Advanced dumping behavior identification method based on big data and multi-source information fusion technology

Abstract

The invention discloses an advanced dumping behavior identification method based on big data and a multi-source information fusion technology, and the method achieves the fusion of AIS, Beidou and radar signal data based on the multi-source information fusion technology, enables the tracking of a monitored target to be more accurate and effective, can effectively track and identify the identity information of the target even if a ship actively closes AIS equipment, and improves the recognition efficiency. Based on the multi-source information fusion technology, independent of external equipment such as a special dumping recorder, the dumping ship is actively monitored, even if the external equipment of the monitored ship is closed, the dumping behavior of the monitored ship can still be analyzed through the navigation track of the ship, and based on the Flink real-time flow calculation processing technology, the dumping behavior of the ship can be analyzed through the real-time flow calculation processing technology. The method can guarantee the real-time push of an alarm event, and effectively shields the interference on behavior recognition caused by the inaccurate target trajectory point based on the algorithm of the trajectory feature recognition target turn-back behavior, and improves the accuracy of a recognition result.

Description

Technical Field

[0001] The present invention relates to the field of big data technology, and in particular to a method for identifying premature dumping behavior based on big data and multi-source information fusion technology. Background Art

[0002] Over the past few decades, the ocean, as the most vast and life-rich natural resource on Earth, has been facing continuous threats from human activities. Among them, dumping activities in the ocean, especially unauthorized and random dumping at sea, have become a major source of marine pollution. International and national environmental protection organizations have delineated specific marine dumping areas through scientific research. These areas have been scientifically demonstrated to have dumped materials that can be naturally absorbed by the ocean to a certain extent and have strong self-purification capabilities.

[0003] However, there are still many dumping ships that do not comply with relevant regulations and illegally dump waste before reaching the designated dumping area. The marine management department is in urgent need of a technology and method to effectively identify such premature dumping that is not in the designated dumping area.

[0004] The prior art has the following defects:

[0005] 1. Using ships or drones to inspect waste dumping ships at sea irregularly requires a lot of manpower and material resources, and it is impossible to achieve 24-hour uninterrupted monitoring, which is inefficient;

[0006] 2. Although relatively accurate monitoring of dumping behavior can be achieved to a certain extent by installing special dumping recorders or other monitoring equipment on dumping vessels, these devices need to be actively installed on the ship and there is a possibility of malicious tampering with information or abnormal shutdown of the equipment. The active cooperation of the ship is required to achieve the effect. If a ship intends to illegally dump waste in real time, it is likely to take various illegal means to refuse to cooperate, resulting in a significant reduction in the monitoring effect;

[0007] 3. Using AIS ship track data to analyze whether the dumping ship has reached the designated dumping area for dumping is a feasible solution, but AIS equipment may be manually shut down or tampered with, resulting in inaccurate and incomplete track data. At present, the logic of judging whether the target has been dumped in advance by track is also very simple, and the impact of track position accuracy on the result is not considered. Summary of the invention

[0008] In order to overcome the shortcomings of the prior art, one of the objectives of the present invention is to provide a method for identifying early dumping behavior based on big data and multi-source information fusion technology.

[0009] One of the purposes of the present invention is achieved by the following technical solution:

[0010] A method for identifying premature dumping behavior based on big data and multi-source information fusion technology, comprising the following steps:

[0011] Step 1: Use the Flink big data computing framework to consume multi-source fused target point data in real time. The main information includes the longitude, latitude, speed, and time of the target as the mainstream data.

