CN115203463A - Method and system for identifying sea swimming behavior based on multi-sense data fusion - Google Patents
Method and system for identifying sea swimming behavior based on multi-sense data fusion Download PDFInfo
- Publication number
- CN115203463A CN115203463A CN202210903536.9A CN202210903536A CN115203463A CN 115203463 A CN115203463 A CN 115203463A CN 202210903536 A CN202210903536 A CN 202210903536A CN 115203463 A CN115203463 A CN 115203463A
- Authority
- CN
- China
- Prior art keywords
- target
- thermal imaging
- sea
- millimeter wave
- detection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000009182 swimming Effects 0.000 title claims abstract description 64
- 238000000034 method Methods 0.000 title claims abstract description 40
- 230000004927 fusion Effects 0.000 title claims abstract description 24
- 238000001514 detection method Methods 0.000 claims abstract description 96
- 238000001931 thermography Methods 0.000 claims abstract description 61
- 239000013074 reference sample Substances 0.000 claims abstract description 29
- 238000006073 displacement reaction Methods 0.000 claims abstract description 27
- 239000000523 sample Substances 0.000 claims description 29
- 238000005259 measurement Methods 0.000 claims description 7
- 238000003384 imaging method Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 208000034699 Vitreous floaters Diseases 0.000 claims description 4
- 230000005855 radiation Effects 0.000 abstract description 3
- 230000006399 behavior Effects 0.000 description 69
- 238000010586 diagram Methods 0.000 description 12
- 238000004458 analytical method Methods 0.000 description 10
- 230000000694 effects Effects 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 238000011897 real-time detection Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000012937 correction Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/48—Thermography; Techniques using wholly visual means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Library & Information Science (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The application provides a method and a system for identifying a swimming behavior at sea based on multi-sense data fusion, which comprise the following steps: s1, acquiring and analyzing thermal imaging detection data and millimeter wave detection data; s2, judging whether the target distances of thermal imaging detection and millimeter wave detection are consistent, and continuing the identification process if the target distances of thermal imaging detection and millimeter wave detection are consistent; s3, analyzing the displacement speed of the target according to the millimeter wave detection data, and if the speed exists, continuing the identification process; s4, calculating the actual size of the target according to the thermal imaging detection data, comparing the actual size with a reference sample database, if the difference is smaller than a set threshold value, judging that the target is a sea swimming behavior, and outputting an alarm; and S5, comparing the displacement speed and the actual size with the type of the sea swimming behavior in the reference sample database, and judging the type of the sea swimming behavior. According to the scheme, the identification mode of judging the swimming behavior by detecting the heat radiation source at sea only by means of thermal imaging is improved, and the effective degree of the swimming behavior identification detection is improved.
Description
Technical Field
The application belongs to the technical field of image target identification, and particularly relates to a method and a system for identifying a swimming behavior at sea based on multi-perception data fusion.
Background
The coastal region of China is closely separated from other regions of China, and crosses the sea by means of tools such as raft boats, surfboards, swim rings and the like, so that the illegal event of entering and exiting the border line from the sea often occurs. At present, the detection and identification means for the ship target on the sea surface are mature, but the detection technology for the swimming behavior still needs to be improved.
There are two main techniques for detection and identification of a swimming behavior in the prior art. One method is that a long-focus zooming high-definition visible light camera is deployed at the front-end seaside, a key control area is divided through the intrusion detection technology of a video image of the visible light camera, when a moving target enters an alert area, an alarm is triggered to return to the back end, characteristics of the target are extracted and compared with a database model, then the target is selected out in a picture, the moving target is selected through continuous and repeated extraction and detection of real-time video streams, and the detection mode is biased to static detection. The problem of this mode lies in only being applicable to daytime, can't survey and discern under the low condition of ambient brightness evening, can't rotate through the automation of camera moreover and patrol and examine and realize the target detection, for the long key management and control coastline of control, need deploy a plurality of cameras, and the cost is higher. The other is to deploy a thermal imaging camera at the front end, detect a marine infrared radiation source and generate an early warning signal to prompt the back end. The problem of this mode lies in only detecting the heat source, and the number of false positives is too much, and the rear-end personnel efficiency of handling is lower.
