CN113222040A - Marine fixed target identification method and device, computer equipment and storage medium - Google Patents
Marine fixed target identification method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN113222040A CN113222040A CN202110567107.4A CN202110567107A CN113222040A CN 113222040 A CN113222040 A CN 113222040A CN 202110567107 A CN202110567107 A CN 202110567107A CN 113222040 A CN113222040 A CN 113222040A
- Authority
- CN
- China
- Prior art keywords
- target
- suspected
- fixed
- fixed target
- cluster
- 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
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000003860 storage Methods 0.000 title claims abstract description 16
- 238000012216 screening Methods 0.000 claims abstract description 26
- 230000004931 aggregating effect Effects 0.000 claims abstract description 19
- 238000007621 cluster analysis Methods 0.000 claims abstract description 17
- 230000002776 aggregation Effects 0.000 claims description 38
- 238000004220 aggregation Methods 0.000 claims description 38
- 238000009826 distribution Methods 0.000 claims description 28
- 238000004590 computer program Methods 0.000 claims description 23
- 238000004458 analytical method Methods 0.000 claims description 18
- 238000001514 detection method Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 7
- 230000003287 optical effect Effects 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 3
- 238000012790 confirmation Methods 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004873 anchoring Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006116 polymerization reaction Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
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)
- Radar Systems Or Details Thereof (AREA)
Abstract
The application relates to a method and a device for identifying a marine fixed target, computer equipment and a storage medium. The method comprises the following steps: acquiring historical target data which is output by a radar device and generated within historical preset days; the method comprises the steps of aggregating marine target objects which have the same historical target identification and belong to the same day to a corresponding cluster set and carrying out cluster analysis to obtain cluster results; based on the obtained clustering result, respectively screening out corresponding suspected fixed targets from each clustering set; determining corresponding suspected fixed target areas according to the corresponding position information of the corresponding suspected fixed targets at different time stamps; calculating the total generation times of suspected fixed target areas belonging to the same suspected fixed target, and taking the area with the total generation times larger than a time threshold value as a fixed target area; and when the real-time target data transmitted by the radar equipment is acquired, identifying the marine fixed target based on the fixed target area.
Description
Technical Field
The present application relates to the field of target positioning technologies, and in particular, to a method and an apparatus for identifying a stationary target on the sea, a computer device, and a storage medium.
Background
With the development of radar positioning technology, positioning and tracking of a marine target by utilizing the radar positioning technology appears, and the technology judges whether the identified target is a fixed target by comparing the variation range of target position information with the detection error range of a radar sensor. However, when a radar sensor is used for positioning and tracking a marine target, because the radar sensor cannot identify the identity of the positioning target, similar fixed targets such as the marine buoy, the lighthouse, the sea wave, the reef and the marine garbage can be identified by the radar sensor and serve as identification targets, and the similar identification targets have no great significance for marine vessel situation analysis, and the analysis efficiency is affected. Therefore, the existing radar positioning technology has the problem that the identification of the marine fixed target is inaccurate.
Disclosure of Invention
In view of the above, it is necessary to provide a method, an apparatus, a computer device and a storage medium for identifying a stationary marine target, which can improve the accuracy of identifying the stationary marine target.
A method of offshore fixed target identification, the method comprising:
acquiring historical target data which is output by a radar device and generated within historical preset days, wherein the historical target data comprises historical target identification, time stamp and position information aiming at each identified marine target object;
aggregating a plurality of marine target objects which have the same historical target identification and belong to the same day into corresponding cluster sets, and performing cluster analysis on each cluster set respectively to obtain corresponding cluster results;
based on the obtained multiple clustering results, screening out at least one suspected fixed target from each clustering set respectively;
for each suspected fixed target, determining a suspected fixed target area corresponding to the corresponding suspected fixed target according to the position information of the corresponding suspected fixed target at different time stamps;
overlapping the generation times of suspected fixed target areas belonging to the same suspected fixed target in historical preset days to obtain corresponding total generation times, and taking the suspected fixed target areas with the total generation times larger than a preset time threshold value as fixed target areas;
and when the real-time target data transmitted by the radar equipment is acquired, carrying out position matching on the real-time target data based on the fixed target area so as to identify the marine fixed target.
In one embodiment, the location information includes latitude and longitude information, and before the step of aggregating a plurality of marine target objects having the same historical target identifier and belonging to the same day into a corresponding cluster set, the method further includes:
filtering invalid data with latitude and longitude being null from the historical target data to obtain historical valid data;
and analyzing the historical effective data to analyze corresponding historical target identification, timestamp information and effective longitude and latitude information from the historical effective data aiming at each identified marine target object.
In one embodiment, the screening at least one suspected fixed target from each cluster set based on the obtained plurality of cluster results comprises:
traversing each cluster set;
regarding a currently traversed cluster set, when a plurality of cluster sets exist in a cluster set result of the cluster set or all are noise points, taking a plurality of offshore target objects included in the cluster set as non-fixed targets;
when only one clustering block and partial noise points exist in the clustering block results of the clustering sets, determining the distribution range of the partial noise points;
if the distribution range of the partial noise points is larger than a preset range threshold, taking a plurality of marine target objects in the cluster set as non-fixed targets; otherwise, taking a plurality of marine target objects in the cluster set as suspected fixed targets;
continuously traversing the plurality of cluster sets until all the cluster sets are traversed;
and screening out at least one suspected fixed target from the traversed cluster set.
In one embodiment, the superimposing the generation times of the suspected fixed target areas belonging to the same suspected fixed target in the historical preset days to obtain the corresponding total generation times includes:
counting suspected fixed target areas belonging to the same day by taking the day as a unit to obtain a corresponding suspected fixed target area list;
traversing various suspected fixed target area lists generated in historical preset days, and recording the traversal times of the suspected fixed target areas;
and when the traversal is finished, overlapping the traversal times of the suspected fixed target areas belonging to the same suspected fixed target to obtain the corresponding total generation times.
In one embodiment, before the step of performing location matching on the real-time target data based on the fixed target area for identification of a stationary target at sea, the method further comprises:
identifying the current marine target object in the fixed target area by using optical detection equipment to obtain a corresponding image identification result;
when the currently identified marine target object is determined to be a non-fixed target according to the image identification result, deleting the corresponding fixed target area;
and when the currently recognized marine target object is determined to be a fixed target according to the image recognition result, reserving a corresponding fixed target area.
In one embodiment, the performing location matching on the real-time target data based on the fixed target area to perform identification of a marine fixed target includes:
aggregating according to the real-time target identification included in the real-time target data, and forming a corresponding track point set;
and performing clustering analysis on the track point set to obtain corresponding clustering points, and taking the currently identified marine target object as a marine fixed target when the positions of the clustering points are distributed in the same fixed target area.
