CN116224279A - Target detection method and device, storage medium and electronic equipment - Google Patents
Target detection method and device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN116224279A CN116224279A CN202310510636.XA CN202310510636A CN116224279A CN 116224279 A CN116224279 A CN 116224279A CN 202310510636 A CN202310510636 A CN 202310510636A CN 116224279 A CN116224279 A CN 116224279A
- Authority
- CN
- China
- Prior art keywords
- target
- radar
- radar data
- data
- detection model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- 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
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The specification discloses a target detection method, a target detection device, a storage medium and electronic equipment. The target detection method comprises the following steps: obtaining a transmitting signal and a receiving signal, generating first radar data according to the transmitting signal and the receiving signal, generating second radar data according to the transmitting signal of a target transmitting antenna and the receiving signal, inputting the second radar data into a detection model, determining an output result, training the detection model by taking the deviation between the minimized output result and the first radar data as an optimized target, deploying the detection model after training, generating radar data according to the receiving signal received by a target radar and the transmitting signal transmitted by the target radar, and inputting the radar data into the detection model to detect the target.
Description
Technical Field
The present disclosure relates to the field of communications technologies, and in particular, to a method and apparatus for detecting an object, a storage medium, and an electronic device.
Background
With the development of radar communication technology, multiple-Input Multiple-Output (MIMO) radar occupies a very important position in the communication field. The MIMO radar can effectively improve the resolution ratio of target detection while keeping lower overall power consumption, so the MIMO radar gradually becomes an innovative and very promising leading-edge research field in the radar industry, and plays an increasingly important role in the fields of automatic driving, building automation, intelligent factories, intelligent home, health care and the like.
At present, the number of MIMO radar signal channels is increased by increasing the number of transmitting antennas or receiving antennas, so that the resolution of the radar is improved, but as the number of antennas is increased, the complexity of a radar system is increased, the calibration difficulty is increased, and the manufacturing cost of the radar is greatly improved.
Therefore, how to reduce the complexity and calibration difficulty of the radar system and the manufacturing cost of the radar on the premise of ensuring the detection precision of the radar is a problem to be solved urgently.
Disclosure of Invention
The present disclosure provides a method, an apparatus, a storage medium, and an electronic device for target detection, so as to partially solve the foregoing problems in the prior art.
The technical scheme adopted in the specification is as follows:
the present specification provides a method of target detection, comprising:
acquiring transmitting signals transmitted by all transmitting antennas and receiving signals received by all receiving antennas arranged on a specified radar;
generating first radar data according to the transmitting signals and the receiving signals, determining a target transmitting antenna in the transmitting antennas, and generating second radar data according to the transmitting signals and the receiving signals transmitted by the target transmitting antenna;
Inputting the second radar data into a detection model to be trained, determining radar data obtained through each transmitting antenna and each receiving antenna through the detection model as an output result, and training the detection model by taking the deviation between the minimized output result and the first radar data as an optimization target;
disposing the trained detection model in a target radar, wherein the number of transmitting antennas arranged in the target radar is matched with the number of target transmitting antennas, and the number of receiving antennas arranged in the target radar is matched with the number of receiving numbers arranged on the appointed radar;
and generating radar data according to a receiving signal received by a receiving antenna arranged on the target radar and a transmitting signal transmitted by a transmitting antenna arranged on the target radar, and inputting the radar data into the detection model to detect the target.
Optionally, the second radar data is input into a detection model to be trained, so as to determine, through the detection model, radar data obtained through each transmitting antenna and each receiving antenna, and as an output result, specifically include:
Inputting the second radar data into a feature extraction layer of the detection model to determine target data features corresponding to the second radar data through the feature extraction layer;
and inputting the target data characteristics into a decision layer of the detection model to determine the output result through the decision layer.
Optionally, inputting the second radar data into a feature extraction layer of the detection model, so as to determine target data features corresponding to the second radar data through the feature extraction layer, which specifically includes:
if the second radar data contains amplitude information and phase information of signals, inputting the amplitude information into a first feature extraction layer of the detection model to obtain first data features, and inputting the phase information into a second feature extraction layer of the detection model to obtain second data features;
and determining the target data characteristic according to the first data characteristic and the second data characteristic.
Optionally, inputting the second radar data into a feature extraction layer of the detection model, so as to determine target data features corresponding to the second radar data through the feature extraction layer, which specifically includes:
And if the data form of the second radar data is complex, inputting the second radar data into a third feature extraction layer of the detection model so as to determine the target data feature through the third feature extraction layer.
Optionally, training the detection model with an optimization objective that minimizes a deviation between the output result and the first radar data specifically includes:
determining a first loss value of the detection model according to the deviation between the phase corresponding to the output result and the phase corresponding to the first radar data, and determining a second loss value of the detection model according to the deviation between the amplitude corresponding to the output result and the amplitude corresponding to the first radar data;
determining a comprehensive loss value of the detection model according to the first loss value and the second loss value;
and training the detection model by taking the minimum comprehensive loss value as an optimization target.
Optionally, before generating the first radar data from the transmit signal and the receive signal, the method further comprises:
and determining signal channels between the transmitting antennas and the receiving antennas, and generating virtual antennas corresponding to the signal channels.
Optionally, generating the first radar data according to the transmitting signal and the receiving signal specifically includes:
and generating radar data corresponding to each virtual antenna as the first radar data according to the transmitting signals and the receiving signals through the virtual antennas corresponding to the signal channels.
Optionally, generating second radar data according to the transmitting signal transmitted by the target transmitting antenna and the receiving signal specifically includes:
and generating radar data corresponding to each target virtual antenna as the second radar data according to the transmitting signals and the receiving signals transmitted by the target transmitting antenna through the target virtual antenna corresponding to the signal channel between the target transmitting antenna and each receiving antenna.
