CN110376593A - A kind of target apperception method and device based on laser radar - Google Patents
A kind of target apperception method and device based on laser radar Download PDFInfo
- Publication number
- CN110376593A CN110376593A CN201910715446.5A CN201910715446A CN110376593A CN 110376593 A CN110376593 A CN 110376593A CN 201910715446 A CN201910715446 A CN 201910715446A CN 110376593 A CN110376593 A CN 110376593A
- Authority
- CN
- China
- Prior art keywords
- target
- laser radar
- electro
- optical system
- unmanned boat
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
- G01C11/02—Picture taking arrangements specially adapted for photogrammetry or photographic surveying, e.g. controlling overlapping of pictures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
- G01C11/04—Interpretation of pictures
- G01C11/06—Interpretation of pictures by comparison of two or more pictures of the same area
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/005—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 with correlation of navigation data from several sources, e.g. map or contour matching
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
- G01C21/203—Specially adapted for sailing ships
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/86—Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
Abstract
The target apperception method and device based on laser radar that the invention discloses a kind of, the described method comprises the following steps: step 1: laser radar sensing module detects unmanned boat surrounding body, obtains the location information of target;Step 2: cradle head control module is used for the positional information calculation electro-optical system holder parameter according to the target, and controls electro-optical system precise positioning target;Step 3: analysis module obtains target category and target position in the picture and Objective extraction profile, size and color for carrying out detection identification to target monitoring picture frame by frame;Step 4: the target data perceived is uploaded into unmanned boat control centre.Target apperception method and device provided by the invention based on laser radar utilizes target position to calculate electro-optical system holder parameter using laser radar and electro-optical system linkage active probe unmanned boat surrounding body, and precise positioning target improves target identification accuracy rate.
Description
Technical field
The present invention relates to a kind of target apperception method and device more particularly to a kind of target apperception sides based on laser radar
Method and device.
Background technique
Unmanned water surface ship (Unmanned Surface Vehicle, USV) is because having small, mobility strong, intelligence
The features such as degree is high and someone's water surface ship can be replaced to complete complicated, hot mission in extreme environment, production, scientific research,
The fields such as national defence have wide practical use.Unmanned boat environmental perception device and method are the passes that unmanned boat realizes autonomous navigation
Key technology has high researching value.
A kind of unmanned boat Global obstacle object that patent document CN109282813A is announced knows method for distinguishing, comprising: navigation thunder
Up to scanning barrier;Calculate the correction position of barrier;Optronic tracker captures barrier, calculates the size of barrier;To obtaining
The data of the barrier taken take mean value;Carry out global avoidance planning.This method detects unmanned boat surrounding objects using pathfinder,
Optronic tracker capture identification target is recycled, actively perceive system is belonged to.Pathfinder detection accuracy described in this method is lower than
Laser radar can not get accurate target position information;This method is not directed to optronic tracker holder calculation method of parameters;
This method only extracts the dimension information of target, cannot carry out identification classification to target.
A kind of actively perceive apparatus and method based on unmanned boat that patent document CN109255820A is announced, comprising: nothing
People's ship navigates by water control unit, boat-carrying laser radar apparatus, camera calibration unit, data acquisition and display unit, data leaflet
Member, bank base server control unit, bank base Target Detection unlit;The bank base Target Detection unlit, for detecting complicated water
After the target of domain, the position of target is determined;The unmanned boat navigates by water control unit, navigates by water for controlling unmanned boat to mesh to be observed
Near mark;Boat-carrying laser radar apparatus, for detecting the specific location of target;The camera calibration unit, for by taking the photograph
Camera demarcates all Cell groups;Data acquisition and display unit, the clear image for photographic subjects;Bank base server
Control unit, for storing data acquisition and display unit acquired image data.This method passes through camera calibration unit
Calibrating camera realizes observation of the video camera to the default area Cell, and staking-out work is cumbersome and positioning accuracy is not high;This method is only adopted
The image data for collecting target, cannot carry out identification classification to target.
It, can be with the location information of actively perceive unmanned boat surrounding body target it is therefore desirable to develop a kind of device.
Summary of the invention
The target apperception method and device based on laser radar that technical problem to be solved by the invention is to provide a kind of, benefit
With laser radar and electro-optical system linkage active probe unmanned boat surrounding body, utilizes target position to calculate electro-optical system holder and join
Number, precise positioning target improve target identification accuracy rate.