[0012] Step 2: Clean the data in the mainstream and filter out invalid data such as fixed targets, stray targets, targets with empty longitude and latitude, and disordered data;

[0013] Step 3: Consume the dumping ship list and all designated dumping area data stored in Redis every 10 seconds. The main information includes the MMSI number of the dumping ship, the regional coordinates and number of the dumping area;

[0014] Step 4: Connect the list of dumping vessels and the data of dumping areas obtained in step 3 with the mainstream data filtered in step 2 through broadcasting;

[0015] Step 5: For the targets in the dumping list, generate the trajectory features of each target in the last 5 minutes and continuously update them by sliding, that is, always save the status of the target in the last 5 minutes. The trajectory features include the following information: the initial point, center point, moving displacement, and moving distance of the target's trajectory in the last 5 minutes;

[0016] Step 6: Determine whether the ratio of the target's moving distance and moving displacement in the last 5 minutes is less than the threshold. The moving distance displacement ratio can effectively determine whether the target is traveling normally. If the moving distance displacement ratio is too large, it means that the target may be turning or moving in a circle. This step finds the trajectory less than the threshold in order to find the target ship traveling normally.

[0017] Step 7: To meet the goal of step 6, start traversing each dumping area in the dumping area list, obtain the position coordinates of the center point of the dumping area through the method provided by JTS, and calculate the vector line angle between the line connecting the starting point to the center point of the trajectory and the line connecting the starting point of the trajectory to the center point of the dumping area in the target's trajectory characteristics in the last 5 minutes, recorded as α;

[0018] Step 8: Determine whether the value of α is less than the threshold. If it is less than the threshold, it means that the target ship is heading towards the dumping area. Mark the state that the target ship is approaching the dumping area, and continuously update and save the trajectory characteristics of the target ship in the last 5 minutes and the position coordinate point closest to the dumping area for subsequent calculations;

[0019] Step 9: Continue to determine the value of α. When the value of α is greater than the preset threshold, it means that the target ship is moving away from the dumping area. At this time, determine whether the target ship is too close to the dumping area. If so, start the next step of calculation.

[0020] Step 10: Take out the line between the starting point and the center point of the trajectory within 5 minutes when the target vessel approaches the dumping area saved in step 8, and the line between the starting point and the center point of the trajectory within 5 minutes when the target vessel starts to move away from the dumping area, and calculate the angle between the two vector lines, which is recorded as β;

[0021] Step 11: When the β value is greater than the preset threshold, it means that the target has turned back. At this time, the coordinate point of the target closest to the center of the dumping area saved in step 8 is taken out to determine the inclusion relationship between the coordinate point and the dumping area. If the dumping area contains the coordinate point, it means that the target has entered the dumping area and performed normal dumping behavior. If the coordinate point is not contained in the dumping area, it means that the target has turned back before entering the designated dumping area. There is a possibility that the target has not entered the designated dumping area for dumping. At this time, an alarm data is pushed to Kafka;

[0022] Step 12: Subsequent programs consume the alarm data in Kafka and perform corresponding alarm processing;

[0023] Step 13: During the alarm generation process, the above algorithm process accurately identifies that the target has not entered the waste dumping area and has turned back in advance, which means there is a possibility of premature dumping.

[0024] Furthermore, in step one, target point data can be obtained from AIS, radar, and BeiDou.

[0025] Furthermore, in step 2, the fixed targets filtered out are buoys, lighthouses, and navigation aids at sea, and the stray targets filtered out are false targets such as sea clutter identified by radar.

[0026] Furthermore, in step five, the center point is the center of mass of the trajectory.

[0027] Furthermore, in step six, the default configuration of the threshold is 1.3, which can be configured through parameters.

[0028] Furthermore, in step eight, the threshold value is configured by default to 15°, which can be configured through parameters.

[0029] Furthermore, in step nine, the threshold is configured by default to 165°, which can be configured through parameters.

[0030] Furthermore, in step 11, the threshold value is configured by default to 145°, which can be configured through parameters.

[0031] Compared with the prior art, the present invention has the following beneficial effects:

[0032] 1. The present invention is based on multi-source information fusion technology, which integrates AIS, Beidou and radar signal data to make the tracking of monitoring targets more accurate and effective. Even if the ship actively turns off the AIS device, it can effectively track and identify the identity information of the target and analyze its dumping behavior;

[0033] 2. The present invention is based on multi-source information fusion technology and does not rely on external equipment such as special dumping recorders. By actively monitoring dumping vessels, even if the monitored vessel turns off its external equipment, its dumping behavior can still be analyzed through its navigation track;

[0034] 3. The present invention is based on Flink real-time stream computing and processing technology, which can ensure the real-time push of alarm events;

[0035] 4. The algorithm of the present invention for identifying target return behavior based on trajectory features effectively shields the interference to behavior identification caused by inaccurate target trajectory points, thereby improving the accuracy of the identification results.

[0036] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the following specifically cites a preferred embodiment and describes it in detail with the accompanying drawings as follows. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a flow chart of the present invention;

[0038] Figure 2 The trajectory of the embodiment of the present invention Figure 1 ;

[0039] Figure 3 The trajectory of the embodiment of the present invention Figure 2 ;

[0040] Figure 4 The trajectory of the embodiment of the present invention Figure 3 ;

[0041] Figure 5 The trajectory of the embodiment of the present invention Figure 4 . DETAILED DESCRIPTION

[0042] The present invention is further described below in conjunction with the accompanying drawings and specific implementation methods. It should be noted that, under the premise of no conflict, the various embodiments or technical features described below can be arbitrarily combined to form a new embodiment.

[0043] It should be noted that when a component is referred to as being "fixed to" another component, it may be directly on the other component or there may also be a component centered. When a component is considered to be "connected to" another component, it may be directly connected to the other component or there may also be a component centered. When a component is considered to be "set on" another component, it may be directly set on the other component or there may also be a component centered. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0044] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0045] See also Figure 1-5 The present invention provides a technical solution: a method for identifying early dumping behavior based on big data and multi-source information fusion technology.

[0046] Step 1: Use the Flink big data computing framework to consume multi-source fused target point data in real time. The target point data can be obtained from AIS, radar, Beidou, etc. The main information includes the longitude, latitude, speed, time, etc. of the target as the mainstream data;

[0047] Step 2: Clean the data in the mainstream and filter out invalid data such as fixed targets, stray targets, targets with empty longitude and latitude, and disordered data. The fixed targets filtered out are buoys, lighthouses, and navigation aids at sea, and the stray targets filtered out are false targets such as sea clutter identified by radar.

[0048] Step 3: Consume the dumping ship list and all designated dumping area data stored in Redis every 10 seconds. The main information includes the MMSI number of the dumping ship, the regional coordinates and number of the dumping area;

[0049] Step 4: Connect the list of dumping vessels and the data of dumping areas obtained in step 3 with the mainstream data filtered in step 2 through broadcasting;

[0050] Step 5: For the targets in the dumping list, generate the trajectory features of each target in the last 5 minutes and continuously update them by sliding, that is, always save the status of the target in the last 5 minutes. The trajectory features include the following information: the initial point, center point, moving displacement, and moving distance of the target's trajectory in the last 5 minutes, and the center point is the center of mass of the trajectory;

[0051] Step 6: Determine whether the ratio of the target's moving distance and displacement in the last 5 minutes is less than the threshold. The default threshold is 1.3. Through parameter configuration, the moving distance displacement ratio can effectively determine whether the target is traveling normally. If the moving distance displacement ratio is too large, it means that the target may be turning or moving in a circle. This step finds the trajectory less than the threshold in order to find the target ship traveling normally.

[0052] Step 7: To meet the goal of step 6, start traversing each dumping area in the dumping area list, obtain the position coordinates of the center point of the dumping area through the method provided by JTS, and calculate the vector line angle between the line connecting the starting point to the center point of the trajectory and the line connecting the starting point of the trajectory to the center point of the dumping area in the target's trajectory characteristics in the last 5 minutes, recorded as α;

[0053] Step 8: Determine whether the value of α is less than the threshold. The default value of the threshold is 15°, which can be configured through parameters. If the value is less than the threshold, it means that the target ship is heading towards the dumping area, as follows Figure 2 As shown, the target vessel is marked as approaching the dumping area, and the trajectory characteristics (initial point, center point, moving displacement, moving distance) of the target vessel in the last 5 minutes and the position coordinate point closest to the dumping area are continuously updated and saved for subsequent calculations.

[0054] Step 9: Continue to judge the value of α. When the value of α is greater than the preset threshold, it means that the target ship is moving away from the dumping area, as shown below Figure 3 As shown, the default threshold is 165°, which can be configured through parameters to determine whether the target ship is too close to the dumping area. If so, the next step of calculation begins;

[0055] Step 10: Take out the line between the starting point and the center point of the trajectory within 5 minutes when the target vessel approaches the dumping area saved in step 8, and the line between the starting point and the center point of the trajectory within 5 minutes when the target vessel starts to move away from the dumping area, and calculate the angle between the two vector lines, recorded as β, as follows Figure 4 As shown;

[0056] Step 11: When the β value is greater than the preset threshold, it means that the target has turned back. At this time, the coordinate point of the target closest to the center of the dumping area saved in step 8 is taken out to determine the inclusion relationship between the coordinate point and the dumping area. If the dumping area contains the coordinate point, it means that the target has entered the dumping area and performed normal dumping behavior. If the coordinate point is not contained in the dumping area, it means that the target has turned back before entering the designated dumping area. There is a possibility that the target has not entered the designated dumping area for dumping. At this time, an alarm data is pushed to Kafka. The default configuration of the threshold is 145°, which can be configured through parameters;

[0057] Step 12: Subsequent programs consume the alarm data in Kafka and perform corresponding alarm processing.

[0058] Step 13: During the alarm generation process, the movement trajectory of the entire target is as follows Figure 5 As shown, the above algorithm process accurately identifies that the target turns back in advance before entering the dumping area, and there is a possibility of premature dumping.

[0059] 1. Based on multi-source information fusion technology, the trajectory tracking of ships at sea is more accurate. Even if the ship turns off the AIS equipment, it can effectively track and identify the identity of the ship target and analyze the target's dumping behavior;

[0060] 2. Trajectory tracking based on multi-source information fusion does not rely on external equipment such as dumping recorders. It is an active monitoring of ships preparing to carry out illegal dumping. Even if the monitored ship turns off the external equipment, its behavior can still be analyzed through its driving trajectory;

[0061] 3. Flink-based big data real-time stream processing computing technology can ensure the real-time performance of data analysis and processing. When monitoring ships dump waste in advance before entering the dumping area, alarm data can be pushed in time for subsequent management departments to handle;

[0062] 4. In the process of ship trajectory analysis, in order to shield the interference caused by inaccurate target trajectory point position information, the trajectory feature algorithm is used to identify the target's return behavior, which greatly improves the accuracy of the recognition results.

[0063] In the description of the present invention, it is to be understood that the terms “center”, “longitudinal”, “lateral”, “length”, “width”, “thickness”, “up”, “down”, “front”, “back”, “left”, “right”, “vertical”, “horizontal”, “top”, “bottom”, “inside”, “outside”, “clockwise”, “counterclockwise”, “axial”, “radial”, “circumferential”, etc., indicating orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0064] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0065] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0066] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, a first feature being "above", "above" or "above" a second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being "below", "below" or "below" a second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.

[0067] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0068] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A method for identifying premature dumping behavior based on big data and multi-source information fusion technology, characterized in that: The following steps are involved: Step 1: Use the Flink big data computing framework to consume multi-source fused target point data in real time. The main information includes the longitude, latitude, speed, and time of the target as the mainstream data. Step 2: Clean the data in the mainstream and filter out invalid data such as fixed targets, stray targets, targets with empty longitude and latitude, and disordered data; Step 3: Consume the dumping ship list and all designated dumping area data stored in Redis every 10 seconds. The main information includes the MMSI number of the dumping ship, the regional coordinates and number of the dumping area; Step 4: Connect the list of dumping vessels and the data of dumping areas obtained in step 3 with the mainstream data filtered in step 2 through broadcasting; Step 5: For the targets in the dumping list, generate the trajectory features of each target in the last 5 minutes and continuously update them by sliding, that is, always save the status of the target in the last 5 minutes. The trajectory features include the following information: the initial point, center point, moving displacement, and moving distance of the target's trajectory in the last 5 minutes; Step 6: Determine whether the ratio of the target's moving distance and moving displacement in the last 5 minutes is less than the threshold. The moving distance displacement ratio can effectively determine whether the target is traveling normally. If the moving distance displacement ratio is too large, it means that the target may be turning or moving in a circle. This step finds the trajectory less than the threshold in order to find the target ship traveling normally. Step 7: To meet the goal of step 6, start traversing each dumping area in the dumping area list, obtain the position coordinates of the center point of the dumping area through the method provided by JTS, and calculate the vector line angle between the line connecting the starting point to the center point of the trajectory and the line connecting the starting point of the trajectory to the center point of the dumping area in the target's trajectory characteristics in the last 5 minutes, recorded as α; Step 8: Determine whether the value of α is less than the threshold. If it is less than the threshold, it means that the target ship is heading towards the dumping area. Mark the state that the target ship is approaching the dumping area, and continuously update and save the trajectory characteristics of the target ship in the last 5 minutes and the position coordinate point closest to the dumping area for subsequent calculations; Step 9: Continue to determine the value of α. When the value of α is greater than the preset threshold, it means that the target ship is moving away from the dumping area. At this time, determine whether the target ship is too close to the dumping area. If so, start the next step of calculation. Step 10: Take out the line between the starting point and the center point of the trajectory within 5 minutes when the target vessel approaches the dumping area saved in step 8, and the line between the starting point and the center point of the trajectory within 5 minutes when the target vessel starts to move away from the dumping area, and calculate the angle between the two vector lines, which is recorded as β; Step 11: When the β value is greater than the preset threshold, it means that the target has turned back. At this time, the coordinate point of the target closest to the center of the dumping area saved in step 8 is taken out to determine the inclusion relationship between the coordinate point and the dumping area. If the dumping area contains the coordinate point, it means that the target has entered the dumping area and performed normal dumping behavior. If the coordinate point is not contained in the dumping area, it means that the target has turned back before entering the designated dumping area. There is a possibility that the target has not entered the designated dumping area for dumping. At this time, an alarm data is pushed to Kafka; Step 12: Subsequent programs consume the alarm data in Kafka and perform corresponding alarm processing; Step 13: During the alarm generation process, the movement trajectory of the entire target is accurately identified through the above algorithm process. The target turns back in advance before entering the waste dumping area, and there is a possibility of premature dumping.

2. The method for identifying premature dumping behavior based on big data and multi-source information fusion technology as claimed in claim 1, characterized in that: Step 1: Target point data can be obtained from AIS, radar, and Beidou.

3. The method for identifying premature dumping behavior based on big data and multi-source information fusion technology as claimed in claim 1, characterized in that: In step 2, the fixed targets filtered out are buoys, lighthouses, and navigation aids at sea, and the stray targets filtered out are false targets such as sea clutter identified by the radar.

4. The method for identifying premature dumping behavior based on big data and multi-source information fusion technology as claimed in claim 1, characterized in that: In step 5, the center point is the centroid of the trajectory.

5. The method for identifying premature dumping behavior based on big data and multi-source information fusion technology as claimed in claim 1, characterized in that: In step 6, the default threshold is 1.3, which can be configured through parameters.

6. The method for identifying premature dumping behavior based on big data and multi-source information fusion technology as claimed in claim 1, characterized in that: In step eight, the default setting of the threshold is 15°, which can be configured through parameters.

7. The method for identifying premature dumping behavior based on big data and multi-source information fusion technology as claimed in claim 1, characterized in that: In step nine, the default setting of the threshold is 165°, which can be configured through parameters.

8. The method for identifying premature dumping behavior based on big data and multi-source information fusion technology as claimed in claim 1, characterized in that: In step 11, the default setting of the threshold is 145°, which can be configured through parameters.

Images