Optionally, the second radar data is input into a detection model to be trained, so as to determine, through the detection model, radar data obtained through each transmitting antenna and each receiving antenna, and as an output result, specifically include:
and inputting the second radar data into the detection model, and determining radar data corresponding to each virtual antenna through the detection model to serve as the output result.
Optionally, inputting the radar data into the detection model for target detection, specifically including:
determining radar data obtained by each virtual antenna in the case where the number of virtual antennas of the target radar is equal to the number of virtual antennas of the specified radar;
combining the radar data obtained through each virtual antenna to obtain target data;
and carrying out target detection according to the target data.
Optionally, performing target detection according to the target data specifically includes:
and determining pose information corresponding to the target object to be detected according to the target data.
Optionally, determining the target transmitting antenna from the transmitting antennas specifically includes:
and determining at least one transmitting antenna positioned in the center of the transmitting antenna array corresponding to the appointed radar from the transmitting antennas as the target transmitting antenna.
Optionally, the radar data includes: range-doppler data.
The present specification provides an apparatus for target detection, comprising:
the acquisition module acquires transmitting signals transmitted by all transmitting antennas and receiving signals received by all receiving antennas arranged on the appointed radar;
The generation module generates first radar data according to the transmitting signals and the receiving signals, determines a target transmitting antenna in the transmitting antennas, and generates second radar data according to the transmitting signals and the receiving signals transmitted by the target transmitting antenna;
the training module inputs the second radar data into a detection model to be trained, determines radar data obtained through each transmitting antenna and each receiving antenna through the detection model as an output result, and trains the detection model by taking the deviation between the minimized output result and the first radar data as an optimization target;
the deployment module deploys the trained detection model in a target radar, the number of transmitting antennas arranged in the target radar is matched with the number of target transmitting antennas, and the number of receiving antennas arranged in the target radar is matched with the number of receiving numbers arranged on the appointed radar;
and the detection module is used for generating radar data according to a receiving signal received by a receiving antenna arranged on the target radar and a transmitting signal transmitted by a transmitting antenna arranged on the target radar, and inputting the radar data into the detection model so as to detect the target. The present specification provides a computer readable storage medium storing a computer program which when executed by a processor implements the method of object detection described above.
The present specification provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing a method of target detection as described above when executing the program.
The above-mentioned at least one technical scheme that this specification adopted can reach following beneficial effect:
in the target detection method provided by the specification, a transmitting signal and a receiving signal are acquired, first radar data is generated according to the transmitting signal and the receiving signal, second radar data is generated according to the transmitting signal and the receiving signal of a target transmitting antenna, the second radar data is input into a detection model, an output result is determined, deviation between the minimized output result and the first radar data is used as an optimized target, the detection model is trained, the trained detection model is deployed, radar data is generated according to the receiving signal received by a target radar and the transmitting signal transmitted by the target radar, and the radar data is input into the detection model to perform target detection.
According to the method, in the process of training the detection model, less radar data generated by the transmitting signals of the target transmitting antennas and the receiving signals of all the receiving antennas can be used for predicting more radar data generated by the transmitting signals of all the transmitting antennas and the receiving signals of all the receiving antennas, so that even if the target radar is provided with only a small number of transmitting antennas, radar data equivalent to more transmitting antennas can be generated, higher detection precision is achieved under the condition of reducing the transmitting antennas, and the manufacturing cost and complexity of the radar are reduced.
Drawings
The accompanying drawings, which are included to provide a further understanding of the specification, illustrate and explain the exemplary embodiments of the present specification and their description, are not intended to limit the specification unduly. In the drawings:
FIG. 1 is a flow chart of a method of target detection provided in the present specification;
fig. 2 is a schematic diagram of an antenna structure of a specific radar provided in the present specification;
fig. 3 is a schematic diagram of an antenna structure of a target radar provided in the present specification;
FIG. 4 is a schematic diagram of an apparatus for target detection provided herein;
fig. 5 is a schematic diagram of an electronic device corresponding to fig. 1 provided in the present specification.
Detailed Description
For the purposes of making the objects, technical solutions and advantages of the present specification more apparent, the technical solutions of the present specification will be clearly and completely described below with reference to specific embodiments of the present specification and corresponding drawings. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present specification. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are intended to be within the scope of the present disclosure.
The following describes in detail the technical solutions provided by the embodiments of the present specification with reference to the accompanying drawings.
Fig. 1 is a flow chart of a method for detecting an object provided in the present specification, which includes the following steps:
s101: and acquiring the transmitting signals transmitted by each transmitting antenna and the receiving signals received by each receiving antenna arranged on the appointed radar.
S102: and generating first radar data according to the transmitting signals and the receiving signals, determining a target transmitting antenna in the transmitting antennas, and generating second radar data according to the transmitting signals and the receiving signals transmitted by the target transmitting antenna.
High-resolution MIMO radar sensors are an important means of ensuring safe and reliable operation of autopilot systems. However, the current radar spatial resolution still has difficulty meeting the stringent requirements of an autopilot system. The mainstream angular resolution enhancement method is to implement a very high number of MIMO virtual antennas by increasing the number of physical antennas of the radar system, but this method greatly increases the complexity of the system. Moreover, the fine and complicated calibration process further reduces the reliability of the radar system and promotes the improvement of software and hardware cost.
Angular resolution of radar
Can be expressed as:
wherein, the liquid crystal display device comprises a liquid crystal display device,
the smaller the value of (2), the higher the resolution of the radar, the greater the detection accuracy, and +.>
For the angle between the beam direction of the radar array and the normal of the antenna plane, < >>
For the number of equivalent virtual antennas of the radar array, < >>
For the radar signal wavelength in free space, +.>
Is the spacing between adjacent virtual antennas.
For example, when the array beam is directed straight ahead,
at least 230 virtual receive antennas (n=230) are required to achieve a spatial resolution of 0.5 °, and a larger number of physical antennas are required by the existing method.
Based on this, the present specification provides a method of target detection, in which radar data of all signal channels is predicted from radar data of a part of the signal channels, so that radar data equivalent to more transmitting antennas can be generated even if a target radar is provided with only a small number of transmitting antennas.
In the present specification, the execution subject of the method for realizing target detection may be a server or a radar terminal in a radar system, and for convenience of description, the present specification will describe one target detection method provided in the present specification by taking the radar terminal as an execution subject only.
The radar terminal needs to acquire the transmitting signals transmitted by each transmitting antenna and the receiving signals received by each receiving antenna, which are arranged on the appointed radar. For ease of understanding, the present disclosure provides a schematic diagram of an antenna structure of a given radar, as shown in fig. 2.
Fig. 2 is a schematic diagram of an antenna structure of a specific radar provided in the present specification.
The receiving antennas are uniformly and linearly arrayed, R1-R4 are sequentially marked from left to right, the transmitting antennas are uniformly and linearly nested arrayed, and T1-T3 are sequentially marked from left to right. The space between the receiving antennas is lambda/2, the space between the transmitting antennas is 2 lambda, and 12 signal channels are shared between each receiving antenna and each transmitting antenna, so that 12 MIMO virtual antenna arrays with adjacent space lambda/2 can be generated, and the virtual antennas are marked as V1-V12 in sequence from left to right.
Specifically, virtual antennas V1 to V4 are generated by the interaction of transmitting antennas T1 and receiving antennas R1 to R4, virtual antennas V5 to V8 are generated by the interaction of transmitting antennas T2 and receiving antennas R1 to R4, and virtual antennas V9 to V12 are generated by the interaction of transmitting antennas T3 and receiving antennas R1 to R4.
The radar terminal can configure the transmitting antennas T1-T3 and the receiving antennas R1-R4 of the appointed radar into a normal working mode. The appointed radar can sequentially activate the transmitting antennas T1, T2 and T3 to transmit radio frequency signals to the detection space according to the working principle of the MIMO array, and simultaneously activate the receiving antennas R1-R4 to sample radar echoes. The radar terminal may perform a distance-dimensional fourier transform and a doppler-dimensional fourier transform according to a transmission signal (radio frequency signal) transmitted by each transmission antenna and a reception signal (echo) received by each reception antenna, and generate, as first radar data, radar data corresponding to each virtual antenna V1 to V12.
It should be noted that, the radar data referred to in the present specification may refer to "range-doppler" two-dimensional data.
Meanwhile, the radar terminal may determine a target transmitting antenna among the transmitting antennas, for example, the radar terminal may determine at least one transmitting antenna located at the center of the radar-corresponding transmitting antenna array among the transmitting antennas as a target transmitting antenna.
Taking fig. 2 as an example, since the transmitting antenna T2 is located at the center of the array, it can be regarded as a target transmitting antenna.
Of course, the radar terminal may also select other transmitting antennas as target transmitting antennas, such as T1 and/or T3 in fig. 2 as target transmitting antennas.
After determining the target transmitting antenna, the radar terminal may generate second radar data according to the transmitting signal and the receiving signal transmitted by the target transmitting antenna.
Also taking fig. 2 as an example, the radar terminal may use radar data generated by the transmission signal of T2 and the reception signals of R1 to R4 (radar data generated by the virtual antennas V5 to V8) as the second radar data.
In this specification, the test scenario of a plurality of specified radars may be exchanged. And under different scenes, repeating the step of generating the distance-Doppler two-dimensional data to obtain enough training data sets. Training dataset was set as 4: the scale of 6 is divided into a training data set and a validation data set.
S103: inputting the second radar data into a detection model to be trained, determining radar data obtained through each transmitting antenna and each receiving antenna through the detection model to serve as an output result, and training the detection model by taking deviation between the minimized output result and the first radar data as an optimization target.
The detection model in this specification can be a deep neural network structure based on an encoder-decoder U-Net model. A self-care layer is added on the channel dimension of the neural network and is used for learning the cross-channel characteristic association. The activation function employs a leak Relu.
The encoder of the detection model comprises a plurality of convolution kernels, the second radar data are subjected to maximum pooling processing and transposed convolution through the convolution kernels, target data features are extracted based on channel attention, and finally an output result of the detection model is determined according to the extracted target data features.
In this specification, an encoder of the detection model may extract data features as a feature extraction layer, and after decoding the extracted features by a decoder, the output result is determined by a final decision layer. Wherein the model structure of the detection model is related to the representation of the radar data.
Specifically, if the second radar data includes amplitude information and phase information of the signal, since the physical characteristics of the amplitude and the phase are obviously different, the detection model needs to create two separate encoders for the amplitude and the phase respectively, and does not share the characteristics, the amplitude information is input into a first feature extraction layer corresponding to one encoder of the detection model to obtain a first data characteristic, and the phase information is input into a second feature extraction layer corresponding to the other encoder of the detection model to obtain a second data characteristic, and then the target data characteristic can be determined according to the first data characteristic and the second data characteristic, so that the output information of the two encoders is combined, and the model is allowed to learn any coupling behavior that the phase and the amplitude are shared in the physical signal.
If the data form of the second radar data is complex, that is, the radar data is characterized by a real part and an imaginary part, the real part data and the imaginary part data can share a set of encoder, only a self-care layer is added to learn the cross-channel characteristic association, and in the process, the second radar data can be input into a third characteristic extraction layer corresponding to the encoder so as to determine the target data characteristic through the third characteristic extraction layer.
