A method and apparatus for ground identification

By performing Fourier transform and inverse Fourier transform on the radar signal, combined with ground frequency domain signal strength threshold filtering, the problems of noise and obstacle influence in traditional radar ground identification methods are solved, achieving a higher identification accuracy.

CN114384513BActive Publication Date: 2025-12-09WHITE RHINO ZHIDA (BEIJING) TECH CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202210062575.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-01-19
Publication Date
2025-12-09
Estimated Expiration
2042-01-19

AI Technical Summary

Technical Problem

Traditional radar ground identification methods are affected by radar noise or obstacles near the ground, resulting in a decrease in identification accuracy.

Method used

By receiving environmental signal sets in real time and performing Fourier transform, the environmental frequency domain signals are filtered using a preset ground frequency domain signal strength threshold to separate ground and obstacle signals, and then inverse Fourier transform is performed to obtain ground information.

Benefits of technology

It improves the accuracy of ground identification, effectively removes radar noise and obstacle components, and provides cleaner ground information.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114384513B_ABST
    Figure CN114384513B_ABST
Patent Text Reader

Abstract

The application discloses a ground identification method and device, the method comprises the following steps: receiving an environment signal set in real time, the environment signal set is obtained by radar periodically scanning the surrounding environment with a plurality of different radii, the environment signal set contains a plurality of environment signals, the number of which is the same as the number of the radii, performing Fourier transform on each group of environment signals to obtain each group of environment frequency domain signals, filtering each group of environment frequency domain signals according to a preset ground frequency domain signal intensity threshold, determining each group of ground frequency domain signals, and performing inverse Fourier transform on each group of ground frequency domain signals to obtain ground information. As can be seen, by performing Fourier transform on the environment signals, the ground signals and non-ground signals can be better distinguished, and by using the preset ground frequency domain signal intensity threshold, the radar noise components and obstacle components can be effectively removed, so that the ground information is cleaner, and the accuracy of ground identification is improved.
Need to check novelty before this filing date? Find Prior Art

Description

TECHNICAL FIELD

[0001] The present application relates to the field of radar signal processing, more particularly, to a ground identification method and device. BACKGROUND

[0002] With the continuous development of information technology, the assisted driving technology is continuously improved. The intelligent driving technology can obtain real-time road conditions and provide the optimal route to the automatic driving vehicle in time. Meanwhile, the intelligent driving technology also needs to consider the driving safety problem and needs to guide the automatic driving vehicle to drive in the safe area. During the driving of the vehicle, the environment is changeable and the ground form around the vehicle is very complex. Therefore, the accurate identification of the drivable ground around the vehicle is extremely important.

[0003] The traditional method for obtaining ground information is to directly survey the ground through the radar. However, the radar noise or obstacle points near the ground will affect the accuracy of ground identification.

[0004] How to realize more accurate identification of the ground is a problem that needs to be concerned. SUMMARY

[0005] In view of the above problems, the present application is proposed to provide a ground identification method and device to improve the accuracy of ground identification.

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

[0007] A ground identification method applied to a driving system terminal, wherein the driving system terminal communicates with a radar, and the method comprises the following steps:

[0008] Real-time receiving an environment signal set, wherein the environment signal set is obtained by periodically scanning the surrounding environment with a plurality of different radii by the radar, and the environment signal set contains a plurality of environment signals with the same number of groups and the same number of radii;

[0009] Performing Fourier transform on each group of environment signals to obtain each group of environment frequency domain signals;

[0010] Filtering each group of environment frequency domain signals according to a preset ground frequency domain signal intensity threshold to determine each group of ground frequency domain signals;

[0011] Performing inverse Fourier transform on each group of ground frequency domain signals to obtain ground information.

[0012] Optionally, the determination process of the ground frequency domain signal intensity threshold comprises:

[0013] receiving the radar periodically scans the surrounding environment with the preset number of radii to obtain a set of empty environment signals, the set of empty environment signals containing the same number of groups as the number of radii;

[0014] performing Fourier transform on each group of empty environment signals to obtain each group of empty environment frequency domain signals;

[0015] determining a ground frequency domain signal intensity threshold based on each group of empty environment frequency domain signals.

[0016] Optionally, each group of environment frequency domain signals is composed of a plurality of environment frequency domain point signals.

[0017] The filtering of each group of environment frequency domain signals according to the preset ground frequency domain signal intensity threshold to determine each group of ground frequency domain signals comprises:

[0018] For each group of environment frequency domain signals, environment frequency domain point signals with signal intensity less than the preset ground frequency domain signal intensity threshold are filtered out, and the remaining environment frequency domain point signals constitute a group of ground frequency domain signals.

[0019] Optionally, the method further comprises:

[0020] For each group of environment frequency domain signals, environment frequency domain signals with signal intensity between the preset ground frequency domain signal intensity threshold and a preset obstacle frequency domain signal intensity threshold are determined as obstacle frequency domain signals.

[0021] performing inverse Fourier transform on each group of obstacle frequency domain signals to obtain obstacle signals.

[0022] Optionally, after the inverse Fourier transform on each group of ground frequency domain signals to obtain ground information, the method further comprises:

[0023] based on the ground information, ground modeling is performed on the radar scanning area to obtain a first ground simulation image.

[0024] Optionally, after the inverse Fourier transform on each group of ground frequency domain signals to obtain ground information, the method further comprises:

[0025] based on the ground information, ground modeling is performed on the radar scanning area to obtain a first ground simulation image.

[0026] based on the obstacle signals, obstacle marking is performed on the first ground simulation image to obtain a second ground simulation image, so as to distinguish the ground and the obstacles.

[0027] The application discloses a ground identification device applied to a driving system terminal, wherein the driving system terminal communicates with a radar, and comprises the following parts:

[0028] A signal set receiving unit is used for receiving an environment signal set in real time, wherein the environment signal set is obtained by periodically scanning a surrounding environment by the radar with a plurality of preset different radii, and the environment signal set comprises a plurality of environment signals with the same number of groups and radii;

[0029] A frequency domain signal conversion unit is used for performing Fourier transform on each group of the environment signals to obtain each group of environment frequency domain signals;

[0030] A frequency domain signal filtering unit is used for filtering each group of the environment frequency domain signals according to a preset intensity threshold of ground frequency domain signals to determine each group of ground frequency domain signals;

[0031] A ground information determining unit is used for performing inverse Fourier transform on each group of the ground frequency domain signals to obtain ground information.

[0032] Optionally, the device further comprises:

[0033] A contrast signal set receiving unit is used for receiving a vacant environment signal set obtained by periodically scanning a surrounding environment by the radar with the plurality of preset different radii when only ground exists in a scanning range of a maximum scanning radius of the radar, and the vacant environment signal set comprises a plurality of vacant environment signals with the same number of groups and radii;

[0034] A contrast signal frequency domain conversion unit is used for performing Fourier transform on each group of the vacant environment signals to obtain each group of vacant environment frequency domain signals;

[0035] An intensity threshold determining unit is used for determining an intensity threshold of ground frequency domain signals based on each group of the vacant environment frequency domain signals.

[0036] Optionally, each group of the environment frequency domain signals is composed of a plurality of environment frequency domain point signals;

[0037] The frequency domain signal filtering unit comprises:

[0038] A frequency domain point signal filtering unit is used for filtering out, for each group of the environment frequency domain signals, an environment frequency domain point signal with a signal intensity less than the preset intensity threshold of ground frequency domain signals, and the remaining environment frequency domain point signals constitute a group of ground frequency domain signals.

[0039] Optionally, the device further comprises:

[0040] The obstacle frequency domain signal determination unit is configured to determine, for each group of environment frequency domain signals, environment frequency domain signals with signal intensity between the intensity threshold of the preset ground frequency domain signal and the intensity threshold of the preset obstacle frequency domain signal as obstacle frequency domain signals.

[0041] The obstacle signal determination unit is configured to perform inverse Fourier transform on each group of obstacle frequency domain signals to obtain obstacle signals.

[0042] Optionally, the device further comprises:

[0043] The first image acquisition unit is configured to, after performing inverse Fourier transform on each group of ground frequency domain signals to obtain ground information, perform ground modeling on the radar scanning area based on the ground information to obtain a first ground simulation image.

[0044] Optionally, the device further comprises:

[0045] The first image acquisition unit is configured to, after performing inverse Fourier transform on each group of ground frequency domain signals to obtain ground information, perform ground modeling on the radar scanning area based on the ground information to obtain a first ground simulation image.

[0046] The second image acquisition unit is configured to, based on the obstacle signals, mark obstacles in the first ground simulation image to obtain a second ground simulation image, so as to distinguish the ground and the obstacles.

[0047] Through the above technical solution, the application receives an environment signal set in real time, the environment signal set is obtained by periodically scanning the surrounding environment by the radar with a preset number of different radii, the environment signal set is composed of a number of environment signal groups equal to the number of radii, further, Fourier transform is performed on each group of environment signals to obtain each group of environment frequency domain signals, each group of environment frequency domain signals is filtered according to a preset intensity threshold of ground frequency domain signals to determine each group of ground frequency domain signals, and finally inverse Fourier transform is performed on each group of ground frequency domain signals to obtain ground information. As can be seen, by performing Fourier transform on the environment signals, the ground signals and non-ground signals can be better distinguished, and by using the preset intensity threshold of ground frequency domain signals, the radar noise component and obstacle component can be effectively removed to obtain cleaner ground information and improve the accuracy of ground identification. BRIEF DESCRIPTION OF DRAWINGS

[0048] Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The detailed description is made with reference to the accompanying drawings.

[0049] Figure 1 A flowchart of a ground recognition method provided by an embodiment of the present application is shown in the figure;

[0050] Figure 2 A device structure diagram of a ground recognition method provided by an embodiment of the present application is shown in the figure;

[0051] Figure 3 A structure diagram of a ground recognition analysis device provided by an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0052] 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 a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0053] The scheme of the present application can be implemented based on a terminal with data processing capability, which can be a mobile phone, a computer, a server, a cloud, etc. The terminal can also communicate with a radar to obtain radar monitoring signals in real time.

[0054] Next, the ground recognition method of the present application will be described in detail with reference to the accompanying drawings. Figure 1 The ground recognition method of the present application can include the following steps:

[0055] Step S110, real-time receiving an environment signal set, the environment signal set being obtained by the radar periodically scanning the surrounding environment at a plurality of different radii, the environment signal set containing a same number of groups of environment signals as the number of radii.

[0056] Specifically, the plurality of different radii can be customized. The radar can be installed on the roof of an autonomous vehicle to emit electromagnetic waves to the ground at a distance of a preset radius, thus forming a ground environment point cloud with the radar as the center and the distance as the preset radius. After a period of time, the radius is changed to the next length, and the electromagnetic waves are continuously emitted to the ground. Therefore, each radius corresponds to each group of ground environment point clouds, i.e., each group of environment signals.

[0057] Step S120, performing Fourier transform on each group of environment signals to obtain each group of environment frequency domain signals.

[0058] Specifically, each group of environment frequency domain signals can contain signal components of different phases and different intensities. Each signal component can represent a reflection signal of different media, such as the ground, people, water, etc.

[0059] Step S130, filtering each group of environment frequency domain signals according to a preset intensity threshold of ground frequency domain signals, to determine each group of ground frequency domain signals.

[0060] Specifically, the preset intensity threshold of ground frequency domain signals can be a minimum intensity value of ground signal components in the frequency domain, which can be determined in advance before the vehicle travels. The determination process of the intensity threshold of ground frequency domain signals can include the following steps:

[0061] S1301, when the scanning range of the maximum scanning radius of the radar is only ground, receiving the radar periodically scanning the surrounding environment at the preset number of radii, obtaining a set of empty environment signals, and the set of empty environment signals contains the same number of groups of empty environment signals as the number of radii.

[0062] It can be understood that a plurality of groups of empty environment signals are collected in advance in the empty area, and the radar scanning radius set during collection is the same as the number of radii in step S110, so that the collected signals are all represented as ground information.

[0063] S1302, performing Fourier transform on each group of empty environment signals to obtain each group of empty environment frequency domain signals.

[0064] It can be understood that for the empty environment signals that only collect ground information, the empty environment frequency domain signals after Fourier transform also only have the components of ground frequency domain signals.

[0065] S1303, determining the intensity threshold of ground frequency domain signals based on each group of empty environment frequency domain signals.

[0066] It can be understood that the ground is not actually smooth, so the intensity of the collected ground frequency domain signals can not be the same. To ensure that the ground components can be more completely separated, the intensity threshold of ground frequency domain signals can be determined as the minimum value of the collected empty environment frequency domain signals. When the intensity of the environment frequency domain signal is greater than or equal to the intensity threshold, the environment frequency domain signal can be represented as a ground frequency domain signal.

[0067] Step S140, performing inverse Fourier transform on each group of ground frequency domain signals to obtain ground information.

[0068] Specifically, performing inverse Fourier transform on the ground frequency domain signal can obtain a ground time domain signal, that is, a signal of the real ground scanned by the radar.

