CN112307805A - Automatic identification method for offshore targets - Google Patents

Automatic identification method for offshore targets Download PDF

Info

Publication number
CN112307805A
CN112307805A CN201910675710.7A CN201910675710A CN112307805A CN 112307805 A CN112307805 A CN 112307805A CN 201910675710 A CN201910675710 A CN 201910675710A CN 112307805 A CN112307805 A CN 112307805A
Authority
CN
China
Prior art keywords
signal source
signal
data
matching
target
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
Application number
CN201910675710.7A
Other languages
Chinese (zh)
Other versions
CN112307805B (en
Inventor
郭伟清
谢云云
黄详淇
刘琳
谷志强
李德正
杨正婷
殷明慧
卜京
张俊芳
姚娟
邹云
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing University of Science and Technology
Original Assignee
Nanjing University of Science and Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Nanjing University of Science and Technology filed Critical Nanjing University of Science and Technology
Priority to CN201910675710.7A priority Critical patent/CN112307805B/en
Publication of CN112307805A publication Critical patent/CN112307805A/en
Application granted granted Critical
Publication of CN112307805B publication Critical patent/CN112307805B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/02—Preprocessing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/08—Feature extraction
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/12—Classification; Matching
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/07—Target detection

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Signal Processing (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Navigation (AREA)
  • Traffic Control Systems (AREA)
  • Radar Systems Or Details Thereof (AREA)

Abstract

The invention discloses an automatic identification method for an offshore target. The method comprises the following steps: firstly, filtering marine target signal data; then identifying the motion track of the marine target; then, according to the obtained signal source data, matching signal source names in a signal source database; and finally, identifying the signal source on the same track, matching the corresponding name, and matching the corresponding ship according to the name of the signal source. According to the marine target signal source data acquired by each sensor, the marine target automatic identification method is realized, the marine target is automatically identified and matched to a specific ship, and the identification and matching results are subjected to credibility analysis, so that the marine target automatic identification method has the advantages of high identification speed, high result credibility, simple flow and convenience in application.