After the target data characteristics are determined, a final output result can be determined through a decision layer of the detection model, and the output result can be radar data generated by virtual antennas corresponding to all signal channels and predicted based on radar data generated by target transmitting antennas and receiving antennas, namely all radar data corresponding to virtual antennas V1-V12 are predicted by partial radar data corresponding to virtual antennas V5-V8.
The radar terminal can train the detection model by taking the first radar data as a sample tag and taking the deviation between the minimized output result and the first radar data as an optimization target.
Specifically, the radar terminal may determine a first loss value of the detection model according to a deviation between a phase corresponding to the output result and a phase corresponding to the first radar data, so as to implement spatial angle estimation of the measured target object, and determine a second loss value of the detection model according to a deviation between an amplitude corresponding to the output result and an amplitude corresponding to the first radar data, so as to reconstruct a phase relationship between the physical antennas.
And then the radar terminal can determine the comprehensive loss value of the detection model according to the first loss value and the second loss value, and train the detection model by taking the minimized comprehensive loss value as an optimization target.
In the training process, the radar terminal can take virtual antennas corresponding to signal channels between a target transmitting antenna and each receiving antenna as a first antenna group (e.g. V5-V8), take other virtual antennas except the first antenna group as a second antenna group (e.g. V1-V4, V9-V12), continuously learn the two-dimensional data characteristics of virtual antennas 'distance-Doppler' in the first antenna group and the second antenna group, establish signal characteristic association between the virtual antennas of the first antenna group and the second antenna group, and finally deduce the two-dimensional data 'distance-Doppler' of the virtual antennas in the second antenna group by utilizing the two-dimensional data characteristics of the virtual antennas 'distance-Doppler' in the first antenna group.
S104: and deploying the trained detection model in a target radar, wherein the number of transmitting antennas arranged in the target radar is matched with the number of target transmitting antennas, and the number of receiving antennas arranged in the target radar is matched with the number of receiving numbers arranged on the appointed radar.
After training the detection model, the radar terminal may deploy the detection model in the target radar, and in practical application, the detection model may be deployed on a central processor (Central Processing Unit, CPU) of the target radar, or of course, may also be deployed on an image processor (Graphic Processing Unit, GPU) of the target radar, or on a field programmable gate array (Field Programmable Gate Array, FPGA) module of the target radar, which is not specifically limited in this specification.
In this specification, the number of transmitting antennas of the target radar may be the same as the number of target transmitting antennas of the above-described specified radar, and the number of receiving antennas of the target radar may be the same as the number of receiving antennas of the specified radar.
Of course, in the present specification, the number of transmitting antennas on the target radar may be an integer multiple of the number of target transmitting antennas on the specified radar, and the number of receiving antennas on the target radar may be the same multiple of the number of receiving antennas on the specified radar.
S105: and generating radar data according to a receiving signal received by a receiving antenna arranged on the target radar and a transmitting signal transmitted by a transmitting antenna arranged on the target radar, and inputting the radar data into the detection model to detect the target.
The radar terminal may generate radar data according to a reception signal received by a reception antenna provided on the target radar and a transmission signal transmitted by a transmission antenna provided on the target radar, and input the radar data into the detection model.
When the number of target radar receiving antennas is equal to the number of target receiving antennas on the specified radar, the detection model may determine, according to the radar data described above, radar data obtained when the number of transmitting antennas of the target radar is equal to the number of all transmitting antennas of the specified radar and the number of receiving antennas of the target radar is equal to the number of receiving antennas of the specified radar, where the radar data may be radar data generated by virtual antennas corresponding to all signal channels of the specified radar, and then combine the radar data corresponding to all virtual antennas to obtain the target data.
When the number of the target radar receiving antennas is a specified integer multiple of the number of the target receiving antennas on the specified radar, the detection model may determine, based on the radar data described above, radar data obtained in a case where the number of the transmitting antennas of the target radar is equal to a specified integer multiple of the number of all the transmitting antennas of the specified radar and the number of the receiving antennas of the target radar is equal to a specified integer multiple of the number of the receiving antennas of the specified radar, which may be set according to the actual situation, which is not particularly limited in this specification.
And then the radar terminal can analyze the target data so as to acquire pose information, distance, speed and other information corresponding to the target object to be detected.
For ease of understanding, the present disclosure provides a schematic diagram of an antenna structure of a target radar, as shown in fig. 3.
Fig. 3 is a schematic diagram of an antenna structure of a target radar provided in the present specification.
The target radar only reserves one transmitting antenna T2, the original virtual antenna arrays generated by the transmitting antenna T2 and the receiving antennas R1-R4 are V5-V8, and based on a detection model, each virtual antenna under the condition that the receiving antennas are T1-T3 can be deduced, so that predicted virtual antenna arrays V1-V4 and V9-V12 are obtained, and therefore the target radar can obtain all radar data corresponding to the virtual antennas V1-V12 only through the transmitting antennas T2 and the receiving antennas RI-R4, and detection accuracy equivalent to the transmitting antennas T1-T3 of the appointed radar is achieved.
When the specified radar (shown in fig. 2) works at 76 GHz-79 GHz, the effective bandwidth is 3 GHz, and the working waveform adopts a Frequency Modulated Continuous Wave (FMCW) environment. The radar signal carrier wavelength is approximately 3.94 mm. The center-to-center spacing of adjacent transmit antennas is 7.88 mm and the center-to-center spacing of adjacent receive antennas is 1.97 mm. The radar system uses 3 transmitting antennas and 4 receiving antennas in total, so that 12 equivalent virtual antennas can be formed according to the MIMO antenna principle, and the distance between adjacent virtual antennas is 1.97 and mm. According to the radar angular resolution formula, theta = lambda/Ndcos theta (wherein theta is the angular resolution of the radar, theta is the angle between the radar array beam direction and the antenna plane normal, N is the number of equivalent virtual antennas, lambda is the radar signal wavelength in free space, d is the adjacent virtual antenna spacing), and in the direction of theta = 0 deg., the corresponding angular resolution has a value of 9.5 deg..
In the target radar (as shown in fig. 3) in the scheme, only one transmitting antenna T2 needs to be reserved, and transmitting antennas T1 and T3 are omitted, so that equivalent virtual antenna arrays generated by the transmitting antennas T2 and receiving antennas R1 to R4 are V5 to V8. According to the radar angular resolution formula, in the direction θ=0°, the corresponding angular resolution is only 28.6 °. In the scheme, the distance-Doppler two-dimensional data of the virtual antennas V1-V4 and V9-V12 can be calculated by utilizing the data of V5-V8. Combining the "range-Doppler" two-dimensional data of V1-V4, V5-V8, V9-V12 together optimizes the value of the angular resolution from 28.6 to 9.5.
In this way, the same resolution as that of a larger number of transmitting antennas can be achieved with a smaller number of transmitting antennas, and the same detection accuracy can be achieved.
According to the method, in the process of training the detection model, less radar data generated by the transmitting signals of the target transmitting antennas and the receiving signals of all the receiving antennas can be used for predicting more radar data generated by the transmitting signals of all the receiving antennas and the receiving signals of all the receiving antennas, so that even if the target radar is provided with only a small number of transmitting antennas, radar data equivalent to more transmitting antennas can be generated, higher detection precision is achieved under the condition of reducing the transmitting antennas, and the manufacturing cost and complexity of the radar are reduced.
The foregoing describes one or more methods for performing object detection according to the present disclosure, and provides a corresponding device for object detection according to the present disclosure based on the same concept, as shown in fig. 4.
Fig. 4 is a schematic diagram of an apparatus for target detection provided in the present specification, including:
an acquisition module 401, configured to acquire a transmission signal transmitted by each transmission antenna and a reception signal received by each reception antenna set on a specified radar;
A generating module 402, configured to generate first radar data according to the transmitting signal and the receiving signal, determine a target transmitting antenna from the transmitting antennas, and generate second radar data according to the transmitting signal and the receiving signal transmitted by the target transmitting antenna;
the training module 403 is configured to input the second radar data into a detection model to be trained, determine, by using the detection model, radar data obtained by using each transmitting antenna and each receiving antenna as an output result, and train the detection model with a deviation between the output result and the first radar data being minimized as an optimization target;
a deployment module 404, configured to deploy the trained detection model in a target radar, where the number of transmitting antennas set in the target radar is matched with the number of target transmitting antennas, and the number of receiving antennas set in the target radar is matched with the number of receiving numbers set on the specified radar;
and the detection module 405 is configured to generate radar data according to a received signal received by a receiving antenna set on the target radar and a transmitted signal transmitted by a transmitting antenna set on the target radar, and input the radar data into the detection model to perform target detection.
Optionally, the training module 403 is specifically configured to input the second radar data into a feature extraction layer of the detection model, so as to determine, by using the feature extraction layer, a target data feature corresponding to the second radar data; and inputting the target data characteristics into a decision layer of the detection model to determine the output result through the decision layer.
Optionally, the training module 403 is specifically configured to, if the second radar data includes amplitude information and phase information of a signal, input the amplitude information into a first feature extraction layer of the detection model to obtain a first data feature, and input the phase information into a second feature extraction layer of the detection model to obtain a second data feature; and determining the target data characteristic according to the first data characteristic and the second data characteristic.
Optionally, the training module 403 is specifically configured to input the second radar data into a third feature extraction layer of the detection model if the data form of the second radar data is complex, so as to determine the target data feature through the third feature extraction layer.
Optionally, the training module 403 is specifically configured to determine a first loss value of the detection model according to a deviation between a phase corresponding to the output result and a phase corresponding to the first radar data, and determine a second loss value of the detection model according to a deviation between an amplitude corresponding to the output result and an amplitude corresponding to the first radar data; determining a comprehensive loss value of the detection model according to the first loss value and the second loss value; and training the detection model by taking the minimum comprehensive loss value as an optimization target.
Optionally, before generating the first radar data according to the transmission signal and the reception signal, the generating module 402 is further configured to determine signal paths between the transmitting antennas and the receiving antennas, and generate virtual antennas corresponding to the signal paths.
Optionally, the generating module 402 is specifically configured to generate, by using virtual antennas corresponding to the signal channels, radar data corresponding to each virtual antenna as the first radar data according to the transmission signal and the reception signal.
Optionally, the generating module 402 is specifically configured to generate, by using a target virtual antenna corresponding to a signal channel between the target transmitting antenna and each receiving antenna, radar data corresponding to each target virtual antenna as the second radar data according to a transmitting signal and the receiving signal transmitted by the target transmitting antenna.
Optionally, the training module 403 is specifically configured to input the second radar data into the detection model, and determine, by using the detection model, radar data corresponding to each virtual antenna as the output result.
Optionally, the detection module 405 is specifically configured to input the radar data into the detection model, and determine radar data obtained through each virtual antenna when the number of virtual antennas of the target radar is equal to the number of virtual antennas of the specified radar; combining the radar data obtained through each virtual antenna to obtain target data; and carrying out target detection according to the target data.
Optionally, the detection module 405 is specifically configured to determine pose information corresponding to the target object to be detected according to the target data.
Optionally, the generating module 402 is specifically configured to determine, from among the transmitting antennas, at least one transmitting antenna located at a center of the transmitting antenna array corresponding to the specified radar as the target transmitting antenna.
Optionally, the radar data includes: range-doppler data.
The present specification also provides a computer readable storage medium storing a computer program operable to perform a method of object detection as provided in fig. 1 above.
The present specification also provides a schematic structural diagram of an electronic device corresponding to fig. 1 shown in fig. 5. At the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile storage, as illustrated in fig. 5, although other hardware required by other services may be included. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs to implement the method of object detection described above with respect to fig. 1. Of course, other implementations, such as logic devices or combinations of hardware and software, are not excluded from the present description, that is, the execution subject of the following processing flows is not limited to each logic unit, but may be hardware or logic devices.
Improvements to one technology can clearly distinguish between improvements in hardware (e.g., improvements to circuit structures such as diodes, transistors, switches, etc.) and software (improvements to the process flow). However, with the development of technology, many improvements of the current method flows can be regarded as direct improvements of hardware circuit structures. Designers almost always obtain corresponding hardware circuit structures by programming improved method flows into hardware circuits. Therefore, an improvement of a method flow cannot be said to be realized by a hardware entity module. For example, a programmable logic device (Programmable Logic Device, PLD) (e.g., field programmable gate array (Field Programmable Gate Array, FPGA)) is an integrated circuit whose logic function is determined by the programming of the device by a user. A designer programs to "integrate" a digital system onto a PLD without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Moreover, nowadays, instead of manually manufacturing integrated circuit chips, such programming is mostly implemented by using "logic compiler" software, which is similar to the software compiler used in program development and writing, and the original code before the compiling is also written in a specific programming language, which is called hardware description language (Hardware Description Language, HDL), but not just one of the hdds, but a plurality of kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), lava, lola, myHDL, PALASM, RHDL (Ruby Hardware Description Language), etc., VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog are currently most commonly used. It will also be apparent to those skilled in the art that a hardware circuit implementing the logic method flow can be readily obtained by merely slightly programming the method flow into an integrated circuit using several of the hardware description languages described above.
The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer readable medium storing computer readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable logic controllers, and embedded microcontrollers, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, atmel AT91SAM, microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic of the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller in a pure computer readable program code, it is well possible to implement the same functionality by logically programming the method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc. Such a controller may thus be regarded as a kind of hardware component, and means for performing various functions included therein may also be regarded as structures within the hardware component. Or even means for achieving the various functions may be regarded as either software modules implementing the methods or structures within hardware components.
The system, apparatus, module or unit set forth in the above embodiments may be implemented in particular by a computer chip or entity, or by a product having a certain function. One typical implementation is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being functionally divided into various units, respectively. Of course, the functions of each element may be implemented in one or more software and/or hardware elements when implemented in the present specification.
It will be appreciated by those skilled in the art that embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, the present specification may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present description can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
The present description is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the specification. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
It will be appreciated by those skilled in the art that embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, the present specification may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present description can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
The description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.
The foregoing is merely exemplary of the present disclosure and is not intended to limit the disclosure. Various modifications and alterations to this specification will become apparent to those skilled in the art. Any modifications, equivalent substitutions, improvements, or the like, which are within the spirit and principles of the present description, are intended to be included within the scope of the claims of the present description.
Claims (16)
1. A method of target detection, comprising:
acquiring transmitting signals transmitted by all transmitting antennas and receiving signals received by all receiving antennas arranged on a specified radar;
generating first radar data according to the transmitting signals and the receiving signals, determining a target transmitting antenna in the transmitting antennas, and generating second radar data according to the transmitting signals and the receiving signals transmitted by the target transmitting antenna;
inputting the second radar data into a detection model to be trained, determining radar data obtained through each transmitting antenna and each receiving antenna through the detection model as an output result, and training the detection model by taking the deviation between the minimized output result and the first radar data as an optimization target;
disposing the trained detection model in a target radar, wherein the number of transmitting antennas arranged in the target radar is matched with the number of target transmitting antennas, and the number of receiving antennas arranged in the target radar is matched with the number of receiving numbers arranged on the appointed radar;
And generating radar data according to a receiving signal received by a receiving antenna arranged on the target radar and a transmitting signal transmitted by a transmitting antenna arranged on the target radar, and inputting the radar data into the detection model to detect the target.
2. The method according to claim 1, wherein inputting the second radar data into a detection model to be trained to determine radar data obtained by the transmitting antennas and the receiving antennas by the detection model as output results, specifically comprises:
inputting the second radar data into a feature extraction layer of the detection model to determine target data features corresponding to the second radar data through the feature extraction layer;
and inputting the target data characteristics into a decision layer of the detection model to determine the output result through the decision layer.
3. The method of claim 2, wherein inputting the second radar data into a feature extraction layer of the detection model to determine target data features corresponding to the second radar data by the feature extraction layer, specifically comprises:
if the second radar data contains amplitude information and phase information of signals, inputting the amplitude information into a first feature extraction layer of the detection model to obtain first data features, and inputting the phase information into a second feature extraction layer of the detection model to obtain second data features;
And determining the target data characteristic according to the first data characteristic and the second data characteristic.
4. The method of claim 2, wherein inputting the second radar data into a feature extraction layer of the detection model to determine target data features corresponding to the second radar data by the feature extraction layer, specifically comprises:
and if the data form of the second radar data is complex, inputting the second radar data into a third feature extraction layer of the detection model so as to determine the target data feature through the third feature extraction layer.
5. The method of claim 1, wherein training the detection model with a view to minimizing a deviation between the output result and the first radar data is performed as an optimization objective, specifically comprising:
determining a first loss value of the detection model according to the deviation between the phase corresponding to the output result and the phase corresponding to the first radar data, and determining a second loss value of the detection model according to the deviation between the amplitude corresponding to the output result and the amplitude corresponding to the first radar data;
Determining a comprehensive loss value of the detection model according to the first loss value and the second loss value;
and training the detection model by taking the minimum comprehensive loss value as an optimization target.
6. The method of claim 1, wherein prior to generating first radar data from the transmit signal and the receive signal, the method further comprises:
and determining signal channels between the transmitting antennas and the receiving antennas, and generating virtual antennas corresponding to the signal channels.
7. The method of claim 6, wherein generating first radar data from the transmit signal and the receive signal, comprises:
and generating radar data corresponding to each virtual antenna as the first radar data according to the transmitting signals and the receiving signals through the virtual antennas corresponding to the signal channels.
8. The method of claim 6, wherein generating second radar data from the transmit signal transmitted by the target transmit antenna and the receive signal, comprises:
and generating radar data corresponding to each target virtual antenna as the second radar data according to the transmitting signals and the receiving signals transmitted by the target transmitting antenna through the target virtual antenna corresponding to the signal channel between the target transmitting antenna and each receiving antenna.
9. The method according to claim 6, wherein inputting the second radar data into a detection model to be trained to determine radar data obtained by the transmitting antennas and the receiving antennas through the detection model as an output result, specifically comprising:
and inputting the second radar data into the detection model, and determining radar data corresponding to each virtual antenna through the detection model to serve as the output result.
10. The method of claim 9, wherein inputting the radar data into the detection model for target detection, in particular comprises:
inputting the radar data into the detection model, and determining radar data obtained through each virtual antenna under the condition that the number of virtual antennas of the target radar is equal to the number of virtual antennas of the appointed radar;
combining the radar data obtained through each virtual antenna to obtain target data;
and carrying out target detection according to the target data.
11. The method of claim 10, wherein performing object detection based on the object data specifically comprises:
and determining pose information corresponding to the target object to be detected according to the target data.
12. The method of claim 1, wherein determining the target transmit antenna among the transmit antennas comprises:
and determining at least one transmitting antenna positioned in the center of the transmitting antenna array corresponding to the appointed radar from the transmitting antennas as the target transmitting antenna.
13. The method of claim 1, wherein the radar data comprises: range-doppler data.
14. An apparatus for target detection, comprising:
the acquisition module acquires transmitting signals transmitted by all transmitting antennas and receiving signals received by all receiving antennas arranged on the appointed radar;
the generation module generates first radar data according to the transmitting signals and the receiving signals, determines a target transmitting antenna in the transmitting antennas, and generates second radar data according to the transmitting signals and the receiving signals transmitted by the target transmitting antenna;
the training module inputs the second radar data into a detection model to be trained, determines radar data obtained through each transmitting antenna and each receiving antenna through the detection model as an output result, and trains the detection model by taking the deviation between the minimized output result and the first radar data as an optimization target;
The deployment module deploys the trained detection model in a target radar, the number of transmitting antennas arranged in the target radar is matched with the number of target transmitting antennas, and the number of receiving antennas arranged in the target radar is matched with the number of receiving numbers arranged on the appointed radar;
and the detection module is used for generating radar data according to a receiving signal received by a receiving antenna arranged on the target radar and a transmitting signal transmitted by a transmitting antenna arranged on the target radar, and inputting the radar data into the detection model so as to detect the target.
15. A computer readable storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, implements the method of any of the preceding claims 1-13.
16. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method of any of the preceding claims 1-13 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310510636.XA CN116224279B (en) | 2023-05-08 | 2023-05-08 | Target detection method and device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310510636.XA CN116224279B (en) | 2023-05-08 | 2023-05-08 | Target detection method and device, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116224279A true CN116224279A (en) | 2023-06-06 |
| CN116224279B CN116224279B (en) | 2023-07-21 |
Family
ID=86589522
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310510636.XA Active CN116224279B (en) | 2023-05-08 | 2023-05-08 | Target detection method and device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116224279B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103744076A (en) * | 2013-12-25 | 2014-04-23 | 河海大学 | Non-convex optimization based MIMO radar moving object detection method |
| CN104849696A (en) * | 2015-04-27 | 2015-08-19 | 中南大学 | MIMO radar antenna array sparse arraying method |
| CN105807267A (en) * | 2016-03-11 | 2016-07-27 | 中国人民解放军国防科学技术大学 | MIMO radar extended target detection method |
| CN106199529A (en) * | 2016-08-19 | 2016-12-07 | 西安电子科技大学 | The aerial array method to set up of minimal redundancy MIMO radar |
| CN110444905A (en) * | 2019-08-16 | 2019-11-12 | 之江实验室 | A kind of two dimension mimo antenna battle array |
| US20200158861A1 (en) * | 2018-11-20 | 2020-05-21 | KMB Telematics, Inc. | Object sensing from a potentially moving frame of reference with virtual apertures formed from sparse antenna arrays |
| CN111413683A (en) * | 2019-01-08 | 2020-07-14 | 智能雷达系统有限公司 | Radar apparatus and radar signal processing method |
| US20200225317A1 (en) * | 2020-03-27 | 2020-07-16 | Chulong Chen | Apparatus, system and method of generating radar perception data |
| CN112666543A (en) * | 2020-12-01 | 2021-04-16 | 安徽隼波科技有限公司 | Sparse array TDM-MIMO radar and correction method thereof |
| CN112673272A (en) * | 2020-07-27 | 2021-04-16 | 华为技术有限公司 | Signal processing method, device and storage medium |
| CN112946582A (en) * | 2021-04-02 | 2021-06-11 | 华域汽车系统股份有限公司 | Antenna array based on vehicle-mounted MIMO radar and use method thereof |
| CN113189592A (en) * | 2021-03-08 | 2021-07-30 | 苏州乐达纳米科技有限公司 | Vehicle-mounted millimeter wave MIMO radar angle measurement method considering amplitude mutual coupling error |
| US20210302538A1 (en) * | 2020-02-20 | 2021-09-30 | Samsung Electronics Co., Ltd. | Method and apparatus for detecting object based on radar signal |
| US20220268911A1 (en) * | 2021-02-25 | 2022-08-25 | Nxp B.V. | Radar-based detection using angle of arrival estimation based on sparse array processing |
| CN115656959A (en) * | 2022-11-10 | 2023-01-31 | 中汽创智科技有限公司 | Radar signal processing method, device, equipment and storage medium |
-
2023
- 2023-05-08 CN CN202310510636.XA patent/CN116224279B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103744076A (en) * | 2013-12-25 | 2014-04-23 | 河海大学 | Non-convex optimization based MIMO radar moving object detection method |
| CN104849696A (en) * | 2015-04-27 | 2015-08-19 | 中南大学 | MIMO radar antenna array sparse arraying method |
| CN105807267A (en) * | 2016-03-11 | 2016-07-27 | 中国人民解放军国防科学技术大学 | MIMO radar extended target detection method |
| CN106199529A (en) * | 2016-08-19 | 2016-12-07 | 西安电子科技大学 | The aerial array method to set up of minimal redundancy MIMO radar |
| US20200158861A1 (en) * | 2018-11-20 | 2020-05-21 | KMB Telematics, Inc. | Object sensing from a potentially moving frame of reference with virtual apertures formed from sparse antenna arrays |
| CN111413683A (en) * | 2019-01-08 | 2020-07-14 | 智能雷达系统有限公司 | Radar apparatus and radar signal processing method |
| CN110444905A (en) * | 2019-08-16 | 2019-11-12 | 之江实验室 | A kind of two dimension mimo antenna battle array |
| US20210302538A1 (en) * | 2020-02-20 | 2021-09-30 | Samsung Electronics Co., Ltd. | Method and apparatus for detecting object based on radar signal |
| US20200225317A1 (en) * | 2020-03-27 | 2020-07-16 | Chulong Chen | Apparatus, system and method of generating radar perception data |
| CN112673272A (en) * | 2020-07-27 | 2021-04-16 | 华为技术有限公司 | Signal processing method, device and storage medium |
| CN112666543A (en) * | 2020-12-01 | 2021-04-16 | 安徽隼波科技有限公司 | Sparse array TDM-MIMO radar and correction method thereof |
| US20220268911A1 (en) * | 2021-02-25 | 2022-08-25 | Nxp B.V. | Radar-based detection using angle of arrival estimation based on sparse array processing |
| CN113189592A (en) * | 2021-03-08 | 2021-07-30 | 苏州乐达纳米科技有限公司 | Vehicle-mounted millimeter wave MIMO radar angle measurement method considering amplitude mutual coupling error |
| CN112946582A (en) * | 2021-04-02 | 2021-06-11 | 华域汽车系统股份有限公司 | Antenna array based on vehicle-mounted MIMO radar and use method thereof |
| CN115656959A (en) * | 2022-11-10 | 2023-01-31 | 中汽创智科技有限公司 | Radar signal processing method, device, equipment and storage medium |
Non-Patent Citations (4)
| Title |
|---|
| SIYI SHEN ET AL.: "Detectability Estimation of Dropped Objects by Millimeter Wave Radar", 2022 INTERNATIONAL CONFERENCE ON MICROWAVE AND MILLIMETER WAVE TECHNOLOGY * |
| 曾建奎;何子述;: "基于隐马尔可夫模型的MIMO雷达目标检测", 电子测量与仪器学报, no. 04 * |
| 洪振清等: "最小冗余ＭＩＭＯ雷达阵列设计", 数据采集与处理, vol. 28, no. 4 * |
| 赵军;沈明威;朱岱寅;: "机载MIMO雷达杂波特征结构的空时自回归算法", 信号处理, no. 04 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116224279B (en) | 2023-07-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Sun et al. | 4D automotive radar sensing for autonomous vehicles: A sparsity-oriented approach | |
| Gante et al. | Deep learning architectures for accurate millimeter wave positioning in 5G | |
| US10794997B2 (en) | Smartphone-based power-efficient radar processing and memory provisioning for detecting gestures | |
| CN107396311B (en) | Non-contact sensing positioning method | |
| CN116740361B (en) | Point cloud segmentation method and device, storage medium and electronic equipment | |
| CN101487888A (en) | Spacing spectrum peak search method | |
| CN116224279B (en) | Target detection method and device, storage medium and electronic equipment | |
| CN117036868B (en) | Training method and device of human body perception model, medium and electronic equipment | |
| US10989801B2 (en) | Method and device for determining distance from object using radar | |
| Yang et al. | Design of airborne target tracking accelerator based on KCF | |
| CN115144855A (en) | Circular SAR sub-aperture image coherent fast imaging algorithm, device and storage medium | |
| KR102062321B1 (en) | The sensoe module using different frequencies to recognize motion of target object and driving method of the same | |
| CN111578446B (en) | Coal mine ventilation equipment detection method, equipment and medium | |
| CN117554920B (en) | Water surface detection method and device, storage medium and electronic equipment | |
| CN117556266B (en) | Signal identification model training method, signal identification method and device | |
| Shi et al. | 3D target location based on RFID polarization phase model | |
| CN113030941B (en) | Method, device, equipment and storage medium for determining azimuth angle of target object | |
| CN115776345B (en) | Interference measurement method and device, storage medium and electronic equipment | |
| CN116643276B (en) | Three-dimensional imaging method, device and storage medium for synthetic aperture radar | |
| CN111114548B (en) | Vehicle detection method and device, electronic equipment and storage medium | |
| US20240061649A1 (en) | In-memory computing (imc) processor and operating method of imc processor | |
| US20230147708A1 (en) | Method and apparatus for simultaneous power estimation of multiple signal sources in communication system | |
| CN114491444A (en) | Identity recognition method, device and equipment | |
| Zhong et al. | Face Recognition Based on Point Cloud Data Captured by Low-cost mmWave Radar Sensors | |
| Ouerghi et al. | CUDA-Accelerated Feature-Based Egomotion Estimation |
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 |