Shape estimation system, object detection system, and communication system, and shape estimation method, object detection method, and communication method

Abstract

According to the present invention, the distance, between a vehicle (1) and a detection object (3), acquired on the basis of the time from when a transmission wave (2A) is transmitted until when a received wave (2B) scattered / reflected from the detection object (3) is received, and an amplitude value / intensity value of the received wave (2B) corresponding to the distance are stored as detection data, the amplitude value / intensity value of the received wave (2B) corresponding to the distance between the vehicle (1) and the detection object (3) are resampled as sampling data of a desired distance, the resampled data is converted from a spatial domain to a spatial frequency domain, a set of spectra in the spatial frequency domain for a plurality of preset object shapes is saved as a database in association with the object shapes, and the shape of the detection object (3) is estimated on the basis of the spectrum of the detection object (3) and the saved set of spectra. In addition, the object shape corresponding to the spectrum closest to the spectrum of the detection object (3) among the set of spectra is estimated to be the shape of the detection object (3).

Description

【Technical Field】 【0001】 The present invention relates to a shape estimation system, an object detection system, and a communication system for a vehicle that detect an object existing around the vehicle and estimate the shape of the object, as well as a shape estimation method, an object detection method, and a communication method. 【Background Art】 【0002】 As a technique for estimating whether an object existing around a vehicle is a human body, for example, there is Patent Document 1. Patent Document 1 describes that "the human body detection device according to the embodiment acquires detection information from an ultrasonic sensor that has received a reflected wave of ultrasonic waves transmitted to a predetermined area. The reflected wave waveform corresponding to the detection information is normalized based on the distance to the ultrasonic wave reflecting object and the attenuation characteristic information corresponding to the distance regarding the ultrasonic wave. When the peak in the normalized reflected wave waveform is greater than or equal to a predetermined threshold value, it is determined that an object has been detected in the predetermined area. When an object is detected by the object detection unit, a reflected wave waveform within a predetermined range including the peak is extracted from the reflected wave waveform after normalization. A predetermined frequency analysis that does not lose time information is performed on the reflected wave waveform within the predetermined range to generate a plurality of parameters. Among the plurality of parameters, a parameter for determining whether the object is a human body is extracted. Based on the extracted parameter, it is determined whether the object is a human body." 【Prior Art Documents】 【Patent Documents】 【0003】 【Patent Document 1】 Japanese Unexamined Patent Application Publication No. 2022-142252 【Summary of the Invention】 【Problems to be Solved by the Invention】 【0004】 In vehicle control systems, the technology to detect objects around the vehicle is crucial for safely and appropriately controlling the vehicle to a desired position. Furthermore, it is desirable that the system not only recognizes the presence or absence of objects around the vehicle, but also estimates the shape of the detected objects. 【0005】 For example, in vehicle control systems such as automatic parking and parking assist, it becomes possible to switch vehicle control methods by recognizing the shape of an object, such as whether it is a vehicle or a curb / wheel stop. 【0006】 Incidentally, for shape estimation systems used in vehicle control systems, it is desirable to be able to estimate the type of detected object with high accuracy, and it would be even more convenient if the system could estimate not only the type of object but also its dimensions. 【0007】 However, in the systems / devices / technologies described in Patent Document 1, etc., there is a possibility of improving the accuracy of type estimation based on theoretical calculation results and actual measurement results. Furthermore, no technology for dimensional estimation is disclosed. 【0008】 The present invention has been made in view of the above problems, and aims to provide a shape estimation system, an object detection system, and a communication system, as well as a shape estimation method, an object detection method, and a communication method, that can estimate the type and dimensions of objects present around a vehicle with high accuracy. [Means for solving the problem] 【0009】 The present invention includes multiple means for solving the above problems, but to give one example, a vehicle shape estimation system, comprising: a storage unit that stores as detection data the distance between the vehicle and the detected object, and the amplitude / intensity value of the wave corresponding to the distance, obtained based on the time from when a transmission unit transmits a transmission wave to a detection area to be observed until a receiving unit receives the wave scattered / reflected from a detected object present in the detection area; a resampling unit that resamples the amplitude / intensity value of the wave corresponding to the distance between the vehicle and the detected object to sampling data of a desired distance based on the detection data; and the The system comprises a conversion processing unit that converts resampled data output from a resampling unit from the spatial domain to the spatial frequency domain, a storage unit that stores a set of spectral groups in the spatial frequency domain for a plurality of pre-set object shapes as a database in relation to the object shapes, and a shape estimation unit that estimates the shape of the detected object based on the spectral group of the detected object output from the conversion processing unit and the spectral group stored in the storage unit, wherein the shape estimation unit estimates the object shape that corresponds to the spectral group of the detected object output from the conversion processing unit, among the spectral groups stored in the storage unit, to be the shape of the detected object. [Effects of the Invention] 【0010】 According to the present invention, it is possible to estimate with high accuracy the type and dimensions of objects present around the vehicle. Other problems, configurations, and effects will be clarified by the following description of the embodiments. [Brief