Method and system for estimating obstacle material using neural network-based radar

Abstract

A method and system for estimating obstacle material using a neural network-based radar are disclosed. An obstacle material estimation method performed by an obstacle material estimation system according to one embodiment may include: a step of collecting radar signal data transmitted to and received from an obstacle via a radar; a step of outputting Intermediate Frequency (IF) signal data using transmitted signal data and reflected signal data included in the collected radar signal data; a step of estimating distance data to the obstacle and material data of the obstacle using a material classification model based on signal characteristics obtained through data processing using the transmitted signal data, reflected signal data, and the outputted IF signal data; and a step of outputting obstacle information including the estimated distance data to the obstacle and material data of the obstacle.

Description

Technology Field

[0001] The following description concerns a technique for estimating obstacle materials. Background Technology

[0003] Recently, research on detecting obstacles using radar has been underway. For example, Korean Patent Publication No. 10-2018-0088009 (published on August 3, 2018) relates to a method and device for measuring distance using radar in an environment where obstacles exist, and discloses a configuration for determining material and thickness by simply training an SVM with reflected wave signals and FFT values. However, it does not specifically present a method for measuring distance from reflected waves, and since it simply trains an SVM with reflected wave signals and frequency components, while it is possible to output classification values ​​as the environment of the collected data becomes more diverse, it is difficult to estimate regression values. The problem to be solved

[0005] We aim to accurately estimate the material of various obstacles using FMW radar. means of solving the problem

[0007] An obstacle material estimation method performed by an obstacle material estimation system may include: a step of collecting radar signal data transmitted to and received from an obstacle via a radar; a step of outputting Intermediate Frequency (IF) signal data using transmitted signal data and reflected signal data included in the collected radar signal data; a step of estimating distance data to the obstacle and material data of the obstacle using a material classification model based on signal characteristics obtained through data processing using the transmitted signal data, reflected signal data, and the outputted IF signal data; and a step of outputting obstacle information including the estimated distance data to the obstacle and material data of the obstacle.

[0008] The above-mentioned collecting step includes receiving a transmit chirp transmitted to an obstacle and a reflect chirp reflected upon reaching the obstacle by generating a signal of a specific frequency over time through a radar, generating transmit signal data using the received transmit chirp, and generating reflect signal data using the received reflect chirp, wherein the reflect chirp may include a delay time delayed by a certain amount of time and reflection noise caused by the surrounding environment.

[0009] The step of outputting the above IF (Intermediate Frequency) signal data includes the step of mixing the transmission signal data and the reflection signal data to output the IF (Intermediate Frequency) signal data, and the IF signal data represents the difference in the frequency domain between the transmission signal data and the reflection signal data and may include time difference data between the transmission chirp and the reflection chirp.

[0010] The above-mentioned estimation step includes a step of obtaining signal characteristics through data processing using the transmitted signal data, reflected signal data, and the output IF signal data, and the reflected signal data may be composed of the transmitted signal data and reflected noise.

[0011] The above-mentioned estimation step includes a step of separating reflection noise and reflection signal data from which reflection noise has been removed using the time difference data included in the transmission signal data, reflection signal data, and the output IF signal data, and the time difference data included in the output IF signal data may be extracted as a signal characteristic.

[0012] The above-mentioned estimation step includes extracting an attenuation rate function obtained through an operation between the transmitted signal data and the reflected signal data from which the reflected noise has been removed as a signal characteristic, and extracting a noise function obtained through a fast Fourier transform (FFT) on the output attenuation rate function and the reflected noise as a signal characteristic, wherein the attenuation rate function derives the reflectance at a wavelength of a specific frequency according to the material, and the noise function derives the noise included in the signal according to the material.

[0013] The above material classification model includes an obstacle distance calculation model and a neural network-based material classification model, and the estimation step may include obtaining a material classification value using an attenuation rate function and a noise function among the signal characteristics through the neural network-based material classification model, and outputting distance data to the obstacle using the time difference data included in the output IF signal data and the obtained material classification value through the obstacle distance calculation model.

[0014] In a computer program stored on a computer-readable storage medium for executing an obstacle material estimation method performed by an obstacle material estimation system, the obstacle material estimation method may include: a step of collecting radar signal data transmitted to and received to an obstacle via a radar; a step of outputting Intermediate Frequency (IF) signal data using transmitted signal data and reflected signal data included in the collected radar signal data; a step of estimating distance data to an obstacle and material data of an obstacle using a material classification model for signal characteristics obtained through data processing using the transmitted signal data, reflected signal data and the outputted IF signal data; and a step of outputting obstacle information including the estimated distance data to an obstacle and material data of an obstacle.

[0015] An obstacle material estimation system may include: a signal acquisition unit that collects radar signal data transmitted to and received from an obstacle via radar; a signal processing unit that outputs Intermediate Frequency (IF) signal data using transmitted signal data and reflected signal data included in the collected radar signal data; a material classification unit that estimates distance data to the obstacle and material data of the obstacle using a material classification model based on signal characteristics obtained through data processing using the transmitted signal data, reflected signal data, and the outputted IF signal data; and an obstacle information output unit that outputs obstacle information including the estimated distance data to the obstacle and material data of the obstacle.

[0016] The signal acquisition unit described above receives a transmit chirp transmitted to an obstacle and a reflect chirp reflected upon reaching the obstacle by generating a signal of a specific frequency over time through a radar, and generates transmit signal data using the received transmit chirp and generates reflect signal data using the received reflect chirp, wherein the reflect chirp may include a delay time delayed by a certain amount of time and noise caused by the surrounding environment.

[0017] The signal processing unit includes mixing the transmitted signal data and the reflected signal data to output an IF (Intermediate Frequency) signal data, and the IF signal data represents the difference between the transmitted signal data and the reflected signal data in the frequency domain and may include time difference data between the transmitted chirp and the reflected chirp.

[0018] The above material classification unit includes obtaining signal characteristics through data processing using the above transmission signal data, reflection signal data, and the above output IF signal data, and the above reflection signal data may be composed of the above transmission signal data and reflection noise.

[0019] The above material classification unit includes separating reflection noise and reflection signal data from which reflection noise has been removed using the time difference data included in the transmission signal data, reflection signal data, and the output IF signal data, and the time difference data included in the output IF signal data may be extracted as a signal characteristic.

[0020] The above material classification unit includes extracting an attenuation rate function obtained through an operation between the transmitted signal data and the reflected signal data from which the reflected noise has been removed as a signal characteristic, and extracting a noise function obtained through a fast Fourier transform (FFT) on the output attenuation rate function and the reflected noise as a signal characteristic, wherein the attenuation rate function derives the reflectance at a wavelength of a specific frequency according to the material, and the noise function derives the noise included in the signal according to the material.

[0021] The above material classification model includes an obstacle distance calculation model and a neural network-based material classification model, and the estimation step can obtain a material classification value using the attenuation rate function and the noise function among the signal characteristics through the neural network-based material classification model, and output distance data to the obstacle using the time difference data included in the output IF signal data and the obtained material classification value through the obstacle distance calculation model. Effects of the invention

[0023] By utilizing the delay times of the original signal and the reflected signal, distance data to obstacles can be accurately output, and by utilizing the signal processing unit to classify the original signal and reflected noise of the reflected wave, material classification performance can be improved. Brief explanation of the drawing

[0025] FIG. 1 is a block diagram illustrating an obstacle material estimation system in one embodiment. FIG. 2 is a flowchart illustrating a method for estimating obstacle material in one embodiment. FIG. 3 is a diagram illustrating an obstacle material estimation operation in one embodiment. FIG. 4 is a diagram illustrating the operation of collecting radar signal data in one embodiment. FIG. 5 is an example of radar signal data in one embodiment. FIG. 6 is a diagram illustrating a signal processing operation in one embodiment. FIG. 7 is a diagram illustrating a material classification operation in one embodiment. FIG. 8 is a diagram illustrating a data processing operation in one embodiment. FIG. 9 is a diagram showing the calculation process of an IF (intermediate Frequency) signal in one embodiment. Specific details for implementing the invention

[0026] Hereinafter, embodiments will be described in detail with reference to the attached drawings.

[0028] FIG. 1 is a block diagram illustrating an obstacle material estimation system in one embodiment, and FIG. 2 is a flowchart illustrating an obstacle material estimation method in one embodiment.

[0029] The processor of the obstacle material estimation system (100) may include a signal collection unit (110), a signal processing unit (120), a material classification unit (130), and an obstacle information output unit (140). These components of the processor may be representations of different functions performed by the processor according to control commands provided by program code stored in the obstacle material estimation system. The processor and the components of the processor may control the obstacle material estimation system to perform steps (210 to 240) included in the obstacle material estimation method of FIG. 2. At this time, the processor and the components of the processor may be implemented to execute instructions according to the code of an operating system included in memory and the code of at least one program.

[0030] The processor can load program code stored in a file of a program for an obstacle material estimation method into memory. For example, when a program is executed in an obstacle material estimation system, the processor can control the obstacle material estimation system to load program code from a file of a program into memory under the control of an operating system. At this time, the signal collection unit (110), the signal processing unit (120), the material classification unit (130), and the obstacle information output unit (140) may each be different functional representations of the processor for executing commands of corresponding parts of the program code loaded into memory to execute subsequent steps (210 to 240).

[0031] In step (210), the signal collection unit (110) can collect radar signal data transmitted to and received from the obstacle via the radar. The signal collection unit (110) receives a transmit chirp transmitted to the obstacle and a reflect chirp reflected upon reaching the obstacle by generating a signal of a specific frequency over time via the radar, and can generate transmit signal data using the received transmit chirp and generate reflect signal data using the received reflect chirp. The reflect chirp may include a delay time delayed by a certain amount of time and reflection noise caused by the surrounding environment.

[0032] In step (220), the IF signal output unit (120) can output Intermediate Frequency (IF) signal data using the transmitted signal data and reflected signal data included in the collected radar signal data. The IF signal output unit (120) can output Intermediate Frequency (IF) signal data by mixing the transmitted signal data and the reflected signal data. At this time, the IF signal data represents the difference in the frequency domain between the transmitted signal data and the reflected signal data, and may include time difference data between the transmitted chirp and the reflected chirp.

[0033] In step (230), the material classification unit (130) can estimate distance data to an obstacle and material data of an obstacle using a material classification model for signal characteristics obtained through data processing using transmitted signal data, reflected signal data, and outputted IF signal data. The material classification unit (130) can obtain signal characteristics through data processing using transmitted signal data, reflected signal data, and outputted IF signal data. At this time, the reflected signal data may consist of transmitted signal data and reflected noise. The material classification unit (130) can separate the reflected noise and the reflected signal data from which the reflected noise has been removed by using the time difference data included in the transmitted signal data, reflected signal data, and outputted IF signal data. At this time, the time difference data included in the outputted IF signal data can be extracted as a signal characteristic. The material classification unit (130) can extract a signal characteristic by performing an operation between the transmitted signal data and the reflected signal data from which reflected noise has been removed, and can extract a signal characteristic by performing a fast Fourier transform (FFT) on the outputted signal characteristic and the reflected noise. The material classification unit (130) can obtain a material classification value using the signal characteristic, the signal characteristic, and the signal characteristic using the signal characteristic, the signal characteristic, and can output distance data to the obstacle using the time difference data included in the outputted IF signal data and the obtained material classification value through an obstacle distance calculation model.

[0034] In step (240), the obstacle information output unit (140) can output obstacle information including distance data to the estimated obstacle and material data of the obstacle.

[0035] FIG. 3 is a diagram illustrating an obstacle material estimation operation in one embodiment.

[0036] The obstacle material estimation system can collect FMCW radar signal data (310). The obstacle material estimation system can collect FMCW radar signal data transmitted to and received from the obstacle. The obstacle material estimation system can collect a transmit chirp transmitted to the obstacle and a reflected chirp received as it reaches the obstacle by generating a signal of a specific frequency over time through the radar. At this time, the reflected chirp may include a delay time of a certain duration and noise caused by the surrounding environment. The obstacle material estimation system can generate transmit signal data using the transmit chirp and generate reflected signal data using the reflected chirp.

[0037] Referring to Fig. 4, this is a diagram illustrating the operation of collecting radar signal data. The obstacle material estimation system can convert analog-based transmitted signal data and reflected signal data into digital-based transmitted signal data and reflected signal data through a Low Pass Filter (LPF).

[0038] Referring to Fig. 5, the collected radar signal data is shown, and transmitted signal data and reflected signal data containing noise can be identified. The transmitted signal data and reflected signal data can be configured as follows.

[0039]

[0040] The obstacle material estimation system can output Intermediate Frequency (IF) signal data through signal processing using transmitted signal data and reflected signal data included in the FMCW radar signal data (320). Referring to Fig. 6, this is a diagram illustrating the signal processing operation. The obstacle material estimation system can output IF signal data by mixing the transmitted signal data and the reflected signal data. For example, the obstacle material estimation system can amplify the reflected signal data to extract attenuation and delay characteristics between the transmitted signal data and the reflected signal data. Referring to Fig. 9, the calculation process of the IF signal data is shown. At this time, the IF signal data is the difference between the transmitted signal data and the reflected signal data in the frequency domain, and includes tau, which is signal difference data between the chirps of the two signals.

[0041] The obstacle material estimation system obtains signal characteristics through data processing (710) using transmitted signal data, reflected signal data, and output IF signal data, and can estimate distance data to the obstacle and material data (material classification value) of the obstacle through a material classification model based on the obtained signal characteristics (330). The obstacle material estimation system can obtain an attenuation rate function, a delay time, and a noise function as signal characteristics through data processing. Here, the attenuation rate function (A(t)) means deriving the reflectance at a specific frequency wavelength according to the material, and the delay time ( ) represents the distance between the surface of the material to be estimated and the radar, and the noise function (N(t)) represents deriving the noise included in the signal depending on the material.

[0042] Referring to Fig. 8, this is a diagram illustrating the data processing operation. The obstacle material estimation system utilizes the fact that the reflected signal data (raw) in the signal generation consists of transmitted signal data and reflected noise to generate idle reflected signal data based on the reflected signal data (raw Rx), thereby separating it into reflected noise and reflected signal data from which reflected noise has been removed. Subsequently, the obstacle material estimation system can output an attenuation rate function (A(t)) through signal processing by performing operations between the transmitted signal data and the reflected signal data from which reflected noise has been removed. Finally, the obstacle material estimation system can output a noise function (N(t)) by applying a fast Fourier transform (FFT) to the attenuation rate function (A(t)) and the reflected noise.

[0043] Referring to Fig. 7, this is a diagram illustrating the material classification operation. The obstacle material estimation system can calculate distance data to the obstacle through an obstacle distance calculation model. The obstacle material estimation system can calculate distance data to the obstacle as the average of the distance value calculated through tau and the distance value calculated through the attenuation rate according to the material, as shown in Equation 5.

[0044] Mathematical formula 5:

[0045]

[0046] An obstacle material estimation system can output a material classification value by inputting a damping rate function (A(t)) and a noise function (N(t)) in the form of a 2-channel n*m*2 to a neural network-based material classification model and passing them through a CNN and an LSTM. In this case, the neural network-based material classification model may be trained in advance to output a classification value for the material using a dataset for obstacle material classification. For example, the obstacle material estimation system can output material information corresponding to the output material classification value using a database that stores material information. In this case, the database storing material information can store material information mapped to each material classification value.

[0047] The obstacle material estimation system can output obstacle information including distance data to the estimated obstacle and material data of the obstacle (340).

[0048] According to one embodiment, a highly reliable method for accurately estimating the material of various obstacles using FMCW radar can be provided. By utilizing the delay times of the original signal and the reflected signal, distance data to the obstacle can be accurately output, and by utilizing a signal processing unit to classify the original signal and reflected noise of the reflected wave, material classification performance can be improved. By monitoring and analyzing in real time, it can be utilized in various industrial fields. Furthermore, composite material estimation is possible by inputting both the original signal (tx, rx) and the reflected noise into the model to determine the material.

[0049] The device described above may be implemented as a hardware component, a software component, and / or a combination of a hardware component and a software component. For example, the device and components described in the embodiments may be implemented using one or more general-purpose or special-purpose computers, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions. The processing unit may execute an operating system (OS) and one or more software applications executed on said operating system. Additionally, the processing unit may access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing unit may be described as being used as a single unit, but those skilled in the art will understand that the processing unit may include a plurality of processing elements and / or a plurality of types of processing elements. For example, the processing unit may include multiple processors or one processor and one controller. Additionally, other processing configurations, such as parallel processors, are also possible.

[0050] Software may include computer programs, code, instructions, or a combination of one or more of these, and may configure a processing unit to operate as desired or instruct the processing unit independently or collectively. Software and / or data may be embodied in any type of machine, component, physical device, virtual equipment, computer storage medium, or device so as to be interpreted by the processing unit or to provide instructions or data to the processing unit. Software may be distributed over networked computer systems and may be stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

[0051] The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., either alone or in combination. The program instructions recorded on the medium may be those specifically designed and configured for the embodiment, or they may be those known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc.

[0052] Although the embodiments have been described above with reference to limited examples and drawings, those skilled in the art can make various modifications and variations from the description above. For example, suitable results can be achieved even if the described techniques are performed in a different order than described, and / or the components of the described system, structure, device, circuit, etc. are combined or assembled in a form different from described, or replaced or substituted by other components or equivalents.

[0053] Therefore, other implementations, other embodiments, and equivalents to the claims also fall within the scope of the claims set forth below.

Claims

Claim 1 A method for estimating the material of an obstacle, performed by an obstacle material estimation system, comprises: a step of collecting radar signal data transmitted to and received to an obstacle via radar; a step of outputting Intermediate Frequency (IF) signal data using transmitted signal data and reflected signal data included in the collected radar signal data; and a step of estimating distance data to the obstacle and material data of the obstacle using a material classification model for signal characteristics obtained through data processing using the transmitted signal data, reflected signal data, and the outputted IF signal data. The method for estimating an obstacle material includes the step of outputting obstacle information including distance data to the estimated obstacle and material data of the obstacle, wherein the estimating step comprises obtaining signal characteristics through data processing using the transmitted signal data, reflected signal data, and the outputted IF signal data, separating the reflected noise and the reflected signal data from which the reflected noise has been removed using time difference data included in the transmitted signal data, reflected signal data, and the outputted IF signal data, extracting an attenuation rate function obtained through an operation between the transmitted signal data and the reflected signal data from which the reflected noise has been removed as a signal characteristic, and extracting a noise function obtained through a fast Fourier transform (FFT) on the outputted attenuation rate function and the reflected noise as a signal characteristic, wherein the reflected signal data is composed of the transmitted signal data and the reflected noise, the time difference data included in the outputted IF signal data is extracted as a signal characteristic, the attenuation rate function derives the reflectance at a wavelength of a specific frequency according to the material, and the noise function derives the noise included in the signal according to the material. Claim 2 In claim 1, the collecting step comprises receiving a transmit chirp transmitted to an obstacle and a reflect chirp reflected upon reaching the obstacle by generating a signal of a specific frequency over time through a radar, generating transmit signal data using the transmit chirp, and generating reflect signal data using the received reflect chirp, wherein the reflect chirp includes a delay time delayed by a certain amount of time and reflection noise caused by the surrounding environment. Claim 3 A method for estimating obstacle material according to claim 1, wherein the step of outputting the IF (Intermediate Frequency) signal data includes the step of mixing the transmitted signal data and the reflected signal data to output the IF (Intermediate Frequency) signal data, and wherein the IF signal data represents the difference in the frequency domain between the transmitted signal data and the reflected signal data, and includes time difference data between the transmitted chirp and the reflected chirp. Claim 4 delete Claim 5 delete Claim 6 delete Claim 7 A method for estimating obstacle material according to claim 1, wherein the material classification model includes an obstacle distance calculation model and a neural network-based material classification model, and the estimation step includes obtaining a material classification value using a damping rate function and a noise function among the signal characteristics through the neural network-based material classification model, and outputting distance data to the obstacle using the time difference data included in the output IF signal data and the obtained material classification value through the obstacle distance calculation model. Claim 8 A computer program stored in a computer-readable storage medium for executing an obstacle material estimation method performed by an obstacle material estimation system, wherein the obstacle material estimation method comprises: a step of collecting radar signal data transmitted to and received to an obstacle via a radar; a step of outputting Intermediate Frequency (IF) signal data using transmitted signal data and reflected signal data included in the collected radar signal data; and a step of estimating distance data to an obstacle and material data of an obstacle using a material classification model for signal characteristics obtained through data processing using the transmitted signal data, reflected signal data and the outputted IF signal data.A computer program stored on a computer-readable storage medium that executes the following steps: outputting obstacle information including distance data to the estimated obstacle and material data of the obstacle; wherein the estimating step comprises obtaining signal characteristics through data processing using the transmitted signal data, reflected signal data, and the outputted IF signal data; separating reflected noise and reflected signal data from which reflected noise has been removed using time difference data included in the transmitted signal data, reflected signal data, and the outputted IF signal data; extracting an attenuation rate function obtained through an operation between the transmitted signal data and the reflected signal data from which reflected noise has been removed as a signal characteristic; and extracting a noise function obtained through a fast Fourier transform (FFT) on the outputted attenuation rate function and the reflected noise as a signal characteristic; wherein the reflected signal data is composed of the transmitted signal data and reflected noise, the time difference data included in the outputted IF signal data is extracted as a signal characteristic, the attenuation rate function derives the reflectance at a wavelength of a specific frequency according to the material, and the noise function derives the noise included in the signal according to the material. Claim 9 In an obstacle material estimation system, a signal acquisition unit that collects radar signal data transmitted to and received from an obstacle via radar; a signal processing unit that outputs Intermediate Frequency (IF) signal data using transmitted signal data and reflected signal data included in the collected radar signal data; and a material classification unit that estimates distance data to the obstacle and material data of the obstacle using a material classification model based on signal characteristics obtained through data processing using the transmitted signal data, reflected signal data, and the outputted IF signal data. An obstacle material estimation system comprising: an obstacle information output unit that outputs obstacle information including distance data to the estimated obstacle and material data of the obstacle; wherein the material classification unit obtains signal characteristics through data processing using the transmitted signal data, reflected signal data, and the outputted IF signal data; separates reflected noise and reflected signal data from which reflected noise has been removed using time difference data included in the transmitted signal data, reflected signal data, and the outputted IF signal data; extracts an attenuation rate function obtained through an operation between the transmitted signal data and the reflected signal data from which reflected noise has been removed as a signal characteristic; and extracts a noise function obtained through a fast Fourier transform (FFT) on the outputted attenuation rate function and the reflected noise as a signal characteristic; wherein the reflected signal data is composed of the transmitted signal data and the reflected noise, the time difference data included in the outputted IF signal data is extracted as a signal characteristic, the attenuation rate function derives the reflectance at a wavelength of a specific frequency according to the material, and the noise function derives the noise included in the signal according to the material. Claim 10 In claim 9, the signal collection unit receives a transmit chirp transmitted to an obstacle and a reflect chirp reflected upon reaching the obstacle by generating a signal of a specific frequency over time through a radar, generates transmit signal data using the transmit chirp, and generates reflect signal data using the received reflect chirp, wherein the reflect chirp includes a delay time delayed by a certain amount of time and reflection noise caused by the surrounding environment, characterized in that the obstacle material estimation system. Claim 11 An obstacle material estimation system according to claim 9, wherein the signal processing unit comprises mixing the transmitted signal data and the reflected signal data to output an IF (Intermediate Frequency) signal data, and the IF signal data represents the difference in the frequency domain between the transmitted signal data and the reflected signal data, and includes time difference data between the transmitted chirp and the reflected chirp. Claim 12 delete Claim 13 delete Claim 14 delete Claim 15 An obstacle material estimation system according to claim 9, wherein the material classification model includes an obstacle distance calculation model and a neural network-based material classification model, and the estimation step is characterized by obtaining a material classification value using a damping rate function and a noise function among the signal characteristics through the neural network-based material classification model, and outputting distance data to the obstacle using the time difference data included in the output IF signal data and the obtained material classification value through the obstacle distance calculation model.

Images