned water surface ship to travel;
(4) position of waterborne target oriented jointly by the present invention's application monopod video camera and these two kinds of sensors of millimetre-wave radar, makes to detect to follow the trail of result more precisely, improves detection efficiency, greatly saves manpower and financial resources, have wide market outlook;
(5) the present invention is research object with waterborne target, detects, identifies and follows the trail of the objective, and searches and rescues, marine ship testing and monitoring manages and following novel military combat strategy has very large theory and realistic meaning to the perils of the sea.
Accompanying drawing explanation
Fig. 1 is structured flowchart of the present invention;
Fig. 2 is the processing procedure schematic diagram to 2D image in the present invention;
Fig. 3 is that in the present invention, texture pattern and motor pattern extract block diagram;
Fig. 4 is the schematic diagram of moving Object Segmentation in the present invention;
Fig. 5 is Moving Target Tracking Algorithm block diagram in the present invention.
Embodiment
Below technical solution of the present invention is described in detail, but protection scope of the present invention is not limited to described embodiment.
As shown in Figure 1, a kind of vision-based detection based on USV of the present invention and waterborne target tracing system, comprise command centre, unmanned surface vehicle and investigation system; Command centre is the control terminal of unmanned surface vehicle, and communicates to connect between unmanned surface vehicle and send instruction to unmanned surface vehicle; Unmanned surface vehicle receives the information sent from investigation system, and completes tracking waterborne target task by navigational system; Investigation system detects the target object on the water surface and locates knows its position coordinates, and information is sent to unmanned surface vehicle, waits for next step instruction of command centre simultaneously; Investigation system is integrated with monopod video camera and millimetre-wave radar.
Wherein, monopod video camera obtains object 2D positional information in the picture, simultaneously, millimetre-wave radar obtains the range information of object, the two coordinates detection and location to the 3D information of waterborne target, completes waterborne target information and exports, namely transfer to unmanned surface vehicle (USV) by the mode of radio communication by navigational system, monitoring personnel can data message received by control terminal (i.e. command centre) Real-Time Monitoring USV, and sends instruction to USV.
Embodiment 1:
First the bench model of unmanned boat is placed in swimming pool, simulates the command centre of whole waterborne target tracker with PC.Bead is thrown into swimming pool arbitrarily, and PC sends the instruction of search front spherical float thing to unmanned boat simultaneously.Detected by spherical object, the camera on unmanned boat and millimetre-wave radar are accurately oriented the 3D position of bead and this information are sent to navigational system, and net result is that unmanned boat leaves for little direction of bowl, namely completes search target operation.
As shown in Figure 2, the detection method for tracing of the above-mentioned vision-based detection based on USV and waterborne target tracing system, specifically comprises the following steps:
(1) monopod video camera gathers the 2D video image of waterborne target, then processes;
(11) image sequence that monopod video camera is taken is carried out the dynamic scene data that pre-service obtains being applicable to computer disposal, and then carry out the detection of background modeling and dynamic object, as shown in Figure 3, in figure, T represents the T moment, owing to there is the relevance in spatial domain in dynamic scene between neighbor, i.e. a kind of symbiosis, therefore this symbiosis is described and is extracted, use the moving target detecting method merged based on texture and motor pattern: use local binary patterns to extract texture pattern; Traditional local binary patterns is extended to time-space domain from spatial domain, for extracting motor pattern simultaneously; Adopt texture pattern and motion model to carry out modeling respectively to each pixel in scene, then in sorter aspect, the background model based on texture pattern and motor pattern is merged;
(12) segmentation of moving target: as shown in Figure 4, by using based on gauss hybrid models and embedding the background modeling method of feature based on neighbour's image block and generate two width backgrounds and wipe out image, then this two width background is wiped out Images uniting one width background and wipe out image; Then extract the connected region of foreground pixel, by connected region and and surrounding neighbors in pixel be divided into foreground seeds pixel, background sub pixel and unmarked pixel; Finally adopt the stingy nomography based on closing form, more meticulous segmentation is carried out to the connected region and surrounding neighbors thereof comprising moving target;
(13) tracking of moving target: as shown in Figure 5, in figure, t represents t two field picture.In the first two field picture, by artificial selected target rectangle frame, target rectangle frame is divided into multiple little topography's block, and uses the technology of integrogram to extract their grey level histogram; All be used as divide the topography's block obtained in the first frame as foreground image block, use the background modeling method based on local space symbiosis to carry out modeling to the background around target rectangle frame simultaneously; In a new two field picture, first by the foreground image block that coupling is all, generate a target weight image collection; Then design the Statistical Operator of a robust, merge target weight image collection, thus determine target position in the current frame; Use local background's model after obtaining the position of target, the image block in target rectangle frame corresponding for target location is divided into foreground image block and background image block; Then upgrade the intensity histogram graph model of foreground image block, upgrade local background's model simultaneously; When following the tracks of video and also not terminating, when namely t does not also reach and follows the tracks of video total frame, to each two field picture, all circulate successively by said process and carry out, terminate until follow the tracks of video, the at this moment tracking of moving target also just completes;
(2) monopod video camera tracing control, the pitching deflection angle of adjustment monopod video camera, makes target remain on the central authorities of image in real time;
(3) utilize millimetre-wave radar to measure distance between unmanned water surface ship and moving target, integrating step (2) the data obtained further, the tracking that the 3D data obtaining moving target complete moving target with accurately locate;
(4) unmanned water surface ship navigational system carries out autonomous trackable surface moving target traveling.
