Detection tool generation and object detection method, apparatus, electronic device, and medium

Abstract

The application discloses a kind of detection tool generation and target detection method, device, electronic equipment and medium, the method and device are applied to electronic equipment, specifically, target area is identified using radar sensor arranged on test carrier, and mobile target is obtained;Sensor speed of radar sensor is calculated according to the vehicle speed of test carrier;The parameters of mobile target and sensor speed are extracted, and a feature set is obtained;Model training is carried out based on the feature set, and target detection tool is obtained.When the target detection tool is applied to radar on vehicle, since the tool can distinguish ghost target, the ghost target can be discarded, so as to avoid target false alarm, and then improve the reliability of radar target detection.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of traffic facilities, and more particularly to a detection tool generation and target detection method and device, electronic equipment and a medium. BACKGROUND

[0002] With the breakthrough and progress of radar technology, radar is used as a sensing device in various fields and scenarios, and microwave radar is widely used because it is not affected by weather conditions.

[0003] However, when processing radar signals, the reflection of non-target object target area surfaces due to multipath effects can easily cause false targets to be generated. In this case, the tracking algorithm will track the false targets, resulting in target false positives, and thus reducing the reliability of microwave radar target detection. This phenomenon is particularly evident and prominent in the target area.

[0004] Existing methods improve the above phenomenon by setting angle returns or manually filtering out noise points, but the effect is not obvious, and the workload of manual filtering is large, and the above problems cannot be well solved. SUMMARY

[0005] Therefore, the present application provides a detection tool generation and target detection method, device, electronic equipment and medium for improving the reliability of radar target detection in the target area.

[0006] In order to achieve the above purpose, the present scheme is as follows:

[0007] A detection tool generation method for constructing a target detection tool, applied to an electronic device, the construction method comprising the steps of:

[0008] Using a radar sensor provided on a test vehicle to perform target recognition in a target area to obtain a moving target;

[0009] Calculating the sensor speed of the radar sensor according to the vehicle speed of the test vehicle;

[0010] Performing feature extraction on the parameters of the moving target and the sensor speed to obtain a feature set;

[0011] Based on the feature set, a model is trained to obtain a target detection tool.

[0012] Optionally, the feature set includes target parameters of the moving target, motion states of the radar sensor, moving object data and static object data around the moving target, moving distances of the moving target within a predetermined period, data of other moving targets, and data of the moving target occupying a grid.

[0013] Optionally, the target parameters include some or all of the angle, relative radial velocity, azimuth angle and reflected power of the moving target relative to the test vehicle.

[0014] Optionally, the motion state includes the absolute value of the sensor speed and the absolute value of the horizontal angular velocity.

[0015] Optionally, the model training based on the feature set includes the steps of:

[0016] The feature set is processed based on a random forest algorithm, and an output class is assigned to the decision algorithm to obtain the target detection tool.

[0017] Optionally, the output class includes real targets, the underlying structure of the target area and ghost targets.

[0018] A target detection method applied to an electronic device, the target detection method comprising the steps of:

[0019] Obtaining a detection signal based on a radar sensor;

[0020] Processing the detection signal based on the target detection tool as described above to obtain a detection target.

[0021] A detection tool generation device for constructing a target detection tool, applied to an electronic device, the construction device comprising:

[0022] A data acquisition module configured to identify a moving target in a target area using a radar sensor arranged on a test vehicle;

[0023] A data calculation module configured to calculate a sensor speed of the radar sensor based on a vehicle speed of the test vehicle;

[0024] A feature extraction module configured to extract features from parameters of the moving target and the sensor speed to obtain a feature set;

[0025] A construction execution module configured to train a model based on the feature set to obtain a target detection tool.

[0026] Optionally, the construction execution module is configured to process the feature set based on a random forest algorithm, and assign an output class to the decision algorithm to obtain the target detection tool.

[0027] A target detection device applied to an electronic device, the target detection device comprising:

[0028] A signal acquisition module configured to obtain a detection signal based on a radar sensor;

[0029] The detection execution module is configured to process the detection signal based on the target detection tool to obtain a detection target.

[0030] An electronic device, comprising at least one processor and a memory connected to the processor, wherein:

[0031] The memory is used to store computer programs or instructions;

[0032] The processor is used to execute the computer programs or instructions, so that the electronic device implements the detection tool generation method or the target detection method.

[0033] A medium applied to an electronic device, and optionally, the medium carries one or more computer programs, which can be executed by the electronic device to make the electronic device implement the detection tool generation method or the target detection method.

[0034] From the above technical solutions, it can be seen that the present application discloses a construction method, a target detection method, an apparatus, an electronic device and a storage medium. The method and apparatus are applied to an electronic device, specifically, a radar sensor arranged on a test carrier is used to identify a target in a target area to obtain a moving target; a sensor speed of the radar sensor is calculated according to a carrier speed of the test carrier; a feature set is obtained by performing feature extraction on parameters of the moving target and the sensor speed; and a target detection tool is obtained by performing model training based on the feature set. When the target detection tool is applied to a radar on a vehicle, the tool can distinguish ghost targets, so that the ghost targets can be discarded, thereby avoiding target false positives and improving the reliability of target detection by the radar. BRIEF DESCRIPTION OF DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments or prior art description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0036] Figure 1 A flowchart of a detection tool generation method according to an embodiment of the present application;

[0037] Figure 2 A schematic diagram of a test carrier according to an embodiment of the present application;

[0038] Figure 3 A flowchart of a target detection method according to an embodiment of the present application;

[0039] Figure 4 A block diagram of a detection tool generation device according to an embodiment of the present application;

[0040] Figure 5 A flowchart of a target detection device according to an embodiment of the present application;

[0041] Figure 6 A block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0042] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0043] Embodiment one

[0044] Figure 1 A flowchart of a detection tool generation method according to an embodiment of the present application.

[0045] As shown in Figure 1 , the detection tool generation method provided by the present embodiment is used to construct a target detection tool for improving the target recognition capability of a microwave radar, and is applied to an electronic device, which can be understood as a computer, a server or an embedded device with data calculation capability and information processing capability. Specifically, the construction method includes the following steps:

[0046] S101, target recognition is performed on a target area by using a radar sensor.

[0047] The radar sensor is arranged on a test vehicle, and the radar sensor realizes target recognition through simple comparison of speeds to obtain a moving target relative to the test vehicle. The radar sensor can be a phased array radar, a MIMO radar, a millimeter wave radar, etc., wherein the millimeter wave radar can be a 4D imaging millimeter wave radar, and the 4D includes four parameters of height, horizontal angle, pitch angle and radial speed. The test vehicle in the present embodiment can be a test vehicle or other walking vehicles. The target area refers to an area with more radial effects, such as a tunnel scene, etc.

[0048] S102, calculating a sensor speed according to a vehicle speed of the test vehicle.

[0049] On the basis of the moving target and its corresponding parameters, the vehicle speed of the test vehicle is collected, and then the sensor speed of the radar sensor is calculated according to the vehicle speed and other parameters. The other parameters include the yaw rate ω of the mounting point of the radar sensor (usually located in the middle of the rear axle of the test vehicle) and the known installation position x', y' of the radar sensor. R

[0050] The sensor speed V of the radar sensor S is calculated according to the following formula:

[0051]

[0052] As shown in Figure 2 , the radial velocity component V S，x , V S，y of the static target at the same height as the radar sensor is equal to the sensor speed V S , and the specific calculation formula is:

[0053] -v D = cos (a) v S，x + sin (a) v S，y . (2)

[0054] Among them, V S，x , V S，y are the radial velocity component and the lateral velocity component of the test vehicle.

[0055] If the above formula (2) does not hold, the detected target is a moving target. In the rare case of pure tangential motion, although formula (2) holds, the detected target is also a moving target. In addition, since the velocity vector is projected into the sensor plane, the measured velocity V D also depends on the installation elevation of the radar sensor, so if the detection height is different from the installation elevation, the calculation result of formula (2) will be reduced, and the specific formula becomes as follows:

[0056] -v D = (cos (a) v S，x + sin (a) v S，y ) · cos (e). (3)

[0057] e in formula (3) is the angle between the line connecting the detected target and the radar mounting point and the sensor plane.

[0058] S103, extracting a feature set from the parameters of the moving target and the sensor speed.

[0059] The parameters of the moving target and the sensor speed are feature extracted to obtain a feature set A, where A is expressed by the following formula: ​

[0060] A = {F1, F2, F3, F4, F5, F6, F7, F8, F9, F10, F11, F12, F13, F14} (4)

[0061] The feature set includes target parameters of the moving target, motion state of the radar sensor, moving object data and static object data around the moving target, moving distance of the moving target within a predetermined period, data of other moving targets and data of the moving target occupying the grid. The meaning of each feature is shown in the following table.

[0062]

[0063] Features F1-F4 are object parameters to be detected.

[0064] F5 and F6 represent the motion state of the test vehicle.

[0065] Feature F7 is used to represent the error of formula (2), which is higher than the aforementioned threshold vDiff of all moving detections.

[0066] Features F8 and F9 indicate the number of moving and static neighbor detections around the object to be detected, respectively. These features can be useful because a real object will generate multiple reflection points for a high-resolution radar sensor.

[0067] Feature F10 is a Boolean variable indicating that a moving target is found around the object to be detected in the previous measurement period. This feature is the only function that does not use data from the current measurement period.

[0068] Feature F11 is also a Boolean variable, which aims to detect ghosting caused by multiple reflections between the sensor and the object or very strong reflection harmonics. The value of these ghosting detections lies in their similar azimuth angle, integer multiple of speed and integer multiple of the actual detection range.

[0069] Features F12 and F13 contain the values of specific cells in the occupancy grid map around the object to be detected.

[0070] Feature F14 is the height value of the object to be detected.

[0071] S104, model training based on the feature set, to obtain a target detection tool.

[0072] After obtaining the above feature set, the random forest algorithm is used to realize model training, the feature set is taken as the input of the decision algorithm, and a plurality of classifications preset are taken as the output for model calculation, so as to obtain the target detection tool. The classifications include real moving targets, basic structures (tunnel shooting or railings, etc.) and ghosting targets.

[0073] The reason for selecting the random forest algorithm in the present application is that it is one of the most effective machine learning models, which can capture highly nonlinear interactions between input variables and output classes, and a small number of training samples is usually sufficient to train a classification model for robust prediction compared with neural networks.

[0074] From the above technical solution, it can be seen that the embodiment provides a detection tool generation method, which is applied to an electronic device, specifically, a radar sensor provided on a test carrier is used to identify a target in a target area to obtain a moving target; a sensor speed of the radar sensor is calculated according to a carrier speed of the test carrier; a feature set is obtained by performing feature extraction on parameters of the moving target and the sensor speed; and a target detection tool is obtained by performing model training based on the feature set. When the target detection tool is applied to a radar on a vehicle, since the tool can distinguish ghost targets, the ghost targets can be discarded, so that target false positives are avoided, and the reliability of target detection by the radar is improved.

[0075] Embodiment two

[0076] Figure 3 A flowchart of a target detection method according to an embodiment of the present application.

[0077] As Figure 3 shown, the target detection method provided by the embodiment is applied to an electronic device, which can be understood as an embedded device of a radar sensor or an in-vehicle infotainment system, and specifically includes the following steps:

[0078] S201, obtaining a detection signal based on a radar sensor.

[0079] That is, in actual application, when an actual carrier such as a vehicle is provided with a radar sensor such as a microwave radar, a detection signal obtained by the radar sensor detecting an environment in which the carrier travels is obtained, and the detection signal is a data signal, so it can also be referred to as detection data.

[0080] S202, processing the detection signal based on a target detection tool.

[0081] After obtaining the above detection signal or detection data, the target detection tool in the previous embodiment is used to process the detection data, and the ghost targets are removed by processing, and the real targets are obtained by removing the ghost targets. In this way, the various targets in the detection area can be effectively detected according to the real targets. Thus, the reliability of target detection by the radar is improved.

[0082] The computer program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0083] While operations are depicted in a particular, sequential order, this should not be understood as requiring or

[0084] It is to be understood that the steps of the methods recited in the method embodiments of the present disclosure can be carried out in a different order and / or concurrently with each other. Additional steps can also be employed.

[0085] Computer program code for carrying out operations of the present disclosure can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0086] Embodiment Three

[0087] Figure 4 A block diagram of a detection tool generation device for embodiments of the present application.

[0088] As Figure 4As shown, the detection tool generation device provided by the embodiment is used to construct a target detection tool for improving the target recognition capability of a microwave radar, and is applied to an electronic device, which can be understood as a computer, a server or an embedded device with data calculation capability and information processing capability. Specifically, the construction device includes a data acquisition module 10, a data processing module 20, a feature extraction module 30 and a construction execution module 40.

[0089] The data acquisition module is used to perform target recognition on a target area by using a radar sensor.

[0090] The radar sensor is arranged on a test vehicle, and the radar sensor realizes target recognition through simple comparison of speeds to obtain a moving target relative to the test vehicle. The radar sensor can be a phased array radar, a MIMO radar, a millimeter wave radar, etc.

[0091] The data processing module is used to calculate the sensor speed according to the vehicle speed of the test vehicle.

[0092] On the basis of obtaining the moving target and the corresponding parameters thereof, the vehicle speed of the test vehicle is collected, and then the sensor speed of the radar sensor is calculated according to the vehicle speed and other parameters. The other parameters include the yaw rate ω and the 2D speed VR (usually located in the middle of the rear axle of the test vehicle) of the installation point of the radar sensor, and the known installation position x', y' of the radar sensor.

[0093] The sensor speed V S of the radar sensor is calculated according to the following formula:

[0094]

[0095] As shown in Figure 2 , the radial velocity component V S，x , V S，y of a static target at the same height as the radar sensor is equal to the sensor speed V S , and the specific calculation formula is as follows:

[0096] -v D = cos (α) v S，x + sin (α) v S,y . (2)

[0097] Wherein V S，x , V S，y are the radial velocity component and the lateral velocity component of the test vehicle.

[0098] If the above formula (2) is not established, the detection target is a moving target. In the case of rarely appearing pure tangential motion, although formula (2) is established, the detection target is also a moving target. In addition, since the velocity vector is projected into the sensor plane, the measured velocity V D Also depends on the installation elevation of the radar sensor, so if the detection height is different from the installation elevation, the calculation result of formula (2) will be reduced, and the specific formula becomes as follows:

[0099] -v D =(cos(α)v S，x +sin(α)v S，y )·cos(ε). (3)

[0100] Epsilon in formula (3) is the angle between the connecting line between the detection target and the radar installation point and the sensor plane.

[0101] The feature extraction module is used to extract a feature set from the parameters of the moving target and the sensor velocity.

[0102] The parameters of the moving target and the sensor velocity are feature extracted to obtain a feature set A, wherein A is expressed by the following formula:

[0103] A={F1,F2,F3,F4,......,F14} (4)

[0104] The feature set includes target parameters of the moving target, motion state of the radar sensor, moving object data and static object data around the moving target, moving distance of the moving target within a predetermined period, data of other moving targets, and data of the moving target occupying the grid.

[0105] The construction execution module is used to train a model based on the feature set to obtain a target detection tool.

[0106] After obtaining the above feature set, the model training is realized by using the random forest algorithm, the feature set is taken as the input of the decision algorithm, and a plurality of classifications preset are taken as the output for model calculation, so as to obtain the target detection tool. The classifications include real moving targets, basic structures (tunnel shooting or railings, etc.) and ghost targets.

[0107] The reason why the random forest algorithm is selected in the present application is that it is one of the most effective machine learning models, which can capture the highly nonlinear interaction between input variables and output classes. Compared with neural networks, a small amount of training samples is usually sufficient to train a classification model for robust prediction.

[0108] From the above technical solution can be seen, the embodiment provides a kind of detection tool generation device, the device is applied to electronic equipment, specifically, target identification is carried out to target area using radar sensor arranged on test carrier, and mobile target is obtained;Sensor speed of radar sensor is calculated according to the carrier speed of test carrier;The parameters of mobile target and sensor speed are extracted, and a feature set is obtained;Model training is carried out based on feature set, and target detection tool is obtained.When the target detection tool is applied to radar on vehicle, since the tool can distinguish ghost target, ghost target can be discarded, so as to avoid target false alarm, and then the reliability of radar target detection is improved.

[0109] Embodiment four

[0110] Figure 5 A block diagram of a target detection device according to an embodiment of the present application.

[0111] As Figure 5 shown, the target detection device provided by the embodiment is applied to electronic equipment, which can be understood as an embedded device of radar sensor or a car machine, and specifically includes a signal acquisition module 50 and a detection execution module 60.

[0112] The signal acquisition module is used to acquire detection signals based on the radar sensor.

[0113] That is, in actual application, when an actual carrier such as a vehicle is provided with a radar sensor such as a microwave radar, the detection signals obtained by the radar sensor for detecting the environment in which the carrier travels are acquired, and the detection signals are data signals, so they can also be called detection data.

[0114] The detection execution module is used to process the detection signals based on the target detection tool.

[0115] After obtaining the above detection signals or detection data, the target detection tool in the previous embodiment is used to process the detection data, and the ghost target is removed by processing, and the real target is obtained by removing the ghost target. Thus, according to the real target, effective detection of various targets in the detection area can be implemented. Thus, the reliability of radar target detection is improved.

[0116] The units described in the embodiments of the present disclosure can be implemented in software or hardware. Among them, the name of the unit does not constitute a limitation on the unit itself in some cases, for example, the first acquisition unit can also be described as "a unit for acquiring at least two internet protocol addresses".

[0117] The functionality described herein above can be performed, at least in part, by one or more hardware logic components. For example, and without limitation, an example type of hardware logic components that can be used include Field-programmable Gate Arrays (FPGAs), Application-specific Integrated Circuits (ASICs), Application-specific Standard Products (ASSPs), System-on-a-chip systems (SOCs), Complex Programmable Logic Devices (CPLDs), etc.

[0118] Embodiment Five

[0119] Figure 6 A block diagram of an electronic device according to an embodiment of the present application.

[0120] Reference Figure 6 As shown, it shows a structural schematic diagram suitable for implementing an electronic device in the embodiments of the present disclosure. The terminal device in the embodiments of the present disclosure can include, but is not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet PCs), PMPs (Portable Multimedia Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and the like, as well as fixed terminals such as digital TVs, desktop computers, and the like. The electronic device is only an example, and should not bring any limitation to the functions and use range of the embodiments of the present disclosure.

[0121] The electronic device can include a processing device (such as a central processor, a graphics processor, etc.) 401, which can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) or loaded into a random access memory (RAM) 403 from an input device 406. In the RAM, various programs and data required for the operation of the electronic device are also stored. The processing device, the ROM, and the RAM are connected to each other through a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0122] Generally, the following devices can be connected to the I / O interface: input devices including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, and the like; output devices 407 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, and the like; storage devices 408 including, for example, a magnetic tape, a hard disk, and the like; and communication devices 409. The communication devices 409 can allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although the electronic device with various devices is shown in the figure, it should be understood that it is not required to implement or have all the shown devices. More or fewer devices can be alternatively implemented or provided.

[0123] The electronic device can specifically identify a target in a target area by using a radar sensor arranged on a test carrier to obtain a moving target, calculate a sensor speed of the radar sensor according to a carrier speed of the test carrier, extract features of parameters of the moving target and the sensor speed to obtain a feature set, and train a model based on the feature set to obtain a target detection tool. When the target detection tool is applied to a radar on a vehicle, the tool can distinguish ghost targets, so that the ghost targets can be discarded, target false positives can be avoided, and the reliability of target detection by the radar is improved.

[0124] Embodiment six

[0125] The embodiment provides a computer readable medium applied to an electronic device, and the medium carries one or more programs, which, when executed by the electronic device, enable the electronic device to identify a target in a target area by using a radar sensor arranged on a test carrier to obtain a moving target, calculate a sensor speed of the radar sensor according to a carrier speed of the test carrier, extract features of parameters of the moving target and the sensor speed to obtain a feature set, and train a model based on the feature set to obtain a target detection tool. When the target detection tool is applied to a radar on a vehicle, the tool can distinguish ghost targets, so that the ghost targets can be discarded, target false positives can be avoided, and the reliability of target detection by the radar is improved.

[0126] It should be noted that the computer readable medium of the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the two. The computer readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination of the above. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0127] In this disclosure, a computer readable medium can be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer readable signal medium can include a propagated data signal with computer readable program code embodied therein, for use by or in connection with an instruction execution system, apparatus, or device. The computer readable program code can be transmitted using any appropriate medium, including but not limited to wireless, wire line, optical fiber cable, RF, etc., or any suitable combination of the foregoing. Computer readable medium can comprise memory such as, but not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD- ROM, digital versatile discs (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer.

[0128] Embodiments in the present specification are described with progression in an exemplary manner. Each embodiment can have a different application, and is intended to be independently useful. Some embodiments can be implemented and performed by one or more of the elements in a hardware manner, or by a combination of hardware and software in a computer readable medium. As such, embodiments of the present specification can cover computer software programs, firmware, computer readable media, structures, systems, apparatuses, methods, and other

[0129] Although the preferred embodiments of the present application have been described, those skilled in the art will be able to make modifications and alterations to this application without departing from the scope of the application. Accordingly, it is intended to cover all such modifications and alterations that fall within the scope of the application. Thus, the attached claims are intended to cover all modifications and alterations of this application.

[0130] Finally, it should be noted that the terms "first", "second", and the like, herein do not denote any order, quantity, combination, or importance, but rather are used to distinguish one element from another, and are more especially used for the purpose of ease of description and illustration. In addition, the words "comprises", "comprising", or the like, and the like, are intended to encompass non-exclusive inclusions, such that a process, method, article, or apparatus that comprises a list of elements is not necessarily limited to those elements, but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. In the absence of a contrary statement, an element specified by the phrase "comprising a" does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes the specified element.

[0131] The technical solutions provided by the present application are described in detail above, and the principles and implementation manners of the present application are described by applying specific examples. The above description of the examples is only used to help understand the method of the present application and its core idea. Meanwhile, for those skilled in the art, according to the idea of the present application, the specific implementation manners and application ranges will be changed, and the above description should not be understood as a limitation on the present application.

Claims

1. A method for generating a detection tool, used to construct a target detection tool for application in electronic devices, characterized in that, The method for generating the detection tool includes the following steps: The target area is identified by using radar sensors mounted on the test vehicle to obtain moving targets. The sensor speed of the radar sensor is calculated based on the vehicle speed of the test vehicle; Feature extraction is performed on the parameters of the moving target and the speed of the sensor to obtain a feature set. The feature set includes the target parameters of the moving target, the motion state of the radar sensor, the data of moving objects and static objects around the moving target, the moving distance of the moving target within a predetermined period, the data of other moving targets, and the data of the grid occupied by the moving target. The target parameters include some or all of the angle, relative radial velocity, azimuth angle, and reflection power of the moving target relative to the test vehicle. The target detection tool is obtained by training the model based on the feature set.

2. The detection tool generation method as described in claim 1, characterized in that, The motion state includes the absolute value of the sensor's velocity and the absolute value of its horizontal angular velocity.

3. The detection tool generation method as described in claim 1, characterized in that, The model training based on the feature set includes the following steps: The feature set is processed using the random forest algorithm, and an output class is assigned to the decision algorithm to obtain the target detection tool.

4. The detection tool generation method as described in claim 3, characterized in that, The output class includes the real target, the basic structure of the target region, and the ghosted target.

5. A target detection method applied to electronic devices, characterized in that, The target detection method includes the following steps: Detection signals are acquired based on radar sensors; The detection signal is processed using the target detection tool as described in any one of claims 1 to 4 to obtain the detection target.

6. A detection tool generation apparatus for constructing a target detection tool for use in electronic devices, characterized in that, The detection tool generating device includes: The data acquisition module is configured to use radar sensors mounted on the test vehicle to identify moving targets in the target area. The data calculation module is configured to calculate the sensor speed of the radar sensor based on the vehicle speed of the test vehicle; The feature extraction module is configured to extract features from the parameters of the moving target and the speed of the sensor to obtain a feature set. The feature set includes the target parameters of the moving target, the motion state of the radar sensor, the data of moving objects and static objects around the moving target, the moving distance of the moving target within a predetermined period, the data of other moving targets, and the data of the grid occupied by the moving target. The target parameters include some or all of the angle, relative radial velocity, azimuth angle, and reflection power of the moving target relative to the test vehicle. An execution module is built and configured to train a model based on the feature set to obtain an object detection tool.

7. The detection tool generating apparatus as described in claim 6, characterized in that, The construction execution module is configured to process the feature set based on the random forest algorithm and assign an output class to the decision algorithm to obtain the target detection tool.

8. A target detection device, applied to electronic equipment, characterized in that, The target detection device includes: The signal acquisition module is configured to acquire detection signals based on radar sensors; The detection execution module is configured to process the detection signal based on the target detection tool as described in claim 6 or 7 to obtain the detection target.

9. An electronic device, characterized in that, It includes at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs or instructions; The processor is used to execute the computer program or instructions to enable the electronic device to implement the detection tool generation method as described in any one of claims 1 to 4, or to implement the target detection method as described in claim 5.

10. A storage medium used in an electronic device, characterized in that, The storage medium carries one or more computer programs that can be executed by the electronic device to enable the electronic device to implement the detection tool generation method as described in any one of claims 1 to 4, or the target detection method as described in claim 5.

Images