An offshore fixed-target identification device, the device comprising:
the acquisition module is used for acquiring historical target data which are output by the radar equipment and generated within historical preset days, wherein the historical target data comprise historical target identification, time stamp and position information aiming at each identified marine target object;
the first aggregation module is used for aggregating a plurality of marine target objects which have the same historical target identification and belong to the same day into corresponding cluster sets, and performing cluster analysis on each cluster set respectively to obtain corresponding cluster results;
the second aggregation module is used for screening out at least one suspected fixed target from each aggregation set based on the obtained multiple aggregation set results;
the pre-judgment module is used for determining a suspected fixed target area corresponding to each suspected fixed target according to the position information of the corresponding suspected fixed target at different timestamps;
the comprehensive judgment module is used for superposing the generation times of the suspected fixed target areas belonging to the same suspected fixed target in historical preset days to obtain corresponding total generation times, and taking the suspected fixed target areas with the total generation times larger than a preset time threshold value as fixed target areas;
and the identification module is used for carrying out position matching on the real-time target data based on the fixed target area when the real-time target data transmitted by the radar equipment is acquired so as to identify the marine fixed target.
In one embodiment, the second aggregation module is further configured to traverse each set of clusters; regarding a currently traversed cluster set, when a plurality of cluster sets exist in a cluster set result of the cluster set or all are noise points, taking a plurality of offshore target objects included in the cluster set as non-fixed targets; when only one clustering block and partial noise points exist in the clustering block results of the clustering sets, determining the distribution range of the partial noise points; if the distribution range of the partial noise points is larger than a preset range threshold, taking a plurality of marine target objects in the cluster set as non-fixed targets; otherwise, taking a plurality of marine target objects in the cluster set as suspected fixed targets; continuously traversing the plurality of cluster sets until all the cluster sets are traversed; and screening out at least one suspected fixed target from the traversed cluster set.
A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
acquiring historical target data which is output by a radar device and generated within historical preset days, wherein the historical target data comprises historical target identification, time stamp and position information aiming at each identified marine target object;
aggregating a plurality of marine target objects which have the same historical target identification and belong to the same day into corresponding cluster sets, and performing cluster analysis on each cluster set respectively to obtain corresponding cluster results;
based on the obtained multiple clustering results, screening out at least one suspected fixed target from each clustering set respectively;
for each suspected fixed target, determining a suspected fixed target area corresponding to the corresponding suspected fixed target according to the position information of the corresponding suspected fixed target at different time stamps;
overlapping the generation times of suspected fixed target areas belonging to the same suspected fixed target in historical preset days to obtain corresponding total generation times, and taking the suspected fixed target areas with the total generation times larger than a preset time threshold value as fixed target areas;
and when the real-time target data transmitted by the radar equipment is acquired, carrying out position matching on the real-time target data based on the fixed target area so as to identify the marine fixed target.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
acquiring historical target data which is output by a radar device and generated within historical preset days, wherein the historical target data comprises historical target identification, time stamp and position information aiming at each identified marine target object;
aggregating a plurality of marine target objects which have the same historical target identification and belong to the same day into corresponding cluster sets, and performing cluster analysis on each cluster set respectively to obtain corresponding cluster results;
based on the obtained multiple clustering results, screening out at least one suspected fixed target from each clustering set respectively;
for each suspected fixed target, determining a suspected fixed target area corresponding to the corresponding suspected fixed target according to the position information of the corresponding suspected fixed target at different time stamps;
overlapping the generation times of suspected fixed target areas belonging to the same suspected fixed target in historical preset days to obtain corresponding total generation times, and taking the suspected fixed target areas with the total generation times larger than a preset time threshold value as fixed target areas;
and when the real-time target data transmitted by the radar equipment is acquired, carrying out position matching on the real-time target data based on the fixed target area so as to identify the marine fixed target.
According to the method, the device, the computer equipment and the storage medium for identifying the marine fixed targets, the marine target objects with the same target identification are aggregated into the same aggregation set, the aggregation set is subjected to clustering analysis, and suspected fixed targets are screened according to the obtained clustering result and the extracted running track characteristics of each marine target; on the other hand, in order to distinguish the marine fixed targets and ships in a berthing state for a long time, the travel tracks of the suspected fixed targets in a plurality of days are comprehensively analyzed, namely the fixed target areas are judged based on the total generation times of the suspected fixed target areas of the same suspected fixed target cluster, so that the corresponding distinguishing effect is achieved, and the identification accuracy of the marine fixed targets is further improved.
Drawings
FIG. 1 is a diagram of an embodiment of an application environment of a method for identifying a marine fixed target;
FIG. 2 is a schematic flow diagram of a method for identifying a stationary offshore object according to one embodiment;
FIG. 3 is a schematic flow chart illustrating the steps of screening out at least one suspected fixation target from each cluster set in one embodiment;
FIG. 4 is a schematic diagram of a logic decision flow of a method for identifying a marine fixed target according to an embodiment;
FIG. 5 is a block diagram of the structure of an offshore fixed target identification device in one embodiment;
FIG. 6 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The method for identifying the marine fixed target can be applied to the application environment shown in fig. 1. Where radar device 102 communicates with computer device 104 over a network. In the current application scenario, first, historical target data generated within a historical preset number of days output via the radar device 102 will be acquired by the computer device 104. Secondly, the computer device 104 aggregates a plurality of marine target objects which have the same historical target identification and belong to the same day into corresponding cluster sets, and the computer device 104 performs cluster analysis on each cluster set respectively to obtain corresponding cluster results. Secondly, the computer device 104 screens out at least one suspected fixed target from each cluster set based on the obtained multi-cluster result, and the computer device 104 determines a suspected fixed target area corresponding to the corresponding suspected fixed target according to the position information of the corresponding suspected fixed target corresponding to different timestamps for each suspected fixed target. Secondly, the computer device 104 superimposes the generation times of the suspected fixed target areas belonging to the same suspected fixed target in the historical preset days to obtain the corresponding total generation times, and the suspected fixed target areas with the total generation times larger than the preset time threshold are used as the fixed target areas. Finally, when the computer device 104 acquires the real-time target data transmitted by the radar device 102, the real-time target data is subjected to position matching based on the fixed target area, so as to identify the marine fixed target.
In the above application scenario, the computer device 104 may be a terminal or a server, where the terminal may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server may be implemented by an independent server or a server cluster formed by multiple servers.
In one embodiment, as shown in fig. 2, there is provided a method for identifying a stationary object at sea, which is illustrated by applying the method to the computer device in fig. 1, and includes the following steps:
step S202, historical target data generated within historical preset days and output by the radar equipment are acquired, wherein the historical target data comprise historical target identification, time stamp and position information aiming at each identified marine target object.