explanation of the drawing] 【0011】 [Figure 1] A block diagram showing an example of the overall configuration of a vehicle equipped with the shape estimation system according to Embodiment 1 of the present invention. [Figure 2] A schematic diagram showing an example of the spatial arrangement of a vehicle, transmitted / received waves, and object during object detection. [Figure 3] This figure shows examples of waveforms of detection signals from a vehicle and signals processed within a shape estimation system during object detection. [Figure 4] An explanatory diagram showing an example of object type estimation performed by a shape estimation system. [Figure 5] An explanatory diagram showing an example of object dimension estimation performed by a shape estimation system. [Figure 6] A flowchart illustrating an example of the processing flow in the shape estimation system according to Embodiment 1 of the present invention. [Figure 7A] This figure shows an example of waveforms obtained when the technical validity of the shape estimation system according to Embodiment 1 of the present invention was verified by simulation. [Figure 7B] This figure shows an example of waveforms obtained when the technical validity of the shape estimation system according to Embodiment 1 of the present invention was verified by simulation. [Figure 7C] This figure shows an example of waveforms obtained when the technical validity of the shape estimation system according to Embodiment 1 of the present invention was verified by simulation. [Figure 7D] This figure shows an example of waveforms obtained when the technical validity of the shape estimation system according to Embodiment 1 of the present invention was verified by simulation. [Figure 8] This figure shows an example of estimation results obtained when the technical validity of the shape estimation system according to Embodiment 1 of the present invention was verified by simulation. [Figure 9] This figure shows an example of the relationship between the error rate and the amount of noise when the technical validity of the shape estimation system according to Embodiment 1 of the present invention was verified by simulation. [Figure 10] A block diagram showing an example of the overall configuration of a vehicle equipped with a shape estimation system according to Embodiment 2 of the present invention, and a communication system. [Modes for carrying out the invention] 【0012】 Hereinafter, embodiments of the shape estimation system, object detection system, and communication system of the present invention, as well as the shape estimation method, object detection method, and communication method, will be described with reference to the drawings. Note that the present invention is not limited to the embodiments described below, and various modifications are possible within the scope of its technical idea. Also, in the drawings used in this specification, the same or corresponding components are given the same or similar reference numerals, and repeated descriptions of these components may be omitted. 【0013】 <Example 1> Embodiment 1 of the shape estimation system, object detection system, and communication system of the present invention, as well as the shape estimation method, object detection method, and communication method, will be described with reference to FIGS. 1 to 9. 【0014】 First, the overall configuration of a vehicle equipped with the shape estimation system will be described with reference to FIG. 1. FIG. 1 shows a block diagram illustrating an example of the overall configuration of a vehicle equipped with the shape estimation system according to Embodiment 1 of the present invention. 【0015】 As shown in FIG. 1, the vehicle 1 is composed of an object detection system 100, a vehicle control unit 130, and an HMI (Human Machine Interface) 140. Although there are many functional blocks included in the vehicle 1, only the functional blocks related to the present invention are illustrated. 【0016】 The object detection system 100 is composed of a transmission / reception unit 110 and a shape estimation system 120, and can detect an object existing around the vehicle and further estimate the shape of the object. 【0017】 The transmission / reception unit 110 includes a transmission unit 111 that transmits a transmission wave 2A (see FIG. 2) to a detection area that is the observation target, a reception unit 112 that receives a reception wave 2B (see FIG. 2) scattered / reflected from a detection object 3 existing in the detection area, and a distance calculation unit 113 that obtains the distance between the vehicle 1 and the detection object 3 based on the time from when the transmission unit 111 transmits the transmission wave 2A until the reception unit 112 receives the reception wave 2B. In order to detect an object around the vehicle, the transmission unit 111 irradiates waves within a desired range. 【0018】 Here, the transmitted wave 2A sent by the transmitting unit 111 and the received wave 2B received by the receiving unit 112 are, for example, ultrasonic waves, light waves, lasers which are considered to have particularly high coherence among light waves, and radio waves. In this invention, ultrasonic waves will be used as an example for the following explanation. 【0019】 If an object is present within the detection range, the receiving unit 112 receives the waves scattered / reflected from the object. Subsequently, the distance calculation unit 113 receives the output signal from the receiving unit 112 and calculates the distance between the vehicle 1 and the object from the time it takes from the time the transmitting unit transmits the wave until the receiving unit receives it. Here, this time can be considered as the time required for the wave to propagate back and forth between the vehicle 1 and the object. 【0020】 The shape estimation system 120 consists of a storage unit 121, a memory unit 122, a resampling unit 123, a conversion processing unit 124, and a comparison calculation unit 125. 【0021】 The storage unit 121 is a storage medium that stores a set of spectral data in the spatial frequency domain for multiple pre-set object shapes, associating them with the object shapes, and stores information on the spectral data in the spatial frequency domain of scattered / reflected waves corresponding to multiple objects, associated with the objects. This spectral data may be created based on simulations, for example, or based on measured data. 【0022】 The memory unit 122 is a recording medium that stores the distance between the vehicle 1 and the detected object 3, and the amplitude / intensity values ​​of the received wave 2B corresponding to the distance, as detection data, based on the time from when the transmission unit 111 transmits the transmission wave 2A to the detection area to be observed until the receiver unit 112 receives the received wave 2B scattered / reflected from the detected object 3 present in the detection area. 【0023】 The resampling unit 123 resamples the amplitude / intensity values ​​of the received wave 2B corresponding to the distance between the vehicle 1 and the detected object 3 to sampled data for a desired distance, based on the detection data recorded in the storage unit 122. This is because, when the vehicle is controlled by the driver or system, it is expected that the vehicle may move forward or backward repeatedly depending on the situation, and the data may not always be in a state that makes it easy for the shape estimation system 120 to estimate the object shape. Therefore, it is necessary to process the data to obtain the desired data. 【0024】 One example of resampling is to perform calculations to determine amplitude / intensity data when the distance between a vehicle and an object changes at regular intervals. 【0025】 The conversion processing unit 124 is responsible for converting the resampled data output from the resampling unit 123 from the spatial domain to the spatial frequency domain. For example, it takes the amplitude / intensity values ​​resampled from the resampling unit 123 as input and processes the data to convert it from spatial domain data to spatial frequency domain data. In this explanation, the conversion process to the spatial frequency domain is given as an example, but the conversion process is not limited to this method, and it is thought that various conversion methods can be used. 【0026】 The comparison calculation unit 125 consists of a type estimation unit 126 and a dimension estimation unit 127, and is the part that estimates the shape of the detected object 3 based on the spectrum of the detected object 3 output from the conversion processing unit 124 and the group of spectra stored in the storage unit 121. In this embodiment, the comparison calculation unit 125 estimates that the shape of the detected object 3 is the object shape corresponding to the spectrum that is closest to the spectrum of the detected object 3 output from the conversion processing unit 124 among the group of spectra stored in the storage unit 121. 【0027】 The type estimation unit 126, in particular, estimates the type of the detected object 3 as a shape estimation of the detected object 3. Here, in type estimation, for example, the characteristics of each type can be learned by machine learning using data of a group of spectra prepared in advance as a database in the storage unit 121 and corresponding object shape information as training data, and the type can be estimated from the measured spectrum of the detected object 3 based on the results of the machine learning. Alternatively, the average difference between the group of spectra prepared in advance as a database in the storage unit 121 and the measured spectrum can be calculated for each type of object, and the type for which this average difference is approximately the smallest can be estimated to be the type of the object being observed. 【0028】 The dimension estimation unit 127, in particular, estimates the dimensions of the detected object 3 as a shape estimation of the detected object 3. Here, for dimension estimation, one possible method is to apply the so-called scatterometry method, which estimates dimensions by comparing a pre-prepared database with measured data. However, while the general shape of the object is known and the measurement method is the same each time in the usual scatterometry method, it is not easy to apply this method to vehicles because the approach method, such as the speed at which the vehicle approaches the object and the number of times it moves forward / backward, differs each time. 【0029】 In addition, the objects of observation can vary, including walls, vehicles, poles, and curbs, making it difficult to easily apply conventional scatterometry methods. Therefore, as mentioned above, a possible solution is to resample the data in the resampling unit 123 so that the data format is suitable for shape estimation, regardless of how the vehicle approaches. 【0030】 Furthermore, the comparison calculation unit 125 can apply the scatterometry method to estimate the dimensions of the object being observed by first narrowing down the types in the type estimation unit 126, and then performing dimension estimation in the dimension estimation unit 127. 【0031】 One example of processing in the dimension estimation unit 127 is to extract a group of spectra that have been prepared in advance as a database in the storage unit 121, limited to the types estimated by the type estimation unit 126, calculate the difference between the extracted spectrum group and the measured spectrum, and estimate the dimension for which this difference is approximately minimized as the dimension of the object being observed. With the above method, the technology can be applied to vehicles, where the degree of freedom of operation is high and the object being observed is unknown, making it extremely difficult to apply the scatterometry method, and it becomes possible to estimate the shape of the object being observed. 【0032】 The vehicle control unit 130 receives shape information of the object to be observed from, for example, the comparison calculation unit 125, and changes the vehicle control method according to the type and dimensions of the object. 【0033】 The HMI140, for example, receives shape information of the object to be observed from the comparison calculation unit 125 and notifies the driver of the object's information. 【0034】 Figure 2 shows an example of the spatial arrangement of a vehicle, transmitting and receiving waves, and an object during object detection. The transmitted wave 2A emitted from vehicle 1 is scattered / reflected by the detected object 3 and detected by vehicle 1 as the received wave 2B. During object detection, for example, vehicle 1 may approach the detected object 3 from the positive direction in the diagram towards the origin O, and in this case, it becomes possible to estimate the shape of the target object that the vehicle is approaching. 【0035】 Figure 3 shows examples of waveforms of the detection signal from the vehicle and the signal processed within the shape estimation system during object detection. 【0036】 Figure 3(a) shows an example of the change in distance between a vehicle and an object over time. In this example, the vehicle initially approaches the object, then moves away, and then approaches again. This is a common scenario, such as when controlling a vehicle to park in a target parking space within a parking lot. 【0037】 Figure 3(b) shows an example of the time evolution of the detection level of waves scattered / reflected from an object. A tendency for the level value to increase as the object is approached is observed. Note that this example shows a 14-bit detection range, and the detection level saturates at 16384. 【0038】 Figure 3(c) shows an example plotting the distance between the vehicle and the object on the horizontal axis and the detection level of waves scattered / reflected from the object on the vertical axis. It can be seen that specific noise occurs around a distance of 1080 mm. In addition, random noise is present throughout the data, and since this noise affects shape estimation, countermeasures are necessary. Furthermore, since the plotted data is not at the desired distance intervals, resampling is desirable as mentioned above. 【0039】 Therefore, the resampling unit 123 can calculate the sampling data by calculating the average value of the amplitude / intensity values ​​of the received wave 2B that is included in the data contained in the detection data and is within a predetermined distance range from a desired distance. 【0040】 For example, Figure 3(d) shows an example of the relationship between distance and detection level after resampling. Resampling involves resampling the detection level values ​​so that the sample data is at equal distance intervals, as described above. When calculating the detection level value at a desired distance, one possible method is to extract detection level values ​​belonging to a predetermined distance range from the desired distance and calculate the average value. This makes it possible to reduce the effects of random noise and specific noise, as shown in Figure 3(d). 【0041】 Figure 3(e) shows an example of the relationship between distance and detection level after preprocessing in the transformation process. For example, when performing a discrete Fourier transform as the transformation process, it is desirable that the detection level value at the minimum distance and the detection level value at the maximum distance are approximately the same, since periodic boundary conditions are assumed. To meet this requirement, window functions are generally applied, but this intentionally distorts the original detection waveform, leading to a decrease in the accuracy of object shape estimation. 【0042】 Therefore, the conversion processing unit 124 can combine the resampled data output from the resampling unit 123 with data obtained by inverting the sign of the distance of the resampled data, and then perform a conversion process from the spatial domain to the spatial frequency domain. 【0043】 For example, as shown in Figure 3(e), one possible approach is to preprocess the data to be suitable for periodic boundary conditions by combining data with the sign of the distance reversed. Here, the meaning of the data with the sign of the distance reversed corresponds to the data acquired in the negative distance region in Figure 2, and can be considered as data acquired when the same detection object 3 is detected by, for example, a transmitting and receiving unit located at the rear of vehicle 1. In other words, Figure 3(e) can be considered as data assuming that data with the same detection level value as the data acquired in the positive distance region can also be acquired in the negative distance region. 【0044】 Figure 3(f) shows an example of the spectrum obtained by performing a discrete Fourier transform on the detection level data shown in Figure 3(e). 【0045】 Figure 4 shows an example of object type estimation performed by the shape estimation system. When performing type estimation, for example, the type of the object being observed is estimated by comparing the measured spectrum with a set of spectra prepared in advance as a database. 【0046】 The database stores spectral data for each type of object, such as walls, curbs, and poles, when their dimensions, such as height and thickness, are varied. As mentioned above, for example, machine learning is used to learn the spectral characteristics of each type based on the spectral data in this database, and this training data is then used to estimate the type of object being observed from the measured spectrum. 【0047】 Alternatively, the average difference between the spectral group in the database stored in the storage unit 121 and the spectral data of the detected object 3 can be calculated for each type, and the type with the smallest average difference can be estimated to be the type of detected object 3. Note that it may not be possible to determine the exact minimum, so an approximate minimum is acceptable. Here, it is also acceptable to estimate that the type with the approximate minimum is the type of the object being observed. Note that the spectral group stored in the database may be prepared by simulation or by measured data. 【0048】 Figure 5 shows an example of dimensional estimation of an object performed by the shape estimation system. 【0049】 When estimating the shape of the detected object 3, the dimension estimation unit 127 can estimate the dimensions of the detected object 3 by referring only to the data related to the identified type of the detected object 3 from the spectral group, since the type estimation unit 126 has already estimated the type of the object being observed. 【0050】 For example, the dimension of the detected object 3 being observed is estimated to be the dimension at which the difference between the measured spectrum and the spectrum stored in the database is approximately minimized. Alternatively, machine learning may be used to estimate the dimension. The spectrum stored in the database may be prepared through simulation or from measured data. 【0051】 Figure 6 shows an example of the processing flow of the shape estimation system according to Embodiment 1 of the present invention. 【0052】 First, detection data regarding the object being observed is acquired using S601. This detection data could include, for example, the distance between the vehicle and the object, and the amplitude and intensity values ​​of scattered / reflected waves from the object, as mentioned earlier. 【0053】 Subsequently, the detection data acquired by S602 is resampled. Here, for example, the amplitude / intensity values ​​are resampled so that the data is acquired at equal distance intervals. 【0054】 Subsequently, S603 performs a conversion process on the resampled amplitude / intensity values. Here, for example, the spatial frequency domain spectrum is obtained by converting from the spatial domain to the spatial frequency domain. 【0055】 Subsequently, S604 is used to estimate the type of object being observed. Here, for example, the type of object is estimated by comparing the measured spectrum with a set of spectra prepared in advance as a database. 【0056】 Subsequently, S605 determines whether dimension estimation is necessary. If dimension estimation is not necessary, the process is terminated. If dimension estimation is necessary, the process is terminated after performing the dimension estimation in S606. Here, the necessity of dimension estimation can be determined, for example, if the object being observed is a curb or wheel stop, dimension estimation may be performed if it is better to compare it with the height of the vehicle's bumper to determine whether a collision occurred. 【0057】 In dimension estimation using S606, for example, a set of spectra prepared in advance as a database is extracted, limited to the estimated type, and the dimensions of the object being observed are estimated by comparing the measured spectrum with this set of spectra. 【0058】 Figures 7A to 7D show examples of waveforms obtained when the technical validity of the shape estimation system according to Embodiment 1 of the present invention was verified by simulation. The calculations were performed for poles and blocks, with three types of poles having diameters of 40 mm, 80 mm, and 200 mm, and three types of blocks having heights of 100 mm, 200 mm, and 300 mm. 【0059】 Figure 7A shows the relationship between the scattered / reflected wave level values ​​calculated by simulation and the distance between the vehicle and the object. As shown in Figure 7A, the scattered / reflected wave level values ​​generally increase as the distance between the vehicle and the object decreases, but in the case of blocks, it can be seen that the scattered / reflected wave level values ​​tend to decrease as the vehicle gets too close and enters a blind spot. 【0060】 Therefore, the comparison calculation unit 125 normalizes all of the spectral groups and the spectra of the detected object 3 output from the conversion processing unit 124 by their respective maximum values, and then estimates the shape of the detected object 3. 【0061】 Figure 7B shows the spectrum obtained by Fourier transforming the scattered / reflected wave level values ​​calculated by the simulation shown in Figure 7A into the spatial frequency domain. Note that in this figure, the values ​​are normalized so that the maximum value is 1. The principle was verified assuming that this spectrum is stored as a database. 【0062】 Figure 7C shows the relationship between the measured scattered / reflected wave levels and the distance between the vehicle and the object. This data was created to resemble actual measured data by superimposing noise onto the data calculated by the simulation shown in Figure 7A. In the principle verification, noise immunity was investigated while varying the amount of added noise, and this figure shows one example. 【0063】 Figure 7D shows the spectral data obtained by Fourier transforming the measured and simulated scattered / reflected wave level values ​​shown in Figure 7C into the spatial frequency domain. By comparing this data with the spectral data prepared in advance as a database through simulation, as shown in Figure 7B, we verified whether the shape of the object could be correctly estimated. 【0064】 Figure 8 shows an example of estimation results obtained when the technical validity of the shape estimation system according to Embodiment 1 of the present invention was verified by simulation. This result shows the estimation results of the data shown in Figure 7C(d). As is clear from Figure 8, both the type and dimensions are all correctly estimated, and it can be seen that the shape of an object being observed can be estimated by utilizing the present invention. 【0065】 Figure 9 shows an example of the relationship between the error rate and the amount of noise when the technical validity of the shape estimation system according to Embodiment 1 of the present invention was verified by simulation. Here, the amount of noise is expressed as a percentage, with the peak value of the scattered / reflected wave level at a block height of 100 mm considered as 100%. 【0066】 Of particular note is that, in species determination, the technology of this invention correctly estimates the species without error even when a large amount of noise is superimposed, indicating that species can be estimated with very high accuracy. Furthermore, in dimensional estimation, dimensions are correctly estimated without error when the noise level is less than 20%, demonstrating that the technology of this invention can correctly estimate the dimensions of the object being observed. 【0067】 Furthermore, by utilizing the tendency for noise to appear on the high-frequency side and applying filtering processing similar to a low-pass filter to separate the signal component from the noise component, it may be possible to further improve the accuracy of dimensional estimation. 【0068】 Next, the effects of this embodiment will be described. 【0069】 The shape estimation system 120 for vehicle 1 of Embodiment 1 of the present invention described above includes a storage unit 122 that stores the distance between vehicle 1 and detected object 3, and the amplitude / intensity values ​​of the received wave 2B corresponding to the distance, as detection data, based on the time from when the transmission unit 111 transmits the transmission wave 2A to the detection area to be observed until the receiving unit 112 receives the received wave 2B scattered / reflected from the detected object 3 present in the detection area, and a resampling unit 123 that resamples the amplitude / intensity values ​​of the received wave 2B corresponding to the distance between vehicle 1 and detected object 3 to sampling data of a desired distance based on the detection data, and a resampling unit The system includes a conversion processing unit 124 that converts the resampled data output from 123 from the spatial domain to the spatial frequency domain, a storage unit 121 that stores a set of spectral groups in the spatial frequency domain for multiple pre-set object shapes as a database in relation to the object shapes, and a comparison calculation unit 125 that estimates the shape of the detected object 3 based on the spectral group of the detected object 3 output from the conversion processing unit 124 and the spectral group stored in the storage unit 121. The comparison calculation unit 125 estimates the shape of the detected object 3 by selecting the spectral group from the spectral group stored in the storage unit 121 that is closest to the spectral group of the detected object 3 output from the conversion processing unit 124. 【0070】 This embodiment offers the advantage of being able to estimate the type and dimensions of an object being observed with higher accuracy than conventional estimation techniques by utilizing not only measured data but also a database prepared in advance using simulations, etc. Furthermore, it has been shown through principle verification that type estimation is possible without errors even when the amount of noise is large, which offers the advantage of high noise immunity. 【0071】 While species and dimensional estimation is possible using stereo cameras / multi-cameras, the technology of the present invention has the advantage of being usable even at night or in bad weather, which is one of the challenges of the above-mentioned camera technologies. Furthermore, by fusing detection information from stereo cameras / multi-cameras with detection information from the technology of the present invention, improved system accuracy can be expected. 【0072】 Furthermore, while sensing using Lidar has been anticipated in recent years, the technology of the present invention can also utilize relatively inexpensive ultrasonic sonar, offering the advantage of being able to construct a system at a low cost. 【0073】 Furthermore, while dimensional estimation sensing often utilizes multiple transceivers, the present invention enables this to be achieved with a single transceiver. This can be achieved by improving the signal processing unit while maintaining the conventional transceiver arrangement configuration, offering the advantages of easy implementation and excellent cost performance. 【0074】 Furthermore, this technology offers the advantage of providing drivers with additional information about the type and dimensions of objects, not only in vehicle control systems but also in conventional systems such as clearance sonar. 【0075】 Furthermore, while conventional scalculometry methods acquire spectral data by changing the wave frequency itself, the present invention utilizes a single-frequency wave and implements spectral data using spatial frequency data, thus offering the advantage of a simpler configuration. 【0076】 Furthermore, the resampling unit 123 calculates the sampling data by calculating the average value of the amplitude / intensity values ​​of the received wave 2B that is included in a predetermined distance range from the desired distance among the data included in the detected data, thereby reducing the influence of random noise and specific noise. 【0077】 Furthermore, the conversion processing unit 124 combines the resampled data output from the resampling unit 123 with data obtained by inverting the sign of the distance between the resampled data, and then performs a conversion process from the spatial domain to the spatial frequency domain. This allows for preprocessing to create data suitable for periodic boundary conditions, and since it is no longer necessary to intentionally distort the original detected waveform when performing a discrete Fourier transform as part of the conversion process, improved accuracy can be achieved. 【0078】 Furthermore, the comparison calculation unit 125 normalizes all of the spectral groups and the spectra of the detected object 3 output from the conversion processing unit 124 by their respective maximum values, and then estimates the shape of the detected object 3. This allows the unit to handle both increases and decreases in the scattered / reflected wave level values, enabling spectral processing of detected objects 3 at various heights. 【0079】 Furthermore, the comparison calculation unit 125 estimates the type of detected object 3 as a shape estimation, which allows for narrowing down the types of objects whose dimensions are estimated during the subsequent dimension estimation process. This enables faster processing and a further reduction in the probability of misjudgment. 【0080】 Furthermore, by estimating the type of detected object 3 as at least a curb / wheel stop, the comparison calculation unit 125 can accurately estimate the shape of these curbs / wheel stops, which was previously difficult. 【0081】 Furthermore, the comparison calculation unit 125 can efficiently improve the accuracy of species estimation by using the spectral group as training data to learn the characteristics of each species, and then estimating the species from the spectrum of the detected object 3 based on the results of the machine learning. 【0082】 Furthermore, the comparison calculation unit 125 calculates the average difference between the spectrum group and the spectrum of the detected object 3 for each type, and estimates that the type with the smallest average difference is the type of the detected object 3, thereby improving the accuracy of type estimation. 【0083】 Furthermore, the comparison calculation unit 125 can more accurately estimate what kind of object the detected object 3 is by estimating the dimensions of the detected object 3 as a shape estimation. 【0084】 Furthermore, when estimating the shape of the detected object 3, the comparison calculation unit 125 estimates the type of the detected object 3, and then estimates the dimensions of the detected object 3 by referring only to the data related to the identified type of detected object 3 from the spectral group. This allows for faster and more accurate estimation processing. 【0085】 Furthermore, the comparison calculation unit 125 can further improve the accuracy of dimension estimation by estimating that the dimension at which the difference between the spectrum group and the spectrum of the detected object 3 is minimized is the dimension of the detected object 3. 【0086】 <Example 2> The shape estimation system, object detection system, and communication system, as well as the shape estimation method, object detection method, and communication method of Embodiment 2 of the present invention, will be described with reference to Figure 10. Figure 10 shows a block diagram illustrating an example of the overall configuration of a vehicle equipped with the shape estimation system according to Embodiment 2 of the present invention and the communication system. 【0087】 As shown in Figure 10, the difference between this embodiment and Embodiment 1 is the addition of a communication system 4 that can communicate with the storage unit 121 inside the vehicle 1. 【0088】 The communication system 4 is a system that communicates with a vehicle 1 equipped with an object detection system 100 via a network, and consists of, for example, a database update unit 410 that updates the database of the database storage unit 420, a database storage unit 420 that stores the database used by the vehicle 1 when estimating the shape of the detected object 3, and a database transmission unit 430 that transmits the database stored in the database storage unit 420 to the storage unit 121 of the vehicle 1. 【0089】 The database update unit 410 updates the spatial frequency domain spectrum group of various objects that the vehicle should prepare in advance as a database, as needed. For example, if the database is prepared by simulation, the database may be updated when the simulation accuracy can be improved compared to the initial state, or when errors in the initial database become a problem. 【0090】 The database storage unit 420 receives the updated database from the database update unit 410 and saves it. 【0091】 The database transmission unit 430 receives the updated database from the database storage unit 420 and updates the database stored in the storage unit 121 of vehicle 1. It is desirable that the database transmission unit 430 transmits the updated database to vehicle 1 when the database update unit 410 updates the database. While a configuration without the database storage unit 420 is also possible, it is desirable to manage the updated database in the database storage unit 420 in order to track the updated database. 【0092】 Therefore, the database stored in the storage unit 121 can be updated via the communication system 4 or a physical medium. 【0093】 Other configurations and operations are substantially the same as those of the shape estimation system, object detection system, and communication system, as well as the shape estimation method, object detection method, and communication method described in Example 1 above, and details are omitted. 【0094】 In the shape estimation system, object detection system, and communication system, as well as the shape estimation method, object detection method, and communication method of Embodiment 2 of the present invention, substantially the same effects as those of the shape estimation system, object detection system, and communication system, as well as the shape estimation method, object detection method, and communication method of Embodiment 1 described above can be obtained. 【0095】 Furthermore, since the scattered / reflected wave spectrum set, which is prepared in advance as a database, can be updated, it has the advantage of being able to address situations where the accuracy of object shape estimation becomes an issue or where estimation accuracy can be improved. 【0096】 As an example, we have shown how to update a database using a communication system, but of course, it is also acceptable to update the database via a physical medium. 【0097】 <Other> The embodiments of the present invention have been described above. It should be noted that the present invention is not limited to the embodiments described above, but includes various modifications and equivalent configurations within the spirit of the attached claims. For example, the embodiments described above are detailed to illustrate the present invention clearly, and the present invention is not necessarily limited to having all the described configurations. Furthermore, a part of the configuration of one embodiment may be replaced with the configuration of another embodiment. Also, a configuration from another embodiment may be added to a configuration of one embodiment. Furthermore, a part of the configuration of each embodiment may be added, deleted, or replaced with other configurations. 【0098】 Furthermore, each of the aforementioned configurations, functions, processing units, and processing means may be implemented in hardware, for example, by designing them as integrated circuits, or they may be implemented in software by having a processor interpret and execute programs that realize each function. 【0099】 Information such as programs, tables, and files that implement each function can be stored in memory, hard disks, SSDs (Solid State Drives), or other storage media such as IC cards, SD cards, and DVDs. 【0100】 Furthermore, the control lines and information lines shown are those deemed necessary for explanation purposes and do not necessarily represent all control lines and information lines required for implementation. In reality, it can be assumed that almost all components are interconnected. [Explanation of symbols] 【0101】 1…Vehicle 2A…Transmission wave 2B...Received wave 3...Detected object 4…Communication systems 100... Object detection system 110... Transmitter / Receiver 111...Transmitter 112... Receiver 113...Distance calculation section 120…Shape estimation system 121...Storage Department 122...Storage section 123...Resampling section 124...Conversion Processing Unit 125…Comparison calculation unit (shape estimation unit) 126...Type Estimation Unit 127...Dimension Estimation Section 130... Vehicle Control Unit 140…HMI 410...Database Update Department 420...Database storage unit 430...Database transmission unit

Claims

[Claim 1] A vehicle shape estimation system, A storage unit stores the distance between the vehicle and the detected object, and the amplitude / intensity values ​​of the wave corresponding to the distance, as detection data, based on the time from when the transmitting unit transmits the transmitted wave to the detection area to be observed until the receiving unit receives the wave scattered / reflected from the detected object present in the detection area. A resampling unit that, based on the detection data, resamples the amplitude / intensity values ​​of the wave corresponding to the distance between the vehicle and the detected object into sampling data for a desired distance. A conversion processing unit that converts the resampled data output from the resampling unit from the spatial domain to the spatial frequency domain, A storage unit that stores a set of spectral data in the spatial frequency domain for multiple pre-defined object shapes as a database, associated with the object shapes, The system includes a shape estimation unit that estimates the shape of the detected object based on the spectrum of the detected object output from the conversion processing unit and the spectrum group stored in the storage unit, The shape estimation unit estimates the shape of the detected object by selecting the object shape from the spectrum group that is closest to the spectrum of the detected object output from the conversion processing unit and storing it in the storage unit. Shape estimation system. [Claim 2] In the shape estimation system according to claim 1, The resampling unit calculates the sampling data by calculating the average value of the amplitude / intensity values ​​of the waves included in the detection data that are within a predetermined distance range from the desired distance. Shape estimation system. [Claim 3] In the shape estimation system according to claim 1, The conversion processing unit combines the resampled data output from the resampling unit with data obtained by inverting the sign of the distance of the resampled data, and then performs a conversion process from the spatial domain to the spatial frequency domain. Shape estimation system. [Claim 4] In the shape estimation system according to claim 1, The shape estimation unit normalizes all of the spectral groups and the spectra of the detected object output from the conversion processing unit by their respective maximum values, and then estimates the shape of the detected object. Shape estimation system. [Claim 5] In the shape estimation system according to claim 1, The shape estimation unit estimates the type of the detected object as the shape estimation of the detected object. Shape estimation system. [Claim 6] In the shape estimation system according to claim 5, The shape estimation unit estimates the type of the detected object to be at least a curb / wheel stop. Shape estimation system. [Claim 7] In the shape estimation system according to claim 5, The shape estimation unit uses the spectral group as training data to learn the characteristics of each type, and based on the results of the machine learning, estimates the type from the spectrum of the detected object. Shape estimation system. [Claim 8] In the shape estimation system according to claim 5, The shape estimation unit calculates the average difference between the spectrum group and the spectrum of the detected object for each type, and estimates that the type with the smallest average difference is the type of the detected object. Shape estimation system. [Claim 9] In the shape estimation system according to claim 1, The shape estimation unit estimates the dimensions of the detected object as the shape estimation of the detected object. Shape estimation system. [Claim 10] In the shape estimation system according to claim 1, The shape estimation unit, when estimating the shape of the detected object, first estimates the type of the detected object, and then estimates the dimensions of the detected object by referring only to the data related to the identified type of the detected object from the spectrum group. Shape estimation system. [Claim 11] In the shape estimation system according to claim 9, The shape estimation unit estimates the dimension of the detected object to be the dimension that minimizes the difference between the spectrum group and the spectrum of the detected object. Shape estimation system. [Claim 12] In the shape estimation system according to claim 1, The aforementioned spectral group was created based on simulations. Shape estimation system. [Claim 13] In the shape estimation system according to claim 1, The aforementioned spectral group was created based on measured data. Shape estimation system. [Claim 14] In the shape estimation system according to claim 1, The database stored in the storage unit can be updated via a communication system or physical medium. Shape estimation system. [Claim 15] In the shape estimation system according to claim 1, The transmitted wave sent by the transmitting unit and the wave received by the receiving unit are ultrasonic waves. Shape estimation system. [Claim 16] A vehicle object detection system, A transmitting unit that transmits a signal wave to the detection area to be observed, A receiving unit that receives waves scattered / reflected from a detected object in the aforementioned detection area, A distance calculation unit that calculates the distance between the vehicle and the detected object based on the time from when the transmitting unit transmits the wave until the receiving unit receives the wave, A shape estimation system according to any one of claims 1 to 15, comprising Object detection system. [Claim 17] A communication system that communicates with a vehicle equipped with the object detection system described in claim 16 via a network, A database storage unit that stores a database used by the vehicle when estimating the shape of detected objects, A database update unit that updates the database of the aforementioned database storage unit, The system includes a database transmission unit that transmits the database stored in the database storage unit to the storage unit of the vehicle. The database transmission unit transmits the updated database to the vehicle when the database update unit updates the database. Communication system. [Claim 18] A method for estimating the shape of a vehicle, A storage step involves storing the distance between the vehicle and the detected object, and the amplitude / intensity values ​​of the wave corresponding to the distance, as detection data, based on the time from when the transmitting unit transmits the transmitted wave to the detection area to be observed until the receiving unit receives the wave scattered / reflected from the detected object present in the detection area. Based on the detection data, a resampling step is performed to resample the amplitude / intensity values ​​of the wave corresponding to the distance between the vehicle and the detected object into sampling data at a desired distance. A conversion process that converts the resampled data output in the resampling process from the spatial domain to the spatial frequency domain, A storage step involves saving a set of spectral data in the spatial frequency domain for a plurality of pre-defined object shapes as a database in association with the object shapes, The system includes a shape estimation step which estimates the shape of the detected object based on the spectrum of the detected object output in the conversion processing step and the group of spectra saved in the storage step, In the shape estimation step, the shape of the detected object is estimated to be the object shape that corresponds to the spectrum from the group of spectra saved in the saving step that is closest to the spectrum of the detected object output in the conversion processing step. Shape estimation method. [Claim 19] An object detection method, A transmission process that transmits waves to the detection area to be observed, A receiving step of receiving waves scattered / reflected from a detected object present in the detection region, A distance calculation step that determines the distance between the vehicle and the detected object based on the time from when the wave is transmitted in the transmission step until when the wave is received in the reception step, Each step of the shape estimation method according to claim 18, Object detection method. [Claim 20] A communication method for communicating via a network with a vehicle having a processing device that performs the shape estimation method described in claim 18, A database storage step for storing a database used by the vehicle when estimating the shape of detected objects, A database update process for updating the aforementioned database, The process includes a database transmission step of transmitting the database to the storage unit of the processing device, In the database transmission step, when the database is updated in the database update step, the updated database is transmitted to the storage unit. Communication method.

Images