The present invention is to solve above-mentioned technical problem and the technical solution adopted is that provide a kind of target based on laser radar
Cognitive method, comprising the following steps:
Step 1: laser radar sensing module detects unmanned boat surrounding body, obtains the location information of target;
Step 2: cradle head control module is used for the positional information calculation electro-optical system holder parameter according to the target, and controls
Electro-optical system precise positioning target processed;
Step 3: analysis module obtains target category and mesh for carrying out detection identification to target monitoring picture frame by frame
Mark position in the picture and Objective extraction profile, size and color;
Step 4: the target data perceived is uploaded into unmanned boat control centre.
Preferably, the analysis module is for carrying out detection identification based on Darknet to target monitoring picture frame by frame
Frame training study yolov3 waterborne target detection model.
Preferably, the step 1 specifically includes the laser radar detection unmanned boat surrounding body, obtains target with respect to nothing
Distance, azimuth and the radial dimension of people's ship, are denoted as D respectivelyVT、θAAnd LT, the position of unmanned boat is obtained by high-precision GPS,
It is denoted as (xlon,ylat), the calculation formula of the location information (x, y) of target is as follows:
Wherein,R is earth mean radius.
Preferably, the step 2 specifically includes electro-optical system holder parameter and is denoted as (p, t, z), adjusts electro-optical system holder
To bearing null, i.e. holder parameter is (0,0,0), obtains the angle of camera lens optical axis and geographical geographical north and the angle with horizontal plane,
It is denoted as θ respectively1, θ2;
Holder parameter (p, t, the z) calculation formula is as follows:
P=θA+θ1
Wherein, θAAzimuth for target relative to unmanned boat;
Wherein,H is height of the electro-optical system installation site away from sea level, DVTFor target relative to
The distance of unmanned boat;
Wherein MmaxFor electro-optical system holder maximum amplification, fminAnd fmaxRespectively electro-optical system camera lens are most
Small focal length and maximum focal length, f are the optimal focal length for focusing display current goal, and calculation formula is as follows:
Wherein,DVTDistance for target relative to unmanned boat, L are electro-optical system video camera sensor devices
The width of CMOS or CCD, LTFor target radial size.
Preferably, the Darknet frame training study yolov3 waterborne target detection model that is based on includes: that acquisition is waterborne
Target, including ship, reef, island, floating log, floating ice and other six class Target Photos of floating material multiple, a portion picture
As training data, another part picture is as verify data.
Preferably, the step 4 includes by target geographic position, target relative to the distance of unmanned boat, azimuth, target
Profile, size, generic upload unmanned boat control centre, and stored.
Another technical solution that the present invention uses to solve above-mentioned technical problem is to provide a kind of based on laser radar
Target apperception device, comprising:
Laser radar sensing module comprising laser radar, high-precision GPS and radar data processing unit, the laser
For radar for obtaining target relative to the distance of unmanned boat, azimuth and radial dimension, the high-precision GPS is described for editing
The position of laser radar, the radar data processing unit are used to obtain the location information of target;
Electro-optical system is connected with cradle head control module with analysis module;
Cradle head control module comprising holder parameter calculation unit and high-speed holder control unit, the holder parameter meter
Unit is calculated to be used to be used for according to the positional information calculation electro-optical system holder parameter of the target, the high-speed holder control unit
Control the electro-optical system precise positioning target;
The analysis module comprising image processing unit and object-recognition unit, described image processing unit are used
In carrying out detection identification to target monitoring picture frame by frame, the object-recognition unit is for obtaining target category and target in image
In position and Objective extraction profile, size and color;
Unmanned boat control centre is used to obtain the target data perceived.
The present invention comparison prior art has following the utility model has the advantages that the target apperception provided by the invention based on laser radar
Method and device improves detection efficient using laser radar and electro-optical system linkage active probe unmanned boat surrounding body;Benefit
Electro-optical system holder parameter is calculated with target position, precise positioning target enhances observation effect, improves target identification accuracy rate;
It is used for waterborne target Classification and Identification based on Darknet frame training yolov3 waterborne target detection model, discrimination to be high;Packet is provided
Target geographic position, target are included relative to mesh such as the distance of unmanned boat, azimuth, radial dimension, the profile of target, generics
Information data is marked, perception information is abundant.
Detailed description of the invention
Fig. 1 is the unmanned surface vehicle actively sense that the target apperception device based on laser radar is equipped in the embodiment of the present invention
Know system schematic;
Fig. 2 is that the holder parameter calculating angular relationship of the target apperception device based on laser radar in the embodiment of the present invention is bowed
View;
Fig. 3 is that the holder parameter of the target apperception device based on laser radar in the embodiment of the present invention calculates angular relationship side
View;
Fig. 4 is the structural schematic diagram of the target apperception device based on laser radar in the embodiment of the present invention.
Specific embodiment
The invention will be further described with reference to the accompanying drawings and examples.
In the following description, in order to provide thorough understanding of the invention, many concrete details are elaborated.However, this hair
Bright to practice in the case where these no concrete details, this will be aobvious and easy for the common technical staff in this field
See.Therefore, concrete details elaboration is only exemplary, and concrete details can be changed by bold and unrestrained spirit and scope
And it is still considered as within the spirit and scope of the present invention.
A kind of target apperception method and device based on laser radar provided in this embodiment, utilizes laser radar and photoelectricity
System interlink active probe unmanned boat surrounding body, using target position calculate electro-optical system holder parameter, precise positioning target,
Improve target identification accuracy rate.
Referring now to Fig. 1,1 is unmanned surface vehicle, and 2 be installation pillar, and 3 be photoelectric nacelle, and 4 be laser radar, and 5 be the water surface
Target, 6 be unmanned boat control centre.
The target apperception method based on laser radar that present embodiment discloses a kind of, comprising the following steps:
Step 1: laser radar sensing module detects unmanned boat surrounding body, obtains the location information of target;
Step 2: cradle head control module is used for the positional information calculation electro-optical system holder parameter according to the target, and controls
Electro-optical system precise positioning target processed;
Step 3: analysis module obtains target category and mesh for carrying out detection identification to target monitoring picture frame by frame
Mark position in the picture and Objective extraction profile, size and color;
Step 4: the target data perceived is uploaded into unmanned boat control centre.
Preferably, the analysis module is for carrying out detection identification based on Darknet to target monitoring picture frame by frame
Frame training study yolov3 waterborne target detection model.
Preferably, the step 1 specifically includes the laser radar detection unmanned boat surrounding body, obtains target with respect to nothing
Distance, azimuth and the radial dimension of people's ship, are denoted as D respectivelyVT、θAAnd LT, the position of unmanned boat is obtained by high-precision GPS,
It is denoted as (xlon,ylat), the calculation formula of the location information (x, y) of target is as follows:
Wherein,R is earth mean radius.
Preferably, the step 2 specifically includes electro-optical system holder parameter and is denoted as (p, t, z), adjusts electro-optical system holder
To bearing null, i.e. holder parameter is (0,0,0), obtains the angle of camera lens optical axis and geographical geographical north and the angle with horizontal plane,
It is denoted as θ respectively1, θ2;
Holder parameter (p, t, the z) calculation formula is as follows:
P=θA+θ1
Wherein, θAAzimuth for target relative to unmanned boat;
Wherein,H is height of the electro-optical system installation site away from sea level, DVTFor target relative to
The distance of unmanned boat;
Wherein MmaxFor electro-optical system holder maximum amplification, fminAnd fmaxRespectively electro-optical system camera lens are most
Small focal length and maximum focal length, f are the optimal focal length for focusing display current goal, and calculation formula is as follows:
Wherein,DVTDistance for target relative to unmanned boat, L are electro-optical system video camera sensor devices
The width of CMOS or CCD, LTFor target radial size.
Preferably, the Darknet frame training study yolov3 waterborne target detection model that is based on includes: that acquisition is waterborne
Target, including ship, reef, island, floating log, floating ice and other six class Target Photos of floating material multiple, a portion picture
As training data, another part picture is as verify data.Such as ship, reef, island, floating log, floating ice and other floatings
Six class Target Photo of object totally 30000, wherein 18000 are used as training data, 12000 are used as verify data, are based on
Darknet frame training study yolov3 waterborne target detection model.Using trained model frame by frame to target monitoring picture
Detection identification is carried out, the position of target category and target in the picture is obtained, to Objective extraction profile, size and external appearance characteristic number
According to.