The radar equipment comprises a radar sensor, the marine target object comprises a marine buoy, a lighthouse, sea waves, reefs, marine garbage and the like which flow in a fixed area for a long time, the marine fixed target with a relatively fixed flowing position also comprises a marine target which normally runs on the sea or stops in the fixed area for a long time due to faults such as anchoring and the like, and the position change rule of the marine target is very similar to that of the marine fixed target.
Specifically, when the communication between the computer device and the radar device is successful, the computer device acquires historical target data transmitted through the radar device, and analyzes the historical target data, so as to obtain the required historical target identifier, timestamp information and position information. The target identification can be understood as an identity identification tag, and specifically, when the radar equipment detects any one marine target object, corresponding target identification is given to the currently detected object; the time stamp information is information for authenticating the time generated by the data, a corresponding time interval mark is also generated according to the time stamp information, and the value of the time interval mark can be flexibly set in a value interval of 0-23 in specific application; the location information includes longitude and latitude coordinates at which the marine target object is located at the corresponding time period.
In one embodiment, when the acquired historical target data is analyzed by using the computer device, a preset regular expression may be used, so as to achieve effective extraction of the historical target identifier, the timestamp information, and the location information. Reference may be made to embodiments in which: key ═ javapythonc + + php; findall ('python', key), the above embodiments may be further understood as extracting the desired string 'python' from the defined key.
Step S204, a plurality of marine target objects which have the same historical target identification and belong to the same day are aggregated into corresponding cluster sets, and each cluster set is subjected to cluster analysis respectively to obtain corresponding cluster results.
Specifically, the computer device aggregates a plurality of marine target objects having the same historical target identifier and belonging to the same day into a corresponding cluster set according to the data extracted in the previous step S202 and with the historical target identifier as an aggregation condition. The cluster set can be further understood as a track point set, the track point set comprises marine target objects indicated by the historical target identifications, and the travel tracks of the marine target objects in a certain past day can be further reflected based on the track point set at positions reached in different time periods.
In one embodiment, the computer device performs cluster analysis on each cluster set according to a Density-Based Clustering algorithm (DBSCAN Clustering of Applications with Noise), wherein corresponding cluster results can be obtained through the set minimum point number and distance threshold. Of course, the computer device may also perform clustering analysis by using other clustering algorithms, such as graph theory clustering, and the like, which is not limited in the embodiment of the present application.
It should be noted that:
(1) the clustering result obtained by analysis comprises a plurality of noise points and a plurality of or only one clustering group; wherein each cluster comprises a plurality of polymerization points.
(2) The DBSCAN clustering algorithm is an algorithm for describing the closeness of a sample set based on a set of neighborhoods, and the closeness of sample distribution of the neighborhoods is described by a parameter (e, MinPts). Where the parameter e describes a neighborhood distance threshold (i.e., distance threshold) for a certain sample, and the parameter MinPts describes a threshold (i.e., minimum number of points) for the number of samples in a neighborhood of the certain sample having a distance e.
(3) An aggregation point refers to an object being a core point if the object contains more than a number MinPts of points within its radius; a noise point means that an object is a noise point if it is neither a core point nor a boundary point. Colloquially, the core points correspond to points inside the dense region, and the noise points correspond to points in the sparse region.
In the above embodiment, aggregation analysis is performed based on the DBSCAN clustering algorithm, abnormal noise data in the analysis data may be allowed, and a dense data set of any shape may be clustered without specifying the number of aggregation clusters, thereby improving the execution efficiency of the offshore regulation target recognition algorithm.
And step S206, based on the obtained multiple clustering results, screening out at least one suspected fixed target from each clustering set.
Specifically, a suspected fixation target refers to an object that flows in a fixed area for a long time. In the current embodiment, the computer device performs aggregation analysis on each cluster set based on a DBSCAN clustering algorithm, screens out at least one suspected fixed target from each cluster set based on noise points included in the cluster set result and distribution of the cluster sets, aggregates the suspected fixed targets belonging to the same cluster set, and forms a corresponding suspected fixed target cluster set.
In one embodiment, when the computer device is used to perform the screening of suspected fixed targets, the following two cases can be used for specific analysis:
(1) if all the clustering results are noise points or a plurality of clustering exists, the current analysis object is proved to be more dispersed in the travel area of the sea, and the analysis object can be regarded as a non-fixed target. It should be noted that the non-stationary target may be understood as a ship target that normally travels on the sea.
(2) If a unique aggregation cluster and a part of noise points exist in the clustering result, when the distribution condition of the part of noise points in the clustering result is analyzed, if the distribution range of the part of noise points is larger than a preset range threshold, the analysis object can be regarded as a non-fixed target, otherwise, the analysis object can be regarded as a suspected fixed target.
In the embodiment, the DBSCAN algorithm is used for carrying out cluster analysis, the ship target which normally runs on the sea and the suspected fixed target are effectively distinguished by extracting the running track characteristics of each target object on the sea and using the range distribution threshold value of the noise points in the cluster result, and therefore the identification accuracy of the suspected fixed target is improved.
Step S208, for each suspected fixed target, determining a suspected fixed target area corresponding to the corresponding suspected fixed target according to the position information corresponding to the corresponding suspected fixed target at different timestamps.
Specifically, the computer device divides the traveling area of the suspected fixed target on the sea based on the position information corresponding to the suspected fixed target at different timestamps.
In one embodiment, the computer device integrates the position information of the suspected fixed target corresponding to different timestamps to form a corresponding boundary range. The boundary range may then be used to determine a corresponding suspected fixation target area. In one embodiment, a suspected fixed target area of the suspected fixed target may be divided by using a rectangular area dividing manner, so as to ensure that positions of the suspected fixed target at different timestamps are all contained in the suspected fixed target area.
Step S210, overlapping the generation times of the suspected fixed target areas belonging to the same suspected fixed target in the historical preset days to obtain the corresponding total generation times, and taking the suspected fixed target areas with the total generation times larger than a preset time threshold value as the fixed target areas.
Specifically, the step of superposing the generation times of the suspected fixed target areas belonging to the same suspected fixed target in the historical preset days to obtain the corresponding total generation times includes: counting suspected fixed target areas belonging to the same day by taking the day as a unit to obtain a corresponding suspected fixed target area list; traversing each suspected fixed target area list generated in historical preset days, and recording the traversal times of the suspected fixed target areas; and when the traversal is finished, overlapping the traversal times of the suspected fixed target areas belonging to the same suspected fixed target to obtain the corresponding total generation times.