Claims (3)
1., based on vision-based detection and the waterborne target tracing system of USV, it is characterized in that: comprise command centre, unmanned surface vehicle and investigation system;
Described command centre is the control terminal of unmanned surface vehicle, and communicates to connect between unmanned surface vehicle and send instruction to unmanned surface vehicle;
Described unmanned surface vehicle receives the information sent from investigation system, and completes tracking waterborne target task by navigational system;
Described investigation system detects the target object on the water surface and locates knows its position coordinates, and information is sent to unmanned surface vehicle, waits for next step instruction of command centre simultaneously; Investigation system is integrated with monopod video camera and millimetre-wave radar.
2., based on a detection method for tracing for the vision-based detection based on USV according to claim 1 and waterborne target tracing system, it is characterized in that: comprise the following steps:
(1) the 2D video image that monopod video camera photographs is processed;
(2) monopod video camera tracing control, the pitching deflection angle of adjustment monopod video camera, makes target remain on the central authorities of image in real time;
(3) utilize the distance between millimetre-wave radar measurement unmanned water surface ship and moving target, integrating step (2) the data obtained, the 3D data obtaining moving target complete the tracking of moving target and accurately locate;
(4) unmanned water surface ship navigational system carries out autonomous trackable surface moving target traveling.
3. the detection method for tracing of the vision-based detection based on USV according to claim 2 and waterborne target tracing system, it is characterized in that: described step (1) comprises image sequence pre-service, carry out the detection of background modeling and moving target, the segmentation of moving target and motion target tracking four steps, detailed process is as follows:
(11) image sequence pre-service comprises image conversion, image denoising and image enhaucament;
(12) detection of background modeling and dynamic object, the i.e. moving object detection of combined with texture and motion model: use local binary patterns to extract texture pattern; Traditional local binary patterns is extended to time-space domain from spatial domain, for extracting motor pattern, concrete grammar is simultaneously: for extracting the descriptor of texture pattern for (x in t image
t,c, y
t,c) the pixel g at place
t,cconsider its eight neighborhood territory pixel g
t,p, p=0 ... .7, carries out binaryzation by each neighborhood territory pixel and this pixel and compares, obtain the binary string of eight, be i.e. a code word LBP at this pixel place
t(x
t,c, y
t,c):
Wherein
This code word portrays pixel (x
t,c, y
t,c) a kind of texture pattern of being formed with its surrounding pixel, then respectively modeling is carried out to each pixel employing texture pattern in scene and motion model, then in sorter aspect, the background model based on texture pattern and motor pattern is merged;
(13) segmentation of moving target: by using based on gauss hybrid models and embedding the background modeling method of feature based on neighbour's image block and generate two width backgrounds and wipe out image, then this two width background is wiped out Images uniting one width background and wipe out image; Then extract the connected region of foreground pixel, by connected region and and surrounding neighbors in pixel be divided into foreground seeds pixel, background sub pixel and unmarked pixel; The stingy nomography based on closing form is finally adopted to carry out more meticulous segmentation to the connected region and surrounding neighbors thereof that comprise moving target;