Preferably, the step 4 includes by target geographic position, target relative to the distance of unmanned boat, azimuth, target
Profile, size, generic upload unmanned boat control centre, and stored, data supporting can be provided for flight course planning.
Referring now to Fig. 4, the present embodiment also discloses a kind of target apperception device based on laser radar, comprising:
Laser radar sensing module comprising laser radar, high-precision GPS and radar data processing unit, the laser
For radar for obtaining target relative to the distance of unmanned boat, azimuth and radial dimension, the high-precision GPS is described for editing
The position of laser radar, the radar data processing unit are used to obtain the location information of target;
Electro-optical system is connected with cradle head control module with analysis module;
Cradle head control module comprising holder parameter calculation unit and high-speed holder control unit, the holder parameter meter
Unit is calculated to be used to be used for according to the positional information calculation electro-optical system holder parameter of the target, the high-speed holder control unit
Control the electro-optical system precise positioning target;
The analysis module comprising image processing unit and object-recognition unit, described image processing unit are used
In carrying out detection identification to target monitoring picture frame by frame, the object-recognition unit is for obtaining target category and target in image
In position and Objective extraction profile, size and color;
Unmanned boat control centre is used to obtain the target data perceived.
To sum up, the target apperception method and device provided in this embodiment based on laser radar, utilizes laser radar and light
Electric system linkage active probe unmanned boat surrounding body, improves detection efficient;Electro-optical system holder is calculated using target position
Parameter, precise positioning target enhance observation effect, improve target identification accuracy rate;Based on Darknet frame training yolov3 water
Area Objects detection model is used for waterborne target Classification and Identification, and discrimination is high;There is provided includes target geographic position, target relative to nothing
The object information datas such as distance, azimuth, radial dimension, the profile of target, the generic of people's ship, perception information are abundant.
Although the present invention is disclosed as above with preferred embodiment, however, it is not to limit the invention, any this field skill
Art personnel, without departing from the spirit and scope of the present invention, when can make a little modification and perfect therefore of the invention protection model
It encloses to work as and subject to the definition of the claims.
Claims (7)
1. a kind of target apperception method based on laser radar, which comprises the following steps:
Step 1: laser radar sensing module detects unmanned boat surrounding body, obtains the location information of target;
Step 2: cradle head control module is used for the positional information calculation electro-optical system holder parameter according to the target, and controls light
Electric system precise positioning target;
Step 3: analysis module obtains target category and target exists for carrying out detection identification to target monitoring picture frame by frame
Position and Objective extraction profile, size and color in image;
Step 4: the target data perceived is uploaded into unmanned boat control centre.
2. the target apperception method according to claim 1 based on laser radar, which is characterized in that the video analysis mould
Block is for carrying out detection identification based on the training study yolov3 waterborne target detection of Darknet frame to target monitoring picture frame by frame
Model.
3. the target apperception method according to claim 2 based on laser radar, which is characterized in that the step 1 is specific
Including the laser radar detection unmanned boat surrounding body, target is obtained with respect to the distance of unmanned boat, azimuth and radial dimension,
It is denoted as D respectivelyVT、θAAnd LT, the position of unmanned boat is obtained by high-precision GPS, is denoted as (xlon,ylat), the location information of target
The calculation formula of (x, y) is as follows:
Wherein,R is earth mean radius.
4. the target apperception method according to claim 3 based on laser radar, which is characterized in that the step 2 is specific
Be denoted as (p, t, z) including electro-optical system holder parameter, adjustment electro-optical system holder to bearing null, i.e., holder parameter be (0,0,
0) angle of camera lens optical axis and geographical geographical north and the angle with horizontal plane, are obtained, is denoted as θ respectively1, θ2;
Holder parameter (p, t, the z) calculation formula is as follows:
P=θA+θ1
Wherein, θAAzimuth for target relative to unmanned boat;
Wherein,H is height of the electro-optical system installation site away from sea level, DVTIt is target relative to nobody
The distance of ship;
Wherein MmaxFor electro-optical system holder maximum amplification, fminAnd fmaxRespectively electro-optical system camera lens are minimum burnt
Away from and maximum focal length, f be the optimal focal length for focusing display current goal, calculation formula is as follows:
Wherein,DVTDistance for target relative to unmanned boat, L be electro-optical system video camera sensor devices CMOS or
The width of CCD, LTFor target radial size.
5. the target apperception method according to claim 4 based on laser radar, which is characterized in that described to be based on
Darknet frame training study yolov3 waterborne target detection model includes: acquisition target waterborne, including ship, reef, island
Small island, floating log, floating ice and other six class Target Photos of floating material multiple, a portion picture is as training data, another part
Picture is as verify data.
6. the target apperception method according to claim 1 based on laser radar, which is characterized in that the step 4 includes
Target geographic position, target are uploaded nobody relative to the distance of unmanned boat, azimuth, the profile of target, size, generic
Ship control centre, and stored.
7. a kind of target apperception device based on laser radar characterized by comprising
Laser radar sensing module comprising laser radar, high-precision GPS and radar data processing unit, the laser radar
For obtaining target relative to the distance of unmanned boat, azimuth and radial dimension, the high-precision GPS is for editing the laser
The position of radar, the radar data processing unit are used to obtain the location information of target;
Electro-optical system is connected with cradle head control module with analysis module;
Cradle head control module comprising holder parameter calculation unit and high-speed holder control unit, the holder parameter calculate single
Member is for the positional information calculation electro-optical system holder parameter according to the target, and the high-speed holder control unit is for controlling
The electro-optical system precise positioning target;
The analysis module comprising image processing unit and object-recognition unit, described image processing unit be used for by
Frame carries out detection identification to target monitoring picture, and the object-recognition unit is used to obtaining target category and target in the picture
Position and Objective extraction profile, size and color;
Unmanned boat control centre is used to obtain the target data perceived.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910715446.5A CN110376593B (en) | 2019-08-05 | 2019-08-05 | Target sensing method and device based on laser radar |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910715446.5A CN110376593B (en) | 2019-08-05 | 2019-08-05 | Target sensing method and device based on laser radar |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110376593A true CN110376593A (en) | 2019-10-25 |
CN110376593B CN110376593B (en) | 2021-05-04 |
Family
ID=68257964
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910715446.5A Active CN110376593B (en) | 2019-08-05 | 2019-08-05 | Target sensing method and device based on laser radar |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110376593B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112835055A (en) * | 2020-12-30 | 2021-05-25 | 潍柴动力股份有限公司 | Positioning method and system of laser SLAM equipment |
CN112927233A (en) * | 2021-01-27 | 2021-06-08 | 湖州市港航管理中心 | Marine laser radar and video combined target capturing method |
CN113064157A (en) * | 2021-06-01 | 2021-07-02 | 北京高普乐光电科技股份公司 | Radar and photoelectric linkage early warning method, device and system |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108471497A (en) * | 2018-03-02 | 2018-08-31 | 天津市亚安科技有限公司 | A kind of ship target real-time detection method based on monopod video camera |
KR20190005413A (en) * | 2017-07-06 | 2019-01-16 | 세한대학교기술지주회사 주식회사 | Collision detection device of Marina leisure ship based on laser sensor |
CN109298708A (en) * | 2018-08-31 | 2019-02-01 | 中船重工鹏力(南京)大气海洋信息系统有限公司 | A kind of unmanned boat automatic obstacle avoiding method merging radar and photoelectric information |
CN109375633A (en) * | 2018-12-18 | 2019-02-22 | 河海大学常州校区 | River course clear up path planning system and method based on global state information |
CN109444911A (en) * | 2018-10-18 | 2019-03-08 | 哈尔滨工程大学 | A kind of unmanned boat waterborne target detection identification and the localization method of monocular camera and laser radar information fusion |
CN109784278A (en) * | 2019-01-17 | 2019-05-21 | 上海海事大学 | The small and weak moving ship real-time detection method in sea based on deep learning |
-
2019
- 2019-08-05 CN CN201910715446.5A patent/CN110376593B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20190005413A (en) * | 2017-07-06 | 2019-01-16 | 세한대학교기술지주회사 주식회사 | Collision detection device of Marina leisure ship based on laser sensor |
CN108471497A (en) * | 2018-03-02 | 2018-08-31 | 天津市亚安科技有限公司 | A kind of ship target real-time detection method based on monopod video camera |
CN109298708A (en) * | 2018-08-31 | 2019-02-01 | 中船重工鹏力(南京)大气海洋信息系统有限公司 | A kind of unmanned boat automatic obstacle avoiding method merging radar and photoelectric information |
CN109444911A (en) * | 2018-10-18 | 2019-03-08 | 哈尔滨工程大学 | A kind of unmanned boat waterborne target detection identification and the localization method of monocular camera and laser radar information fusion |
CN109375633A (en) * | 2018-12-18 | 2019-02-22 | 河海大学常州校区 | River course clear up path planning system and method based on global state information |
CN109784278A (en) * | 2019-01-17 | 2019-05-21 | 上海海事大学 | The small and weak moving ship real-time detection method in sea based on deep learning |
Non-Patent Citations (2)
Title |
---|
MUHAMMAD ASROFI ET AL.: "Optimal Path Planning of a Mini USV using Sharp Cornering Algorithm", 《2016 INTERNATIONAL CONFERENCE ON INFORMATION TECHNOLOGY SYSTEMS AND INNOVATION (ICITSI)》 * |
严新平: "智能船舶的研究现状与发展趋势", 《交通与港航》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112835055A (en) * | 2020-12-30 | 2021-05-25 | 潍柴动力股份有限公司 | Positioning method and system of laser SLAM equipment |
CN112927233A (en) * | 2021-01-27 | 2021-06-08 | 湖州市港航管理中心 | Marine laser radar and video combined target capturing method |
CN113064157A (en) * | 2021-06-01 | 2021-07-02 | 北京高普乐光电科技股份公司 | Radar and photoelectric linkage early warning method, device and system |
CN113064157B (en) * | 2021-06-01 | 2022-05-27 | 北京高普乐光电科技股份公司 | Radar and photoelectric linkage early warning method, device and system |
Also Published As
Publication number | Publication date |
---|---|
CN110376593B (en) | 2021-05-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109931939B (en) | Vehicle positioning method, device, equipment and computer readable storage medium | |
US9465129B1 (en) | Image-based mapping locating system | |
CN110376593A (en) | A kind of target apperception method and device based on laser radar | |
CN106408601B (en) | A kind of binocular fusion localization method and device based on GPS | |
CN110142785A (en) | A kind of crusing robot visual servo method based on target detection | |
CN104501779A (en) | High-accuracy target positioning method of unmanned plane on basis of multi-station measurement | |
US20220024549A1 (en) | System and method for measuring the distance to an object in water | |
CN109446973B (en) | Vehicle positioning method based on deep neural network image recognition | |
CN106092054A (en) | A kind of power circuit identification precise positioning air navigation aid | |
Nagai et al. | UAV borne mapping by multi sensor integration | |
CN206611521U (en) | A kind of vehicle environment identifying system and omni-directional visual module based on multisensor | |
KR20210007767A (en) | Autonomous navigation ship system for removing sea waste based on deep learning-vision recognition | |
CN113627473B (en) | Multi-mode sensor-based water surface unmanned ship environment information fusion sensing method | |
CN104599281B (en) | A kind of based on the conforming panorama sketch in horizontal linear orientation and remote sensing figure method for registering | |
CN115717867A (en) | Bridge deformation measurement method based on airborne double cameras and target tracking | |
CN107741233A (en) | A kind of construction method of the outdoor map of three-dimensional | |
JP5152913B2 (en) | Offshore monitoring system and method | |
KR100878781B1 (en) | Method for surveying which can measure structure size and coordinates using portable terminal | |
CN104613928A (en) | Automatic tracking and air measurement method for optical pilot balloon theodolite | |
US11587241B2 (en) | Detection of environmental changes to delivery zone | |
Fan et al. | Bio-inspired multisensor navigation system based on the skylight compass and visual place recognition for unmanned aerial vehicles | |
CN111402324B (en) | Target measurement method, electronic equipment and computer storage medium | |
CN115471555A (en) | Unmanned aerial vehicle infrared inspection pose determination method based on image feature point matching | |
WO2022059603A1 (en) | Flood damage determination device, flood damage determination method, and program | |
CN113592837A (en) | Road kiln well lid height difference calculation method based on unmanned aerial vehicle fixed-point aerial photography |
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 |