In one embodiment, the computer device performs iterative computation on a suspected fixed target area list generated every day within a historical preset number of days, and counts the total number of times each area is identified as a suspected fixed target area. For a target area with the total counted times larger than the time threshold, it may be determined that the target area is a fixed target area. To facilitate subsequent data retrieval, the location information of the fixed target area may be stored in a database.
In addition, it is considered that some ships are in a parked state for a long time due to a fault and the like, but it cannot be excluded that the ships are recovered to corresponding places by staff within 2-3 days (or a longer time period), and the traveling areas of the ships are distributed and scattered within a longer time period. In the current embodiment, in order to distinguish the marine fixed target and the ship in a berthed state for a long time, the advancing tracks of the suspected fixed targets in multiple days are comprehensively analyzed, that is, the fixed target area is judged based on the total generation times of the suspected fixed target areas belonging to the same suspected fixed target, so that the corresponding distinguishing effect is achieved, and the recognition accuracy of the marine fixed target is further improved.
Step S212, when the real-time target data transmitted by the radar equipment is acquired, the real-time target data is subjected to position matching based on the fixed target area, so that the maritime fixed target is identified.
Specifically, the position matching is performed on real-time target data based on a fixed target area so as to identify a marine fixed target, and the method comprises the following steps: aggregating according to real-time target identification included in the real-time target data, and forming a corresponding track point set; and clustering and analyzing the track point set to obtain corresponding clustering points, and taking the currently identified marine target object as a marine fixed target when the positions of the clustering points are distributed in the same fixed target area.
In one embodiment, real-time target data transmitted via a radar device is acquired by a computer device, aggregation is performed according to real-time target identifications included in the real-time target data, a corresponding aggregation result is obtained (a specific aggregation analysis process can refer to step S204), based on position distribution of each cluster point, after all noise points included in the aggregation result are eliminated, a fixed target area output in step S210 is used as a matching reference, and when the positions of the cluster points are judged to be distributed in the same fixed target area, a currently recognized marine target object can be used as a marine fixed target.
In the method for identifying the marine fixed targets, marine target objects with the same target identification are aggregated into the same aggregation set, the aggregation set is subjected to clustering analysis, and suspected fixed targets are screened according to the obtained clustering result and the extracted running track characteristics of the marine targets; on the other hand, in order to distinguish the marine fixed targets and ships in a berthing state for a long time, the travel tracks of the suspected fixed targets in a plurality of days are comprehensively analyzed, namely the fixed target areas are judged based on the total generation times of the suspected fixed target areas of the same suspected fixed target cluster, so that the corresponding distinguishing effect is achieved, and the identification accuracy of the marine fixed targets is further improved.
In one embodiment, as shown in fig. 3, the step of screening out at least one suspected fixation target from each cluster set specifically includes the following steps:
step S302, traversing each cluster set.
Step S304, regarding the currently traversed cluster set, when a plurality of cluster sets or all noise points exist in the cluster set result of the cluster set, a plurality of offshore target objects included in the cluster set are taken as non-fixed targets.
It should be noted that, for a currently traversed cluster set, when a plurality of cluster sets or all cluster sets are noise points in the cluster set result, it may be considered that the position distribution of the offshore target objects indicated by the cluster set is relatively dispersed, and because there is a position change rule that the position distribution is relatively aggregated within a certain period of time due to offshore fixed targets such as an offshore buoy and a lighthouse, it may be further determined that a plurality of offshore target objects included in the cluster set are non-fixed targets based on the position change rule of the offshore fixed targets.
In step S306, when there is only one cluster and partial noise points in the cluster result of the cluster set, a distribution range of the partial noise points is determined.
Step S308, if the distribution range of part of the noise points is larger than a preset range threshold, a plurality of marine target objects in the cluster set are used as non-fixed targets; otherwise, the plurality of marine target objects included in the cluster set are used as suspected fixed targets.
And step S310, continuously traversing the plurality of cluster sets until all the cluster sets are traversed.
It should be noted that, the computer device completes the traversal of each cluster set, and during the traversal, the above-mentioned steps S304-S308 are executed for each cluster set, so as to screen out at least one suspected fixed target from the corresponding cluster set.
Step S312, screening out at least one suspected fixed target from the traversed cluster set.
In the above embodiment, when there are noise points in the aggregation result, based on the number of the aggregation clusters and when there are partial noise points, the corresponding suspected fixed targets are screened out from the aggregation set by using the position distribution range of the partial noise points, and based on the above manner, the interference caused by the measurement error can be effectively eliminated, and the accuracy of identifying the marine fixed targets can be improved.
In an embodiment, as shown in fig. 4, the logic determination flow diagram of the method for identifying the marine fixed target in an embodiment specifically includes the following implementation steps:
(1) taking out historical target data, which is output via a radar device and generated in a past day, from a data warehouse; wherein, the historical target data mainly comprises: information such as target identification, MMSI (Markime Mobile Service identification), target category, timestamp, longitude, latitude, speed, course, heading, captain, and nationality;
(2) and (3) cleaning the historical target data acquired in the step (1), and filtering invalid data with latitude and longitude being null to obtain historical valid data.
(3) Preprocessing the historical effective data, taking out the target identification, MMSI, longitude, latitude and timestamp information in the historical effective data, and generating a corresponding time interval mark according to the timestamp information, wherein the value of the time interval mark is 0-23.
(4) And (4) according to the target identification extracted in the step (3), aggregating a plurality of marine target objects with the same target identification, and generating a corresponding track point set.
(5) And carrying out clustering analysis on track characteristics of the track points in each track point set by using a DBSCAN clustering algorithm. And clustering results corresponding to the track point sets can be obtained by setting the minimum point number and the distance threshold value.
(6) According to the clustering results respectively corresponding to the track point sets, if all the noise points exist in the clustering results or a plurality of clustering clusters exist in the clustering results, a plurality of marine target objects included in the corresponding clustering sets can be judged to be non-fixed targets.
(7) According to the clustering result corresponding to each trace point set, if a unique cluster and a part of noise points exist, then the distribution range of the part of noise points needs to be judged. If the distribution range of the partial noise points is larger than a preset distribution threshold, a plurality of marine target objects in the corresponding cluster set can be judged to be non-fixed targets, and otherwise, the marine target objects are suspected fixed targets.
(8) And aggregating the suspected fixed targets belonging to the same cluster set to form a corresponding suspected fixed target cluster. And aiming at each suspected fixed target cluster, integrating the position information of all the suspected fixed targets contained in the cluster, determining a corresponding boundary range, and generating a corresponding fixed target area according to the boundary range.
(9) And combining the fixed target areas to form a corresponding fixed target area set.
(10) And (3) repeating the steps (1) to (9), and generating a corresponding fixed target area set by taking days as a unit until a preset iteration termination condition is reached (for example, only historical target data of the last 30 days can be analyzed, and when the iteration is repeated to 30 th time, after the corresponding fixed target area set is output, a loop is skipped), and executing the step (11).
(11) And performing iterative computation on the generated multiple fixed target area sets, counting the total times of the areas identified as suspected fixed target areas, and taking the area with the total times larger than a certain time threshold value as the fixed target area.
(12) Manually carrying out secondary confirmation on each fixed target area obtained based on the calculation in the step (12); the secondary confirmation can adopt past experience or call a camera to confirm the marine target object in the fixed target area, and when the marine target object is confirmed to be a running ship or a fault ship which is in a berthing state for a long time due to fault, corresponding fixed target area data is deleted.
(13) And performing position calculation on real-time target data acquired in real time according to the generated fixed target area, forming a corresponding track point set by aggregation according to the real-time target identification, and judging that the target is a marine fixed target if the positions of the cluster points are in the same fixed area after eliminating noise points by using a DBSCAN clustering algorithm.
In one embodiment, the location information includes latitude and longitude information, and before the step of aggregating a plurality of marine target objects having the same historical target identifier and belonging to the same day into a corresponding cluster set, the method further includes: filtering invalid data with latitude and longitude being null from the historical target data to obtain historical valid data; and analyzing the historical effective data to analyze corresponding historical target identification, timestamp information and effective longitude and latitude information from the historical effective data aiming at each identified marine target object.
In one embodiment, prior to the step of location matching the real-time target data based on the fixed target area for identification of the stationary target at sea, the method further comprises: identifying the current marine target object in the fixed target area by using optical detection equipment to obtain a corresponding image identification result; when the currently identified marine target object is determined to be a non-fixed target through an image identification result, deleting a corresponding fixed target area; and when the currently recognized marine target object is determined to be a fixed target through the image recognition result, reserving a corresponding fixed target area. In the current embodiment, the accuracy of the fixed target area is further improved through artificial secondary confirmation, and the accuracy of marine fixed target identification is improved by eliminating interference caused by measurement errors in data.
It should be understood that although the various steps in the flow charts of fig. 1-4 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 1-4 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed in turn or alternately with other steps or at least some of the other steps.
In one embodiment, as shown in fig. 5, there is provided an offshore fixed target identification device, comprising: an obtaining module 501, a first aggregation module 502, a second aggregation module 503, a pre-judging module 504, a comprehensive judgment module 505, and an identifying module 506, wherein:
an obtaining module 501, configured to obtain historical target data generated within historical preset days and output by a radar device, where the historical target data includes a historical target identifier, a timestamp, and location information for each identified marine target object.
The first aggregation module 502 is configured to aggregate a plurality of marine target objects that have the same historical target identifier and belong to the same day into corresponding cluster sets, and perform cluster analysis on each cluster set to obtain corresponding cluster results.
And a second clustering module 503, configured to screen out at least one suspected fixed target from each cluster set based on the obtained plurality of cluster sets.
A pre-determining module 504, configured to, for each suspected fixed target, determine, according to location information corresponding to different timestamps of the corresponding suspected fixed target, a suspected fixed target area corresponding to the corresponding suspected fixed target.
And the comprehensive judgment module 505 is configured to superimpose the generation times of the suspected fixed target areas belonging to the same suspected fixed target within the historical preset days to obtain a corresponding total generation time, and use the suspected fixed target area with the total generation time greater than a preset time threshold as the fixed target area.
The identifying module 506 is configured to, when the real-time target data transmitted by the radar device is acquired, perform position matching on the real-time target data based on the fixed target area, so as to identify the marine fixed target.
In one embodiment, the location information includes latitude and longitude information, and the apparatus further includes a preprocessing module, wherein:
the preprocessing module is used for filtering invalid data with latitude and longitude being null from the historical target data to obtain historical valid data; and analyzing the historical effective data to analyze corresponding historical target identification, timestamp information and effective longitude and latitude information from the historical effective data aiming at each identified marine target object.
In one embodiment, the second aggregation module is further configured to traverse each set of clusters; regarding a currently traversed cluster set, when a plurality of cluster sets exist in a cluster set result of the cluster set or all the cluster sets are noise points, a plurality of offshore target objects included in the cluster set are used as non-fixed targets; when only one cluster and partial noise points exist in the cluster results of the cluster set, determining the distribution range of the partial noise points; if the distribution range of part of the noise points is larger than a preset range threshold, taking a plurality of marine target objects in the cluster set as non-fixed targets; otherwise, taking a plurality of marine target objects in the cluster set as suspected fixed targets; continuously traversing the plurality of cluster sets until all the cluster sets are traversed; and screening out at least one suspected fixed target from the traversed cluster set.
In one embodiment, the comprehensive judgment module 505 is further configured to count suspected fixed target areas belonging to the same day by taking the day as a unit, so as to obtain a corresponding suspected fixed target area list; traversing each suspected fixed target area list generated in historical preset days, and recording the traversal times of the suspected fixed target areas; and when the traversal is finished, overlapping the traversal times of the suspected fixed target areas belonging to the same suspected fixed target to obtain the corresponding total generation times.
In one embodiment, the apparatus further comprises a secondary determination module, wherein:
the secondary judgment module is used for identifying the current marine target object in the fixed target area by using the optical detection equipment to obtain a corresponding image identification result; when the currently identified marine target object is determined to be a non-fixed target through an image identification result, deleting a corresponding fixed target area; and when the currently recognized marine target object is determined to be a fixed target through the image recognition result, reserving a corresponding fixed target area.
In one embodiment, the recognition module 506 is further configured to obtain real-time target data transmitted by the radar device, aggregate the real-time target data according to a real-time target identifier included in the real-time target data, and form a corresponding trace point set; and clustering and analyzing the track point set to obtain corresponding clustering points, and taking the currently identified marine target object as a marine fixed target when the positions of the clustering points are distributed in the same fixed target area.
The offshore fixed target recognition device aggregates offshore target objects with the same target identification into the same aggregation set, performs cluster analysis on the aggregation set, and performs screening of suspected fixed targets according to the obtained clustering result and the extracted running track characteristics of each offshore target; on the other hand, in order to distinguish the marine fixed targets and ships in a berthing state for a long time, the travel tracks of the suspected fixed targets in a plurality of days are comprehensively analyzed, namely the fixed target areas are judged based on the total generation times of the suspected fixed target areas of the same suspected fixed target cluster, so that the corresponding distinguishing effect is achieved, and the identification accuracy of the marine fixed targets is further improved.
For specific limitations of the marine fixed target identification device, reference may be made to the above limitations of the marine fixed target identification method, which are not described herein again. The modules in the above-mentioned marine fixed target identification device can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a terminal or a server, and its internal structure diagram may be as shown in fig. 6. The computer device includes a processor, a memory, and a communication interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless communication can be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a method of marine stationary target identification.
Those skilled in the art will appreciate that the architecture shown in fig. 6 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program: acquiring historical target data which is output by a radar device and generated within historical preset days, wherein the historical target data comprises historical target identification, time stamp and position information aiming at each identified marine target object; aggregating a plurality of marine target objects which have the same historical target identification and belong to the same day into corresponding cluster sets, and performing cluster analysis on each cluster set respectively to obtain corresponding cluster results; based on the obtained multiple clustering results, screening out at least one suspected fixed target from each clustering set respectively; aiming at each suspected fixed target, determining a suspected fixed target area corresponding to the corresponding suspected fixed target according to the position information of the corresponding suspected fixed target at different time stamps; overlapping the generation times of suspected fixed target areas belonging to the same suspected fixed target in historical preset days to obtain corresponding total generation times, and taking the suspected fixed target areas with the total generation times larger than a preset time threshold value as fixed target areas; and when the real-time target data transmitted by the radar equipment is acquired, performing position matching on the real-time target data based on the fixed target area so as to identify the marine fixed target.
In one embodiment, the processor, when executing the computer program, further performs the steps of: filtering invalid data with latitude and longitude being null from the historical target data to obtain historical valid data; and analyzing the historical effective data to analyze corresponding historical target identification, timestamp information and effective longitude and latitude information from the historical effective data aiming at each identified marine target object.
In one embodiment, the processor, when executing the computer program, further performs the steps of: traversing each cluster set; regarding a currently traversed cluster set, when a plurality of cluster sets exist in a cluster set result of the cluster set or all the cluster sets are noise points, a plurality of offshore target objects included in the cluster set are used as non-fixed targets; when only one cluster and partial noise points exist in the cluster results of the cluster set, determining the distribution range of the partial noise points; if the distribution range of part of the noise points is larger than a preset range threshold, taking a plurality of marine target objects in the cluster set as non-fixed targets; otherwise, taking a plurality of marine target objects in the cluster set as suspected fixed targets; continuously traversing the plurality of cluster sets until all the cluster sets are traversed; and screening out at least one suspected fixed target from the traversed cluster set.
In one embodiment, the processor, when executing the computer program, further performs the steps of: counting suspected fixed target areas belonging to the same day by taking the day as a unit to obtain a corresponding suspected fixed target area list; traversing each suspected fixed target area list generated in historical preset days, and recording the traversal times of the suspected fixed target areas; and when the traversal is finished, overlapping the traversal times of the suspected fixed target areas belonging to the same suspected fixed target to obtain the corresponding total generation times.
In one embodiment, the processor, when executing the computer program, further performs the steps of: identifying the current marine target object in the fixed target area by using optical detection equipment to obtain a corresponding image identification result; when the currently identified marine target object is determined to be a non-fixed target through an image identification result, deleting a corresponding fixed target area; and when the currently recognized marine target object is determined to be a fixed target through the image recognition result, reserving a corresponding fixed target area.
In one embodiment, the processor, when executing the computer program, further performs the steps of: aggregating according to real-time target identification included in the real-time target data, and forming a corresponding track point set; and clustering and analyzing the track point set to obtain corresponding clustering points, and taking the currently identified marine target object as a marine fixed target when the positions of the clustering points are distributed in the same fixed target area.
The computer equipment aggregates the marine target objects with the same target identification into the same aggregation set, performs cluster analysis on the aggregation set, and performs screening of suspected fixed targets according to the obtained clustering result and the extracted running track characteristics of each marine target; on the other hand, in order to distinguish the marine fixed targets and ships in a berthing state for a long time, the travel tracks of the suspected fixed targets in a plurality of days are comprehensively analyzed, namely the fixed target areas are judged based on the total generation times of the suspected fixed target areas of the same suspected fixed target cluster, so that the corresponding distinguishing effect is achieved, and the identification accuracy of the marine fixed targets is further improved.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of: acquiring historical target data which is output by a radar device and generated within historical preset days, wherein the historical target data comprises historical target identification, time stamp and position information aiming at each identified marine target object; aggregating a plurality of marine target objects which have the same historical target identification and belong to the same day into corresponding cluster sets, and performing cluster analysis on each cluster set respectively to obtain corresponding cluster results; based on the obtained multiple clustering results, screening out at least one suspected fixed target from each clustering set respectively; aiming at each suspected fixed target, determining a suspected fixed target area corresponding to the corresponding suspected fixed target according to the position information of the corresponding suspected fixed target at different time stamps; overlapping the generation times of suspected fixed target areas belonging to the same suspected fixed target in historical preset days to obtain corresponding total generation times, and taking the suspected fixed target areas with the total generation times larger than a preset time threshold value as fixed target areas; and when the real-time target data transmitted by the radar equipment is acquired, performing position matching on the real-time target data based on the fixed target area so as to identify the marine fixed target.
In one embodiment, the computer program when executed by the processor further performs the steps of: filtering invalid data with latitude and longitude being null from the historical target data to obtain historical valid data; and analyzing the historical effective data to analyze corresponding historical target identification, timestamp information and effective longitude and latitude information from the historical effective data aiming at each identified marine target object.
In one embodiment, the computer program when executed by the processor further performs the steps of: traversing each cluster set; regarding a currently traversed cluster set, when a plurality of cluster sets exist in a cluster set result of the cluster set or all the cluster sets are noise points, a plurality of offshore target objects included in the cluster set are used as non-fixed targets; when only one cluster and partial noise points exist in the cluster results of the cluster set, determining the distribution range of the partial noise points; if the distribution range of part of the noise points is larger than a preset range threshold, taking a plurality of marine target objects in the cluster set as non-fixed targets; otherwise, taking a plurality of marine target objects in the cluster set as suspected fixed targets; continuously traversing the plurality of cluster sets until all the cluster sets are traversed; and screening out at least one suspected fixed target from the traversed cluster set.
In one embodiment, the computer program when executed by the processor further performs the steps of: counting suspected fixed target areas belonging to the same day by taking the day as a unit to obtain a corresponding suspected fixed target area list; traversing each suspected fixed target area list generated in historical preset days, and recording the traversal times of the suspected fixed target areas; and when the traversal is finished, overlapping the traversal times of the suspected fixed target areas belonging to the same suspected fixed target to obtain the corresponding total generation times.
In one embodiment, the computer program when executed by the processor further performs the steps of: identifying the current marine target object in the fixed target area by using optical detection equipment to obtain a corresponding image identification result; when the currently identified marine target object is determined to be a non-fixed target through an image identification result, deleting a corresponding fixed target area; and when the currently recognized marine target object is determined to be a fixed target through the image recognition result, reserving a corresponding fixed target area.