(14) tracking of moving target: in the first two field picture, by artificial selected target rectangle frame, is divided into multiple little topography's block by target rectangle frame, and uses the technology of integrogram to extract their grey level histogram; All be used as divide the topography's block obtained in the first frame as foreground image block, use the background modeling method based on local space symbiosis to carry out modeling to the background around target rectangle frame simultaneously; In a new two field picture, first by the foreground image block that coupling is all, generate a target weight image collection; Then design the Statistical Operator of a robust, merge target weight image collection, thus determine target position in the current frame; Use local background's model after obtaining the position of target, the image block in target rectangle frame corresponding for target location is divided into foreground image block and background image block; Then upgrade the intensity histogram graph model of foreground image block, upgrade local background's model simultaneously; In each two field picture, all carry out successively by said process, terminate until follow the tracks of video.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510509429.8A CN105184816A (en) | 2015-08-18 | 2015-08-18 | Visual inspection and water surface target tracking system based on USV and detection tracking method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510509429.8A CN105184816A (en) | 2015-08-18 | 2015-08-18 | Visual inspection and water surface target tracking system based on USV and detection tracking method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105184816A true CN105184816A (en) | 2015-12-23 |
Family
ID=54906868
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510509429.8A Pending CN105184816A (en) | 2015-08-18 | 2015-08-18 | Visual inspection and water surface target tracking system based on USV and detection tracking method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105184816A (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105741234A (en) * | 2016-01-27 | 2016-07-06 | 江苏科技大学 | Three-dimensional panorama look-around based automatic anchoring visual assistance system for unmanned ship |
| CN105923114A (en) * | 2016-06-17 | 2016-09-07 | 上海遨拓深水装备技术开发有限公司 | Semisubmersible unmanned ship and using method thereof |
| CN106643683A (en) * | 2016-10-15 | 2017-05-10 | 中国人民解放军海军大连舰艇学院 | Sea-surface target automatic detecting device and target detecting method |
| CN106780598A (en) * | 2016-12-05 | 2017-05-31 | 歌尔科技有限公司 | A kind of floating on water object detecting method and unmanned plane based on unmanned plane |
| CN106933232A (en) * | 2017-04-27 | 2017-07-07 | 上海大学 | A kind of context aware systems and method based on collaboration unmanned boat group |
| CN106970618A (en) * | 2017-04-06 | 2017-07-21 | 北京臻迪科技股份有限公司 | A kind of unmanned boat control method and system |
| CN107024903A (en) * | 2017-03-10 | 2017-08-08 | 江苏省新通智能交通科技发展有限公司 | The method and system that a kind of ship lockage video detection is checked |
| CN107830860A (en) * | 2017-10-31 | 2018-03-23 | 江苏科技大学 | A kind of unmanned boat lifting recovery visual guide method |
| CN108170139A (en) * | 2017-12-12 | 2018-06-15 | 武汉华之洋科技有限公司 | A kind of photoelectricity multitask system for unmanned boat and perform method |
| CN108646741A (en) * | 2018-05-31 | 2018-10-12 | 哈尔滨工程大学 | A kind of unmanned boat method for tracking target of view-based access control model feedback |
| WO2019000855A1 (en) * | 2017-04-14 | 2019-01-03 | 江苏科技大学 | Integrated control system of semi-submersible small unmanned surface vehicle |
| CN109850093A (en) * | 2019-01-10 | 2019-06-07 | 安徽天帆智能科技有限责任公司 | A kind of anti-collision human lifeboat |
| CN109960250A (en) * | 2017-12-26 | 2019-07-02 | 浙江大学 | The agricultural unmanned aerodynamic ship and method of self-navigation are carried out based on unmanned plane vision |
| CN110110797A (en) * | 2019-05-13 | 2019-08-09 | 哈尔滨工程大学 | A kind of waterborne target training set automatic acquiring method based on Multi-sensor Fusion |
| CN110610134A (en) * | 2019-08-13 | 2019-12-24 | 上海大学 | Unmanned ship autonomous docking method |
| CN112233138A (en) * | 2019-06-28 | 2021-01-15 | 北京京东乾石科技有限公司 | Target detection method and device |
| CN113850848A (en) * | 2021-09-26 | 2021-12-28 | 大连海事大学 | Unmanned boat-mounted marine radar and visual image cooperative marine multi-target long-term detection and tracking method |
