CN114218978A - Embedded lightweight millimeter wave radar target identification method - Google Patents
Embedded lightweight millimeter wave radar target identification method Download PDFInfo
- Publication number
- CN114218978A CN114218978A CN202111314205.3A CN202111314205A CN114218978A CN 114218978 A CN114218978 A CN 114218978A CN 202111314205 A CN202111314205 A CN 202111314205A CN 114218978 A CN114218978 A CN 114218978A
- Authority
- CN
- China
- Prior art keywords
- target
- data
- electromagnetic wave
- wave radar
- millimeter wave
- 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
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
- G06F2218/04—Denoising
- G06F2218/06—Denoising by applying a scale-space analysis, e.g. using wavelet analysis
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
- G01S7/411—Identification of targets based on measurements of radar reflectivity
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
- G01S7/417—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section involving the use of neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Evolutionary Biology (AREA)
- Molecular Biology (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention discloses an embedded light millimeter wave radar target identification method, which relates to the technical field of target identification and comprises the following steps: receiving electromagnetic wave envelope signals returned by an object at different distances or different speeds; denoising the electromagnetic wave envelope signals by a wavelet threshold method, manually marking the denoised electromagnetic wave envelope signals to generate a sample library, and constructing a category set; training a lightweight convolution network model by using a sample library, wherein the range of the number of convolution layers of the lightweight convolution network model is 36-58, and the range of compression factors of compression layers is 0.3-0.5; collecting electromagnetic wave envelope signals returned by the target to be detected through a millimeter wave radar, denoising the signals through a wavelet threshold method, inputting the denoised signals into a lightweight convolution network model, and identifying the category of the target to be detected; the method is based on the lightweight convolution network model and combines the millimeter wave radar sensor to realize object class identification, can more effectively reveal the physical characteristics of the target object, and has strong flexibility and practical value.
Description
Technical Field
The invention relates to the technical field of target identification, in particular to an embedded light-weight millimeter wave radar target identification method.
Background
The coming of the intelligent era brings more and more convenience to people. The intelligent perception is used as a part of intelligent life, the surrounding environment is perceived at any time, the state information of surrounding targets is known, the motion trail of the surrounding targets is tracked, and the intelligent perception plays an important role in pedestrian tracking, traffic control and other aspects;
the current commonly used sensors comprise a vision sensor, a laser radar and the like, but the vision sensor cannot measure the distance information of a target and is easily influenced by weather; the laser radar is expensive, the applicability is poor in rainy and foggy weather, data are output in a point cloud format, and the calculated amount is large; the millimeter wave radar has the characteristics of low ranging precision, high penetrability, all weather and all day time, is suitable for relatively severe environments and has small data volume; therefore, an embedded light-weight millimeter wave radar target identification method is provided.
Disclosure of Invention
In order to solve the problems existing in the scheme, the invention provides an embedded light-weight millimeter wave radar target identification method.
The purpose of the invention can be realized by the following technical scheme:
an embedded light-weight millimeter wave radar target identification method comprises the following steps:
the method comprises the following steps: the millimeter wave radar receives electromagnetic wave envelope signals returned by an object at different distances or at different speeds by transmitting millimeter wave signals, wherein the electromagnetic wave envelope signals comprise speed, angle, distance information, signal intensity, phase and amplitude;
step two: data preprocessing: denoising the electromagnetic wave envelope signals by a wavelet threshold method, manually marking the denoised electromagnetic wave envelope signals to generate a sample library, and constructing a category set;
step three: training a lightweight convolution network model by using a sample library, wherein the range of the number of convolution layers of the lightweight convolution network model is 36-58, and the range of compression factors of compression layers is 0.3-0.5;
step four: electromagnetic wave envelope signals returned by the target to be detected are collected through a millimeter wave radar, and are input into the lightweight convolution network model after being denoised through a wavelet threshold method, so that the category of the target to be detected is identified.
Further, the data preprocessing comprises the following specific steps:
denoising an original electromagnetic wave envelope signal by a wavelet threshold method; screening out points with the period energy value larger than a preset threshold value from the denoised electromagnetic wave envelope signals as effective point cloud to obtain point cloud data, and converting the point cloud data into space coordinate information and speed information;
processing point cloud data through a nearest neighbor clustering method to obtain a target clustering object; manually marking the obtained target clustering objects in a supervised learning mode, marking the same target with different distances or different speeds as a sample, classifying and dividing each sample into threshold value intervals, and constructing a class set to form a sample library.
Further, the period energy value refers to a value obtained by accumulating energy of received continuous multiple bits of data and averaging the accumulated energy.
Further, the specific training steps of the lightweight convolutional network model are as follows:
obtaining a sample library, randomly selecting 80% of target clustering objects from the sample library as training samples, 10% of target clustering objects as test samples, and taking the rest target clustering objects as cross validation samples;
and inputting the training sample, the test sample and the cross validation sample into a lightweight convolution network model for training, and iterating parameters of the lightweight convolution network model.
Further, in the fourth step, the specific step of identifying the category of the target to be detected is as follows:
measuring the distance between the millimeter-wave radar and the target to be detected and the speed of the target to be detected through the millimeter-wave radar, and recording the signal intensity, the phase and the amplitude of the returned electromagnetic wave envelope signal;
and comparing the signal intensity, the phase and the amplitude of the target to be detected at the moment with the data at the corresponding distance and speed in the database through the trained lightweight convolution network model, and outputting the identification result of the target to be detected.
Further, the method further comprises: correcting the collected electromagnetic wave envelope signal returned by the target to be detected, specifically:
acquiring a current electromagnetic wave envelope signal and environmental data which are acquired, establishing a correction model, and inputting the current electromagnetic wave envelope signal and the environmental data into the correction model to obtain a correction signal;
and inputting the correction signal into a lightweight convolution network model, and identifying the category of the target to be detected.
Further, the method for establishing the correction model comprises the following steps:
acquiring historical identification data, wherein the historical identification data comprises historical identification target categories and environment data during identification, and acquiring corresponding actual target categories;
constructing an artificial intelligence model; the artificial intelligence model comprises an error reverse propagation neural network, an RBF neural network and a deep convolution neural network;
dividing historical identification data and corresponding actual target categories into a training set, a test set and a check set according to a set proportion; the set proportion comprises 4: 2: 2. 3: 2: 1 and 3: 1: 1; training, testing and verifying the artificial intelligent model through a training set, a testing set and a verifying set; and marking the trained artificial intelligence model as a correction model.
Further, the environmental data includes wind data, noise data, temperature data, humidity data, and barometric pressure data.
Compared with the prior art, the invention has the beneficial effects that: the millimeter wave radar target identification method is based on the lightweight convolution network model and combines the millimeter wave radar sensor to realize object class identification, and the method has strong flexibility, practical value, capability of more effectively revealing the physical characteristics of the target object and very wide application prospect; meanwhile, the influence of the external environment is considered, a correction module is established to correct the acquired electromagnetic wave envelope signals, and the identification efficiency and accuracy of the target object are improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic block diagram of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the following embodiments, and it should be understood that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, an embedded light-weight millimeter wave radar target identification method includes the following steps:
the method comprises the following steps: the millimeter wave radar receives electromagnetic wave envelope signals returned by an object at different distances or at different speeds by transmitting millimeter wave signals, wherein the electromagnetic wave envelope signals comprise speed, angle, distance information, signal intensity, phase and amplitude;
step two: data preprocessing: denoising the electromagnetic wave envelope signals by a wavelet threshold method, manually marking the denoised electromagnetic wave envelope signals to generate a sample library, and constructing a category set; the method specifically comprises the following steps:
s21: denoising an original electromagnetic wave envelope signal by a wavelet threshold method;
s22: screening out points with the period energy value larger than a preset threshold value from the denoised electromagnetic wave envelope signals as effective point cloud to obtain point cloud data, and converting the point cloud data into space coordinate information and speed information; the period energy value is a value obtained by accumulating the energy of received continuous multiple bit data and averaging;
s23: the point cloud data can obtain a target clustering object through a preset clustering algorithm, wherein the clustering algorithm comprises a K-mean clustering method and a nearest neighbor clustering method;