In one embodiment, the computer program when executed by the processor further performs the steps of: aggregating according to real-time target identification included in the real-time target data, and forming a corresponding track point set; and clustering and analyzing the track point set to obtain corresponding clustering points, and taking the currently identified marine target object as a marine fixed target when the positions of the clustering points are distributed in the same fixed target area.
The computer storage medium aggregates the marine target objects with the same target identification into the same aggregation set, performs cluster analysis on the aggregation set, and performs screening of suspected fixed targets according to the obtained clustering result and the extracted running track characteristics of each marine target; on the other hand, in order to distinguish the marine fixed targets and ships in a berthing state for a long time, the travel tracks of the suspected fixed targets in a plurality of days are comprehensively analyzed, namely the fixed target areas are judged based on the total generation times of the suspected fixed target areas of the same suspected fixed target cluster, so that the corresponding distinguishing effect is achieved, and the identification accuracy of the marine fixed targets is further improved.
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 hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method for identifying an offshore fixed target, the method comprising:
acquiring historical target data which is output by a radar device and generated within historical preset days, wherein the historical target data comprises historical target identification, time stamp and position information aiming at each identified marine target object;
aggregating a plurality of marine target objects which have the same historical target identification and belong to the same day into corresponding cluster sets, and performing cluster analysis on each cluster set respectively to obtain corresponding cluster results;
based on the obtained multiple clustering results, screening out at least one suspected fixed target from each clustering set respectively;
for each suspected fixed target, determining a suspected fixed target area corresponding to the corresponding suspected fixed target according to the position information of the corresponding suspected fixed target at different time stamps;
overlapping the generation times of suspected fixed target areas belonging to the same suspected fixed target in historical preset days to obtain corresponding total generation times, and taking the suspected fixed target areas with the total generation times larger than a preset time threshold value as fixed target areas;
and when the real-time target data transmitted by the radar equipment is acquired, carrying out position matching on the real-time target data based on the fixed target area so as to identify the marine fixed target.
2. The method of claim 1, wherein the location information comprises latitude and longitude information, and wherein before the step of aggregating a plurality of marine target objects having the same historical target identification and belonging to the same day into a corresponding cluster set, the method further comprises:
filtering invalid data with latitude and longitude being null from the historical target data to obtain historical valid data;
and analyzing the historical effective data to analyze corresponding historical target identification, timestamp information and effective longitude and latitude information from the historical effective data aiming at each identified marine target object.
3. A method as recited in claim 1, wherein said screening out at least one suspected fixation target from each cluster set based on the plurality of cluster results obtained comprises:
traversing each cluster set;
regarding a currently traversed cluster set, when a plurality of cluster sets exist in a cluster set result of the cluster set or all are noise points, taking a plurality of offshore target objects included in the cluster set as non-fixed targets;
when only one clustering block and partial noise points exist in the clustering block results of the clustering sets, determining the distribution range of the partial noise points;
if the distribution range of the partial noise points is larger than a preset range threshold, taking a plurality of marine target objects in the cluster set as non-fixed targets; otherwise, taking a plurality of marine target objects in the cluster set as suspected fixed targets;
continuously traversing the plurality of cluster sets until all the cluster sets are traversed;
and screening out at least one suspected fixed target from the traversed cluster set.
4. The method according to claim 1, wherein the step of superposing the generation times of the suspected fixed target areas belonging to the same suspected fixed target in the historical preset days to obtain a corresponding total generation time includes:
counting suspected fixed target areas belonging to the same day by taking the day as a unit to obtain a corresponding suspected fixed target area list;
traversing various suspected fixed target area lists generated in historical preset days, and recording the traversal times of the suspected fixed target areas;
and when the traversal is finished, overlapping the traversal times of the suspected fixed target areas belonging to the same suspected fixed target to obtain the corresponding total generation times.
5. The method of claim 1, wherein prior to the step of location matching the real-time target data based on the fixed target area for identification of stationary targets at sea, the method further comprises:
identifying the current marine target object in the fixed target area by using optical detection equipment to obtain a corresponding image identification result;
when the currently identified marine target object is determined to be a non-fixed target according to the image identification result, deleting the corresponding fixed target area;
and when the currently recognized marine target object is determined to be a fixed target according to the image recognition result, reserving a corresponding fixed target area.
6. The method of any one of claims 1 to 5, wherein said location matching said real-time target data based on said fixed target area for identification of a stationary target at sea comprises:
aggregating according to the real-time target identification included in the real-time target data, and forming a corresponding track point set;
and performing clustering analysis on the track point set to obtain corresponding clustering points, and taking the currently identified marine target object as a marine fixed target when the positions of the clustering points are distributed in the same fixed target area.
7. An apparatus for identifying an offshore fixed target, the apparatus comprising:
the acquisition module is used for acquiring historical target data which are output by the radar equipment and generated within historical preset days, wherein the historical target data comprise historical target identification, time stamp and position information aiming at each identified marine target object;
the first aggregation module is used for aggregating a plurality of marine target objects which have the same historical target identification and belong to the same day into corresponding cluster sets, and performing cluster analysis on each cluster set respectively to obtain corresponding cluster results;
the second aggregation module is used for screening out at least one suspected fixed target from each aggregation set based on the obtained multiple aggregation set results;
the pre-judgment module is used for determining a suspected fixed target area corresponding to each suspected fixed target according to the position information of the corresponding suspected fixed target at different timestamps;
the comprehensive judgment module is used for superposing the generation times of the suspected fixed target areas belonging to the same suspected fixed target in historical preset days to obtain corresponding total generation times, and taking the suspected fixed target areas with the total generation times larger than a preset time threshold value as fixed target areas;
and the identification module is used for carrying out position matching on the real-time target data based on the fixed target area when the real-time target data transmitted by the radar equipment is acquired so as to identify the marine fixed target.