[0069] The ground recognition method provided in the embodiment can effectively remove radar noise components and obstacle components, obtain cleaner ground information, and improve the accuracy of ground recognition.

[0070] For each group of environment frequency domain signals mentioned in the foregoing embodiments, the environment frequency domain signals can be composed of a plurality of environment frequency domain point signals. Based on this, in some embodiments of the present application, the process of performing Fourier transform on each group of open environment signals to obtain each group of open environment frequency domain signals in the above step S120 is introduced. The process can include:

[0071] For each group of environment frequency domain signals, the environment frequency domain point signals with a signal intensity less than the intensity threshold of the preset ground frequency domain signal are filtered out, and the remaining environment frequency domain point signals constitute a group of ground frequency domain signals.

[0072] Specifically, for the radar scanning signals received in real time, when the radar scans a non-ground, the returned environment signal is not indicative of the ground, and therefore the signal intensity of the converted environment frequency domain signal is also less than the intensity threshold of the preset ground frequency domain signal. After filtering out all the environment frequency domain signal points that do not indicate the ground in each group of environment frequency domain signals, the remaining environment frequency domain signal points can all indicate the ground.

[0073] The ground recognition method provided in the embodiment filters the environment frequency domain point signals less than the intensity threshold of the preset ground frequency domain signal to obtain environment frequency domain point signals indicative of the ground, so that the signals indicative of the ground are cleaner.

[0074] In some embodiments of the present application, considering the need to provide obstacle information to an autonomous vehicle to effectively avoid obstacles, another ground recognition method is provided in the embodiments of the present application. On the basis of the foregoing scheme, a process of obtaining obstacle signals can be further added, which can include:

[0075] S1, for each group of environment frequency domain signals, the environment frequency domain signals with a signal intensity between the intensity threshold of the preset ground frequency domain signal and the intensity threshold of the preset obstacle frequency domain signal are determined as obstacle frequency domain signals.

[0076] Specifically, for the radar scanning signals received in real time, when the radar scans an obstacle such as a pedestrian, a vehicle, a rock base or the like, the returned environmental signal is not indicative of the ground, but also not no signal, and thus the signal strength of the converted environmental frequency domain signal is less than the preset ground frequency domain signal strength threshold, but greater than the preset obstacle frequency domain signal strength threshold, that is, the environmental frequency domain signal between the preset ground frequency domain signal strength threshold and the preset obstacle frequency domain signal strength threshold can be represented as an obstacle frequency domain signal, and the obstacle frequency domain signal is extracted.

[0077] If there is no returned signal or the returned signal is extremely weak in a certain direction of the radar scanning, it can be indicated that there is no obstruction in a long distance in the direction of the radar transmitted signal, which can be represented as a cliff, a depression or the like in real-time road conditions.

[0078] S2, inverse Fourier transform is performed on each group of obstacle frequency domain signals to obtain an obstacle signal.

[0079] Specifically, inverse Fourier transform is performed on the obstacle frequency domain signal to obtain an obstacle time domain signal, that is, a signal of a real obstacle scanned by the radar.

[0080] The ground recognition method provided in the embodiment extracts the environmental frequency domain signal between the preset ground frequency domain signal strength threshold and the preset obstacle frequency domain signal strength threshold to obtain an environmental frequency domain point signal representing an obstacle, and converts the environmental frequency domain point signal into a time domain signal to obtain a component of the obstacle scanned by the radar. On this basis, the automatic driving vehicle can be provided with a reference, so that the automatic driving vehicle can more purposefully avoid the obstacle.

[0081] In addition, for the driving situation of the driver, the driver can also be provided with obstacle information to assist in observing the road surface and improving driving safety.

[0082] In some embodiments of the present application, in order to timely show the finally recognized road surface information to the passengers in the automatic driving vehicle, another ground recognition method is provided in the embodiments of the present application. After the process of inverse Fourier transform on each group of ground frequency domain signals to obtain the ground information in the above step S140, a process of modeling the ground can be further added, and specifically, the process can include:

[0083] S1, based on the ground information, ground modeling is performed on the radar scanning area to obtain a first ground simulation image.

[0084] Specifically, the ground information can be a point cloud representing an effective ground. Based on the distribution of the point cloud representing the effective ground, scattered points can be filled in the radar scanning area, and the filled positions can represent positions of the effective ground. Based on the distribution of the point cloud representing the effective ground, positions in the radar scanning area that are outside the point cloud and that can represent the ground can also be filled.

[0085] The first ground simulation image can be composed of a plurality of points representing the ground.

[0086] The ground recognition method provided in this embodiment can model the ground in the radar scanning area based on the point cloud representing the effective ground as the ground information, obtain the first ground simulation image, and display the finally recognized road surface simulation image to passengers in the autonomous vehicle, thereby improving the riding experience of the passengers.

[0087] Further, another ground modeling process is provided. After the process of modeling the ground in the radar scanning area based on the ground information to obtain the first ground simulation image in step S1, a process of marking obstacles can be further added. Specifically, the process can include:

[0088] Based on the obstacle signal, the first ground simulation image is marked with the obstacles to obtain a second ground simulation image, so as to distinguish the ground and the obstacles.

[0089] It can be understood that the first ground simulation image can only include information of the ground. Considering that the autonomous vehicle needs to rely on some obstacles for emergency avoidance, for example, when the brake fails and needs to be stopped urgently to avoid falling off a cliff, the obstacle can be considered to collide with an obstacle with less damage, and at the same time, the autonomous vehicle can distinguish the ground and the obstacles more quickly through the simulation image.

[0090] The ground recognition method provided in this embodiment can mark the obstacle information based on the first ground simulation image and the separated obstacle information to obtain the second ground simulation image, so as to quickly determine the surrounding environment during driving.

[0091] In addition, for the driving of the driver, in an environment with low visibility, the driver can observe the road surface according to the obstacle information in the simulation image to improve the driving safety.

[0092] The device for recognizing the ground provided in the embodiments of this application is described below. The device for recognizing the ground described below can be correspondingly referred to the method for recognizing the ground described above.

[0093] Referring to Figure 2 ,Figure 2 A device structure schematic diagram for implementing ground recognition disclosed in an embodiment of the present application.

[0094] As shown in the figure, the device is applied to a driving system terminal, which communicates with a radar, and can include: Figure 2

[0095] a signal set receiving unit 11 for receiving an environment signal set in real time, the environment signal set being obtained by the radar periodically scanning the surrounding environment with a plurality of preset different radii, and the environment signal set containing the same number of groups of environment signals as the number of radii;

[0096] a frequency domain signal conversion unit 12 for performing Fourier transform on each group of environment signals to obtain each group of environment frequency domain signals;

[0097] a frequency domain signal filtering unit 13 for filtering each group of environment frequency domain signals according to a preset intensity threshold of ground frequency domain signals to determine each group of ground frequency domain signals;

[0098] a ground information determination unit 14 for performing inverse Fourier transform on each group of ground frequency domain signals to obtain ground information.

[0099] Optionally, the device further includes:

[0100] a comparison signal set receiving unit for receiving, when the scanning range of the maximum scanning radius of the radar is only ground, a set of empty environment signals obtained by the radar periodically scanning the surrounding environment with the plurality of preset radii, the set of empty environment signals containing the same number of groups of empty environment signals as the number of radii;

[0101] a comparison signal frequency domain conversion unit for performing Fourier transform on each group of empty environment signals to obtain each group of empty environment frequency domain signals;

[0102] an intensity threshold determination unit for determining the intensity threshold of ground frequency domain signals based on each group of empty environment frequency domain signals.

[0103] Optionally, each group of environment frequency domain signals is composed of a plurality of environment frequency domain point signals;

[0104] the frequency domain signal filtering unit 12 includes:

[0105] a frequency domain point signal filtering unit for filtering out, for each group of environment frequency domain signals, environment frequency domain point signals with signal intensity less than the preset intensity threshold of ground frequency domain signals, and the remaining environment frequency domain point signals constituting a group of ground frequency domain signals.

[0106] Optionally, the device further includes: ​

[0107] The obstacle frequency domain signal determination unit is configured to determine, for each group of environment frequency domain signals, an environment frequency domain signal with a signal strength between the strength threshold of the preset ground frequency domain signal and the strength threshold of the preset obstacle frequency domain signal as an obstacle frequency domain signal.

[0108] The obstacle signal determination unit is configured to perform inverse Fourier transform on each group of obstacle frequency domain signals to obtain an obstacle signal.

[0109] Optionally, the apparatus further comprises:

[0110] The first image acquisition unit is configured to, after performing inverse Fourier transform on each group of ground frequency domain signals to obtain ground information, perform ground modeling on the radar scanning area based on the ground information to obtain a first ground simulation image.

[0111] Optionally, the apparatus further comprises:

[0112] The first image acquisition unit is configured to, after performing inverse Fourier transform on each group of ground frequency domain signals to obtain ground information, perform ground modeling on the radar scanning area based on the ground information to obtain a first ground simulation image.

[0113] The second image acquisition unit is configured to, based on the obstacle signal, mark obstacles in the first ground simulation image to obtain a second ground simulation image, so as to distinguish the ground and the obstacles.

[0114] The apparatus for ground recognition provided in the embodiments of the present application can be applied to a ground recognition device, such as a terminal, a mobile phone, a computer, etc. Optionally, Figure 3 A hardware structure block diagram of ground recognition is shown, referring to Figure 3 The hardware structure of the ground recognition device can include at least one processor 1, at least one communication interface 2, at least one memory 3 and at least one communication bus 4.

[0115] In the embodiments of the present application, the number of the processor 1, the communication interface 2, the memory 3 and the communication bus 4 is at least one, and the processor 1, the communication interface 2 and the memory 3 complete communication with each other through the communication bus 4.

[0116] The processor 1 can be a central processing unit CPU, or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application, etc.

[0117] The memory 3 can comprise a high-speed RAM memory and can also comprise a non-volatile memory such as at least one disk memory;

[0118] The memory stores a program, and the processor can invoke the program stored in the memory, and the program is used for:

[0119] Real-time receiving an environment signal set, the environment signal set is obtained by the radar periodically scanning the surrounding environment with a plurality of different radii, and the environment signal set comprises a plurality of groups of environment signals with the same number of groups as the number of radii;

[0120] Performing Fourier transform on each group of environment signals to obtain each group of environment frequency domain signals;

[0121] According to a preset intensity threshold of the ground frequency domain signal, filtering each group of environment frequency domain signals to determine each group of ground frequency domain signals;

[0122] Performing inverse Fourier transform on each group of ground frequency domain signals to obtain ground information.

[0123] Optionally, the detailed functions and extended functions of the program can refer to the description above.

[0124] The embodiment of the application further provides a storage medium, which can store a program suitable for processor execution, and the program is used for:

[0125] Real-time receiving an environment signal set, the environment signal set is obtained by the radar periodically scanning the surrounding environment with a plurality of different radii, and the environment signal set comprises a plurality of groups of environment signals with the same number of groups as the number of radii;

[0126] Performing Fourier transform on each group of environment signals to obtain each group of environment frequency domain signals;

[0127] According to a preset intensity threshold of the ground frequency domain signal, filtering each group of environment frequency domain signals to determine each group of ground frequency domain signals;

[0128] Performing inverse Fourier transform on each group of ground frequency domain signals to obtain ground information.

[0129] Optionally, the detailed functions and extended functions of the program can refer to the description above.

[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 not intended to denote the presence of any such actual relationship or order. Moreover, the terms "include", "have", or any other variant thereof are intended to encompass non-exclusive inclusions, such that processes, methods, articles, or apparatuses that comprise a list of elements are not required to comprise only those elements in the list, but can include other elements not expressly listed, or also include elements inherent in such processes, methods, articles, or apparatuses. Without additional restrictions, an element preceded by "comprises... a" does not exclude the existence of additional identical elements in the process, method, article, or apparatus that comprises the stated element.

[0131] The various embodiments in the specification are described in progressive order with each embodiment building on one or more of the previous embodiments, however the order of the embodiments described is not intended to be construed as a requirement or limitation for these embodiments. Any one or more of the embodiments described with reference to a particular set of one or more other embodiments are optionally employable together with one or more other embodiments and / or in any appropriate combination.

[0132] The above description of disclosed embodiments is intended to enable persons skilled in the art to make or use the application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and generic principles defined herein can be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method of ground identification, characterized in that, The method is applied to a driving system terminal in communication with a radar, and comprises the following steps: receiving an environment signal set in real time, the environment signal set being obtained by the radar periodically scanning a surrounding environment at a plurality of preset different radii, the environment signal set comprising a same number of groups of environment signals as the number of radii; performing Fourier transform on each group of environment signals to obtain each group of environment frequency domain signals; filtering each group of environment frequency domain signals according to a preset ground frequency domain signal intensity threshold to determine each group of ground frequency domain signals; performing inverse Fourier transform on each group of ground frequency domain signals to obtain ground information; the determination process of the ground frequency domain signal intensity threshold comprises: when the scanning range of the maximum scanning radius of the radar is only ground, receiving a vacant environment signal set obtained by the radar periodically scanning the surrounding environment at the plurality of preset radii, the vacant environment signal set comprising a same number of groups of vacant environment signals as the number of radii; performing Fourier transform on each group of vacant environment signals to obtain each group of vacant environment frequency domain signals; determining the ground frequency domain signal intensity threshold based on each group of vacant environment frequency domain signals.

2. The method of claim 1, wherein, each group of environment frequency domain signals is composed of a plurality of environment frequency domain point signals; the filtering of each group of environment frequency domain signals according to the preset ground frequency domain signal intensity threshold to determine each group of ground frequency domain signals comprises: for each group of environment frequency domain signals, filtering out environment frequency domain point signals with a signal intensity less than the preset ground frequency domain signal intensity threshold, and the remaining environment frequency domain point signals constitute a group of ground frequency domain signals.

3. The method of claim 1, wherein, further comprising: for each group of environment frequency domain signals, determining environment frequency domain signals with a signal intensity between the preset ground frequency domain signal intensity threshold and a preset obstacle frequency domain signal intensity threshold as obstacle frequency domain signals; performing inverse Fourier transform on each group of obstacle frequency domain signals to obtain obstacle signals.

4. The method of claim 1, wherein, after the inverse Fourier transform of each group of ground frequency domain signals to obtain ground information, further comprising: based on the ground information, modeling the ground of the radar scanning area to obtain a first ground simulation image.

5. The method of claim 3, wherein, after the inverse Fourier transform of each group of ground frequency domain signals to obtain ground information, further comprising: based on the ground information, modeling the ground of the radar scanning area to obtain a first ground simulation image; based on the obstacle signals, marking obstacles in the first ground simulation image to obtain a second ground simulation image, so as to distinguish the ground and obstacles.

6. An apparatus for ground identification, characterized by The method is applied to a driving system terminal in communication with a radar, and comprises the following steps: a signal set receiving unit for receiving an environment signal set in real time, the environment signal set being obtained by the radar periodically scanning a surrounding environment at a plurality of preset different radii, the environment signal set comprising a same number of groups of environment signals as the number of radii; a frequency domain signal conversion unit for performing Fourier transform on each group of environment signals to obtain each group of environment frequency domain signals; a filtering unit for filtering each group of environment frequency domain signals according to a preset ground frequency domain signal intensity threshold to determine each group of ground frequency domain signals; The frequency domain signal filtering unit is configured to filter each group of environment frequency domain signals according to a preset ground frequency domain signal intensity threshold value, and determine each group of ground frequency domain signals; The ground information determination unit is configured to perform inverse Fourier transform on each group of ground frequency domain signals to obtain ground information; The contrast signal set receiving unit is configured to receive a set of empty environment signals obtained by periodically scanning the surrounding environment by the radar at a plurality of preset radii when only ground exists within the scanning range of the maximum scanning radius of the radar, the set of empty environment signals including a same number of groups of empty environment signals as the number of radii. The contrast signal frequency domain transformation unit is configured to perform Fourier transform on each group of empty environment signals to obtain each group of empty environment frequency domain signals. The intensity threshold value determination unit is configured to determine the intensity threshold value of the ground frequency domain signal based on each group of empty environment frequency domain signals.

7. The apparatus of claim 6, wherein, Each group of environment frequency domain signals is composed of a plurality of environment frequency domain point signals. The frequency domain signal filtering unit includes: The frequency domain point signal filtering unit is configured to filter out environment frequency domain point signals with a signal intensity less than the preset ground frequency domain signal intensity threshold value from each group of environment frequency domain signals, and the remaining environment frequency domain point signals constitute a group of ground frequency domain signals.

8. The apparatus of claim 6, wherein, Further comprising: The obstacle frequency domain signal determination unit is configured to determine environment frequency domain signals with a signal intensity between the preset ground frequency domain signal intensity threshold value and a preset obstacle frequency domain signal intensity threshold value as obstacle frequency domain signals for each group of environment frequency domain signals. The obstacle signal determination unit is configured to perform inverse Fourier transform on each group of obstacle frequency domain signals to obtain obstacle signals.

Citation Information

Patent Citations

  • Device for recognizing obstacle around vehicle and method thereof

    US20170067738A1