Description

Automatic identification method for offshore targets
Technical Field
The invention belongs to the technical field of target identification, and particularly relates to an automatic identification method for a marine target.
Background
The territory is an enemy which is inviolable by the holy of the country, and the monitoring and the defense of potential danger to the territory are effective guarantee of the safety of the territory. The marine monitoring is the first step of marine defense, and mainly detects, tracks and identifies targets on the sea, and monitors the fighting action of marine enemies when necessary. The monitoring objects on the sea comprise underwater targets, air and water surfaces, such as various submarines in water, various airplanes in the air, various ships on the water surface and the like.
In the later 70 s of the 20 th century, people put forward an information fusion concept based on multiple sensors, the information fusion concept is a modern processing technology formed by effectively combining sensors, image signal processing, computer simulation and artificial intelligence, information (touch, image, taste and sound) sensed by human sensing organs (four limbs, eyes, nose and ears) is effectively simulated, and then the information is comprehensively analyzed by using priori knowledge, so that the aim of effectively and reliably analyzing and judging the surrounding strange environment is fulfilled. Various ships are the main bodies of marine targets, and during the navigation process of the ships, various electromagnetic signals can be transmitted or reflected at different time points based on requirements of navigation, positioning, communication and the like, and the signals are received by the sensors and become the main basis for identifying the identity of the targets.
The signal sources of electromagnetic signals can be classified into four types, i.e., R type, L1 type, L2 type, and a type, and there are four types of sensors for receiving these signals. The signal data provided by the sensors comprises two parts of time-space position information and signal characteristic information, wherein the time-space position information refers to dynamic parameters for describing the motion state of a target, and comprises position (longitude and latitude, height), speed, acceleration, parameters relative to a ship and the like; signal characteristic information refers to pertinent information that helps establish the identity of a target. Data having the same "signal source lot" are from the same signal source, and their space-time location information includes "time", "longitude", and "latitude", and signal characteristic information includes "L1A _ 1", "L1A _ 2", and "L1A _ 3".
The existing Shanghai target automatic identification technology mainly adopts the steps of firstly fusing data and then analyzing and judging the fused data to finally obtain a corresponding target identification result and credibility.
Disclosure of Invention
The invention aims to provide the offshore target automatic identification method which is high in identification speed, high in result reliability, simple in process and convenient to apply.
The technical solution for realizing the purpose of the invention is as follows: an automatic identification method for offshore targets comprises the following steps:
step 1, filtering marine target signal data;
step 2, identifying the motion track of the marine target;
step 3, matching signal source names in a signal source database according to the acquired signal source data;
and 4, identifying the signal source on the same track, matching the corresponding name, and matching the corresponding ship according to the name of the signal source.
Further, the filtering processing on the marine target signal data in step 1 is specifically as follows:
step 1.1, establishing a sampling data queue with the length of N by using continuous sampling data of an offshore target, removing the first data of the sampling data queue after a new measurement, sequentially moving the rest N-1 data forwards, and taking the new sampling data as the tail data of the new sampling data queue;
step 1.2, processing the signal of the new sampling data queue, and taking the processing result as the result of the measurement;
in signal processing, a Moving Average Filter (Moving Average Filter) is used for denoising, and the calculation formula of the Moving Average Filter is as follows:
Figure BDA0002143202940000021
wherein y (n) is an output signal; x (n) is an input signal; n is the input data length.
Further, the motion trajectory of the marine target is identified in step 2, which specifically includes:
step 2.1, calculating time screening threshold aTmin：
(2.1.1) calculating the sampling time interval of the signal sources with the same batch number and recording the minimum time interval TiWherein i is 1,2, … n, n is the total number of signal sources with different batch numbers;
(2.1.2) comparing the minimum sampling time intervals T of signal sources of different batchesiObtaining the minimum sampling time interval T among signal sources of different batchesmin；
(2.1.3) minimum sampling time interval T to be obtainedminMultiplying by a coefficient a to obtain a time screening threshold aTmin；
Step 2.2, calculating longitude and latitude screening threshold value aTminSmax：
(2.2.1) calculating the change rate of longitude and latitude data of the signal source of the same batch number along with the time and recording the change rate as SiWherein i is 1,2, … n, n is the total number of signal sources with different batch numbers;
(2.2.2) comparing the change rate S of the longitude and latitude data of signal sources of different batches along with timeiObtaining different batchesMaximum value S of longitude and latitude degree change rate in signal sourcemax；
(2.2.3) obtaining the maximum value S of the longitude and latitude change ratemaxMultiplied by a temporal screening threshold aTminObtaining the latitude and longitude screening threshold value aTminSmax；
Step 2.3, screening the threshold aT according to timeminAnd latitude and longitude screening threshold value aTminSmaxAnd judging whether points with the same space-time information exist in the two groups of signal sources, if the points with the same space-time information exist, calculating the moving speed of the two signal sources, and if the speeds of the two signal sources are equal, determining that the two groups of signal sources belong to the same track.
Further, the matching of the signal source name in the signal source database according to the acquired data of each signal source in step 3 is as follows:
step 3.1, setting the matching times i to be 1;
step 3.2, extracting each characteristic data of the ith target class A, comparing the characteristic data with each data in the signal source database, recording the name of the signal source if the matching is successful, and adding 1 to the matching times;
step 3.3, if the matching times i are less than the total target number, i is equal to i +1, and the step 3.2 is returned; otherwise, entering step 3.4;
step 3.4, inquiring whether the matching result is one-to-one matching, if so, successfully matching; otherwise, changing the matching rule and re-matching.
Further, the signal source on the same track is identified and the corresponding name is matched in step 4, and the corresponding ship is matched according to the signal source name, which specifically includes the following steps:
step 4.1, matching signal source names according to signal source data on the same track;
4.2, matching the corresponding target ship name in a target database according to the signal source name;
step 4.3, evaluating the accuracy P of target identification according to the number of signal sources of a target and the number of signal source name matches, wherein the formula is as follows:
Figure BDA0002143202940000031
compared with the prior art, the invention has the following remarkable advantages: (1) according to the marine target signal source data acquired by each sensor, the automatic identification of the marine target is realized, the marine target is automatically identified and matched with a specific ship, and the identification speed is high; (2) credibility analysis is carried out on the identification and matching results, the result credibility is high, accurate identification of ships is achieved, the process is simple, and application is convenient.
Drawings
Fig. 1 is a schematic flow chart of the offshore object automatic identification method of the present invention.
FIG. 2 is a schematic flow chart of the time screening threshold value calculation according to the present invention.
FIG. 3 is a schematic diagram of a process for calculating latitude and longitude screening threshold values according to the present invention.
Fig. 4 is a schematic flow chart of a signal source identification algorithm according to the present invention.
FIG. 5 is a schematic flow chart of a model algorithm in the present invention.
Detailed Description
The invention is described in further detail below with reference to the figures and specific examples.
With reference to fig. 1, the method for automatically identifying an offshore object of the present invention includes the following steps:
step 1, filtering marine target signal data, specifically as follows:
step 1.1, establishing a sampling data queue with the length of N by using continuous sampling data of an offshore target, removing the first data of the sampling data queue after a new measurement, sequentially moving the rest N-1 data forwards, and taking the new sampling data as the tail data of the new sampling data queue;
step 1.2, processing the signal of the new sampling data queue, and taking the processing result as the result of the measurement;
when in signal processing, a moving average filter is adopted for denoising, and the calculation formula of the moving average filter is as follows:
Figure BDA0002143202940000041
wherein y (n) is an output signal; x (n) is an input signal; n is the input data length.
And 2, identifying the motion trail of the marine target, wherein the space-time position information of the same signal source can form a motion trail, and the motion trails of different signal sources are possibly consistent, so that the motion trails belong to the same target. To determine which signal sources belong to the same target, it is necessary to determine whether the positioning information (time, longitude, latitude) of the signal sources are consistent.
Firstly, time judgment is carried out, a proper time length is selected according to the time interval of sampling points, when the time interval of samples in two batches of signal sources is smaller than the time length, the difference of the longitude and latitude of the two samples is considered, if the difference of the longitude and latitude meets a small enough range, the two sample points are considered to be positioned at the same position of the same time, if a plurality of groups of data in a plurality of batches of signal sources meet the condition, the two samples can be judged to belong to the same target, and the specific following steps are carried out:
step 2.1, calculating time screening threshold aTminThe specific process is shown in fig. 2:
(2.1.1) calculating the sampling time interval of the signal sources with the same batch number and recording the minimum time interval TiWherein i is 1,2, … n, n is the total number of signal sources with different batch numbers;
(2.1.2) comparing the minimum sampling time intervals T of signal sources of different batchesiObtaining the minimum sampling time interval T among signal sources of different batchesmin；
(2.1.3) minimum sampling time interval T to be obtainedminMultiplying by a coefficient a to obtain a time screening threshold aTmin；
Step 2.2, calculating longitude and latitude screening threshold value aTminSmaxThe specific process is shown in fig. 3:
(2.2.1) calculating longitude and latitude data of signal source of same batch numberRate of change over time and recorded as SiWherein i is 1,2, … n, n is the total number of signal sources with different batch numbers;
(2.2.2) comparing the change rate S of the longitude and latitude data of signal sources of different batches along with timeiObtaining the maximum value S of the longitude and latitude change rate in the signal sources of different batch numbersmax；
(2.2.3) obtaining the maximum value S of the longitude and latitude change ratemaxMultiplied by a temporal screening threshold aTminObtaining the latitude and longitude screening threshold value aTminSmax；
Step 2.3, screening the threshold aT according to timeminAnd latitude and longitude screening threshold value aTminSmaxAnd judging whether points with the same space-time information exist in the two groups of signal sources, if the points with the same space-time information exist, calculating the moving speed of the two signal sources, and if the speeds of the two signal sources are equal, determining that the two groups of signal sources belong to the same track.
Step 3, matching signal source names in a signal source database according to the acquired signal source data, and combining with fig. 4, specifically as follows:
step 3.1, setting the matching times i to be 1;
step 3.2, extracting each characteristic data of the ith target class A, comparing the characteristic data with each data in the signal source database, recording the name of the signal source if the matching is successful, and adding 1 to the matching times;
step 3.3, if the matching times i are less than the total target number, i is equal to i +1, and the step 3.2 is returned; otherwise, entering step 3.4;
step 3.4, inquiring whether the matching result is one-to-one matching, if so, successfully matching; otherwise, changing the matching rule and re-matching.
Step 4, identifying signal sources on the same track, matching corresponding names, and matching corresponding ships according to the signal source names;
according to the method of step 2 and step 3, a plurality of signal sources belonging to the same target (a track) are determined, signal source names are matched according to the data of the signal sources, corresponding target (ship) names are matched in a target database according to the signal source names on the target, and the accuracy of target identification is evaluated according to the number of signal sources and the number of matched signal source names of one target, which is specifically as follows in combination with fig. 5:
step 4.1, matching signal source names according to signal source data on the same track;
4.2, matching the corresponding target ship name in a target database according to the signal source name;
step 4.3, evaluating the accuracy P of target identification according to the number of signal sources of a target and the number of signal source name matches, wherein the formula is as follows:
Figure BDA0002143202940000061
。
example 1
The data types of this embodiment are: the signal sources of electromagnetic signals are classified into four types, i.e., R type, L1 type, L2 type, and a type, and there are four types of sensors that receive these signals, accordingly. The signal data provided by the sensors comprises two parts of time-space position information and signal characteristic information, wherein the time-space position information refers to dynamic parameters for describing the motion state of a target, and comprises position (longitude and latitude, height), speed, acceleration, parameters relative to a ship and the like; signal characteristic information refers to pertinent information that helps establish the identity of a target. The data with the same signal source batch number come from the same signal source, the time-space position information of the data comprises time, longitude and latitude, the signal characteristic information comprises L1A _1, L1A _2 and L1A _3, and the data source is a mathematic modeling website of Nanjing university of science and engineering.
Firstly, whether the signal sources are from the same target or not, namely whether the signal sources belong to the same track or not is determined, and table 1 shows points with the same sampling time among signal sources in batches calculated by the method.
TABLE 1 number of time-coincident signals (partial)
Figure BDA0002143202940000062
After the points with the same sampling time are screened out, whether the sampling points at the moments are at the same position is judged, and the result is shown in table 2:
TABLE 2 number of signals (parts) of position coincidence
Figure BDA0002143202940000071
According to the time and position matching result, the credibility of the two batches of signal sources belonging to the unified target is calculated, and the result is shown in table 3:
TABLE 3 Signal source match confidence (partial results)
Figure BDA0002143202940000072
And extracting the result with the confidence coefficient higher than 0.6 to obtain the signal source batch number set with high matching confidence coefficient.
And obtaining the batch numbers of the signal sources corresponding to the same target, wherein the results are shown in a table 4:
TABLE 4 target matching results
Figure BDA0002143202940000081
This establishes the signal sources belonging to the same target.
Then, according to the signal source data of each target, matching the corresponding signal source name, and according to the signal source name, matching the corresponding target, the result is shown in table 5:
TABLE 5 Ship object recognition results
Figure BDA0002143202940000082
In this way, the corresponding target in the database can be identified from the signal source data acquired by the sensor.
In conclusion, according to the marine target signal source data acquired by each sensor, the marine target is automatically identified and matched with a specific ship, and the identification speed is high; in addition, credibility analysis is carried out on the identification and matching results, the result credibility is high, accurate identification of ships is achieved, the process is simple, and application is convenient.

Claims (5)

1. An automatic identification method for offshore targets is characterized by comprising the following steps:
step 1, filtering marine target signal data;
step 2, identifying the motion track of the marine target;
step 3, matching signal source names in a signal source database according to the acquired signal source data;
and 4, identifying the signal source on the same track, matching the corresponding name, and matching the corresponding ship according to the name of the signal source.
2. The method for automatically identifying an offshore object according to claim 1, wherein the filtering processing is performed on the offshore object signal data in step 1, specifically as follows:
step 1.1, establishing a sampling data queue with the length of N by using continuous sampling data of an offshore target, removing the first data of the sampling data queue after a new measurement, sequentially moving the rest N-1 data forwards, and taking the new sampling data as the tail data of the new sampling data queue;
step 1.2, processing the signal of the new sampling data queue, and taking the processing result as the result of the measurement;
when in signal processing, a moving average filter is adopted for denoising, and the calculation formula of the moving average filter is as follows:
Figure FDA0002143202930000011
wherein y (n) is an output signal; x (n) is an input signal; n is the input data length.
3. The method for automatically identifying offshore targets according to claim 1, wherein the motion trail of the offshore targets identified in the step 2 is as follows:
step 2.1, calculating time screening threshold aTmin：
(2.1.1) calculating the sampling time interval of the signal sources with the same batch number and recording the minimum time interval TiWherein i is 1,2, … n, n is the total number of signal sources with different batch numbers;
(2.1.2) comparing the minimum sampling time intervals T of signal sources of different batchesiObtaining the minimum sampling time interval T among signal sources of different batchesmin；
(2.1.3) minimum sampling time interval T to be obtainedminMultiplying by a coefficient a to obtain a time screening threshold aTmin；
Step 2.2, calculating longitude and latitude screening threshold value aTminSmax：
(2.2.1) calculating the change rate of longitude and latitude data of the signal source of the same batch number along with the time and recording the change rate as SiWherein i is 1,2, … n, n is the total number of signal sources with different batch numbers;
(2.2.2) comparing the change rate S of the longitude and latitude data of signal sources of different batches along with timeiObtaining the maximum value S of the longitude and latitude change rate in the signal sources of different batch numbersmax；
(2.2.3) obtaining the maximum value S of the longitude and latitude change ratemaxMultiplied by a temporal screening threshold aTminObtaining the latitude and longitude screening threshold value aTminSmax；
Step 2.3, screening the threshold aT according to timeminAnd latitude and longitude screening threshold value aTminSmaxAnd judging whether points with the same space-time information exist in the two groups of signal sources, if the points with the same space-time information exist, calculating the moving speed of the two signal sources, and if the speeds of the two signal sources are equal, determining that the two groups of signal sources belong to the same track.
4. The method for automatically identifying an offshore object according to claim 1, wherein the signal source name is matched in the signal source database according to the acquired data of each signal source in step 3, and the method specifically comprises the following steps:
step 3.1, setting the matching times i to be 1;
step 3.2, extracting each characteristic data of the ith target class A, comparing the characteristic data with each data in the signal source database, recording the name of the signal source if the matching is successful, and adding 1 to the matching times;
step 3.3, if the matching times i are less than the total target number, i is equal to i +1, and the step 3.2 is returned; otherwise, entering step 3.4;
step 3.4, inquiring whether the matching result is one-to-one matching, if so, successfully matching; otherwise, changing the matching rule and re-matching.
5. The method for automatically identifying offshore targets according to claim 1, wherein the signal sources on the same track are identified and matched with corresponding names in step 4, and corresponding ships are matched according to the signal source names, specifically as follows:
step 4.1, matching signal source names according to signal source data on the same track;
4.2, matching the corresponding target ship name in a target database according to the signal source name;
step 4.3, evaluating the accuracy P of target identification according to the number of signal sources of a target and the number of signal source name matches, wherein the formula is as follows:
Figure FDA0002143202930000021
。
CN201910675710.7A 2019-07-25 2019-07-25 Automatic identification method for offshore targets Active CN112307805B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910675710.7A CN112307805B (en) 2019-07-25 2019-07-25 Automatic identification method for offshore targets

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910675710.7A CN112307805B (en) 2019-07-25 2019-07-25 Automatic identification method for offshore targets

Publications (2)

Publication Number Publication Date
CN112307805A true CN112307805A (en) 2021-02-02
CN112307805B CN112307805B (en) 2022-09-27

Family

ID=74329198

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910675710.7A Active CN112307805B (en) 2019-07-25 2019-07-25 Automatic identification method for offshore targets

Country Status (1)

Country Link
CN (1) CN112307805B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117557789A (en) * 2024-01-12 2024-02-13 国研软件股份有限公司 Intelligent detection method and system for offshore targets

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106871900A (en) * 2017-01-23 2017-06-20 中国人民解放军海军工程大学 Image matching positioning method in ship magnetic field dynamic detection
CN107273530A (en) * 2017-06-28 2017-10-20 南京理工大学 Important ship target dynamic monitoring method based on internet information

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106871900A (en) * 2017-01-23 2017-06-20 中国人民解放军海军工程大学 Image matching positioning method in ship magnetic field dynamic detection
CN107273530A (en) * 2017-06-28 2017-10-20 南京理工大学 Important ship target dynamic monitoring method based on internet information

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117557789A (en) * 2024-01-12 2024-02-13 国研软件股份有限公司 Intelligent detection method and system for offshore targets
CN117557789B (en) * 2024-01-12 2024-04-09 国研软件股份有限公司 Intelligent detection method and system for offshore targets

Also Published As

Publication number Publication date
CN112307805B (en) 2022-09-27

Similar Documents

Publication Publication Date Title
US20220197281A1 (en) Intelligent decision-making method and system for unmanned surface vehicle
CN106887011B (en) A kind of multi-template method for tracking target based on CNN and CF
CN112308881B (en) Ship multi-target tracking method based on remote sensing image
CN114299417A (en) Multi-target tracking method based on radar-vision fusion
US20120300587A1 (en) Gunshot locating system and method
CN110738138A (en) Underwater acoustic communication signal modulation mode identification method based on cyclic neural network
CN108256634A (en) A kind of ship target detection method based on lightweight deep neural network
CN109655815A (en) Sonar target detection method based on SSD
CN111983676A (en) Earthquake monitoring method and device based on deep learning
CN112307805B (en) Automatic identification method for offshore targets
CN113822201B (en) Deep learning method for underwater object shape recognition based on flow field velocity component time course
CN113807314A (en) Millimeter wave radar video fusion method based on micro-Doppler effect
CN116152928A (en) Drowning prevention early warning method and system based on lightweight human body posture estimation model
CN113075648A (en) Clustering and filtering method for unmanned cluster target positioning information
Bhat et al. Energy models for network-on-chip components
CN117215316B (en) Method and system for driving environment perception based on cooperative control and deep learning
CN109886132B (en) Method, device and system for detecting target of cloud sea background airplane
CN106093891A (en) Radar fence anti-crowding measure false target jamming profile method based on doppler velocity inspection
CN114898222B (en) Ship target track identification method and device
Karnowski et al. Automated video surveillance for the study of marine mammal behavior and cognition
KR101837845B1 (en) System and method for obtaining information of underwater target
Klay et al. Advanced methods for passive acoustic detection, classification, and localization of marine mammals
KR20230068050A (en) Method and Apparatus for Target Identification Based on Different Features
Han et al. Rapid cigarette detection based on faster R-CNN
CN113537198A (en) Control method for automatic photographing during image acquisition of unmanned aerial vehicle

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant