CN112446371A - Multi-camera underwater image recognition device and enhancement processing method thereof - Google Patents
Multi-camera underwater image recognition device and enhancement processing method thereof Download PDFInfo
- Publication number
- CN112446371A CN112446371A CN202011327956.4A CN202011327956A CN112446371A CN 112446371 A CN112446371 A CN 112446371A CN 202011327956 A CN202011327956 A CN 202011327956A CN 112446371 A CN112446371 A CN 112446371A
- Authority
- CN
- China
- Prior art keywords
- camera
- module
- nano processor
- jetson nano
- cameras
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 12
- 238000004891 communication Methods 0.000 claims abstract description 9
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 13
- 238000001514 detection method Methods 0.000 claims description 6
- 230000002708 enhancing effect Effects 0.000 claims description 4
- 238000013480 data collection Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 2
- 241000196171 Hydrodictyon reticulatum Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000000034 method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/695—Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Theoretical Computer Science (AREA)
- Automation & Control Theory (AREA)
- Studio Devices (AREA)
Abstract
The invention provides a multi-camera underwater image recognition device and an enhancement processing method thereof, wherein the recognition device comprises: the device comprises a Jetson NANO processor, a device main body, a data acquisition module, a power control module, a camera module and an LED module; the data acquisition module comprises a pressure sensor and an MPU6050 six-axis attitude sensing module which is in communication connection with the Jetson NANO processor; the power control module comprises four propellers; the camera module comprises three cameras; the LED module comprises three LED devices; the propeller, the camera and the LED device are connected with the Jetson NANO processor. The multi-camera underwater image recognition device and the enhancement processing method thereof have the advantages of high recognition precision, simplicity in operation, capability of adjusting the posture in real time, image enhancement, improvement of device stability and guarantee of recognition efficiency.
Description
Technical Field
The invention relates to the technical field of underwater recognition, in particular to a multi-camera underwater image recognition device and an enhancement processing method thereof.
Background
Along with the continuous development and the maturity of internet of things, the intelligent and automatic requirement of recognition device under water is also higher and higher, because recognition device under water all has that the cost is lower relatively, no casualties risk, survivability are strong, mobility is good, convenient to use's advantage such as for recognition device under water all uses widely in military affairs and civilian aspect, and the main application market includes: salvage at sea, offshore search, river crossing pipeline inspection, observation under ice, underwater photography, deep water net cage fishery culture, artificial fishing reef investigation and reservoir dam maintenance.
According to statistical analysis, the market demand of the underwater recognition device for civil use and scientific research in China is large in recent years, and the application prospect is good, but the related application of the underwater recognition is in the primary stage at the present stage. Particularly, the existing underwater recognition device generally records video through a camera, only has a camera shooting function, is difficult to measure the depth of the device, is difficult to control the real-time posture of the underwater recognition device, and limits the depth of underwater recognition and the maneuverability of the underwater recognition device. And the underwater environment is complex, and the illumination condition is limited, so that the image collected by the camera is blurred. How to improve the recognition efficiency and maneuverability of an underwater recognition device and carry out underwater recognition at an accurate depth is a technical focus and difficulty to be urgently solved by technical personnel in the field.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides the multi-camera underwater image recognition device and the enhancement processing method thereof, which have the advantages of high recognition precision and simplicity in operation, and can adjust the posture in real time, enhance the image, improve the stability of the device and ensure the recognition efficiency.
In order to achieve the above object, the present invention provides a multi-camera underwater image recognition apparatus, comprising: the device comprises a Jetson NANO processor, a device main body, a data acquisition module, a power control module, a camera module and an LED module, wherein the data acquisition module, the power control module, the camera module and the LED module are arranged on the device main body; the data acquisition module comprises a pressure sensor and an MPU6050 six-axis attitude sensing module, and the pressure sensor and the MPU6050 six-axis attitude sensing module are in communication connection with the Jetson NANO processor; the power control module comprises four propellers; the camera module comprises three cameras which are distributed on the surface of the device main body at intervals along a straight line; the LED module comprises three LED devices, and the LED devices are respectively arranged below the three cameras; the thruster, the camera and the LED device are connected with the Jetson NANO processor; the Jetson NANO processor is in communication connection with an upper computer.
Preferably, the thrusters are respectively located in a geometrical central plane of the device body, and the thrusters are at an angle of 90 ° to each other.
Preferably, the Jetson NANO processor feeds back the power control module through the real-time posture information acquired by the data acquisition module, and adjusts the real-time posture of the device body by controlling the rotating speed of the propeller.
Preferably, pins of the MPU6050 six-axis gesture sensing module are respectively connected to GPIO pins of the Jetson NANO processor through an ICC communication mode.
Preferably, the device main body is further provided with four motor driving modules, and the thruster is connected with the Jetson NANO processor through one motor driving module respectively.
Preferably, the camera module is connected to a USB interface of the Jetson NANO processor.
The invention relates to an enhancement processing method of a multi-camera underwater image recognition device, which comprises the following steps:
s1: carrying out initialization setting, and entering a working state after the Jetson NANO processor receives the upper computer command;
s2: receiving a detection signal of the pressure sensor, and obtaining the water depth according to the detection signal;
s3: judging whether the water depth exceeds a preset depth, if so, carrying out the next step, and if not, returning to the step S2;
s4: the MPU6050 six-axis attitude sensing module sends signals to measure and calculate the real-time attitude of the device main body;
s5: the Jetson NANO processor sends an adjusting signal to the thruster according to the real-time posture, so that the thruster pushes the device main body to vertically move underwater;
s6: the propeller continuously works, the camera module collects images, enhancement operation is carried out on the images, and the step S4 is returned.
Preferably, the step of performing an enhancement operation on the image further comprises the steps of:
a. reading the current real-time posture of the device main body;
b. rotating the angles of the images collected by the three cameras of the camera module;
c. calculating the average color level of the images collected by two cameras positioned at two ends in the three cameras;
d. and enhancing the image acquired by one camera positioned in the middle of the three cameras by taking the average color level as a threshold value to obtain an enhanced image, and transmitting the enhanced image.
Preferably, the step of S6 is preceded by an image feedback step, and the image feedback step includes the steps of:
e. the Jetson NANO processor receives image information collected by the three cameras;
f. the Jetson NANO processor calculating a declination of the device body according to the image information and the real-time pose;
g. and the Jetson NANO processor adjusts the propeller according to the deflection angle, so that the connecting line direction of the three cameras is vertical and downward.
Due to the adoption of the technical scheme, the invention has the following beneficial effects:
due to the arrangement of the pressure sensor, the multi-camera underwater image recognition device can be used for various underwater recognition work in deeper water areas and various complex environments, can meet the requirement of collecting deeper water samples, and has high working efficiency and simple working mode; and the acquired image information is sent to the data acquisition module, so that the data acquisition module acquires the current posture of the device according to the acquired image information and adjusts the propeller to always keep the vertical motion of the device main body. The method ensures the identification precision after image enhancement, improves the stability of the device, has obvious progress and is suitable for popularization and application.
Drawings
FIG. 1 is a schematic structural diagram of a multi-camera underwater image recognition device according to an embodiment of the present invention;
FIG. 2 is an electrical schematic of a Jetson NANO processor according to an embodiment of the present invention;
FIG. 3 is a flow chart of image enhancement according to an embodiment of the present invention;
fig. 4 is a control schematic block diagram of an embodiment of the present invention.
Detailed Description
The following description of the preferred embodiments of the present invention will be provided in conjunction with the accompanying drawings of fig. 1 to 4, and will make the functions and features of the present invention better understood.
Referring to fig. 1 and 2, a multi-camera underwater image recognition device according to an embodiment of the present invention includes a Jetson NANO processor 1, a device main body 2, and a data acquisition module, a power control module, a camera module, and an LED module mounted on the device main body 2; the data acquisition module comprises a pressure sensor 3 and an MPU6050 six-axis attitude sensing module 4, the pressure sensor 3 and the MPU6050 six-axis attitude sensing module 4 are in communication connection with the Jetson NANO processor 1, the pressure sensor 3 is used for measuring the depth of the device, and the MPU6050 six-axis attitude sensing module 4 is used for measuring the real-time attitude of the device; the power control module comprises four propellers 5, and the real-time posture of the rotating speed adjusting device of the propellers 5 can be controlled; the camera module comprises three cameras 6, the cameras 6 are distributed on the surface of the device main body 2 at intervals along a straight line, and connecting lines of the three cameras 6 are parallel to a perpendicular bisector of the device main body 2; the LED module comprises three LED devices 7, the LED devices 7 are respectively arranged below the three cameras 6, and the LED module is lightened to assist the cameras 6 to shoot when in work; the thruster 5, the camera 6 and the LED device 7 are connected with the Jetson NANO processor 1; the Jetson NANO processor 1 is communicatively coupled to an upper computer 8 via an ethernet mode. The device main body 2 is further connected with a cable 9, and supplies power to the Jetson NANO processor 1, the data acquisition module, the power control module, the camera module and the LED module through the cable 9.
The propellers 5 are respectively positioned in the geometrical central plane of the device body 2, the propellers 5 form an included angle of 90 degrees with each other, and the holding device can stably move vertically under water.
The Jetson NANO processor 1 feeds back the power control module through the real-time posture information acquired by the data acquisition module, and the real-time posture of the rotating speed adjusting device main body 2 of the propeller 5 is controlled.
The MPU6050 pins of the six-axis attitude sensing module 4 are respectively connected with GPIO pins of the Jetson NANO processor 1 through the ICC communication mode. Specifically, pins 1 to 4 of the MPU6050 six-axis attitude sensing module 4 are respectively connected to GPIO pins 1, 6, 5, and 3 of the Jetson NANO processor 1.
The device main body 2 is also provided with four motor driving modules 10, and the thruster 5 is respectively connected with the Jetson NANO processor 1 through one motor driving module 10; the motor drive module 10 is used to control the propeller 5.
The camera module is connected with the USB interface of the Jetson NANO processor 1.
Referring to fig. 2, the Jetson NANO processor 1 is connected to four motor driving modules 10, and the motor driving modules 10 control the corresponding thrusters 5 to maintain the vertical movement of the device; the Jetson NANO processor 1 is connected with the three cameras 6 for image acquisition; the Jetson NANO processor 1 is connected with an image processing module 11, and is used for enhancing images collected by the camera 6 and transmitting processed data to the upper computer 8.
Referring to fig. 1 to 4, an enhanced processing method of a multi-camera underwater image recognition device according to the present invention includes the steps of:
s1: carrying out initialization setting, and entering a working state after the Jetson NANO processor 1 receives a command of the upper computer 8;
s2: receiving a detection signal of the pressure sensor 3, and obtaining the water depth according to the detection signal;
s3: judging whether the depth of water exceeds the preset depth, if so, carrying out the next step, otherwise, returning to the step S2;
s4: the MPU6050 six-axis attitude sensing module 4 sends signals to measure and calculate the real-time attitude of the device main body 2;
s5: the Jetson NANO processor 1 sends an adjusting signal to the thruster 5 according to the real-time posture, so that the thruster 5 pushes the device main body 2 to move vertically underwater;
s6: the propeller 5 continuously works, the image pickup module collects images, enhancement operation is carried out on the images, and the operation returns to the step S4.
The step of performing an enhancement operation on the image further comprises the steps of:
a. reading the real-time posture of the current device main body 2;
b. rotating the angles of the images acquired by the three cameras 6 of the camera module;
c. calculating the average color gradation of the images collected by the two cameras 6 positioned at the two ends in the three cameras 6;
d. and enhancing the image collected by one camera 6 positioned in the middle of the three cameras 6 by taking the average color level as a threshold value to obtain an enhanced image, and transmitting the enhanced image.
The step of S6 is preceded by an image feedback step, and the image feedback step comprises the steps of:
e. the Jetson NANO processor 1 receives image information collected by the three cameras 6;
f. the Jetson NANO processor 1 calculates a declination of the device body 2 according to the image information and the real-time pose;
g. the Jetson NANO processor 1 adjusts the propeller 5 according to the deflection angle, so that the connection direction of the three cameras 6 is vertical and downward.
In conclusion, it can be seen that: the multi-camera underwater image recognition device and the enhancement processing method thereof can be used for collecting various kinds of monitoring data under different complex environment water, and the images collected by the camera module are enhanced, so that the recognition precision is high, the operation is simple, the posture can be adjusted in real time, the stability of the device is improved, and the recognition efficiency is ensured.
While the present invention has been described in detail and with reference to the embodiments thereof as illustrated in the accompanying drawings, it will be apparent to one skilled in the art that various changes and modifications can be made therein. Therefore, certain details of the embodiments are not to be interpreted as limiting, and the scope of the invention is to be determined by the appended claims.
Claims (9)
1. A multi-camera underwater image recognition device, comprising: the device comprises a Jetson NANO processor, a device main body, a data acquisition module, a power control module, a camera module and an LED module, wherein the data acquisition module, the power control module, the camera module and the LED module are arranged on the device main body; the data acquisition module comprises a pressure sensor and an MPU6050 six-axis attitude sensing module, and the pressure sensor and the MPU6050 six-axis attitude sensing module are in communication connection with the Jetson NANO processor; the power control module comprises four propellers; the camera module comprises three cameras which are distributed on the surface of the device main body at intervals along a straight line; the LED module comprises three LED devices, and the LED devices are respectively arranged below the three cameras; the thruster, the camera and the LED device are connected with the Jetson NANO processor; the Jetson NANO processor is in communication connection with an upper computer.
2. The multi-camera underwater image recognition device according to claim 1, wherein the thrusters are respectively located in a geometrical center plane of the device body, and the thrusters are at an angle of 90 ° with respect to each other.
3. The multi-camera underwater image recognition device according to claim 1, wherein the Jetson NANO processor feeds back the power control module through real-time attitude information collected by the data collection module, and adjusts a real-time attitude of the device body by controlling a rotation speed of the propeller.
4. The multi-camera underwater image recognition device according to claim 1, wherein pins of the MPU6050 six-axis attitude sensing module are respectively connected to GPIO pins of the Jetson NANO processor through an ICC communication mode.
5. The multi-camera underwater image recognition device according to claim 1, wherein the device body is further mounted with four motor driving modules, and the thrusters are respectively connected to the Jetson NANO processor through one motor driving module.
6. The multi-camera underwater image recognition device according to claim 1, wherein the camera module is connected to a USB interface of the Jetson NANO processor.
7. An enhancement processing method of the multi-camera underwater image recognition device according to any one of claims 1 to 6, comprising the steps of:
s1: carrying out initialization setting, and entering a working state after the Jetson NANO processor receives the upper computer command;
s2: receiving a detection signal of the pressure sensor, and obtaining the water depth according to the detection signal;
s3: judging whether the water depth exceeds a preset depth, if so, carrying out the next step, and if not, returning to the step S2;
s4: the MPU6050 six-axis attitude sensing module sends signals to measure and calculate the real-time attitude of the device main body;
s5: the Jetson NANO processor sends an adjusting signal to the thruster according to the real-time posture, so that the thruster pushes the device main body to vertically move underwater;
s6: the propeller continuously works, the camera module collects images, enhancement operation is carried out on the images, and the step S4 is returned.
8. The enhancement processing method according to claim 7, wherein said step of performing an enhancement operation on said image further comprises the steps of:
a. reading the current real-time posture of the device main body;
b. rotating the angles of the images collected by the three cameras of the camera module;
c. calculating the average color level of the images collected by two cameras positioned at two ends in the three cameras;
d. and enhancing the image acquired by one camera positioned in the middle of the three cameras by taking the average color level as a threshold value to obtain an enhanced image, and transmitting the enhanced image.
9. The enhancement processing method according to claim 8, further comprising an image feedback step before the step of S6, wherein the image feedback step comprises the steps of:
e. the Jetson NANO processor receives image information collected by the three cameras;
f. the Jetson NANO processor calculating a declination of the device body according to the image information and the real-time pose;
g. and the Jetson NANO processor adjusts the propeller according to the deflection angle, so that the connecting line direction of the three cameras is vertical and downward.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011327956.4A CN112446371A (en) | 2020-11-24 | 2020-11-24 | Multi-camera underwater image recognition device and enhancement processing method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011327956.4A CN112446371A (en) | 2020-11-24 | 2020-11-24 | Multi-camera underwater image recognition device and enhancement processing method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112446371A true CN112446371A (en) | 2021-03-05 |
Family
ID=74737394
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011327956.4A Pending CN112446371A (en) | 2020-11-24 | 2020-11-24 | Multi-camera underwater image recognition device and enhancement processing method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112446371A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102819263A (en) * | 2012-07-30 | 2012-12-12 | 中国航天科工集团第三研究院第八三五七研究所 | Multi-camera visual perception system for UGV (Unmanned Ground Vehicle) |
| CN103546665A (en) * | 2012-07-11 | 2014-01-29 | 北京博雅华录视听技术研究院有限公司 | Method for enhancing image definition on basis of multiple cameras |
| CN105282424A (en) * | 2014-12-22 | 2016-01-27 | 维沃移动通信有限公司 | Multiarea-synchronous co-filming method of mobile terminal and mobile terminal |
| CN107270900A (en) * | 2017-07-25 | 2017-10-20 | 广州阿路比电子科技有限公司 | A kind of 6DOF locus and the detecting system and method for posture |
| CN107329421A (en) * | 2017-06-09 | 2017-11-07 | 上海大学 | A kind of underwater photographic system |
| CN107340777A (en) * | 2016-12-06 | 2017-11-10 | 北京臻迪科技股份有限公司 | A kind of underwater unmanned boat control system and method |
| CN107566730A (en) * | 2017-09-27 | 2018-01-09 | 维沃移动通信有限公司 | A kind of panoramic picture image pickup method and mobile terminal |
| CN107623803A (en) * | 2016-07-15 | 2018-01-23 | 李海锋 | A kind of implementation method and equipment of the augmented reality with light stream positioning function |
| CN109068116A (en) * | 2018-08-31 | 2018-12-21 | 青岛海信移动通信技术股份有限公司 | Image processing method, device, mobile terminal and storage medium based on light filling |
| CN109684945A (en) * | 2018-12-10 | 2019-04-26 | 平安科技（深圳）有限公司 | Biopsy method, device, server and storage medium based on pupil |
-
2020
- 2020-11-24 CN CN202011327956.4A patent/CN112446371A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103546665A (en) * | 2012-07-11 | 2014-01-29 | 北京博雅华录视听技术研究院有限公司 | Method for enhancing image definition on basis of multiple cameras |
| CN102819263A (en) * | 2012-07-30 | 2012-12-12 | 中国航天科工集团第三研究院第八三五七研究所 | Multi-camera visual perception system for UGV (Unmanned Ground Vehicle) |
| CN105282424A (en) * | 2014-12-22 | 2016-01-27 | 维沃移动通信有限公司 | Multiarea-synchronous co-filming method of mobile terminal and mobile terminal |
| CN107623803A (en) * | 2016-07-15 | 2018-01-23 | 李海锋 | A kind of implementation method and equipment of the augmented reality with light stream positioning function |
| CN107340777A (en) * | 2016-12-06 | 2017-11-10 | 北京臻迪科技股份有限公司 | A kind of underwater unmanned boat control system and method |
| CN107329421A (en) * | 2017-06-09 | 2017-11-07 | 上海大学 | A kind of underwater photographic system |
| CN107270900A (en) * | 2017-07-25 | 2017-10-20 | 广州阿路比电子科技有限公司 | A kind of 6DOF locus and the detecting system and method for posture |
| CN107566730A (en) * | 2017-09-27 | 2018-01-09 | 维沃移动通信有限公司 | A kind of panoramic picture image pickup method and mobile terminal |
| CN109068116A (en) * | 2018-08-31 | 2018-12-21 | 青岛海信移动通信技术股份有限公司 | Image processing method, device, mobile terminal and storage medium based on light filling |
| CN109684945A (en) * | 2018-12-10 | 2019-04-26 | 平安科技（深圳）有限公司 | Biopsy method, device, server and storage medium based on pupil |
Non-Patent Citations (2)
| Title |
|---|
| 刘赫 等: "具有水样采集功能的观测型水下机器人的设计", 《吉林大学学报(信息科学版)》, vol. 38, no. 6, 15 November 2020 (2020-11-15), pages 737 - 743 * |
| 李旭: "40相机阵列的水下结构表观观测***的实现与应用", 《中国优秀硕士学位论文全文数据库 基础科学辑》, no. 05, 15 May 2019 (2019-05-15) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107094683B (en) | Automatic feeding and water quality monitoring control system for aquaculture | |
| CN109238240B (en) | Unmanned aerial vehicle oblique photography method considering terrain and photography system thereof | |
| CN106094819B (en) | Underwater robot control system and course heading control method based on sonar image target identification | |
| CN109931909B (en) | Unmanned aerial vehicle-based marine fan tower column state inspection method and device | |
| WO2019232247A1 (en) | Biomass estimation in an aquaculture environment | |
| CN111998772B (en) | Pixel-level target positioning method based on laser and monocular vision fusion | |
| CN110110797B (en) | Water surface target training set automatic acquisition method based on multi-sensor fusion | |
| CN110133667B (en) | Underwater three-dimensional detection system based on mobile forward looking sonar | |
| CN113358665A (en) | Unmanned aerial vehicle tunnel defect detection method and system | |
| CN116255908B (en) | Underwater robot-oriented marine organism positioning measurement device and method | |
| CN108549381A (en) | A kind of unmanned boat obstacle avoidance apparatus and method based on image vision | |
| CN111746728B (en) | Novel overwater cleaning robot based on reinforcement learning and control method | |
| KR20210007767A (en) | Autonomous navigation ship system for removing sea waste based on deep learning-vision recognition | |
| KR101988963B1 (en) | Discovery system using the deep-learning | |
| CN106094829A (en) | A kind of autonomous type Stichopus japonicus fishes for robot system and method | |
| CN213812165U (en) | Three-dimensional scanning imaging system applied underwater | |
| CN110412584A (en) | A kind of mobile quick splicing system of underwater Forward-Looking Sonar | |
| CN112809703A (en) | Bottom sowing sea cucumber catching robot based on ESRGAN enhanced super-resolution and CNN image recognition | |
| CN207835648U (en) | A kind of underwater robot light vision monitoring apparatus | |
| CN112254668A (en) | Underwater three-dimensional scanning imaging device and imaging method | |
| CN109765931B (en) | Near-infrared video automatic navigation method suitable for breakwater inspection unmanned aerial vehicle | |
| CN111832379A (en) | Unmanned aerial vehicle real-time video detection system based on convolutional neural network | |
| Yin | Inspection robot for submarine pipeline based on machine vision | |
| CN112446371A (en) | Multi-camera underwater image recognition device and enhancement processing method thereof | |
| CN114396921A (en) | Qiantanjiang river tidal bore height and propagation speed measuring method based on unmanned aerial vehicle |
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 |