| CN114228937A (en) * | 2022-02-28 | 2022-03-25 | 中国海洋大学 | Ship recognition system based on wave glider |
| CN116974305A (en) * | 2023-09-18 | 2023-10-31 | 中国海洋大学 | Marine vision tracking system and method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102186241A (en) * | 2011-04-26 | 2011-09-14 | 江苏科技大学 | Parallel distributed particle filter based wireless sensor network target tracking method |
| CN102982555A (en) * | 2012-11-01 | 2013-03-20 | 江苏科技大学 | Guidance infrared small target tracking method based on self-adaption manifold particle filters |
| CN103760902A (en) * | 2014-01-14 | 2014-04-30 | 上海海事大学 | USV straight path tracking method based on fuzzy control |
| CN103777522A (en) * | 2014-01-21 | 2014-05-07 | 上海海事大学 | Unmanned surface vessel linear tracking method based on fuzzy PID |
-
2015
- 2015-08-18 CN CN201510509429.8A patent/CN105184816A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102186241A (en) * | 2011-04-26 | 2011-09-14 | 江苏科技大学 | Parallel distributed particle filter based wireless sensor network target tracking method |
| CN102982555A (en) * | 2012-11-01 | 2013-03-20 | 江苏科技大学 | Guidance infrared small target tracking method based on self-adaption manifold particle filters |
| CN103760902A (en) * | 2014-01-14 | 2014-04-30 | 上海海事大学 | USV straight path tracking method based on fuzzy control |
| CN103777522A (en) * | 2014-01-21 | 2014-05-07 | 上海海事大学 | Unmanned surface vessel linear tracking method based on fuzzy PID |
Non-Patent Citations (5)
| Title |
|---|
| 刘茜: "水面移动机器人目标检测与定位方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 庄佳园 等: "基于雷达图像的水面无人艇目标检测技术", 《哈尔滨工程大学学报》 * |
| 曾文静: "基于光视觉的无人艇水面目标检测与跟踪研究", 《中国博士学位论文全文数据库 工程科技Ⅱ辑》 * |
| 钟必能: "复杂动态场景中运动目标检测与跟踪算法研究", 《中国博士学位论文全文数据库 信息科技辑》 * |
| 马忠丽 等: "无人艇视觉系统多类水面目标特征提取与识别", 《西安交通大学学报》 * |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105741234B (en) * | 2016-01-27 | 2019-03-29 | 江苏科技大学 | It is anchored automatically vision-aided system based on the unmanned boat that three-dimensional panorama is looked around |
| CN105741234A (en) * | 2016-01-27 | 2016-07-06 | 江苏科技大学 | Three-dimensional panorama look-around based automatic anchoring visual assistance system for unmanned ship |
| CN105923114A (en) * | 2016-06-17 | 2016-09-07 | 上海遨拓深水装备技术开发有限公司 | Semisubmersible unmanned ship and using method thereof |
| CN106643683A (en) * | 2016-10-15 | 2017-05-10 | 中国人民解放军海军大连舰艇学院 | Sea-surface target automatic detecting device and target detecting method |
| CN106780598A (en) * | 2016-12-05 | 2017-05-31 | 歌尔科技有限公司 | A kind of floating on water object detecting method and unmanned plane based on unmanned plane |
| CN107024903A (en) * | 2017-03-10 | 2017-08-08 | 江苏省新通智能交通科技发展有限公司 | The method and system that a kind of ship lockage video detection is checked |
| CN106970618A (en) * | 2017-04-06 | 2017-07-21 | 北京臻迪科技股份有限公司 | A kind of unmanned boat control method and system |
| WO2019000855A1 (en) * | 2017-04-14 | 2019-01-03 | 江苏科技大学 | Integrated control system of semi-submersible small unmanned surface vehicle |
| CN106933232A (en) * | 2017-04-27 | 2017-07-07 | 上海大学 | A kind of context aware systems and method based on collaboration unmanned boat group |
| CN107830860B (en) * | 2017-10-31 | 2019-09-27 | 江苏科技大学 | A kind of unmanned boat lifting recycling visual guide method |
| CN107830860A (en) * | 2017-10-31 | 2018-03-23 | 江苏科技大学 | A kind of unmanned boat lifting recovery visual guide method |
| CN108170139A (en) * | 2017-12-12 | 2018-06-15 | 武汉华之洋科技有限公司 | A kind of photoelectricity multitask system for unmanned boat and perform method |
| CN109960250A (en) * | 2017-12-26 | 2019-07-02 | 浙江大学 | The agricultural unmanned aerodynamic ship and method of self-navigation are carried out based on unmanned plane vision |
| CN108646741A (en) * | 2018-05-31 | 2018-10-12 | 哈尔滨工程大学 | A kind of unmanned boat method for tracking target of view-based access control model feedback |
| CN109850093A (en) * | 2019-01-10 | 2019-06-07 | 安徽天帆智能科技有限责任公司 | A kind of anti-collision human lifeboat |
| CN110110797A (en) * | 2019-05-13 | 2019-08-09 | 哈尔滨工程大学 | A kind of waterborne target training set automatic acquiring method based on Multi-sensor Fusion |
| CN110110797B (en) * | 2019-05-13 | 2022-10-28 | 哈尔滨工程大学 | Water surface target training set automatic acquisition method based on multi-sensor fusion |
| CN112233138A (en) * | 2019-06-28 | 2021-01-15 | 北京京东乾石科技有限公司 | Target detection method and device |
| CN110610134A (en) * | 2019-08-13 | 2019-12-24 | 上海大学 | Unmanned ship autonomous docking method |
| CN110610134B (en) * | 2019-08-13 | 2022-12-20 | 上海大学 | Unmanned ship autonomous docking method |
| CN113850848A (en) * | 2021-09-26 | 2021-12-28 | 大连海事大学 | Unmanned boat-mounted marine radar and visual image cooperative marine multi-target long-term detection and tracking method |
| CN113850848B (en) * | 2021-09-26 | 2024-04-02 | 大连海事大学 | Marine multi-target long-term detection and tracking method based on cooperation of unmanned ship carrying navigation radar and visual image |
| CN114228937A (en) * | 2022-02-28 | 2022-03-25 | 中国海洋大学 | Ship recognition system based on wave glider |
| CN116974305A (en) * | 2023-09-18 | 2023-10-31 | 中国海洋大学 | Marine vision tracking system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105184816A (en) | Visual inspection and water surface target tracking system based on USV and detection tracking method thereof | |
| CN110414396B (en) | Unmanned ship perception fusion algorithm based on deep learning | |
| CN109444911A (en) | A kind of unmanned boat waterborne target detection identification and the localization method of monocular camera and laser radar information fusion | |
| CN103218607B (en) | A kind of cooperative target for unmanned plane autonomous landing on the ship designs and localization method | |
| Galceran et al. | A real-time underwater object detection algorithm for multi-beam forward looking sonar | |
| CN107132530A (en) | My god/the integral monitoring system of sky/ships and light boats/buoy/islands and reefs base marine site multisensor | |
| CN110580044A (en) | unmanned ship full-automatic navigation heterogeneous system based on intelligent sensing | |
| CN107818326A (en) | A kind of ship detection method and system based on scene multidimensional characteristic | |
| US20220024549A1 (en) | System and method for measuring the distance to an object in water | |
| CA2950791A1 (en) | Binocular visual navigation system and method based on power robot | |
| CN103364408A (en) | Method for detecting underwater surface crack of hydraulic concrete structure by using underwater robot system | |
| CN104535066A (en) | Marine target and electronic chart superposition method and system in on-board infrared video image | |
| CN109213204A (en) | AUV sub-sea floor targets based on data-driven search navigation system and method | |
| US11948344B2 (en) | Method, system, medium, equipment and terminal for inland vessel identification and depth estimation for smart maritime | |
| KR20210007767A (en) | Autonomous navigation ship system for removing sea waste based on deep learning-vision recognition | |
| Zhang et al. | Research on unmanned surface vehicles environment perception based on the fusion of vision and lidar | |
| CN110443201B (en) | Target identification method based on multi-source image joint shape analysis and multi-attribute fusion | |
| CN110472500A (en) | A kind of water surface sensation target fast algorithm of detecting based on high speed unmanned boat | |
| Zhang et al. | Submarine pipeline tracking technology based on AUVs with forward looking sonar | |
| CN109859202A (en) | A kind of deep learning detection method based on the tracking of USV water surface optical target | |
| CN110427030B (en) | Unmanned ship autonomous docking recovery method based on Tiny-YolOship target detection algorithm | |
| Wu et al. | Autonomous UAV landing system based on visual navigation | |
| Shi et al. | Obstacle type recognition in visual images via dilated convolutional neural network for unmanned surface vehicles | |
| Zhou et al. | A real-time algorithm for visual detection of high-speed unmanned surface vehicle based on deep learning | |
| CN116246139A (en) | Target identification method based on multi-sensor fusion for unmanned ship navigation environment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20151223 |
|
| RJ01 | Rejection of invention patent application after publication |