s24: manually marking the obtained target clustering objects in a supervised learning mode, marking the same target with different distances or different speeds as a sample, classifying and dividing each sample into threshold value intervals, and constructing a class set to form a sample library;
step three: training a lightweight convolution network model by using a sample library, wherein the range of the number of convolution layers of the lightweight convolution network model is 36-58, and the range of compression factors of compression layers is 0.3-0.5; the specific training steps are as follows:
obtaining a sample library, randomly selecting 80% of target clustering objects from the sample library as training samples, 10% of target clustering objects as test samples, and taking the rest target clustering objects as cross validation samples;
inputting training samples, test samples and cross validation samples into a lightweight convolution network model for training, and iterating lightweight convolution network model parameters;
step four: collecting electromagnetic wave envelope signals returned by the target to be detected through a millimeter wave radar, denoising the signals through a wavelet threshold method, inputting the denoised signals into a lightweight convolution network model, and identifying the category of the target to be detected; the method specifically comprises the following steps:
measuring the distance between the millimeter-wave radar and the target to be detected and the speed of the target to be detected through the millimeter-wave radar, and recording the signal intensity, the phase and the amplitude of the returned electromagnetic wave envelope signal;
comparing the signal intensity, the phase and the amplitude of the target to be detected with the data at the corresponding distance and speed in the database through the trained lightweight convolution network model, and outputting the identification result of the target to be detected;
the method further comprises the following steps: correcting the collected electromagnetic wave envelope signal returned by the target to be detected, which specifically comprises the following steps:
acquiring a current electromagnetic wave envelope signal and environmental data which are acquired, establishing a correction model, and inputting the current electromagnetic wave envelope signal and the environmental data into the correction model to obtain a correction signal;
inputting the correction signal into a lightweight convolution network model, and identifying the category of the target to be detected;
the method for establishing the correction model comprises the following steps:
acquiring historical identification data, wherein the historical identification data comprises historical identification target categories and environmental data during identification, and the environmental data comprises wind data, noise data, temperature data, humidity data and air pressure data;
acquiring a corresponding actual target category, and constructing an artificial intelligence model; the artificial intelligence model comprises an error reverse propagation neural network, an RBF neural network and a deep convolution neural network;
dividing historical identification data and corresponding actual target categories into a training set, a test set and a check set according to a set proportion; the set proportion comprises 4: 2: 2. 3: 2: 1 and 3: 1: 1; training, testing and verifying the artificial intelligent model through a training set, a testing set and a verifying set; marking the trained artificial intelligence model as a correction model;
the millimeter wave radar target identification method is based on the lightweight convolution network model and combines the millimeter wave radar sensor to realize object class identification, and the method has strong flexibility, practical value, capability of more effectively revealing the physical characteristics of the target object and very wide application prospect; meanwhile, the influence of the external environment is considered, a correction module is established to correct the acquired electromagnetic wave envelope signals, and the identification efficiency and accuracy of the target object are improved.
The working principle of the invention is as follows:
when the embedded light-weight millimeter wave radar target identification method works, firstly, a millimeter wave radar transmits millimeter wave signals, receives electromagnetic wave envelope signals returned by an object at different distances or different speeds, denoises the electromagnetic wave envelope signals through a wavelet threshold method, manually marks the denoised electromagnetic wave envelope signals to generate a sample library, and constructs a category set; then training a lightweight convolution network model by using a sample library, randomly selecting 80% of target clustering objects as training samples, 10% of target clustering objects as test samples, and taking the rest target clustering objects as cross validation samples; inputting training samples, test samples and cross validation samples into a lightweight convolution network model for training, and iterating lightweight convolution network model parameters; then, measuring the distance between the millimeter-wave radar and the target to be detected and the speed of the target to be detected through the millimeter-wave radar, denoising through a wavelet threshold method, and recording the signal intensity, the phase and the amplitude of the returned electromagnetic wave envelope signal; comparing the signal intensity, the phase and the amplitude of the target to be detected with the data at the corresponding distance and speed in the database through the trained lightweight convolution network model, and outputting the identification result of the target to be detected;
meanwhile, the method also comprises the steps of correcting the collected electromagnetic wave envelope signal returned by the target to be detected, acquiring the collected current electromagnetic wave envelope signal and the collected environmental data, establishing a correction model, and inputting the current electromagnetic wave envelope signal and the environmental data into the correction model to obtain a correction signal; and inputting the correction signal into a lightweight convolution network model, identifying the category of the target to be detected, and improving the identification efficiency and accuracy of the target object.
In the description herein, references to the description of "one embodiment," "an example," "a specific example" or the like are intended to mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise forms disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention. The invention is limited only by the claims and their full scope and equivalents.
Claims (8)
1. An embedded light-weight millimeter wave radar target identification method is characterized by comprising the following steps:
the method comprises the following steps: the millimeter wave radar receives electromagnetic wave envelope signals returned by an object at different distances or at different speeds by transmitting millimeter wave signals, wherein the electromagnetic wave envelope signals comprise speed, angle, distance information, signal intensity, phase and amplitude;
step two: data preprocessing: denoising the electromagnetic wave envelope signals by a wavelet threshold method, manually marking the denoised electromagnetic wave envelope signals to generate a sample library, and constructing a category set;
step three: training a lightweight convolution network model by using a sample library, wherein the range of the number of convolution layers of the lightweight convolution network model is 36-58, and the range of compression factors of compression layers is 0.3-0.5;
step four: electromagnetic wave envelope signals returned by the target to be detected are collected through a millimeter wave radar, and are input into the lightweight convolution network model after being denoised through a wavelet threshold method, so that the category of the target to be detected is identified.
2. The embedded light-weight millimeter wave radar target recognition method of claim 1, wherein the data preprocessing comprises the following specific steps:
denoising an original electromagnetic wave envelope signal by a wavelet threshold method; screening out points with the period energy value larger than a preset threshold value from the denoised electromagnetic wave envelope signals as effective point cloud to obtain point cloud data, and converting the point cloud data into space coordinate information and speed information;
processing point cloud data through a nearest neighbor clustering method to obtain a target clustering object; manually marking the obtained target clustering objects in a supervised learning mode, marking the same target with different distances or different speeds as a sample, classifying and dividing each sample into threshold value intervals, and constructing a class set to form a sample library.
3. The embedded light-weight millimeter wave radar target identification method according to claim 2, wherein the period energy value is obtained by accumulating energy of a plurality of continuous bit data received and averaging the accumulated energy.
4. The embedded light-weight millimeter wave radar target recognition method according to claim 2, wherein the specific training steps of the light-weight convolutional network model are as follows:
obtaining a sample library, randomly selecting 80% of target clustering objects from the sample library as training samples, 10% of target clustering objects as test samples, and taking the rest target clustering objects as cross validation samples;
and inputting the training sample, the test sample and the cross validation sample into a lightweight convolution network model for training, and iterating parameters of the lightweight convolution network model.
5. The embedded light-weight millimeter wave radar target identification method according to claim 1, wherein in the fourth step, the specific step of identifying the type of the target to be detected is as follows:
measuring the distance between the millimeter-wave radar and the target to be detected and the speed of the target to be detected through the millimeter-wave radar, and recording the signal intensity, the phase and the amplitude of the returned electromagnetic wave envelope signal;
and comparing the signal intensity, the phase and the amplitude of the target to be detected at the moment with the data at the corresponding distance and speed in the database through the trained lightweight convolution network model, and outputting the identification result of the target to be detected.
6. The embedded light-weighted millimeter wave radar target identification method of claim 1, further comprising: correcting the collected electromagnetic wave envelope signal returned by the target to be detected, specifically:
acquiring a current electromagnetic wave envelope signal and environmental data which are acquired, establishing a correction model, and inputting the current electromagnetic wave envelope signal and the environmental data into the correction model to obtain a correction signal;
and inputting the correction signal into a lightweight convolution network model, and identifying the category of the target to be detected.
7. The embedded light-weight millimeter wave radar target recognition method of claim 6, wherein the establishment method of the correction model is as follows:
acquiring historical identification data, wherein the historical identification data comprises historical identification target categories and environment data during identification, and acquiring corresponding actual target categories;
constructing an artificial intelligence model; the artificial intelligence model comprises an error reverse propagation neural network, an RBF neural network and a deep convolution neural network;
dividing historical identification data and corresponding actual target categories into a training set, a test set and a check set according to a set proportion; the set proportion comprises 4: 2: 2. 3: 2: 1 and 3: 1: 1; training, testing and verifying the artificial intelligent model through a training set, a testing set and a verifying set; and marking the trained artificial intelligence model as a correction model.
8. The embedded light-weight millimeter wave radar target recognition method of claim 7, wherein the environmental data comprises wind data, noise data, temperature data, humidity data, and barometric pressure data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111314205.3A CN114218978A (en) | 2021-11-08 | 2021-11-08 | Embedded lightweight millimeter wave radar target identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111314205.3A CN114218978A (en) | 2021-11-08 | 2021-11-08 | Embedded lightweight millimeter wave radar target identification method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114218978A true CN114218978A (en) | 2022-03-22 |
Family
ID=80696643
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111314205.3A Pending CN114218978A (en) | 2021-11-08 | 2021-11-08 | Embedded lightweight millimeter wave radar target identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114218978A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114924274A (en) * | 2022-04-08 | 2022-08-19 | 苏州大学 | High-dynamic railway environment radar sensing method based on fixed grids |
| TWI832242B (en) * | 2022-05-13 | 2024-02-11 | 廣達電腦股份有限公司 | Preprocessing method and electronic device for radar point cloud |
-
2021
- 2021-11-08 CN CN202111314205.3A patent/CN114218978A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114924274A (en) * | 2022-04-08 | 2022-08-19 | 苏州大学 | High-dynamic railway environment radar sensing method based on fixed grids |
| TWI832242B (en) * | 2022-05-13 | 2024-02-11 | 廣達電腦股份有限公司 | Preprocessing method and electronic device for radar point cloud |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114218978A (en) | Embedded lightweight millimeter wave radar target identification method | |
| CN111899568B (en) | Bridge anti-collision early warning system, method and device and storage medium | |
| CN106680806A (en) | Multi-radar plot fusion method | |
| CN110456320B (en) | Ultra-wideband radar identity recognition method based on free space gait time sequence characteristics | |
| CN111352113B (en) | Strong convection weather short-term forecasting method and system, storage medium and terminal | |
| CN110501006B (en) | Heterogeneous sensor combined track association and tracking method | |
| CN108537122A (en) | Image fusion acquisition system containing meteorological parameters and image storage method | |
| CN110940971B (en) | Radar target point trace recording method and device and storage medium | |
| CN104880160B (en) | Two-dimensional-laser real-time detection method of workpiece surface profile | |
| CN110764083B (en) | Anti-intrusion data fusion method and system for millimeter wave radar | |
| CN112379393B (en) | Train collision early warning method and device | |
| CN104299248A (en) | Method for utilizing foresight sonar image for predicting motion of multiple underwater dynamic targets | |
| KR102478596B1 (en) | Radar-based detection system and method for domain adaptation | |
| CN110378387B (en) | Cloud bottom height monitoring method based on wind-cloud-fourth satellite and ground-based millimeter wave radar | |
| CN106932752A (en) | A kind of real-time indoor orientation method based on RF phse monitoring | |
| CN112180361A (en) | Vehicle-mounted radar target tracking method based on dynamic federal filtering | |
| CN105678047A (en) | Wind field characterization method with empirical mode decomposition noise reduction and complex network analysis combined | |
| CN107064865A (en) | The passive co-located method of polar coordinates Dynamic Programming clustered based on depth | |
| CN115342814B (en) | Unmanned ship positioning method based on multi-sensor data fusion | |
| CN110599800A (en) | Parking lot parking space state monitoring system and monitoring method | |
| CN117571056B (en) | Environment protection monitoring method and system based on Internet of things | |
| CN113608193A (en) | Radar multi-target distance and speed estimation method based on UNet | |
| CN113687429A (en) | Device and method for determining boundary of millimeter wave radar monitoring area | |
| Scharf et al. | A semi-automated multi-sensor data labeling process for deep learning in automotive radar environment | |
| CN117029840A (en) | Mobile vehicle positioning method and system |
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 |