8. The apparatus of claim 7, wherein the second aggregation module is further configured to traverse each set of clusters; regarding a currently traversed cluster set, when a plurality of cluster sets exist in a cluster set result of the cluster set or all are noise points, taking a plurality of offshore target objects included in the cluster set as non-fixed targets; when only one clustering block and partial noise points exist in the clustering block results of the clustering sets, determining the distribution range of the partial noise points; if the distribution range of the partial noise points is larger than a preset range threshold, taking a plurality of marine target objects in the cluster set as non-fixed targets; otherwise, taking a plurality of marine target objects in the cluster set as suspected fixed targets; continuously traversing the plurality of cluster sets until all the cluster sets are traversed; and screening out at least one suspected fixed target from the traversed cluster set.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 6.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110567107.4A CN113222040B (en) | 2021-05-24 | 2021-05-24 | Marine fixed target identification method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110567107.4A CN113222040B (en) | 2021-05-24 | 2021-05-24 | Marine fixed target identification method, device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113222040A true CN113222040A (en) | 2021-08-06 |
| CN113222040B CN113222040B (en) | 2024-04-26 |
Family
ID=77098177
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110567107.4A Active CN113222040B (en) | 2021-05-24 | 2021-05-24 | Marine fixed target identification method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113222040B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113932282A (en) * | 2021-11-11 | 2022-01-14 | 武汉中绘炫图信息科技有限公司 | Urban heating supervision method and system |
| CN117111019A (en) * | 2023-10-25 | 2023-11-24 | 深圳市先创数字技术有限公司 | Target tracking and monitoring method and system based on radar detection |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010014491A (en) * | 2008-07-02 | 2010-01-21 | National Institute Of Advanced Industrial & Technology | Offshore monitoring system method |
| CN107832778A (en) * | 2017-10-13 | 2018-03-23 | 中国舰船研究设计中心 | A kind of same target recognition methods based on spatial synthesis similarity |
| CN110309240A (en) * | 2018-03-14 | 2019-10-08 | 北京京东尚科信息技术有限公司 | The method and apparatus for removing dynamic object |
| CN111581314A (en) * | 2020-04-26 | 2020-08-25 | 亿海蓝（北京）数据技术股份公司 | Berth identification method and device based on ship track |
| CN112100303A (en) * | 2020-09-14 | 2020-12-18 | 拉扎斯网络科技（上海）有限公司 | Building entity position determining method and device, computer equipment and readable storage medium |
| CN112613455A (en) * | 2020-12-29 | 2021-04-06 | 武汉理工大学 | Ship anchoring gathering area identification method and device |
-
2021
- 2021-05-24 CN CN202110567107.4A patent/CN113222040B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010014491A (en) * | 2008-07-02 | 2010-01-21 | National Institute Of Advanced Industrial & Technology | Offshore monitoring system method |
| CN107832778A (en) * | 2017-10-13 | 2018-03-23 | 中国舰船研究设计中心 | A kind of same target recognition methods based on spatial synthesis similarity |
| CN110309240A (en) * | 2018-03-14 | 2019-10-08 | 北京京东尚科信息技术有限公司 | The method and apparatus for removing dynamic object |
| CN111581314A (en) * | 2020-04-26 | 2020-08-25 | 亿海蓝（北京）数据技术股份公司 | Berth identification method and device based on ship track |
| CN112100303A (en) * | 2020-09-14 | 2020-12-18 | 拉扎斯网络科技（上海）有限公司 | Building entity position determining method and device, computer equipment and readable storage medium |
| CN112613455A (en) * | 2020-12-29 | 2021-04-06 | 武汉理工大学 | Ship anchoring gathering area identification method and device |
Non-Patent Citations (1)
| Title |
|---|
| LIANG CHENG等: ""Invariant triangle-based stationary oil platform detection from multitemporal synthetic aperture radar data"", 《JOURNAL OF APPLIED REMOTING SENSING》, 9 July 2013 (2013-07-09), pages 073537 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113932282A (en) * | 2021-11-11 | 2022-01-14 | 武汉中绘炫图信息科技有限公司 | Urban heating supervision method and system |
| CN113932282B (en) * | 2021-11-11 | 2024-03-01 | 武汉中绘炫图信息科技有限公司 | Urban heating supervision method and system |
| CN117111019A (en) * | 2023-10-25 | 2023-11-24 | 深圳市先创数字技术有限公司 | Target tracking and monitoring method and system based on radar detection |
| CN117111019B (en) * | 2023-10-25 | 2024-01-09 | 深圳市先创数字技术有限公司 | Target tracking and monitoring method and system based on radar detection |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113222040B (en) | 2024-04-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xiao et al. | Maritime traffic probabilistic forecasting based on vessels’ waterway patterns and motion behaviors | |
| Laxhammar et al. | Inductive conformal anomaly detection for sequential detection of anomalous sub-trajectories | |
| CN111897318A (en) | Unmanned ship-based intelligent water pollution investigation method and device | |
| CN113222040B (en) | Marine fixed target identification method, device, computer equipment and storage medium | |
| CN110706261A (en) | Vehicle violation detection method and device, computer equipment and storage medium | |
| CN109829936B (en) | Target tracking method and device | |
| CN111582380A (en) | Ship track density clustering method and device based on space-time characteristics | |
| CN113822513B (en) | Port congestion monitoring method based on anchor ground and berth automatic identification algorithm | |
| CN111209457A (en) | Target typical activity pattern deviation warning method | |
| Sevlian et al. | Travel time estimation using floating car data | |
| CN112200059B (en) | Method and device for counting flow of aquatic moving target and computer equipment | |
| CN113269042A (en) | Intelligent traffic management method and system based on running vehicle violation identification | |
| CN110443319B (en) | Track duplicate removal method and device and storage medium | |
| CN115830010A (en) | Method and device for detecting crossing distance of power transmission conductors and computer equipment | |
| Yan et al. | Development of denoising and compression algorithms for AIS-based vessel trajectories | |
| Xu et al. | Trajectory clustering for SVR-based Time of Arrival estimation | |
| Ahmed et al. | Choosing thresholds for density-based map construction algorithms | |
| CN115187884A (en) | High-altitude parabolic identification method and device, electronic equipment and storage medium | |
| CN110796129A (en) | Text line region detection method and device | |
| CN113160279A (en) | Method and device for detecting abnormal behaviors of pedestrians in subway environment | |
| CN113158084A (en) | Method and device for processing movement track data, computer equipment and storage medium | |
| Salamanis et al. | Evaluating the effect of time series segmentation on STARIMA-based traffic prediction model | |
| CN111190975A (en) | River channel patrol method for calculating task track coverage rate according to GPS data | |
| Wang et al. | Extracting the main routes and speed profiles between two locations from massive uncertain historical trajectories | |
| CN115587308A (en) | Method and device for determining navigation channel, electronic equipment 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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230719 Address after: 570000 Unit B, 14 #, Fortune Plaza, 103 Binhai Avenue, Haikou City, Hainan Province Applicant after: Haikou Branch of Guangzhou Bureau of China Southern Power Grid Co.,Ltd. Address before: 510700 Building 2, 223 science Avenue, Huangpu District, Guangzhou City, Guangdong Province Applicant before: GUANGZHOU BUREAU OF EXTRA HIGH VOLTAGE TRANSMISSION COMPANY OF CHINA SOUTHERN POWER GRID Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |