CN110969213A - Ship detection method and device based on fast RCNN and electronic equipment - Google Patents
Ship detection method and device based on fast RCNN and electronic equipment Download PDFInfo
- Publication number
- CN110969213A CN110969213A CN201911258328.2A CN201911258328A CN110969213A CN 110969213 A CN110969213 A CN 110969213A CN 201911258328 A CN201911258328 A CN 201911258328A CN 110969213 A CN110969213 A CN 110969213A
- Authority
- CN
- China
- Prior art keywords
- ship
- data
- detection
- model
- training
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of intelligent identification, in particular to a ship detection method and device based on fast RCNN and electronic equipment. The method comprises the following steps: acquiring a plurality of ship pictures to form a ship data set; preprocessing a ship data set, labeling the ship data, and outputting a labeling result; inputting the first ship data into a preset training model for training to obtain a detection model; and outputting the ship detection result by inputting the second ship data into the detection model. Building a training model by using a fast RCNN network, and detecting ship data; the method comprises the steps of inputting a data picture of video image disassembly in a trained detection model, identifying and positioning ships existing in the picture, and realizing intelligent detection through a deep learning method, so that the ship detection efficiency is improved, and the missing detection probability is reduced.
Description
Technical Field
The invention relates to the technical field of intelligent identification, in particular to a ship detection method and device based on fast RCNN and electronic equipment.
Background
In modern society, ship inspection is an important measure for guaranteeing the safety of marine defense, maintaining the security order of ports, finding illegal crimes such as sneak ferrying and smuggling in time and correcting the illegal behaviors.
The main objects of the ship inspection are individual ships and foreign ships, unknown and unnamed ships, ships with passenger pick-up phenomena or without anchoring, ships with suspicious signs, ships running according to the laws of climate and tide, ships in violation of regulations and entering ports at night and the like.
In the prior art, a combination of daytime inspection and nighttime inspection is mainly adopted, and the emphasis inspection is combined with the general inspection, such as: the frontier defense dispatching place or the frontier defense workstation insists on observing the ships in the port every day; regular or irregular ship inspection is carried out in a busy port, and the inspection is organized at any time when enemy notice or major condition occurs; the centralized inspection is planned to be carried out during major festivals or fish flood. However, the detection of the running ship by adopting the manual observation mode not only consumes a lot of manpower and has low detection efficiency, but also has the possibility of missed detection.
Disclosure of Invention
In view of this, embodiments of the present invention provide a ship detection method, apparatus, and electronic device, so as to solve the problems of low detection efficiency and missed detection when a ship is manually detected.
According to a first aspect, an embodiment of the present invention provides a ship detection method based on fast RCNN, including: acquiring a plurality of ship pictures to form a ship data set; preprocessing the ship data set, labeling the ship data, and outputting a labeling result; wherein, the labeling result comprises: first vessel data and second vessel data; inputting the first ship data into a preset training model for training to obtain a detection model; outputting a ship detection result by inputting the second ship data into the detection model; wherein the ship detection result comprises: detected vessel type data and vessel position data.
Building a training model by using a fast RCNN network, and detecting ship data; the method comprises the steps of inputting a data picture of video image disassembly in a trained detection model, identifying and positioning ships existing in the picture, and realizing intelligent detection through a deep learning method, so that the ship detection efficiency is improved, and the missing detection probability is reduced.
With reference to the first aspect, in a first implementation manner of the first aspect, the ship data set includes a picture set stored in a picture format by acquiring surveillance video data frames of a coastal region, wherein the picture set includes ships of different sizes and shapes.
With reference to the first aspect, in a second embodiment of the first aspect, the vessel data set is preprocessed, comprising: and carrying out image graying, image noise reduction and image transformation on the ship data set.
By preprocessing the ship data, the characteristics of the image are highlighted, and subsequent characteristic extraction is facilitated.
With reference to the first aspect, in a third implementation manner of the first aspect, inputting the first ship data into a preset training model for training to obtain a detection model includes: and setting the learning rate and the maximum iteration number in the training process by adopting a fast RCNN model.
The accuracy of the training model can be adjusted by adjusting the learning rate and the maximum iteration number, so that the identification precision of the trained model is ensured by using the maximum iteration number.
With reference to the first aspect, in a fourth embodiment of the first aspect, the fast RCNN network model includes:
inputting the first ship data into a CNN network to obtain ship characteristic information;
inputting the ship characteristic information into an RPN network to obtain the characteristic information of the candidate frame;
and judging and classifying the characteristic information of the candidate frame by using a classifier, and outputting a classification result.
By using the fast RCNN network model, the marine vessel can be identified efficiently, and the identification efficiency is improved.
With reference to the first aspect, in a fifth implementation manner of the first aspect, the performing judgment and classification on feature information of the candidate frame by using a classifier includes:
acquiring feature information of the candidate frame, and dividing the feature information of the candidate frame into first feature information and second feature information;
training the first characteristic information through a classification algorithm to generate a classification model;
and testing the second sample by using the obtained classification model, and outputting a classification result.
Feature classification is performed by a classifier to reduce duplicate detection while enabling further vessel data determination.
According to a second aspect, an embodiment of the present invention provides a ship detection apparatus based on fast RCNN, including:
the acquisition module is used for acquiring a plurality of ship pictures to form a ship data set;
the preprocessing module is used for preprocessing the ship data set, marking the ship data and outputting a marking result;
the training module is used for inputting the first ship data into a preset training model for training so as to obtain a detection model;
and the detection output module is used for outputting a ship detection result by inputting the second ship data into the detection model.
According to a third aspect, an embodiment of the present invention provides an electronic device, including: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to execute the fast RCNN-based ship detection method according to the first aspect or any one of the embodiments of the first aspect.
According to a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the fast RCNN-based ship detection method according to the first aspect or any one of the embodiments of the first aspect.
Drawings
The features and advantages of the present invention will be more clearly understood by reference to the accompanying drawings, which are illustrative and not to be construed as limiting the invention in any way, and in which:
FIG. 1 is a flow chart of a fast RCNN based ship detection method according to an embodiment of the present invention;
FIG. 2 is a flow chart of a modeling of a fast RCNN based ship detection method according to an embodiment of the present invention;
FIG. 3 is a block diagram of a fast RCNN based ship detection apparatus according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present invention.
Reference numerals
10-an acquisition module; 20-a pre-processing module; 30-a training module; 40-a detection output module;
401-a processor; 402-a bus; 403-a communication interface; 404-memory.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
An embodiment of the present invention provides a ship detection method based on fast RCNN, as shown in fig. 1, including:
s10, acquiring a plurality of ship pictures to form a ship data set; the method comprises the steps of monitoring a marine ship by using an unmanned aerial vehicle and a monitoring camera, and acquiring a monitoring picture shot by the camera, wherein a plurality of frames of ship monitoring pictures are combined into a ship data set.
S20, preprocessing the ship data set, labeling the ship data, and outputting a labeling result; wherein, the labeling result comprises: first vessel data and second vessel data; the ship data are marked through marking software, wherein the first ship data can be data used for training a model, the second ship data can be test data needing to be detected, and the first ship data and the second ship data are pictures.
S30, inputting the first ship data into a preset training model for training to obtain a detection model; the preset training model may be a training model built through a deep learning network, for example: a CNN network.
S40, outputting a ship detection result by inputting the second ship data into the detection model; wherein the ship detection result comprises: detected vessel type data and vessel position data.
Building a training model by using a fast RCNN network, and detecting ship data; the method is characterized in that a data picture disassembled from a video image is input into a trained detection model, ships existing in the picture are identified and positioned, and intelligent detection is realized through a deep learning method, so that the ship detection efficiency is improved, and the missing detection probability is reduced.
Wherein, training in presetting the training model to first ship data input to obtain detection model, include: and setting the learning rate and the maximum iteration number in the training process by adopting a fast RCNN model. Specifically, the modeling process of the fast RCNN network model, as shown in fig. 2, includes:
s201, inputting the first ship data into a CNN network to obtain ship characteristic information; inputting the first ship data into a CNN network, and performing convolution processing to obtain ship characteristic information, wherein the ship characteristic information can be a ship characteristic diagram; the ship feature map can ensure that the ship features can be identified quickly.
S202, inputting ship feature information into an RPN (resilient packet network) to obtain feature information of a candidate frame; through the feature map obtained in step S201, picture information with rectangular frame is obtained in conjunction with the RPN network. The preliminary identified ship results can be obtained by this step.
S203, judging and classifying the feature information of the candidate frame by using a classifier, and outputting a classification result; the method comprises the following steps:
s203a, acquiring the feature information of the candidate frame, and dividing the feature information of the candidate frame into first feature information and second feature information;
s203b, training the first characteristic information through a classification algorithm to generate a classification model;
and S203c, testing the second sample by using the obtained classification model, and outputting a classification result.
The classifier judges the feature information of the candidate frame, and selects and classifies the picture with the rectangular frame, wherein the feature information of the candidate frame is divided into first feature information and second feature information for training and testing so as to ensure the data accuracy of the classified ship type.
Optionally, the ships can be classified according to the size, color and category of the ship, and the output result is that ships with different sizes, colors and categories are marked by frame selection.
Optionally, the classification result output by the training model includes preliminarily detected ship type data and ship position number
Optionally, the ship data set includes a picture set which collects monitoring video data frames of the coastal area and stores the monitoring video data frames in a picture format, wherein the picture set includes ships with different sizes and shapes.
Optionally, the preprocessing the ship data set includes: and carrying out image graying, image noise reduction and image transformation on the ship data set.
An embodiment of the present invention provides a ship detection apparatus based on fast RCNN, as shown in fig. 3, including:
the acquisition module 10 is used for acquiring a plurality of ship pictures to form a ship data set;
the preprocessing module 20 is configured to preprocess the ship data set, label the ship data, and output a labeling result;
a training module 30, configured to input the first ship data into a preset training model for training to obtain a detection model;
and the detection output module 40 is used for outputting the ship detection result by inputting the second ship data into the detection model.
The image data is obtained through the obtaining module, the image data is sent to the preprocessing module for preprocessing, the preprocessed data is sent to the training module, the ship detection result is output through the detection output module after being trained to generate the detection model, the characteristics in the image data are strengthened through preprocessing, the image after the data are strengthened is input to the training module, the image characteristic information is extracted from the training module and is identified to the ship, meanwhile, the size type of the ship is classified through the classifier, the training result is finally output, and the training result further comprises the position information of the ship. The preprocessing module is used for training and extracting characteristics for the post-stage picture data as a basis, and the training module is used for intelligently identifying and outputting the ship identification result, so that the ship detection efficiency is improved, and the missing probability is reduced.
The embodiment of the invention provides an optional implementation mode, which comprises the following steps:
the method comprises the following steps: acquiring ship images by using the marine monitoring data video, and forming a ship image data set; the data frame image is generated by decomposing the marine monitoring data video, and the decomposed data frame image is collected to obtain the ship image data set. Thereby ensuring that the trained model is suitable for the actual detection environment.
Step two: preprocessing the formed ship image data set, and dividing the ship image data into training data and testing data by using a picture marking tool; image enhancement by preprocessing can also be used for eliminating interference data, such as: and eliminating seabirds and the like without identifying data so as to improve the ship detection efficiency. Wherein, the picture marking tool can be: LabelImg, yolo _ mark, Vatic, images _ annotation _ program, etc.
Step three: inputting training data into a training model for training to obtain a recognition model; a FasterRCNN frame can be used for training a model, and the iteration times and the learning rate are set so as to ensure that a high-efficiency detection model can be obtained; wherein, include:
firstly, sending a ship image into a CNN network for convolution, and outputting a ship characteristic diagram; sending the ship feature map into an RPN network to obtain feature information of a candidate area; the classifier is used for judging whether homogeneous data exists in the feature information extracted from the candidate area.
Step four: and inputting the test data into the recognition model, and outputting a recognition result and a positioning result of the test image. Wherein the image recognition result is that the recognized ship is confirmed and the coordinates of the ship are displayed.
An embodiment of the present invention further provides an electronic device, as shown in fig. 4, the electronic device may include a processor 401 and a memory 402, where the processor 401 and the memory 402 may be connected by a bus 403 or in another manner, and fig. 4 takes the connection by the bus as an example.
The memory 402, which is a non-transitory computer-readable storage medium, may be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as program instructions/modules (e.g., the acquisition module 10, the preprocessing module 20, the training module 30, and the detection output module 40 shown in fig. 3) corresponding to the key shielding method of the in-vehicle display device in the embodiment of the present invention. The processor 401 executes various functional applications and data processing of the processor by running the non-transitory software programs, instructions and modules stored in the memory 402, namely, implements the fast RCNN-based ship detection method in the above-described method embodiment.
The memory 402 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created by the processor 401, and the like. Further, the memory 402 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, memory 402 may optionally include memory located remotely from processor 401, which may be connected to processor 401 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The one or more modules are stored in the memory 402 and, when executed by the processor 401, perform a fast RCNN-based ship detection method as in the embodiment of fig. 1-2.
The specific details of the vehicle terminal may be understood by referring to the corresponding related descriptions and effects in the embodiments shown in fig. 1 to fig. 2, and are not described herein again.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a Flash Memory (Flash Memory), a Hard Disk (Hard Disk Drive, abbreviated as HDD) or a Solid State Drive (SSD), etc.; the storage medium may also comprise a combination of memories of the kind described above.
Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations fall within the scope defined by the appended claims.
Claims (9)
1. A ship detection method based on fast RCNN is characterized by comprising the following steps:
acquiring a plurality of ship pictures to form a ship data set;
preprocessing the ship data set, labeling the ship data, and outputting a labeling result; wherein, the labeling result comprises: first vessel data and second vessel data;
inputting the first ship data into a preset training model for training to obtain a detection model;
outputting a ship detection result by inputting the second ship data into the detection model; wherein the ship detection result comprises: detected vessel type data and vessel position data.
2. The method of claim 1, wherein the vessel data set comprises a set of pictures that save the acquired coastal region surveillance video data frames in a picture format, wherein the set of pictures comprises vessel images of different sizes and shapes.
3. The method of claim 1, wherein the pre-processing the ship data set comprises: and carrying out image graying, image noise reduction and image transformation on the ship data set.
4. The method of claim 1, wherein said inputting said first vessel data into a predetermined training model for training to obtain a test model comprises:
and setting the learning rate and the maximum iteration number in the training process by adopting a fast RCNN model.
5. The method according to claim 4, wherein the Faster RCNN network model comprises:
inputting the first ship data into a CNN network to obtain ship characteristic information;
inputting the ship characteristic information into an RPN network to obtain the characteristic information of the candidate frame;
and judging and classifying the characteristic information of the candidate frame by using a classifier, and outputting a classification result.
6. The method of claim 5, wherein the performing the decision classification on the feature information of the candidate box by using the classifier comprises:
acquiring feature information of the candidate frame, and dividing the feature information of the candidate frame into first feature information and second feature information;
training the first characteristic information through a classification algorithm to generate a classification model;
and testing the second sample by using the obtained classification model, and outputting a classification result.
7. A ship detection device based on fast RCNN, comprising:
the acquisition module is used for acquiring a plurality of ship pictures to form a ship data set;
the preprocessing module is used for preprocessing the ship data set, marking the ship data and outputting a marking result;
the training module is used for inputting the first ship data into a preset training model for training so as to obtain a detection model;
and the detection output module is used for outputting the ship detection result by inputting the second ship data into the detection model.
8. An electronic device, comprising:
a memory and a processor, the memory and the processor being communicatively connected to each other, the memory having stored therein computer instructions, the processor executing the computer instructions to perform the fast RCNN-based ship detection method according to any one of claims 1 to 6.
9. A computer-readable storage medium storing computer instructions for causing a computer to perform the fast RCNN-based ship detection method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911258328.2A CN110969213A (en) | 2019-12-10 | 2019-12-10 | Ship detection method and device based on fast RCNN and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911258328.2A CN110969213A (en) | 2019-12-10 | 2019-12-10 | Ship detection method and device based on fast RCNN and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110969213A true CN110969213A (en) | 2020-04-07 |
Family
ID=70033498
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911258328.2A Pending CN110969213A (en) | 2019-12-10 | 2019-12-10 | Ship detection method and device based on fast RCNN and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110969213A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111666938A (en) * | 2020-05-21 | 2020-09-15 | 珠海大横琴科技发展有限公司 | Two-place double-license-plate detection and identification method and system based on deep learning |
| CN112270326A (en) * | 2020-11-18 | 2021-01-26 | 珠海大横琴科技发展有限公司 | Detection optimization method and device for ship sheltering and electronic equipment |
| CN112329707A (en) * | 2020-11-23 | 2021-02-05 | 珠海大横琴科技发展有限公司 | Unmanned aerial vehicle image ship tracking algorithm and device based on KCF filtering |
| CN112416968A (en) * | 2020-12-09 | 2021-02-26 | 中国船舶工业系统工程研究院 | Unmanned ship data management system supporting data set generation |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107818326A (en) * | 2017-12-11 | 2018-03-20 | 珠海大横琴科技发展有限公司 | A kind of ship detection method and system based on scene multidimensional characteristic |
| CN108052940A (en) * | 2017-12-17 | 2018-05-18 | 南京理工大学 | SAR remote sensing images waterborne target detection methods based on deep learning |
| CN108921099A (en) * | 2018-07-03 | 2018-11-30 | 常州大学 | Moving ship object detection method in a kind of navigation channel based on deep learning |
| CN109145872A (en) * | 2018-09-20 | 2019-01-04 | 北京遥感设备研究所 | A kind of SAR image Ship Target Detection method merged based on CFAR with Fast-RCNN |
| CN109299688A (en) * | 2018-09-19 | 2019-02-01 | 厦门大学 | Ship Detection based on deformable fast convolution neural network |
| CN109409286A (en) * | 2018-10-25 | 2019-03-01 | 哈尔滨工程大学 | Ship target detection method based on the enhancing training of pseudo- sample |
| CN109598241A (en) * | 2018-12-05 | 2019-04-09 | 武汉大学 | Satellite image marine vessel recognition methods based on Faster R-CNN |
| CN109711295A (en) * | 2018-12-14 | 2019-05-03 | 北京航空航天大学 | A kind of remote sensing image offshore Ship Detection |
| CN109919113A (en) * | 2019-03-12 | 2019-06-21 | 北京天合睿创科技有限公司 | Ship monitoring method and system and harbour operation prediction technique and system |
| CN109934088A (en) * | 2019-01-10 | 2019-06-25 | 海南大学 | Sea ship discrimination method based on deep learning |
| CN110378308A (en) * | 2019-07-25 | 2019-10-25 | 电子科技大学 | The improved harbour SAR image offshore Ship Detection based on Faster R-CNN |
-
2019
- 2019-12-10 CN CN201911258328.2A patent/CN110969213A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107818326A (en) * | 2017-12-11 | 2018-03-20 | 珠海大横琴科技发展有限公司 | A kind of ship detection method and system based on scene multidimensional characteristic |
| CN108052940A (en) * | 2017-12-17 | 2018-05-18 | 南京理工大学 | SAR remote sensing images waterborne target detection methods based on deep learning |
| CN108921099A (en) * | 2018-07-03 | 2018-11-30 | 常州大学 | Moving ship object detection method in a kind of navigation channel based on deep learning |
| CN109299688A (en) * | 2018-09-19 | 2019-02-01 | 厦门大学 | Ship Detection based on deformable fast convolution neural network |
| CN109145872A (en) * | 2018-09-20 | 2019-01-04 | 北京遥感设备研究所 | A kind of SAR image Ship Target Detection method merged based on CFAR with Fast-RCNN |
| CN109409286A (en) * | 2018-10-25 | 2019-03-01 | 哈尔滨工程大学 | Ship target detection method based on the enhancing training of pseudo- sample |
| CN109598241A (en) * | 2018-12-05 | 2019-04-09 | 武汉大学 | Satellite image marine vessel recognition methods based on Faster R-CNN |
| CN109711295A (en) * | 2018-12-14 | 2019-05-03 | 北京航空航天大学 | A kind of remote sensing image offshore Ship Detection |
| CN109934088A (en) * | 2019-01-10 | 2019-06-25 | 海南大学 | Sea ship discrimination method based on deep learning |
| CN109919113A (en) * | 2019-03-12 | 2019-06-21 | 北京天合睿创科技有限公司 | Ship monitoring method and system and harbour operation prediction technique and system |
| CN110378308A (en) * | 2019-07-25 | 2019-10-25 | 电子科技大学 | The improved harbour SAR image offshore Ship Detection based on Faster R-CNN |
Non-Patent Citations (1)
| Title |
|---|
| 王冰: "基于深度学习的舰船目标检测研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111666938A (en) * | 2020-05-21 | 2020-09-15 | 珠海大横琴科技发展有限公司 | Two-place double-license-plate detection and identification method and system based on deep learning |
| CN112270326A (en) * | 2020-11-18 | 2021-01-26 | 珠海大横琴科技发展有限公司 | Detection optimization method and device for ship sheltering and electronic equipment |
| CN112270326B (en) * | 2020-11-18 | 2022-03-22 | 珠海大横琴科技发展有限公司 | Detection optimization method and device for ship sheltering and electronic equipment |
| CN112329707A (en) * | 2020-11-23 | 2021-02-05 | 珠海大横琴科技发展有限公司 | Unmanned aerial vehicle image ship tracking algorithm and device based on KCF filtering |
| CN112416968A (en) * | 2020-12-09 | 2021-02-26 | 中国船舶工业系统工程研究院 | Unmanned ship data management system supporting data set generation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110969213A (en) | Ship detection method and device based on fast RCNN and electronic equipment | |
| CN108389197B (en) | Power transmission line defect detection method based on deep learning | |
| US11455805B2 (en) | Method and apparatus for detecting parking space usage condition, electronic device, and storage medium | |
| CN108806334A (en) | A kind of intelligent ship personal identification method based on image | |
| CN109993138A (en) | A kind of car plate detection and recognition methods and device | |
| CN109376580B (en) | Electric power tower component identification method based on deep learning | |
| CN108318773B (en) | Transmission conductor strand breakage detection method and system | |
| CN111523362A (en) | Data analysis method and device based on electronic purse net and electronic equipment | |
| CN112541372B (en) | Difficult sample screening method and device | |
| CN111435446A (en) | License plate identification method and device based on L eNet | |
| CN113420673A (en) | Garbage classification method, device, equipment and storage medium | |
| CN111832556A (en) | Ship board character accurate detection method based on deep learning | |
| CN111523558A (en) | Ship shielding detection method and device based on electronic purse net and electronic equipment | |
| CN112163544A (en) | Method and system for judging random placement of non-motor vehicles | |
| CN111553183A (en) | Ship detection model training method, ship detection method and ship detection device | |
| CN115082813A (en) | Detection method, unmanned aerial vehicle, detection system and medium | |
| CN111931721B (en) | Method and device for detecting color and number of annual inspection label and electronic equipment | |
| CN113536847A (en) | Industrial scene video analysis system and method based on deep learning | |
| CN110634120B (en) | Vehicle damage judgment method and device | |
| CN115063739B (en) | Abnormal behavior detection method, device, equipment and computer storage medium | |
| CN112308061B (en) | License plate character recognition method and device | |
| CN112232295B (en) | Method and device for confirming newly-added target ship and electronic equipment | |
| CN114724091A (en) | Method and device for identifying foreign matters on transmission line wire | |
| Mutholib et al. | Optimization of ANPR algorithm on Android mobile phone | |
| CN113723258A (en) | Dangerous goods vehicle image identification method and related equipment thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200407 |