Disclosure of Invention
In order to solve the above problem, a first aspect of the present application provides a method for identifying a cross behavior at sea based on fusion of multiple sensing data, including the following steps:
s1, acquiring and analyzing thermal imaging detection data and millimeter wave detection data;
s2, judging whether the target distances of thermal imaging detection and millimeter wave detection are consistent, and continuing the identification process if the target distances of thermal imaging detection and millimeter wave detection are consistent;
s3, analyzing the displacement speed of the target according to the millimeter wave detection data, and if the speed exists, continuing the identification process;
s4, calculating the actual size of the target according to the thermal imaging detection data, comparing the actual size with a reference sample database, if the difference is smaller than a set threshold value, judging that the target is a sea swimming behavior, and outputting an alarm;
and S5, comparing the displacement speed and the actual size with the type of the sea swimming behavior in the reference sample database, and judging the type of the sea swimming behavior.
According to the scheme, data acquired by two types of sensors are fused and compared to obtain the actual size, the displacement speed and the distance of the relative equipment of a target, the actual size, the displacement speed and the distance of the relative equipment of the target are compared and analyzed with characteristic behavior data samples of a database reference comparison sample, and when all data are within a threshold range, the fact that people in the sea area swim across is judged, so that the early warning prompt rear end is generated; and simultaneously, prompting the corresponding alarm behavior sample type according to the size of the behavior target close to which sample of the database. According to the scheme, the identification mode of detecting and judging the swimming behavior of the marine thermal radiation source by purely relying on thermal imaging is improved, the effective degree of the swimming behavior identification and detection is improved, and all-weather detection and early warning of the swimming behavior of the marine illegal swimming across the boundary line can be efficiently realized.
Further, whether the target distances are consistent or not is judged according to a distance deviation conversion formula B multiplied by B% = C multiplied by C%, wherein B is a target distance of thermal imaging detection, B% is a thermal imaging-satellite distance deviation, C is a target distance of millimeter wave detection, and C% is a millimeter wave-satellite distance deviation; b% and c% are determined by satellite positioning measurement distances of the introduced samples,namely: a. The 0 ＝B 0 ×b％＝C 0 X c% where A 0 Measuring distances for satellite positioning of target samples, B 0 Detecting the distance for thermal imaging of the target sample, C 0 The millimeter wave detection distance of the target sample. Whether the targets detected by the thermal imaging sensing data and the millimeter wave sensing data are consistent or not can be confirmed in an auxiliary mode through the distance deviation conversion formula, and errors generated in the using process of the equipment can be found and corrected in time. Preferably, within a distance segment, b%, c% are fixed values. According to different distances, the deviation percentage can also change along with the distance, and a distance section and a corresponding percentage relation are fixed through the discrete distribution of two measured distances, so that the distance measurement error can be reduced.
Further, the actual size of the target is calculated according to the following formula:
D＝n×L×IFOV
wherein, D is the actual size of the target, n is the number of pixels occupied by the target in the imaging of the focal plane, L is the target distance, IFOV is the spatial resolution, IFOV = D/f, wherein D is the pixel size of thermal imaging, and f is the focal length value corresponding to the target.
Further, the construction of the reference sample database comprises the steps of collecting sample data of the sea swimming behavior, wherein the data comprise sample size, the number of occupied pixel points and the sample distance in imaging of a sample focal plane detected by thermal imaging, and the sample displacement speed and the sample distance detected by millimeter waves.
Further, the types of the sea swimming behavior in the reference sample database include a human belt float, a human head, and a human. The classification is established based on the historical case analysis, and is more in line with the actual detection situation.
In a second aspect, the application provides a system for identifying a cross behavior at sea based on fusion of multiple sensing data, comprising:
the target detection module is configured to acquire and analyze thermal imaging detection data and millimeter wave detection data;
the target comparison module is configured to judge whether the target distances of the thermal imaging detection and the millimeter wave detection are consistent, and if so, the identification process is continued;
the displacement speed judging module is configured for analyzing the displacement speed of the target according to the millimeter wave detection data, and if the speed exists, the identification process is continued;
the actual size calculation module is configured to calculate the actual size of the target according to the thermal imaging detection data, compare the actual size with a reference sample database, and if the difference is smaller than a set threshold, determine that the target is a sea swimming behavior, and output an alarm;
and the target type judgment module is configured to compare the displacement speed and the actual size with the type of the sea swimming behavior in the reference sample database, and judge the type of the sea swimming behavior.
Further, a thermal imaging camera and a millimeter wave sensor are arranged in the target detection module. Preferably, the thermal imaging camera and the millimeter wave sensor are integrated in the same holder shield, so that the workload of azimuth calibration in the construction process can be reduced, and the consistency of the detection azimuth and the target behavior of the two sensing devices is ensured.
Furthermore, 2 thermal imaging cameras are configured in the target detection module, and the target can be searched and sensed in two distance ranges at the same time.
According to the scheme, the millimeter wave sensor of the active detection device and the thermal imaging camera of the passive detection device are integrated into the cloud deck front-end device to conduct sea area real-time detection, after a suspicious target is sensed, the collected original data are transmitted back to the rear-end platform, usable data are obtained through protocol analysis, the usable data are calculated and compared with a reference sample, whether the behavior is a swimming behavior or not is judged, and alarm information is generated to prompt a manager if the behavior is a swimming behavior.
According to the invention, the target data collected by the front-end active and passive detection equipment are converged and combined, so that the all-weather identification rate of the swimming across behavior of the sea is realized. The two sensors are not influenced by the ambient brightness, and can realize the real-time detection of unattended operation day and night, thereby achieving the goal of reducing personnel and increasing efficiency. The accuracy rate of the identification of the swimming behavior can be improved by combining the advantages of the two sensors, and the target can be well identified for the environment with complex sea conditions.
Drawings
The accompanying drawings assist in a further understanding of the present application. For convenience of description, only portions related to the related invention are shown in the drawings.
Fig. 1 is a flowchart of a method for identifying a cross behavior at sea based on fusion of multiple sensing data according to an embodiment;
fig. 2 is a schematic diagram illustrating a configuration of a sea swimming behavior identification system based on multi-sense data fusion in an embodiment;
FIG. 3 is a physical diagram of a behavior data acquisition pan-tilt for acquiring thermal imaging detection data and millimeter wave detection data according to an embodiment;
fig. 4 is a schematic flow chart illustrating a comparison process of the comparison reference sample database of the swimming across behavior in the embodiment;
FIG. 5 is a schematic diagram illustrating a comparison analysis process for detecting the real-time cross behavior in one embodiment;
FIG. 6 is a diagram illustrating the human detection and identification effect in one embodiment;
FIG. 7 is a diagram illustrating the detection and identification of a person with a floating object according to an embodiment;
FIG. 8 is a diagram illustrating human head detection and recognition effects according to an embodiment;
fig. 9 is a schematic structural diagram of the sea swimming behavior identification system based on the multi-sense data fusion in the embodiment.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention.
Fig. 1 is a flowchart of a method for identifying a swimming across sea based on multi-sense data fusion according to an embodiment of the present invention, where the method includes the following steps:
s1, acquiring and analyzing thermal imaging detection data and millimeter wave detection data;
s2, judging whether the target distances of thermal imaging detection and millimeter wave detection are consistent, and continuing the identification process if the target distances of thermal imaging detection and millimeter wave detection are consistent;
s3, analyzing the displacement speed of the target according to the millimeter wave detection data, and if the speed exists, continuing the identification process;
s4, calculating the actual size of the target according to the thermal imaging detection data, comparing the actual size with a reference sample database, if the difference is smaller than a set threshold value, judging that the target is a sea swimming behavior, and outputting an alarm;
and S5, comparing the displacement speed and the actual size with the type of the sea swimming behavior in the reference sample database, and judging the type of the sea swimming behavior.
Fig. 2 is a schematic diagram of a cross behavior recognition system at sea based on fusion of multiple sensing data according to an embodiment of the present invention, which includes an integrated behavior data sensing pan/tilt integrated with a thermal imaging camera and a millimeter wave sensor, a cross behavior detection module, and a comparison reference sample database.
Fig. 3 is a physical diagram of the behavior data acquisition holder for acquiring thermal imaging detection data and millimeter wave detection data in this embodiment. In the scheme implementation process, the orientation calibration needs to be carried out on the orientations of the thermal imaging camera and the millimeter wave sensor, the consistency of the detection orientations of the two sensing devices and the target behavior is ensured, and the thermal imaging camera and the millimeter wave sensor are integrated in the same holder shield for reducing the workload of the orientation calibration in the construction process. In this embodiment, 2 thermal imaging cameras are arranged, and the sea area in two distance ranges can be searched and the target can be sensed at the same time.
The detection module for the swimming behavior is composed of a thermal imaging video image processing unit, a millimeter wave sensor for analyzing the orientation information and the relative displacement speed of the behavior target, a behavior target attribute fusion judging unit and the like.
When the system is deployed for the first time, a comparison reference sample database of the swimming behavior needs to be established. Fig. 4 is a schematic diagram of a process of establishing a comparison reference sample database of the swimming behavior. Collecting video samples with a swimming behavior aiming at a marine application scene, and detecting targets in the video by adopting thermal imaging and millimeter waves. The number of occupied pixel points and the sample distance in imaging of a sample focal plane can be obtained by analyzing thermal imaging detection data, and the sample displacement speed and the sample distance can be obtained by analyzing millimeter wave detection data through a data protocol of the millimeter wave sensor. And according to the displacement speed corresponding to the test behavior target in the video data, the size of the pixel points occupied in the thermal imaging picture and the actual size of the actually measured target, a reference sample database can be constructed. The known swimming behavior is generally performed purely by swimming or with floaters by the history case analysis, and therefore, in the preferred embodiment, the reference sample database includes three types of "buoy" (human floaters), "head" (human head), and "person".
In the preferred embodiment, in the process of establishing the sample library, the target relative equipment distance is calculated secondarily because the thermal imaging camera detects that the target distance is deviated from the millimeter wave radar detection distance. The calculation method comprises the steps of introducing a high-precision satellite positioning measurement distance A as a comparison sample, analyzing a thermal imaging measurement distance B and satellite data deviation B thereof, a millimeter wave measurement distance C and satellite data deviation C thereof, and obtaining a distance deviation conversion formula, namely A = B × B% = C × C%. The deviation percentage will change with the distance, and the distance measurement error can be reduced by fixing a distance segment and the corresponding percentage relation through the discrete distribution of the distance measured by the two devices. The formula can assist in confirming whether the thermal imaging sensor and the millimeter wave sensor detect the target in accordance.
Fig. 5 is a schematic diagram of a comparison analysis process for detecting the real-time swimming across behavior in an embodiment. In this embodiment, after the pan-tilt detects a heat source target, the spatial resolution IFOV = d/f is calculated according to a focal length value f corresponding to the target and a pixel size d of thermal imaging; and calculating the actual size D = n multiplied by L multiplied by IFOV = (n multiplied by L multiplied by D)/f of the target according to the distance L between the behavior target and the holder and the spatial resolution IFOV, wherein the number n of pixel points occupied by each target in the imaging of the focal plane. The actual distance L of the behavior target relative to the pan/tilt head can be obtained by the distance a calculated by the distance deviation conversion formula in the previous preferred embodiment. Whether the targets detected by the thermal imaging camera and the millimeter wave sensor are consistent or not can be confirmed through the actual distance L, if so, the comparison and analysis are continued by the swimming behavior detection module, and if not, the alarm is given for correction. The relative displacement speed of the target is obtained by analyzing the original data acquired by the millimeter wave sensor through a corresponding equipment data protocol, and if the target has no displacement speed, the target may be a fixed buoy or reef on the sea, so that the target is firstly excluded.
The method comprises the steps of obtaining a plurality of original data of the same target through passive sensing of a thermal imaging camera and active sensing of millimeter waves, conducting multi-dimensional fusion, analysis, calculation and analysis on the original data through the steps to obtain behavior characteristic data comprising the relative displacement speed of the behavior target, the actual size of the behavior target and the like, conducting comparison analysis on the behavior characteristic data samples and characteristic behavior data samples of a reference comparison sample database, and judging that people cross the sea area when all data are within a threshold range, so that the rear end of an early warning prompt is generated.
In a preferred embodiment, the comparison with different types of swimming behaviors in the reference sample database can be performed to judge the type of the target behavior sample, and the corresponding alarm is displayed for the target in the middle of the real-time preview picture, and fig. 6 to 8 are graphs of detection and identification effects of people, human floaters and human heads respectively. If a swimming behavior occurs but is not detected, the respective data of the behavior target are updated manually into the reference sample library.
Fig. 9 is a schematic diagram of a system structure 900 for identifying the cross behavior of the sea based on the fusion of the multi-sense data according to an embodiment of the present invention, which includes,
an object detection module 901 configured to acquire and analyze thermal imaging detection data and millimeter wave detection data;
a target comparison module 902, configured to determine whether target distances of thermal imaging detection and millimeter wave detection are consistent, and if so, continue to identify the process;
a displacement speed judgment module 903, configured to analyze the displacement speed of the target according to the millimeter wave detection data, and if there is a speed, continue the identification process;
the actual size calculation module 904 is configured to calculate an actual size of the target according to the thermal imaging detection data, compare the actual size with a reference sample database, determine that the target is a sea swimming behavior if the difference is smaller than a set threshold, and output an alarm;
the target type determination module 905 is configured to compare the displacement speed and the actual size with a type of the marine swimming behavior in the reference sample database, and determine the type of the marine swimming behavior.
According to the method and the device, the comparison reference sample database of the swimming behavior is established by collecting sample data through the integrated cradle head, and the comparison analysis is carried out on the comparison reference sample database and the characteristic data of the behavior target of thermal imaging passive detection and millimeter wave active real-time detection, so that the effect of automatic identification and early warning of the swimming behavior is achieved.
While this application has been particularly shown and described with references to preferred embodiments thereof, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the application as defined by the appended claims.
Claims (10)
1. The method for identifying the cross behavior of the sea based on the multi-sense data fusion is characterized by comprising the following steps of:
s1, acquiring and analyzing thermal imaging detection data and millimeter wave detection data;
s2, judging whether the target distances of thermal imaging detection and millimeter wave detection are consistent, and continuing the identification process if the target distances of thermal imaging detection and millimeter wave detection are consistent;
s3, analyzing the displacement speed of the target according to the millimeter wave detection data, and if the speed exists, continuing the identification process;
s4, calculating the actual size of the target according to the thermal imaging detection data, comparing the actual size with a reference sample database, judging that the target swims across the sea if the difference is smaller than a set threshold value, and outputting an alarm;
and S5, comparing the displacement speed and the actual size with the type of the sea swimming behavior in the reference sample database, and judging the type of the sea swimming behavior.
2. The sea crossing behavior based on the multi-sense data fusion of claim 1The identification method is characterized in that whether the target distances are consistent or not is judged in S2 according to a distance deviation conversion formula B multiplied by B% = C multiplied by C%, wherein B is the target distance of thermal imaging detection, B% is thermal imaging-satellite distance deviation, C is the target distance of millimeter wave detection, and C% is millimeter wave-satellite distance deviation; b% and c% are determined by the satellite positioning measurement distance of the incoming sample, i.e.: a. The 0 ＝B 0 ×b％＝C 0 X c% where A 0 Measuring distances for satellite positioning of target samples, B 0 Detection distance for thermal imaging of target sample, C 0 The millimeter wave detection range of the target sample.
3. The method for identifying the sea swimming behavior based on the multi-sense data fusion of claim 2, wherein b% and c% are fixed values in a distance segment.
4. The method for identifying a sea swimming behavior based on multi-sense data fusion according to claim 1, wherein the actual size of the target is calculated in S4 according to the following formula:
D＝n×L×IFOV
and D is the actual size of the target, n is the number of pixel points occupied by the target in the imaging of the focal plane, L is the target distance, IFOV is the spatial resolution, and IFOV = D/f, wherein D is the pixel size of thermal imaging, and f is the focal length value corresponding to the target.
5. The method for identifying the cross swimming behavior based on the fusion of the multi-sensing data according to claim 1, wherein the constructing of the reference sample database comprises collecting sample data of the cross swimming behavior, the data comprising a sample size, the number of occupied pixel points and a sample distance in imaging of a sample focal plane detected by thermal imaging, and a sample displacement speed and a sample distance detected by millimeter waves.
6. The method for identifying sea swimming behavior based on multi-sense data fusion of claim 1, wherein the types of sea swimming behavior in the reference sample database comprise human floaters, human head and human.
7. A sea swimming behavior identification system based on multi-sense data fusion, characterized by comprising:
the target detection module is configured to acquire and analyze thermal imaging detection data and millimeter wave detection data;
the target comparison module is configured to judge whether the target distances of the thermal imaging detection and the millimeter wave detection are consistent, and if so, the identification process is continued;
the displacement speed judging module is configured for analyzing the displacement speed of the target according to the millimeter wave detection data, and if the speed exists, the flow is continuously identified;
the actual size calculation module is configured to calculate the actual size of the target according to the thermal imaging detection data, compare the actual size with a reference sample database, and if the difference is smaller than a set threshold, determine that the target is a sea swimming behavior, and output an alarm;
and the target type judging module is configured to compare the displacement speed and the actual size with the type of the sea swimming behavior in the reference sample database, and judge the type of the sea swimming behavior.
8. The system for identifying sea swimming behavior based on multi-sensing data fusion according to claim 7, wherein the target detection module is configured with a thermal imaging camera and a millimeter wave sensor.
9. The multi-sensing data fusion based sea swimming behavior identification system according to claim 8, wherein the thermal imaging camera and the millimeter wave sensor are integrated in the same pan-tilt shield.
10. The system for identifying sea swimming behavior based on multi-sense data fusion of claim 7, wherein the object detection module is configured with 2 thermal imaging cameras.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210903536.9A CN115203463A (en) | 2022-07-28 | 2022-07-28 | Method and system for identifying sea swimming behavior based on multi-sense data fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210903536.9A CN115203463A (en) | 2022-07-28 | 2022-07-28 | Method and system for identifying sea swimming behavior based on multi-sense data fusion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115203463A true CN115203463A (en) | 2022-10-18 |
Family
ID=83583222
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210903536.9A Pending CN115203463A (en) | 2022-07-28 | 2022-07-28 | Method and system for identifying sea swimming behavior based on multi-sense data fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115203463A (en) |
-
2022
- 2022-07-28 CN CN202210903536.9A patent/CN115203463A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111523465B (en) | Ship identity recognition system based on camera calibration and deep learning algorithm | |
| US20210073573A1 (en) | Ship identity recognition method based on fusion of ais data and video data | |
| CN110414396B (en) | Unmanned ship perception fusion algorithm based on deep learning | |
| US7889232B2 (en) | Method and system for surveillance of vessels | |
| CN105306892B (en) | A kind of generation of ship video of chain of evidence form and display methods | |
| KR101798396B1 (en) | The monitoring systems for Marine aquaculture and a shaft aligning method of the cameras | |
| CN111045000A (en) | Monitoring system and method | |
| CN111435081B (en) | Sea surface measuring system, sea surface measuring method and storage medium | |
| CN113591592B (en) | Overwater target identification method and device, terminal equipment and storage medium | |
| CN110517280A (en) | System is monitored based on infrared identification ship tail gas | |
| CN115184917A (en) | Regional target tracking method integrating millimeter wave radar and camera | |
| CN115035470A (en) | Low, small and slow target identification and positioning method and system based on mixed vision | |
| CN116453276A (en) | Marine wind power electronic fence monitoring and early warning method and system | |
| CN117075112A (en) | Unmanned ship radar photoelectric fusion method for azimuth track matching | |
| CN114401354A (en) | Intelligent control method and system for over-the-horizon monitoring of offshore ship | |
| CN109785562B (en) | Vertical photoelectric ground threat alert system and suspicious target identification method | |
| CN114998846A (en) | Method and system for realizing intelligent system of offshore drilling platform and related components | |
| JP3443106B2 (en) | Floating object detection / monitoring method and device | |
| CN117173215A (en) | Inland navigation ship whole-course track identification method and system crossing cameras | |
| CN116935551A (en) | Perimeter intrusion detection method, system, equipment and storage medium | |
| CN115203463A (en) | Method and system for identifying sea swimming behavior based on multi-sense data fusion | |
| CN116469276A (en) | Water area safety early warning method, device, equipment and storage medium | |
| JP6894356B2 (en) | Ship tracking system | |
| CN114219825A (en) | Target contact force tracking method and system under multiple photoelectric distributed deployments | |
| CN115909285A (en) | Radar and video signal fused vehicle tracking method |
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 |