CN117914953A - Ship data processing method, device and equipment - Google Patents
Ship data processing method, device and equipment Download PDFInfo
- Publication number
- CN117914953A CN117914953A CN202410316564.XA CN202410316564A CN117914953A CN 117914953 A CN117914953 A CN 117914953A CN 202410316564 A CN202410316564 A CN 202410316564A CN 117914953 A CN117914953 A CN 117914953A
- Authority
- CN
- China
- Prior art keywords
- data
- ship
- processing
- target
- compression processing
- 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
- 238000003672 processing method Methods 0.000 title abstract description 6
- 238000012545 processing Methods 0.000 claims abstract description 177
- 238000007499 fusion processing Methods 0.000 claims abstract description 55
- 238000000034 method Methods 0.000 claims abstract description 42
- 238000007906 compression Methods 0.000 claims description 109
- 230000006835 compression Effects 0.000 claims description 109
- 238000005070 sampling Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 abstract description 16
- 230000008569 process Effects 0.000 abstract description 11
- 230000004927 fusion Effects 0.000 abstract description 7
- 238000001514 detection method Methods 0.000 description 16
- 238000011176 pooling Methods 0.000 description 11
- 238000010606 normalization Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 238000001914 filtration Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000000354 decomposition reaction Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005215 recombination Methods 0.000 description 2
- 230000006798 recombination Effects 0.000 description 2
- 230000001629 suppression Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Landscapes
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention provides a processing method, a device and equipment of ship data, wherein the method comprises the following steps: acquiring a ship data set of a ship in a preset driving period; the ship data set comprises a plurality of different types of data acquired by different acquisition devices; performing light weight processing on various different types of data in the ship data set to obtain ship data after the light weight processing; carrying out fusion processing on the ship data after the light weight processing to obtain target ship data after the fusion processing; and sending the target ship data after the fusion processing to an operation control system of the target ship to control the operation state of the target ship. The scheme provided by the invention can realize unified analysis and fusion of multidimensional data of the intelligent ship in the navigation operation process, and improve the safety of navigation operation of the intelligent ship.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a method, an apparatus, and a device for processing ship data.
Background
Currently, the technical functions of operation data acquisition and analysis for technical attack and achievement transformation such as intelligent navigation design selection, technical research and development, standard formulation and the like of ships are to be solved. The requirements of the autonomous development, advanced and sophisticated and standard collaborative ship intelligent navigation system are quickened, the key technology of intelligent navigation data acquisition and analysis of the ship is broken through, and comprehensive technical support is provided for intelligent ship industry innovation. The existing intelligent navigation data acquisition and analysis of the ship mainly has the following problems:
1) The existing ship navigation operation data acquisition and analysis mainly adopts a ship end data remote transmission mode, and the data acquisition dimension is single, and the data cannot be fused and compared for analysis.
2) The architecture of the existing ship navigation operation data acquisition and analysis system is mainly deployed locally, and cannot realize data acquisition and analysis in a multi-place cooperation mode.
Disclosure of Invention
The invention aims to solve the technical problem of providing a ship data processing method, device and equipment so as to realize unified analysis and fusion of multidimensional data of an intelligent ship in the navigation operation process and improve the safety of navigation operation of the intelligent ship.
In order to solve the above technical problems, the implementation of the present invention provides a method for processing ship data, including:
A method of processing ship data, comprising:
Acquiring a ship data set of a ship in a preset driving period; the ship data set comprises a plurality of different types of data acquired by different acquisition devices;
performing light weight processing on various different types of data in the ship data set to obtain ship data after the light weight processing;
carrying out fusion processing on the ship data after the light weight processing to obtain target ship data after the fusion processing;
and sending the target ship data after the fusion processing to an operation control system of the target ship to control the operation state of the target ship.
Optionally, the plurality of different types of data includes: radar data, vessel dynamic data, video data, and sea chart data of the vessel;
Performing light weight processing on a plurality of different types of data in the ship data set to obtain light weight processed ship data, wherein the light weight processing comprises the following steps:
And respectively compressing the radar data, the ship dynamics, the video data and the sea chart data to obtain compressed radar data, compressed ship dynamics data, compressed video data and compressed sea chart data.
Optionally, compressing the radar data and the ship dynamic data respectively to obtain compressed radar data and compressed ship dynamic data, which includes: grouping the radar data according to a first preset time interval to obtain a plurality of first data sets of the radar data;
Grouping the ship dynamic data according to a second preset time interval to obtain a plurality of second data sets of the ship dynamic data;
according to the first linear degree of the radar data in the first data sets, compressing the radar data in the first data sets to obtain compressed radar data;
And according to the second linearity of the ship dynamic data in the plurality of second data sets, performing compression processing on the ship dynamic data in the plurality of second data sets, and obtaining the ship dynamic data after the compression processing.
Optionally, compressing the video data and the chart data respectively to obtain compressed video data and compressed chart data, which includes:
Sampling the video data according to a preset frequency to obtain a plurality of sample image frames corresponding to the video data;
Determining a target image frame in a plurality of sample image frames according to first pixel information of a target ship in each sample image frame in the plurality of sample image frames, and determining the target image frame as an image frame of the compressed video data;
And determining target sea chart data in the sea chart data according to second pixel information of the target ship in the sea chart data, and determining the target sea chart data as the sea chart data after compression processing.
Optionally, the fusing processing is performed on the plurality of types of ship data after the light weight processing to obtain target ship data after the fusing processing, including:
acquiring index data of at least two types of data among the radar data after compression processing, the ship dynamic data after compression processing, the video data after compression processing and the chart data after compression processing;
and according to the index data and a preset index threshold, carrying out fusion processing on the radar data after compression processing, the ship dynamic data after compression processing, the video data after compression processing and the chart data after compression processing to obtain the target ship data after fusion processing.
Optionally, obtaining index data of at least two types of data among the radar data after compression processing, the ship dynamic data after compression processing, the video data after compression processing, and the chart data after compression processing includes:
Acquiring a first association degree of a first navigational speed of a target ship in the compressed radar data and a second navigational speed of the target ship in the compressed ship dynamic data;
Acquiring a second association degree of a first course of a target ship in the compressed radar data and a second course of the target ship in the compressed ship dynamic data;
And acquiring the difference value between any two of the first position information of the target ship in the radar data after the compression processing, the second position information of the target ship in the video data after the compression processing and the third position information of the target ship in the sea chart data after the compression processing.
Optionally, according to the index data and a preset index threshold, performing fusion processing on the radar data after compression processing, the ship dynamic data after compression processing, the video data after compression processing and the chart data after compression processing to obtain target ship data after fusion processing, where the fusion processing includes:
And when the first association degree is larger than a first association degree threshold value, the second association degree is larger than a second association degree threshold value and the difference value is larger than a difference value threshold value, integrating the radar data after compression processing corresponding to the first association degree and the second association degree with the ship dynamic data after compression processing, and the video data after compression processing corresponding to the difference value and the chart data after compression processing, so as to obtain the target ship data after fusion processing.
A processing apparatus for ship data, comprising:
the acquisition module is used for acquiring a ship data set of the ship in a preset running period; the ship data set comprises a plurality of different types of data acquired by different acquisition devices;
The processing module is used for carrying out light weight processing on various different types of data in the ship data set to obtain ship data after the light weight processing; carrying out fusion processing on the ship data after the light weight processing to obtain target ship data after the fusion processing; and sending the target ship data after the fusion processing to an operation control system of the target ship to control the operation state of the target ship.
Embodiments of the present invention also provide a computing device comprising: a processor, a memory storing a computer program which, when executed by the processor, performs a method as claimed in any one of the preceding claims.
Embodiments of the present invention also provide a computer readable storage medium storing instructions that when executed on a computer cause the computer to perform a method as claimed in any one of the preceding claims.
The scheme of the invention at least comprises the following beneficial effects:
According to the scheme, the ship data set of the ship in the preset running period is obtained; the ship data set comprises a plurality of different types of data acquired by different acquisition devices; performing light weight processing on various different types of data in the ship data set to obtain ship data after the light weight processing; carrying out fusion processing on the ship data after the light weight processing to obtain target ship data after the fusion processing; and sending the target ship data after the fusion processing to an operation control system of the target ship to control the operation state of the target ship. The scheme provided by the invention can realize unified analysis and fusion of multidimensional data of the intelligent ship in the navigation operation process, and improve the safety of navigation operation of the intelligent ship.
Drawings
FIG. 1 is a flow chart of a processing method of ship data provided by an embodiment of the invention;
Fig. 2 is a block diagram of a processing device module for ship data according to an alternative embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
As shown in fig. 1, an embodiment of the present invention provides a method for processing ship data, including:
Step 11, acquiring a ship data set of a ship in a preset running period; the ship data set comprises a plurality of different types of data acquired by different acquisition devices;
Step 12, carrying out light weight processing on various different types of data in the ship data set to obtain ship data after the light weight processing;
Step 13, carrying out fusion processing on the ship data after the light weight processing to obtain target ship data after the fusion processing;
And step 14, sending the target ship data after the fusion processing to an operation control system of the target ship to control the operation state of the target ship.
In this embodiment, the data in the ship data set may include: radar data, vessel dynamic data, video data, and sea chart data of the vessel; here, different kinds of ships can be acquired by different control systems or different sensors in the target ship in real time; different kinds of ship data are collected through different sensors so as to provide multidimensional ship data, the accuracy of subsequent ship data fusion analysis is improved, the accuracy of control of the running state of the target ship is further improved, and the safety of navigation operation of the target ship is ensured;
the acquired ship data of various different types are subjected to light weight processing, so that the ship data after the light weight processing is obtained, the data quantity and redundancy are reduced, and the efficiency of subsequent data fusion processing and the data transmission efficiency are improved;
Further, in step 13, fusion processing is performed on the ship data after the light weight processing to obtain fused target ship data, so as to determine the association relationship between different types of ship data, increase the diversity of data required during the navigation operation analysis of the target ship, and further control the operation state of the target ship according to the association relationship between the associated ship data, so as to ensure the safety of navigation operation.
In one example of the present invention, the data in the ship data set is collected by a plurality of different types of sensors or devices, such as: the system comprises radar equipment, camera equipment, navigation recorder, anemograph, weather instrument and the like, wherein after data are acquired, different sensors or equipment can adopt different protocols to encapsulate corresponding ship data, so as to ensure that the analysis and fusion of the ship data can be carried out smoothly, the acquired ship data can be converted into uniform-format ship data according to a preset format, the real-time, efficient and flexible analysis and transmission of the ship data are ensured, and further, the application requirements of various distributed real-time communication are met; here, the preset format may be set according to the need at the time of processing, and is not particularly limited herein;
Further, as the ship data is affected by the collecting frequency and period in the collecting process, certain noise data or error data exist in the collected ship data, such as: noise generated during ship running or measurement errors caused by the accuracy problem of the sensor are used for ensuring the accuracy of subsequent ship data fusion; here, the collected ship data in the unified format can be subjected to filtering processing in a kalman filtering mode, so that the filtered ship data after the filtering processing is obtained, and the influence of related noise and measurement errors is reduced.
In an alternative embodiment of the present invention, the radar data may include: the navigation speed, heading, position and other information of the ship are acquired through the radar; the dynamic ship data may include: the ship automatic identification system is used for acquiring information such as the position, the navigational speed, the rotation angle, the azimuth and the heading of the ship; the video data may include: position information of the ship during sailing and the like acquired by the ship-borne camera equipment; the chart data may include: the ship position information and the like which are acquired by the acoustic wave detector and comprise the target ship; it should be noted that the radar data, the dynamic ship data, the video data, and the sea chart data are all time-stamped time-series data; the navigation speed, the course and the position information in the radar data can be regarded as a data set forming a ship navigation track, and each position information can be regarded as a track point;
The step 12 may include:
step 121, compressing the radar data, the ship dynamics, the video data and the sea chart data respectively to obtain compressed radar data, compressed ship dynamics data, compressed video data and compressed sea chart data;
here, the radar data, the ship dynamics, the video data and the chart data are respectively compressed, and the data obtained after the filtering processing is compressed, so as to reduce the data quantity and redundancy, improve the efficiency of the subsequent data fusion processing and the data transmission efficiency, and further improve the accuracy and efficiency of the subsequent fusion analysis processing.
In an optional embodiment of the present invention, in step 121, compressing the radar data and the ship dynamic data to obtain compressed radar data and compressed ship dynamic data may include:
Step 121a-1, grouping the radar data according to a first preset time interval to obtain a plurality of first data sets of the radar data;
Step 121a-2, grouping the ship dynamic data according to a second preset time interval to obtain a plurality of second data sets of the ship dynamic data;
step 121a-3, performing compression processing on the radar data in the plurality of first data sets according to the first linear degree of the radar data in the plurality of first data sets, so as to obtain the radar data after the compression processing;
And step 121a-4, performing compression processing on the ship dynamic data in the second data sets according to the second linearity of the ship dynamic data in the second data sets, and obtaining the ship dynamic data after compression processing.
In this embodiment, the first preset time interval and the second preset time interval may be set according to a requirement of a compression rate in actual processing, and the higher the compression rate is, the larger the first preset time interval and the second preset time interval are; the first data set and the second data set each represent a sailing track segment of a ship;
Further, when the first linearity of the position information of the plurality of radar data in any one first data set is smaller than a first preset linearity threshold value, determining that the track points in the current first data set meet the linear relation, and taking the average value of the navigational speeds and the navigational directions of all the track points in the current first data set as the navigational speeds and the navigational directions of the navigational track sections corresponding to the current first data set; when the first linearity is greater than or equal to a first preset linearity threshold value, determining that track points in the current first data set do not meet the linearity relation, removing track points deviating from a navigation track section to the maximum in the current first data set, taking average values of the speed and the heading of all the rest track points as the speed and the heading of the navigation track section corresponding to the current first data set, and compressing the speed and the heading in each first data set corresponding to each time period;
when the second linearity of the position information of the plurality of ship dynamic data in any one second data set is smaller than a second preset linearity threshold value, determining that the track points in the current second data set meet the linear relation, and taking the average value of the speeds and the headings of all the track points in the current second data set as the speeds and the headings of the navigation track segments corresponding to the current second data set; when the second linearity is greater than or equal to a second preset linearity threshold value, determining that the track points in the current second data set do not meet the linearity relation, removing the track point deviating from the maximum navigation track section in the current second data set, taking the average value of the speed and the heading of all the rest track points as the speed and the heading of the navigation track section corresponding to the current second data set, and compressing the speed and the heading in each second data set corresponding to each time period;
In an alternative embodiment of the present invention, the first linearity of the first data set may be calculated by the following formula:
；
Wherein d 1 is a first linear degree, x 1、y1 is longitude and latitude of a track point in the first data set, and a 1、b1、c1 is a set first conversion parameter;
the second linearity of the second data set may be calculated by the following formula:
；
Where d 2 is the first linear degree, x 2、y2 is the longitude and latitude of the track point in the second data set, and a 2、b2、c2 is the set second conversion parameter.
In an optional embodiment of the present invention, in step 121, compressing the video data and the chart data to obtain compressed video data and compressed chart data may include:
step 121b-1, sampling the video data according to a preset frequency to obtain a plurality of sample image frames corresponding to the video data;
step 121b-2 of determining a target image frame of the plurality of sample image frames according to the first pixel information of the target ship in each of the plurality of sample image frames, and determining the target image frame as an image frame of the compressed video data;
And step 121b-3, determining target chart data in the chart data according to second pixel information of the target ship in the chart data, and determining the target chart data as the compressed chart data.
In this embodiment, the video data is sampled according to the preset frequency, so as to reduce the calculated amount and improve the processing efficiency; here, the preset frequency can be set according to the operation period of the ship control system, so that the sampling frequency is consistent with the operation period of the ship control system, a plurality of more accurate and smooth sample image frames are ensured to be obtained, and the precision and the accuracy of subsequent processing are ensured;
the first pixel information represents pixel offset of the ship in the current image frame, which is acquired by the ship-borne camera equipment; the second pixel information represents the pixel offset of the ship in the current sea chart, which is acquired by the acoustic wave detector;
Here, the ship appearing in each image can be detected in real time by a preset algorithm, and the left vertex of each image is used as a reference point, and the target ship is detected by respectively analyzing the image frame and the chart; further, for detecting the image frame and the sea chart of the target ship, first pixel information of the ship in the current image frame and second pixel information of the ship in the sea chart can be calculated respectively, wherein the first pixel information can be represented as ('X 3s,∆Y3s'), wherein, X 3s represents that the ship in the current image frame is offset by X 3 pixels in the horizontal direction compared with the reference point, and Y 3s represents that the ship in the current image frame is offset by Y 3 pixels in the vertical direction compared with the reference point; the second pixel information may be represented as (+X 4t,∆Y4t) where father X 4t represents that the vessel in the current sea chart is offset by X 4 pixels in the horizontal direction from the reference point and Y 4t represents that the vessel in the current sea chart is offset by Y 4 pixels in the vertical direction from the reference point; s and t are positive integers, s represents the s-th image frame, and t represents the t-th chart;
Further, a first difference value of first pixel information between two adjacent image frames is sequentially obtained, if the first difference value is smaller than or equal to first preset pixel information, it is indicated that the ship position in the current two adjacent image frames is unchanged, any one of the current two adjacent image frames can be removed, and one image frame is reserved, so that compression of the image frames is achieved; if the first difference value is larger than the first preset pixel information, eliminating is not needed;
Sequentially acquiring a second difference value of second pixel information between two adjacent sea charts, and when the second difference value is smaller than or equal to second preset pixel information, indicating that the ship position in the current two adjacent sea charts is unchanged, removing any sea chart in the current two adjacent sea charts, and reserving one sea chart to compress the sea charts; if the second difference value is larger than the second preset pixel information, eliminating is not needed;
In an implementation example of the present invention, the specific flow steps of detecting, in real time, the ship appearing in each image frame and each chart by the preset algorithm are as follows:
Step 21, area suggestion:
The image frames or sea charts may be processed by a depth-full convolution algorithm and a region suggestion generated, for each anchor point in the target vessel region (where anchor points are rectangular frames of the vessel generated at fixed locations in each image frame, each sea chart, the rectangular frames having different dimensions and aspect ratios), a bounding box regression is predicted to correct the location and dimensions of the anchor point, as follows:
；
；
；
；
Wherein Deltax, deltay, deltaw and Deltah respectively represent the adjustment values of the abscissa, the ordinate, the width and the height of the anchor point; x a、ya、wa、ha represents the abscissa, ordinate, width and height of the anchor point, respectively; x, y, w, h represent the abscissa, ordinate, width and height of the anchor-predicted bounding box, respectively;
Step 22, pooling:
Step 221, defining an input area: on each sea chart input into each image frame, determining candidate regions according to the region suggestions in the step 21;
Step 222, fixed size output: each image frame and each sea chart are respectively divided into grids with the size of preset height multiplied by preset width; here, the number of divided meshes, for example, a height 112×width 92, which is divided into meshes of a preset height 56×preset width 46, may be determined according to the size of each image frame, each sea chart, and then there are 2×2=4 meshes in total;
Step 223, pooling operation: in each grid cell, performing a max pooling operation to extract the most important features;
for each grid cell corresponding rectangular region [ r x,ry,rw,rh ] (where r x,ry is the coordinates of the top left corner of the rectangle, r w,rh is the width and height) and H W's pooling layer, the process of pooling operation can be expressed as: the output of each pooling unit (i, j) is composed of the corresponding sub-region of the original rectangular region The features in the grid cells are obtained through maximum pooling, so that only the maximum feature value is reserved in all the features in each grid cell; where (i, j) denotes an index of one element in the output of the pooling layer, where i denotes an index (number of rows) in the vertical direction and j denotes an index (number of columns) in the horizontal direction;
Step 224, outputting a feature map: by the pooling operation described above, each pooling layer generates a fixed size (H W) signature, regardless of the pooling layer size and scale;
step 23, classification and bounding box regression:
Step 231, classification: calculating the class probability p l corresponding to the target ship in each feature map by using a softmax function;
；
where k is the total number of categories, Z l represents the initial set score for the first category;
step 232, bounding box regression: for bounding box regression, four predictors (t x,ty,tw,th) represent the offset of the x and y coordinates and the logarithmic scale of width and height of the center of the predicted bounding box, respectively, and the specific conversion formula is as follows:
；
；
；
；
step 24, non-maximum suppression: selecting an optimal one from a plurality of overlapped candidate areas to reduce repeated detection and improve detection accuracy, wherein the method comprises the following specific steps:
step 241, candidate detection: generating a series of candidate detection packages according to the classified image blocks and the image blocks subjected to the bounding box regression, wherein each candidate detection package comprises a predicted bounding box and a confidence coefficient;
Step 242, ordering: sequencing the candidate detection packets from high to low according to the confidence level;
Step 243, selecting and suppressing: selecting a candidate detection packet with highest confidence as a reference, and removing all other candidate detection packets with overlapping degrees (which can be represented by an overlap ratio (IOU)) exceeding a preset threshold value from the candidate detection packet;
Step 244, repeat: repeating the steps 242-243, selecting one candidate detection packet with highest confidence from the rest candidate detection packets each time, and removing other candidate detection packets which are overlapped with the one candidate detection packet with high confidence;
Step 245, final detection: the process of steps 242-244 continues until all candidate detection packets are considered, and the final remaining candidate detection packets are the result of the non-maximum suppression processing, that is, the final remaining prediction bounding box, and the position and class information of the target object corresponding to the currently remaining prediction bounding box are output.
In an optional embodiment of the present invention, the step 13 may include:
Step 131, obtaining index data of at least two types of data among the radar data after compression processing, the ship dynamic data after compression processing, the video data after compression processing and the chart data after compression processing;
Specifically, it may include:
Step 1311, obtaining a first association degree between a first navigational speed of a target ship in the compressed radar data and a second navigational speed of the target ship in the compressed ship dynamic data;
step 1312, obtaining a second association degree between a first heading of the target ship in the compressed radar data and a second heading of the target ship in the compressed ship dynamic data;
Step 1313, obtaining a difference value between any two position information of the target ship in the radar data after the compression processing, the second position information of the target ship in the video data after the compression processing, and the third position information of the target ship in the sea chart data after the compression processing;
in the embodiment, the first association degree of the speed and the second association degree of the course are obtained, and the association degree between the speed and the course obtained through the radar and the speed and the course obtained through the ship automatic identification system can be evaluated;
the value range of the association degree is 0 to 1, and the closer the value is to 1, the higher the association degree is, and the closer the value is to 0, the lower the association degree is.
Here, the first degree of association and the second degree of association may be obtained by a gray scale association algorithm calculation; taking a first association degree of a navigational speed as an example, a specific process for acquiring the first association degree is as follows:
Data normalization: in order to eliminate the influence of dimension, normalizing the navigational speed acquired by the radar and the navigational speed acquired by the automatic ship identification system; the normalization process here may include: linear normalization, mean normalization, etc., without limitation in particular; the speed of the radar acquisition after normalization processing can be expressed as: a= (a 1,a2,…,am); the navigational speed obtained by the ship automatic identification system after normalization processing can be expressed as: b= (B 1,b2,…,bm), wherein m is a positive integer representing the number of samples;
Establishing an association matrix: and respectively constructing an n multiplied by n two-dimensional correlation matrix according to the normalized navigational speeds of two groups of different sources, wherein each element represents the degree of correlation between navigational speeds of two groups of different sources. For the elements in the ith row and the jth column in the incidence matrix, representing the incidence between the navigational speed acquired by the radar of the ith sample point and the navigational speed acquired by the ship automatic identification system of the jth sample point;
Calculating the association degree: calculating an absolute difference value between the navigational speed acquired by the radar and the navigational speed acquired by the ship automatic identification system, normalizing the absolute difference value to the range of [0,1], and specifically calculating the following formula:
；
Wherein P kg represents a first degree of association, k, g=1, 2, …, m; the value range of the first association degree is 0 to 1, the closer the value is to 1, the higher the association degree is, and the closer the value is to 0, the lower the association degree is;
through the steps, the correlation degree between the calculated radar speed and the speed of the ship automatic identification system can be used, and the correlation between the calculated radar speed and the speed of the ship automatic identification system can be evaluated; the second association degree of the heading may also be obtained through the above steps, which is not described herein.
In the above embodiment of the present invention, the difference between any two of the first position information of the target ship in the radar data after the compression processing, the second position information of the target ship in the video data after the compression processing, and the third position information of the target ship in the sea chart data after the compression processing may be obtained by direct calculation through the identified third position information of the target ship in the sea chart, the identified second position information of the target ship in the video data image frame, and the first position information of the target ship acquired by the radar, so as to confirm the correlation of three sets of different source data subsequently, and ensure the accuracy of the data fusion processing;
And step 132, performing fusion processing on the radar data after compression processing, the ship dynamic data after compression processing, the video data after compression processing and the chart data after compression processing according to the index data and a preset index threshold value, and obtaining the target ship data after fusion processing.
Specifically, it may include:
Step 1321, when the first association degree is greater than a first association degree threshold, the second association degree is greater than a second association degree threshold, and the difference value is greater than a difference value threshold, integrating the radar data after compression processing corresponding to the first association degree and the second association degree with the ship dynamic data after compression processing, and the video data after compression processing corresponding to the difference value and the sea chart data after compression processing, so as to obtain the target ship data after fusion processing;
Here, the first association degree threshold, the second association degree threshold and the difference value threshold may be set according to the requirement in actual processing, and when the first association degree is greater than the first association degree threshold and the second association degree is greater than the second association degree threshold, and at the same time, the difference value between any two of the first position information of the target ship in the radar data after the compression processing, the second position information of the target ship in the video data after the compression processing and the third position information of the target ship in the sea chart data after the compression processing is greater than the difference value threshold, it is indicated that the ship data currently acquired through the radar, the ship automatic identification system, the on-board camera device, the acoustic wave detector and other devices belong to the same target ship; further, the radar data, the ship dynamic data, the video data and the sea chart data after the compression processing can be integrated and fused to obtain a fused set containing target ship data with various different sources; meanwhile, the collection of the target ship data is stored, so that the later-stage rapid extraction and check and the analysis and control of the ship operation are facilitated, and the safety of the ship operation is ensured;
According to the embodiment of the invention, the ship data after the light weight processing is obtained by carrying out the light weight processing on various different types of data in the ship data sets with various different sources; further carrying out fusion processing on the ship data after the light weight processing to obtain target ship data after the fusion processing, thereby solving the problem of unsmooth information on water; the target ship data after the fusion processing is sent to an operation control system of the target ship so as to control the operation state of the target ship; meanwhile, the system can also be used for tracking and consulting in the running process of the ship, can provide support on data for disputes on water for checking, analyzing and judging, solves the problems of case backlog, incapability of giving reasonable judgment and the like caused by incomplete data, incapability of tracing past records and other data reasons, and further can ensure the running safety of the ship.
As shown in fig. 2, an embodiment of the present invention further provides a processing apparatus 20 for ship data, including:
An acquisition module 21 for acquiring a ship data set of the ship in a preset traveling period; the ship data set comprises a plurality of different types of data acquired by different acquisition devices;
The processing module 22 is configured to perform light weight processing on a plurality of different types of data in the ship data set, so as to obtain light weight processed ship data; carrying out fusion processing on the ship data after the light weight processing to obtain target ship data after the fusion processing; and sending the target ship data after the fusion processing to an operation control system of the target ship to control the operation state of the target ship.
Optionally, the plurality of different types of data includes: radar data, vessel dynamic data, video data, and sea chart data of the vessel;
The processing module 22 performs light weight processing on a plurality of different types of data in the ship data set to obtain light weight processed ship data, including:
And respectively compressing the radar data, the ship dynamics, the video data and the sea chart data to obtain compressed radar data, compressed ship dynamics data, compressed video data and compressed sea chart data.
Optionally, the processing module 22 performs compression processing on the radar data and the ship dynamic data, to obtain compressed radar data and compressed ship dynamic data, which includes: grouping the radar data according to a first preset time interval to obtain a plurality of first data sets of the radar data;
Grouping the ship dynamic data according to a second preset time interval to obtain a plurality of second data sets of the ship dynamic data;
according to the first linear degree of the radar data in the first data sets, compressing the radar data in the first data sets to obtain compressed radar data;
And according to the second linearity of the ship dynamic data in the plurality of second data sets, performing compression processing on the ship dynamic data in the plurality of second data sets, and obtaining the ship dynamic data after the compression processing.
Optionally, the processing module 22 performs compression processing on the video data and the chart data to obtain compressed video data and compressed chart data, which includes:
Sampling the video data according to a preset frequency to obtain a plurality of sample image frames corresponding to the video data;
Determining a target image frame in a plurality of sample image frames according to first pixel information of a target ship in each sample image frame in the plurality of sample image frames, and determining the target image frame as an image frame of the compressed video data;
And determining target sea chart data in the sea chart data according to second pixel information of the target ship in the sea chart data, and determining the target sea chart data as the sea chart data after compression processing.
Optionally, the processing module 22 performs fusion processing on the plurality of different types of ship data after the light weight processing to obtain target ship data after the fusion processing, including:
acquiring index data of at least two types of data among the radar data after compression processing, the ship dynamic data after compression processing, the video data after compression processing and the chart data after compression processing;
and according to the index data and a preset index threshold, carrying out fusion processing on the radar data after compression processing, the ship dynamic data after compression processing, the video data after compression processing and the chart data after compression processing to obtain the target ship data after fusion processing.
Optionally, obtaining index data of at least two types of data among the radar data after compression processing, the ship dynamic data after compression processing, the video data after compression processing, and the chart data after compression processing includes:
Acquiring a first association degree of a first navigational speed of a target ship in the compressed radar data and a second navigational speed of the target ship in the compressed ship dynamic data;
Acquiring a second association degree of a first course of a target ship in the compressed radar data and a second course of the target ship in the compressed ship dynamic data;
And acquiring the difference value between any two of the first position information of the target ship in the radar data after the compression processing, the second position information of the target ship in the video data after the compression processing and the third position information of the target ship in the sea chart data after the compression processing.
Optionally, the processing module 22 performs fusion processing on the radar data after compression processing, the ship dynamic data after compression processing, the video data after compression processing, and the chart data after compression processing according to the index data and a preset index threshold, to obtain the target ship data after fusion processing, where the fusion processing includes:
And when the first association degree is larger than a first association degree threshold value, the second association degree is larger than a second association degree threshold value and the difference value is larger than a difference value threshold value, integrating the radar data after compression processing corresponding to the first association degree and the second association degree with the ship dynamic data after compression processing, and the video data after compression processing corresponding to the difference value and the chart data after compression processing, so as to obtain the target ship data after fusion processing.
It should be noted that, the device is a device corresponding to the above-mentioned processing method of ship data, and all implementation manners in the above-mentioned method embodiments are applicable to the embodiment of the device, so that the same technical effects can be achieved.
Embodiments of the present invention also provide a computing device comprising: a processor, a memory storing a computer program which, when executed by the processor, performs the method as described above. All the implementation manners in the method embodiment are applicable to the embodiment, and the same technical effect can be achieved.
Embodiments of the present invention also provide a computer-readable storage medium comprising instructions which, when run on a computer, cause the computer to perform a method as described above. All the implementation manners in the method embodiment are applicable to the embodiment, and the same technical effect can be achieved.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk, etc.
Furthermore, it should be noted that in the apparatus and method of the present invention, it is apparent that the components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered as equivalent aspects of the present invention. Also, the steps of performing the series of processes described above may naturally be performed in chronological order in the order of description, but are not necessarily performed in chronological order, and some steps may be performed in parallel or independently of each other. It will be appreciated by those of ordinary skill in the art that all or any of the steps or components of the methods and apparatus of the present invention may be implemented in hardware, firmware, software, or a combination thereof in any computing device (including processors, storage media, etc.) or network of computing devices, as would be apparent to one of ordinary skill in the art after reading this description of the invention.
The object of the invention can thus also be achieved by running a program or a set of programs on any computing device. The computing device may be a well-known general purpose device. The object of the invention can thus also be achieved by merely providing a program product containing program code for implementing said method or apparatus. That is, such a program product also constitutes the present invention, and a storage medium storing such a program product also constitutes the present invention. It is apparent that the storage medium may be any known storage medium or any storage medium developed in the future. It should also be noted that in the apparatus and method of the present invention, it is apparent that the components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered as equivalent aspects of the present invention. The steps of executing the series of processes may naturally be executed in chronological order in the order described, but are not necessarily executed in chronological order. Some steps may be performed in parallel or independently of each other.
While the foregoing is directed to the preferred embodiments of the present invention, it will be appreciated by those skilled in the art that various modifications and adaptations can be made without departing from the principles of the present invention, and such modifications and adaptations are intended to be comprehended within the scope of the present invention.
Claims (10)
1. A method of processing ship data, comprising:
Acquiring a ship data set of a ship in a preset driving period; the ship data set comprises a plurality of different types of data acquired by different acquisition devices;
performing light weight processing on various different types of data in the ship data set to obtain ship data after the light weight processing;
carrying out fusion processing on the ship data after the light weight processing to obtain target ship data after the fusion processing;
and sending the target ship data after the fusion processing to an operation control system of the target ship to control the operation state of the target ship.
2. The method of processing ship data according to claim 1, wherein the plurality of different types of data includes: radar data, vessel dynamic data, video data, and sea chart data of the vessel;
Performing light weight processing on a plurality of different types of data in the ship data set to obtain light weight processed ship data, wherein the light weight processing comprises the following steps:
And respectively compressing the radar data, the ship dynamics, the video data and the sea chart data to obtain compressed radar data, compressed ship dynamics data, compressed video data and compressed sea chart data.
3. The method according to claim 2, wherein the compressing the radar data and the ship dynamic data to obtain the compressed radar data and the compressed ship dynamic data, respectively, comprises:
Grouping the radar data according to a first preset time interval to obtain a plurality of first data sets of the radar data;
Grouping the ship dynamic data according to a second preset time interval to obtain a plurality of second data sets of the ship dynamic data;
according to the first linear degree of the radar data in the first data sets, compressing the radar data in the first data sets to obtain compressed radar data;
And according to the second linearity of the ship dynamic data in the plurality of second data sets, performing compression processing on the ship dynamic data in the plurality of second data sets, and obtaining the ship dynamic data after the compression processing.
4. The method according to claim 2, wherein compressing the video data and the sea chart data to obtain compressed video data and compressed sea chart data, respectively, comprises:
Sampling the video data according to a preset frequency to obtain a plurality of sample image frames corresponding to the video data;
Determining a target image frame in a plurality of sample image frames according to first pixel information of a target ship in each sample image frame in the plurality of sample image frames, and determining the target image frame as an image frame of the compressed video data;
And determining target sea chart data in the sea chart data according to second pixel information of the target ship in the sea chart data, and determining the target sea chart data as the sea chart data after compression processing.
5. The method according to claim 2, wherein the fusion processing is performed on the plurality of different types of ship data after the light weight processing to obtain the target ship data after the fusion processing, comprising:
acquiring index data of at least two types of data among the radar data after compression processing, the ship dynamic data after compression processing, the video data after compression processing and the chart data after compression processing;
and according to the index data and a preset index threshold, carrying out fusion processing on the radar data after compression processing, the ship dynamic data after compression processing, the video data after compression processing and the chart data after compression processing to obtain the target ship data after fusion processing.
6. The method according to claim 5, wherein acquiring index data of at least two or more types of data among the radar data after compression processing, the ship dynamic data after compression processing, the video data after compression processing, and the sea chart data after compression processing, comprises:
Acquiring a first association degree of a first navigational speed of a target ship in the compressed radar data and a second navigational speed of the target ship in the compressed ship dynamic data;
Acquiring a second association degree of a first course of a target ship in the compressed radar data and a second course of the target ship in the compressed ship dynamic data;
And acquiring the difference value between any two of the first position information of the target ship in the radar data after the compression processing, the second position information of the target ship in the video data after the compression processing and the third position information of the target ship in the sea chart data after the compression processing.
7. The method according to claim 6, wherein performing fusion processing on the radar data after compression processing, the ship dynamic data after compression processing, the video data after compression processing, and the sea chart data after compression processing according to the index data and a preset index threshold value to obtain the target ship data after fusion processing, comprises:
And when the first association degree is larger than a first association degree threshold value, the second association degree is larger than a second association degree threshold value and the difference value is larger than a difference value threshold value, integrating the radar data after compression processing corresponding to the first association degree and the second association degree with the ship dynamic data after compression processing, and the video data after compression processing corresponding to the difference value and the chart data after compression processing, so as to obtain the target ship data after fusion processing.
8. A ship data processing apparatus, comprising:
the acquisition module is used for acquiring a ship data set of the ship in a preset running period; the ship data set comprises a plurality of different types of data acquired by different acquisition devices;
The processing module is used for carrying out light weight processing on various different types of data in the ship data set to obtain ship data after the light weight processing; carrying out fusion processing on the ship data after the light weight processing to obtain target ship data after the fusion processing; and sending the target ship data after the fusion processing to an operation control system of the target ship to control the operation state of the target ship.
9. A computing device, comprising: a processor, a memory storing a computer program which, when executed by the processor, performs the method of any one of claims 1 to 7.
10. A computer readable storage medium storing instructions which, when run on a computer, cause the computer to perform the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410316564.XA CN117914953B (en) | 2024-03-20 | 2024-03-20 | Ship data processing method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410316564.XA CN117914953B (en) | 2024-03-20 | 2024-03-20 | Ship data processing method, device and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117914953A true CN117914953A (en) | 2024-04-19 |
| CN117914953B CN117914953B (en) | 2024-06-07 |
Family
ID=90692647
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410316564.XA Active CN117914953B (en) | 2024-03-20 | 2024-03-20 | Ship data processing method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117914953B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE4423233A1 (en) * | 1994-07-02 | 1996-01-04 | Diethard Kersandt | Identifying, quantifying, monitoring and directing ships for automatic on-board and land assisted steering system |
| CN111025295A (en) * | 2019-11-22 | 2020-04-17 | 青岛海狮网络科技有限公司 | Multi-ship cooperative sensing data fusion system and method based on shore-based radar |
| CN111310646A (en) * | 2020-02-12 | 2020-06-19 | 智慧航海（青岛）科技有限公司 | Method for improving navigation safety based on real-time detection of remote images |
| KR20220045762A (en) * | 2020-10-06 | 2022-04-13 | 주식회사 스카이시스 | System for automatic recognition and monitoring of vessel using artificial intelligence image processing and method for providing the same |
| CN114647184A (en) * | 2022-01-28 | 2022-06-21 | 中电科（宁波）海洋电子研究院有限公司 | Speed regulation method of ship host rotating speed control system based on incremental PID algorithm |
| CN115733940A (en) * | 2022-11-04 | 2023-03-03 | 中国船舶集团有限公司第七〇九研究所 | Multi-source heterogeneous video processing display device and method for ship system |
| CN116110255A (en) * | 2023-01-18 | 2023-05-12 | 武汉理工大学 | Ship berthing collision early warning method, system and storage medium |
-
2024
- 2024-03-20 CN CN202410316564.XA patent/CN117914953B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE4423233A1 (en) * | 1994-07-02 | 1996-01-04 | Diethard Kersandt | Identifying, quantifying, monitoring and directing ships for automatic on-board and land assisted steering system |
| CN111025295A (en) * | 2019-11-22 | 2020-04-17 | 青岛海狮网络科技有限公司 | Multi-ship cooperative sensing data fusion system and method based on shore-based radar |
| CN111310646A (en) * | 2020-02-12 | 2020-06-19 | 智慧航海（青岛）科技有限公司 | Method for improving navigation safety based on real-time detection of remote images |
| KR20220045762A (en) * | 2020-10-06 | 2022-04-13 | 주식회사 스카이시스 | System for automatic recognition and monitoring of vessel using artificial intelligence image processing and method for providing the same |
| CN114647184A (en) * | 2022-01-28 | 2022-06-21 | 中电科（宁波）海洋电子研究院有限公司 | Speed regulation method of ship host rotating speed control system based on incremental PID algorithm |
| CN115733940A (en) * | 2022-11-04 | 2023-03-03 | 中国船舶集团有限公司第七〇九研究所 | Multi-source heterogeneous video processing display device and method for ship system |
| CN116110255A (en) * | 2023-01-18 | 2023-05-12 | 武汉理工大学 | Ship berthing collision early warning method, system and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117914953B (en) | 2024-06-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10706285B2 (en) | Automatic ship tracking method and system based on deep learning network and mean shift | |
| CN111369581A (en) | Image processing method, device, equipment and storage medium | |
| CN111428625A (en) | Traffic scene target detection method and system based on deep learning | |
| CN113591968A (en) | Infrared weak and small target detection method based on asymmetric attention feature fusion | |
| CN102975826A (en) | Portable ship water gauge automatic detection and identification method based on machine vision | |
| CN112818969A (en) | Knowledge distillation-based face pose estimation method and system | |
| CN112232371A (en) | American license plate recognition method based on YOLOv3 and text recognition | |
| CN112149620A (en) | Method for constructing natural scene character region detection model based on no anchor point | |
| CN113033315A (en) | Rare earth mining high-resolution image identification and positioning method | |
| CN116310837B (en) | SAR ship target rotation detection method and system | |
| CN111815708A (en) | Service robot grabbing detection method based on dual-channel convolutional neural network | |
| CN109409285B (en) | Remote sensing video target detection method based on overlapped slices | |
| CN117914953B (en) | Ship data processing method, device and equipment | |
| US11468572B2 (en) | Image processing device, image recognition device, image processing program, and image recognition program | |
| CN113095316B (en) | Image rotation target detection method based on multilevel fusion and angular point offset | |
| CN112101168A (en) | Satellite and unmanned aerial vehicle linkage-based commonweal litigation auxiliary evidence obtaining system and method | |
| JPWO2018143277A1 (en) | Image feature output device, image recognition device, image feature output program, and image recognition program | |
| CN115830514B (en) | Whole river reach surface flow velocity calculation method and system suitable for curved river channel | |
| CN116229419B (en) | Pedestrian detection method and device | |
| CN115390047B (en) | Satellite-borne photon counting laser radar data denoising and filtering method and device | |
| CN108182492B (en) | Data assimilation method and device | |
| CN114782500A (en) | Kart race behavior analysis method based on multi-target tracking | |
| CN113449812A (en) | GNSS-R sea ice detection method and device based on local linear embedding algorithm | |
| CN113780462A (en) | Vehicle detection network establishment method based on unmanned aerial vehicle aerial image and application thereof | |
| CN112380986A (en) | Vehicle type detection method and system for resisting complex street background interference and storage medium |
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 |