EP3652035A1 - Verfahren zur radar-klassifikation der strassenoberfläche - Google Patents
Verfahren zur radar-klassifikation der strassenoberflächeInfo
- Publication number
- EP3652035A1 EP3652035A1 EP18789070.2A EP18789070A EP3652035A1 EP 3652035 A1 EP3652035 A1 EP 3652035A1 EP 18789070 A EP18789070 A EP 18789070A EP 3652035 A1 EP3652035 A1 EP 3652035A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- data structure
- information
- radar
- soil
- structure units
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/89—Radar or analogous systems specially adapted for specific applications for mapping or imaging
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
- B60W40/06—Road conditions
- B60W40/064—Degree of grip
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
- G01S7/411—Identification of targets based on measurements of radar reflectivity
- G01S7/412—Identification of targets based on measurements of radar reflectivity based on a comparison between measured values and known or stored values
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
- G01S7/414—Discriminating targets with respect to background clutter
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
- G01S7/415—Identification of targets based on measurements of movement associated with the target
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/165—Anti-collision systems for passive traffic, e.g. including static obstacles, trees
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
- G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
- G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
- G01S2013/932—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles using own vehicle data, e.g. ground speed, steering wheel direction
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
- G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
- G01S2013/9327—Sensor installation details
- G01S2013/93271—Sensor installation details in the front of the vehicles
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/0112—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from the vehicle, e.g. floating car data [FCD]
Definitions
- the invention relates to a method and a radar system for
- supplementary sensor data are evaluated in order to merge these into a common detection result.
- Substantial optical features such as lane markings. These are used with optical detection systems, for example
- a disadvantage of the hitherto known radar systems is that with these no lane detection can be realized if no clear boundary structure with a significant backscatter cross section is available. A classification of the soil texture from the Backscatter behavior of the respective soil structure can not be realized with the available radar systems so far.
- Soil type is possible in order to draw conclusions about the course of the road.
- the task is performed by a procedure with the characteristics of
- the invention relates to a method for classifying the ground condition in the environment of a vehicle by means of a radar sensor.
- the method comprises the following steps:
- Receiver unit of a radar system received.
- the radar signals are preferably in the frequency range between 76GHz and 81 GHz, in order to achieve the highest possible resolution, but may be chosen deviating in the frequency range of 24 GHz.
- Transformation into the spectral region in particular a fast Fourier transformation (FFT), are calculated from the received fractions of the FFT.
- Radar signal derived by the radar system or an associated control unit information related to discrete local areas of a radar image.
- the information can be up for example, on the amplitude of the received reflected portion of the radar signal, on the power of the received reflected portion of the radar signal, on the complex representation of the received reflected portion of the radar signal, etc., or be measurements derived therefrom.
- the information obtained is assigned to data structure units of a data structure.
- Each data structure unit is assigned to a fixed geographic location and the assignment of the
- the data structure units correspond to raster areas of a geographic stationary, i. not with the vehicle mitbewegten radar map and the allocation of information in the
- Data structure units take into account the location of the reflection, which is responsible for the formation of information in the radar system and compensating for a movement of the
- the radar sensor successively performs a plurality of individual measurements in time, each leading to the information described above. These successively won over
- Information is stored spatially resolved in the data structure units, ie, according to the location of the reflection that was responsible for the generation of the information.
- a variety of information is collected in the respective data structure units, the information being obtained from reflected portions of radar signals transmitted at different times.
- each data structure unit comprises a plurality of individual measurements taken at different times information, so based on the information contained in the respective data structure unit Information the temporal course of the reflections can be evaluated at the respective location.
- Data structure evaluated by means of a classifier to obtain information regarding the soil condition can be designed to extract essential characteristics from the information for the classification of the soil conditions and to compare them with known criteria in order to draw conclusions therefrom
- Soil type is present at the respective location.
- Raster area of the radar map which is assigned to the respective data structure unit, is present.
- the main advantage of the method is that of the spatial and temporal course of the.
- Radar sensor determined power spectrum surface structures are classifiable, for example, according to the categories asphalt, grass, pavement, etc. and thus the road course can be estimated.
- only information is used for the classification of the soil condition, which arise due to reflections on non-moving, ie stationary targets.
- all the information that can be identified, for example, due to the Doppler shift, is therefore are moving targets, not fed to the data structure units and thus not used to classify the soil condition.
- a classifier when evaluating the information contained in the data structure by means of a classifier only information, for example, signal or measured values
- Evaluation of radar signals is the evaluation of information in the reverse manner, i. E. only high amplitude signal or measurement values are used to select the main reflections and thus minimize the required computational power.
- the invention evaluates exactly the signal or measured values in the low amplitude range, since these often result from ground reflections and thus conclusions can be drawn on the soil conditions.
- the information stored in the data structure are signal values or measured values
- the power of the reflected portion of the radar signal is a measure of the backscatter cross section of the object or the structure on which the reflection has taken place. From the temporal and spatial course of the signal values it is possible to draw conclusions about the soil condition.
- the information stored in the data structure is signal values or measured values which are assigned to the data structure units without amount limitation or at least without truncation in the lower amplitude range of the signal values. This ensures that signal or measured values, especially in the low amplitude range can be stored in the data structure units based on the information in the low
- Amplitude range to be able to make a soil condition classification Amplitude range to be able to make a soil condition classification.
- each data structure unit is assigned a respective raster area of a two-dimensional radar map.
- this radar map is a fixed radar map relating to a fixed geographic point, i. not moved with the vehicle.
- classification information obtained from the data structure units can be applied to raster areas of the
- an information associated with a particular discrete local area is a single one
- Assigned data structure unit or assigned to a particular discrete local area information is more
- these data structure units are correlated with adjacent arranged raster areas of the two-dimensional radar map.
- the radar sensor can provide a locally discretized radar image, which is moved with the vehicle and in which the information provided by the radar system, in particular the power reflected at the respective location of the radar system
- Discretization of the stationary radar map be.
- the size of the grid areas of the moving radar image can be the same or different from the size of the grid areas of the stationary
- the co-moving radar image preferably has a coarser discretization than the stationary radar map.
- the information obtained in a single measurement associated with a grid area of the co-moving radar image associated with a group of a plurality of data structure units or a group of multiple raster areas of the stationary radar map.
- Each group of raster areas of the stationary radar map are arranged adjacent to each other. This achieves a higher resolution and significantly improves the accuracy of the classification of the soil condition.
- the evaluation of the information contained in the data structure is carried out separately based on the information contained in a data structure unit. In other words, the evaluation of the information takes place
- Data structure unit without consideration of information from other data structure units.
- the power spectrum detected with respect to a location can be used for
- Soil quality classification are used.
- Data structure unit of the data structure contained information regarding temporal / spectral properties evaluated. As described above, in each data structure unit, information is stored from a plurality of individual measurements, which were performed successively in time. This is done in contrast to known methods in which the obtained with respect to a location, reflected
- Performance values are added up. That is to say, in the known methods, after a plurality of individual measurements, there is not a plurality of information per raster area of the stationary radar map, but merely a summation value formed by summing up a plurality of information or measured variables. From the time course of a place Information gathered can have an advantageous
- the evaluation of the information contained in the data structure is based on groups of data structure units, wherein each group of data structure units includes a plurality of data structure units that are adjacent to each other
- Data structure units of the data structure contain information across data structures in terms of temporal / spectral
- the temporal course of the information recorded with respect to one location may change the information about the time (and thus due to the movement of the vehicle from different directions), on the other hand under
- the change in the information about the location (for example in a region with a close local context) can be determined.
- the location dependence of the reflections it is possible, for example, to identify spatially different structure sizes. This allows an improved classification of soil conditions in the
- the classifier uses statistical classifiers, machine-learning or model-based methods.
- a so-called “deep learning” method using, for example, a neural network, such as a “convolutional neural network” (CNN) .
- CNN convolutional neural network
- a correction step is performed in which at least partially allocates the data structure units
- Soil texture types based on information from
- This correction step may be based on known correction or
- Classification errors can be effectively resolved by including classification results in the adjacent grid areas.
- Data structure units assigned to types of soil properties estimated a lane course For example, based on the types of soil types recognized, contiguous areas of a particular type of soil condition or boundary lines between different types of soil types can be identified.
- Boundary lines can then be used for the roadway assessment, in particular for a roadway assessment in addition to an optical, for example, camera-based method.
- the radar map may be a three-dimensional radar map, ie the radar system is not designed as a 2D radar system (ie resolution in azimuth and distance) but as a 3D radar system (ie resolution in azimuth, Elevation and distance).
- the radar system is not designed as a 2D radar system (ie resolution in azimuth and distance) but as a 3D radar system (ie resolution in azimuth, Elevation and distance).
- the invention relates to a
- Computer program product comprises a computer-readable storage medium with program instructions, wherein the program instructions are executable by a processor to cause the processor to carry out a method according to one of the preceding embodiments.
- the invention relates to a radar system for a vehicle comprising a radar sensor and a control unit, by means of which the reflected components of a radar signal received by the radar sensor are evaluated.
- the control unit is designed to:
- each data structure unit being associated with a fixed geographic location, and assigning the information taking into account
- Movement information of the vehicle takes place
- Data structure units made up of reflected units obtained from radar signals transmitted at different times;
- classifier in the context of the present invention is a
- the classifier is designed to analyze the information stored in the data structure units and to recognize to which types of soil properties the respective information is to be assigned.
- information derived from the reflected portions of the radar signal is understood to mean all information that can be obtained by suitable analysis or analysis
- Calculation methods are derived, in particular signal strength, reflected signal amplitude, reflected power or derived quantities.
- data structure in the sense of the present invention means any information-storing structures, in particular data storage structures
- the data structure can be stored, for example, in a volatile or non-volatile memory unit of the radar system, for example a random access memory (RAM).
- RAM random access memory
- data structure unit is understood to be a logical unit within the data structure that can store a plurality of different identifiable information
- Data structure unit can be formed in particular by a memory area in a memory unit of the radar system.
- Fig. 1 by way of example and schematically a obtained by a radar system of a vehicle radar image as a result of
- Fig. 2a exemplifies the local and temporal reflection behavior of asphalt; 2b shows by way of example the local and temporal reflection behavior of 2-steinpflaster;
- Fig. 2c exemplifies the local and temporal reflection behavior of grass
- FIG. 3 shows by way of example and schematically the assignment of a raster region of a radar image moved with the vehicle to a plurality of data structure units of a data structure or
- FIG. 4 shows, by way of example and schematically, an unadjusted radar map with a multiplicity of raster areas to which information about types of soil are respectively assigned;
- FIG. 5 shows by way of example and schematically the adjusted radar map according to FIG. 4;
- Fig. 6 shows an example of the method for the classification of
- FIG. 7 shows by way of example a block diagram of a radar system which can be used for the classification of the soil condition.
- FIG. 1 shows by way of example a radar image generated by a radar system 1 of a vehicle 10. For example, this is about the azimuth ⁇ and the distance r information plotted, in particular the power spectrum of the radar sensor of the radar system 1 back-reflected portions of the radar signal after a single measurement and after a Fourier transform.
- the density or the intensity of the blackening here is a measure of what proportion or how much power of the radar signal from the respective position in space to the
- Radar sensor 1 .1 of the vehicle was reflected back.
- a plurality of individual measurements are used in relation to their geographical location assigned in the correct position, ie Compensates the vehicle movement between the individual measurements and analyzes the signal values of a large number of individual measurements in order to obtain information regarding the nature of the soil.
- the control unit 4 can be formed by a module in which only the necessary for the radar system 1 calculation and control steps are completed, for example, the received radar signals from analog signals are converted into digital signals and calculations on the digital signals, in particular the calculations for transformation into the
- control unit 4 can be assigned to the radar system 1, in particular be provided directly adjacent to the radar sensor and exclusively
- control unit 4 can also be formed by a remote control unit, in addition to the processing of
- Information of the radar sensor 1 .1 also fulfills other control tasks in the vehicle.
- sufficient Bandwidth for example Ethernet or similar respectively.
- a remote control unit 4 a partial processing of the received radar signals is already completed in or in the immediate vicinity of the radar sensor 1 .1, for example an analog / digital conversion, so that digitized received radar signals are transmitted to the remote control unit 4 can be.
- ground texture types store these low amplitude signal values over multiple individual measurements, taking into account the geographic location of the particular reflection. These are then related to a defined geographical location signal values of the
- Classification method analyzed to determine the type of soil condition at the given geographical location based on the low amplitude signal values.
- the invention is based on the finding that the
- Gaps between the paving stones arises.
- FIGS. 2 a to 2 c show, by way of example and schematically, the reflected power (P, vertical axis) in the case of different ground conditions over the location r (in each case the left-hand representation) or over the time t (in each case the right-hand representation).
- the representations of FIG. 2a show the location-dependent and time-dependent reflected power in the case of asphalt
- the representations of FIG. 2b the location-dependent and time-dependent reflected power in large stone paving
- Power values in the low amplitude range are, for example, 15 dB to 30 dB below the power values of the main reflections.
- Movement of the vehicle is time-variant, i. the radar image changes with individual measurements taken one after the other.
- the radar system 1 comprises a data structure comprising a multiplicity of
- the data structure may for example be stored in a memory unit and the data structure units represent areas in this memory unit, for example logical Storage areas. These memory areas are used to store a large number of information items, each of which has been determined in succession from individual measurements.
- the information can be obtained, for example, by means of a digital transformation (fast-Fourier transformation, FFT) from the received reflected portions of the radar signal of a respective individual measurement.
- FFT fast-Fourier transformation
- the information may, for example, relate to the amplitude of the received reflected component of the radar signal, to the power of the received reflected component of the radar signal, etc., or to be measured values derived from these parameters.
- the data structure units are each a fixed one
- Each data structure unit includes information that is all related to reflections at the same defined geographic location.
- the information contained in the data structure units of the data structure can be used to generate a geographically stationary radar map (see Figures 4 and 5), with the information contained in the data structure units
- the data structure units are each associated with a raster area of a fixed radar map grid, and information stored in these data structure units is based on reflections that have occurred at the geographic location associated with the respective fixed radar map grid area.
- Vehicle odometry used to obtain the information obtained in the individual measurements the respective
- Assign data structure units and store the information in the respective data structure units. This includes each
- the radar image shown in Figure 1 is formed by a plurality of discrete pieces of information calculated from a single measurement.
- the information is calculated at discrete azimuth and distance values.
- the spatial discretization in each individual measurement i.e., the radar image
- Data structure units may be the same or different.
- the data structure may be more finely discretized than the spatial discretization underlying the individual measurement (super-resolution principle).
- Discretization of the radar image moved with the vehicle higher discretization of the data structure is achieved in that a signal value is assigned not only to a single data structure unit but to a group of several data structure units, as shown by way of example in FIG.
- the information obtained from the radar system 1 is obtained from the radar system 1
- a data structure unit corresponds to a box in the lower grid of FIG. Grid areas of the stationary radar map assigned or stored in this.
- This classifier is designed to evaluate the information stored in the data structure in terms of their temporal and spatial change. The aim of the evaluation is to determine what type of soil type, such as grass, pavement, asphalt, ice, vegetation (e.g., shrubs), etc., is present at the particular geographical location.
- the classifier can be statistical classification methods, machine-learning methods (eg deep learning algorithms, in particular deep learning with convolutional neural networks (CNNs)) or model-based methods.
- the classification can be preselected solely on the information obtained temporally offset and stored in a single data structure unit.
- the classification is preferably carried out based on information from a plurality of data structure units, so that, in particular, reflected portions of the radar signals with a close spatial relationship are evaluated. In particular, both the change in the information over time and over the place can be used for classification.
- 4 shows by way of example a classification result of an area in the vicinity of a vehicle 10. As a result, spatially discrete information exists as a radar map RK indicating which
- Soil type is present at the respective spatially discrete position.
- a grid area R of the grid of the radar map RK in FIG. 4 corresponds to a data structure unit of the data structure described above.
- the different hatching or filling of the raster areas R stand for different
- the left and right stripes marked with the capital letter “A” represent grassed areas
- the narrower stripes marked with the letter “C” represent a paved walkway
- the broader stripes marked with the letter “B” represent an asphalted roadway.
- the classification result may include errors or inaccuracies.
- the troubleshooting may be done by reclassifying the localized areas of the other type of soil condition to the type of soil condition present in the immediate vicinity of the faulted area.
- known algorithms can be used, for example by means of model-based smoothing methods, curve approximation methods, low-pass filters, etc.
- the corrected radar map RK shown in FIG. 5 can be used to detect passable areas in the surrounding area of the vehicle, to determine boundary lines between the individual areas and thus to estimate the course of the road.
- the information obtained by the radar system 1 can be redundant or complementary to other sensor systems of the vehicle 10, for example
- imaging systems (camera etc.).
- FIG. 6 schematically shows a block-based flowchart of a
- step S10 reflections of a radar signal are first received.
- one or more radar signals are emitted by the radar sensor 1 .1 and those on this
- the information or signal values can be, for example
- Amplitude values that indicate the reflected power at the respective local area can be displayed in a radar image with local reference to the vehicle 10, for example, based on a coordinate system that the vehicle 10 as
- the calculation is done for example by a
- Transformation method such as an FFT, in particular a 3D FFT.
- the calculation can be carried out in a control unit 4 inherent to the radar system 1, which is assigned directly to the radar sensor 1 .1 and, for example, the aforementioned calculations and, if necessary,
- Control tasks at the radar sensor 1 .1 completes.
- the control unit 4 may be a higher-level control unit, which performs control tasks for other systems of the vehicle 10 in addition to the radar system 1.
- the information obtained by the calculation is then assigned to data structure units of a data structure (S12).
- Data structure units form for example stack-like
- the data structure units are each assigned to a grid area of a stationary radar map RK (also called radar grid), ie each data structure unit stores the information resulting from reflections at the location area that is assigned to the respective data structure unit.
- RK also called radar grid
- Vehicle are transformed into information relating to a fixed geographic location. This can be done, for example, under
- the data structure units contain a variety of information resulting from reflected portions of radar signals that are different
- the information stored in the data structure is subsequently supplied to a classification process in order to classify the soil condition according to predetermined soil texture types based on the information stored in the data structure (S14).
- the classifier for classifying a raster area can only use information from a single data structure unit that is assigned to the raster area. However, it is preferable that the classification of a raster region using a plurality of
- Data structure units are correlated with grid areas that are locally closely related to the one to be classified
- Data structure units are assigned, assigned to soil type (S15).
- soil type S15
- a radar map with grid areas, wherein each grid area is assigned a determined by the radar system 1 soil texture type. This makes it possible to determine boundary lines between different types of soil types which can be used, for example, to estimate the course of the lane or its redundant recognition.
- Fig. 7 shows an example and schematically a block diagram of a
- the radar system 1 which can be used to classify the soil condition.
- the radar system 1 comprises a
- the control unit 4 has a radar control unit 4.1. This is in communication with the transmitting unit 2 in order to suitably control an HF signal generator 2.1 in the transmitting unit 2.
- the RF signal generator 2.1 can be, for example, a voltage-controlled oscillator (voltage-controlled oscillator VCO) or a phase-locked loop (PLL).
- the radar system 1 can use a frequency in the range of 24 GHz or in the range of 76 GHz to 81 GHz. A radar system in the range of 76 GHz to 81 GHz is preferred, since higher resolutions can be achieved due to the larger bandwidth.
- the signal generated by the RF signal generator 2.1 can preferably via
- Phase shifter 2.2 are transmitted to an amplifier unit via which the signal is amplified and then the transmitting antenna 2.4 is supplied.
- the receiving unit 3 has at least one receiving antenna 3.1, which is coupled to at least one amplifier 3.2.
- at least two receiving antennas are provided 3.1 to a desired Receiving characteristic at the receiving unit 3 to achieve (beam-forming).
- the amplifiers 3.2 are coupled on the output side each with a mixer 3.3.
- the mixer 3.3 the transmission signal, that is supplied to the signal generated by the RF oscillator 2.1 to the
- the radar system 1 may in particular be a so-called.
- Continuous wave radar frequency modulated continuous wave radar, FMCW radar.
- FMCW radar frequency modulated continuous wave radar
- the mixer 3.3 At the output of the mixer 3.3 is in each case the so-called. Beat frequency available, which arises by mixing the received signal with the transmission signal. Subsequently, the downmixed signals can be low-pass filtered in lowpasses 3.4.
- the control unit 4 effects a digital signal processing of
- Output signals of the receiver unit In particular, the optionally low-pass filtered output signals of the mixer 3.3 are converted by analog / digital converter 4.2 into digital signals. These digitized signals are transmitted via a transformation process, such as a
- 3D-FFT three-dimensional fast Fourier transform
- the control unit 4 can be formed in particular by a microprocessor or a microprocessor-based control unit.
- the output signals of the control unit 4 are then transmitted via a vehicle interface 5 to one or more higher-level control units, for example via a vehicle bus system (eg CAN bus).
- vehicle bus system eg CAN bus
Landscapes
- Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Electromagnetism (AREA)
- Automation & Control Theory (AREA)
- Mathematical Physics (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Radar Systems Or Details Thereof (AREA)
- Traffic Control Systems (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| DE102017123969.3A DE102017123969B4 (de) | 2017-10-16 | 2017-10-16 | Verfahren zur Klassifikation von flächigen Strukturen |
| PCT/EP2018/078074 WO2019076812A1 (de) | 2017-10-16 | 2018-10-15 | Verfahren zur radar-klassifikation der strassenoberfläche |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| EP3652035A1 true EP3652035A1 (de) | 2020-05-20 |
Family
ID=63896141
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| EP18789070.2A Withdrawn EP3652035A1 (de) | 2017-10-16 | 2018-10-15 | Verfahren zur radar-klassifikation der strassenoberfläche |
Country Status (5)
| Country | Link |
|---|---|
| US (1) | US11500087B2 (de) |
| EP (1) | EP3652035A1 (de) |
| CN (1) | CN111491845B (de) |
| DE (1) | DE102017123969B4 (de) |
| WO (1) | WO2019076812A1 (de) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102018200814B3 (de) * | 2018-01-18 | 2019-07-18 | Audi Ag | Verfahren zum Betrieb eines zur vollständig automatischen Führung eines Kraftfahrzeugs ausgebildeten Fahrzeugführungssystems des Kraftfahrzeugs und Kraftfahrzeug |
| SE542921C2 (en) | 2019-01-24 | 2020-09-15 | Acconeer Ab | Autonomous moving object with radar sensor |
| WO2020261525A1 (ja) * | 2019-06-28 | 2020-12-30 | 日本電気株式会社 | レーダ装置、イメージング方法およびイメージングプログラム |
| CN113587941A (zh) * | 2020-05-01 | 2021-11-02 | 华为技术有限公司 | 高精度地图的生成方法、定位方法及装置 |
| CN112184549B (zh) * | 2020-09-14 | 2023-06-23 | 阿坝师范学院 | 基于时空变换技术的超分辨图像重建方法 |
| EP4001962A1 (de) * | 2020-11-23 | 2022-05-25 | Aptiv Technologies Limited | Vorrichtung, verfahren und programm zur bestimmung vom freien raum |
| CN113140048B (zh) * | 2021-04-15 | 2023-02-24 | 北京世纪高通科技有限公司 | 一种车辆里程确定方法、装置、系统及存储介质 |
| US20230035002A1 (en) * | 2021-07-27 | 2023-02-02 | Symeo Gmbh | Apparatus and method for particle deposition distribution estimation |
| CN114675247A (zh) * | 2022-03-17 | 2022-06-28 | 四川豪智融科技有限公司 | 一种基于毫米波雷达的极近距离地面种类判断方法 |
| US12221128B2 (en) * | 2022-11-28 | 2025-02-11 | Gm Cruise Holdings Llc | Reducing and processing simulated and real-world radar data |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE19545704A1 (de) * | 1995-12-07 | 1997-06-12 | Horsch Maschinen Gmbh | Verfahren und Einrichtung zum Vermessen landwirtschaftlicher Nutzflächen unter Verwendung von GPS |
| DE102014210770A1 (de) * | 2014-06-05 | 2015-12-17 | Conti Temic Microelectronic Gmbh | Verfahren und system zur bestimmung einer fahrzeugposition eines fahrzeuges |
| DE102015003115A1 (de) * | 2015-03-11 | 2016-09-15 | Audi Ag | Verfahren zur Ermittlung einer Fahrbahnzustandsinformation und Kraftfahrzeug |
| DE102017103969A1 (de) * | 2016-02-25 | 2017-08-31 | Ford Global Technologies, Llc | Autonome Fahrzeugsteuerung mit Risikofaktor |
Family Cites Families (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE19932094A1 (de) * | 1999-07-09 | 2001-01-25 | Daimler Chrysler Ag | Multisensorielle, vorausschauende Straßenzustandserkennung |
| US9377528B2 (en) * | 2010-03-19 | 2016-06-28 | Northeastern University | Roaming mobile sensor platform for collecting geo-referenced data and creating thematic maps |
| US8996228B1 (en) * | 2012-09-05 | 2015-03-31 | Google Inc. | Construction zone object detection using light detection and ranging |
| WO2014065856A1 (en) | 2012-10-25 | 2014-05-01 | Massachusetts Institute Of Technology | Vehicle localization using surface penetrating radar |
| DE102013002333A1 (de) * | 2013-02-12 | 2014-08-14 | Continental Teves Ag & Co. Ohg | Verfahren und Strahlensensormodul zur vorausschauenden Straßenzustandsbestimmung in einem Fahrzeug |
| EP2972252B1 (de) * | 2013-03-14 | 2023-10-18 | Robert Ernest Troxler | Systeme und verfahren zur bodeneigenschaften- und bodenfeuchtigkeitsmessung mit einem bodendurchdringenden radar |
| JP6321448B2 (ja) * | 2013-06-03 | 2018-05-09 | 株式会社デンソー | レーダ装置、及びプログラム |
| US9383426B2 (en) * | 2013-09-17 | 2016-07-05 | Farrokh Mohamadi | Real-time, two dimensional (2-D) tracking of first responders with identification inside premises |
| DE102013017347A1 (de) | 2013-10-18 | 2015-04-23 | Knorr-Bremse Systeme für Nutzfahrzeuge GmbH | Verfahren zum Klassifizieren von Hindernissen |
| DE102015001386A1 (de) | 2015-02-04 | 2016-08-04 | Audi Ag | Verfahren zur Ermittlung einer Querpositionsinformantion eines Kraftfahrzeugs auf einer Fahrbahn und Kraftfahrzeug |
| CN106324618B (zh) * | 2015-06-17 | 2019-03-15 | 高田汽车电子(上海)有限公司 | 实现基于激光雷达检测车道线系统的方法 |
| US10503983B2 (en) | 2015-08-19 | 2019-12-10 | Mitsubishi Electric Corporation | Lane recognition apparatus and lane recognition method |
| JP6580982B2 (ja) * | 2015-12-25 | 2019-09-25 | 日立建機株式会社 | オフロードダンプトラック及び障害物判別装置 |
| DE102016200642A1 (de) * | 2016-01-19 | 2017-07-20 | Conti Temic Microelectronic Gmbh | Verfahren und vorrichtung zum klassifizieren von fahrbahnbegrenzungen und fahrzeug |
| US10656265B2 (en) * | 2016-03-14 | 2020-05-19 | Hitachi Construction Machinery Co., Ltd. | Mining work machine |
| US10353053B2 (en) * | 2016-04-22 | 2019-07-16 | Huawei Technologies Co., Ltd. | Object detection using radar and machine learning |
| CN106127113A (zh) * | 2016-06-15 | 2016-11-16 | 北京联合大学 | 一种基于三维激光雷达的道路车道线检测方法 |
| DE102017000753A1 (de) | 2017-01-27 | 2017-07-13 | Daimler Ag | Verfahren zur Detektion von Feuchtigkeit in einer Fahrzeugumgebung |
| US10127462B1 (en) * | 2017-05-09 | 2018-11-13 | Toyota Research Institute, Inc. | Systems and methods for detecting markers on a roadway |
-
2017
- 2017-10-16 DE DE102017123969.3A patent/DE102017123969B4/de active Active
-
2018
- 2018-10-15 EP EP18789070.2A patent/EP3652035A1/de not_active Withdrawn
- 2018-10-15 CN CN201880064201.4A patent/CN111491845B/zh active Active
- 2018-10-15 US US16/756,447 patent/US11500087B2/en active Active
- 2018-10-15 WO PCT/EP2018/078074 patent/WO2019076812A1/de not_active Ceased
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE19545704A1 (de) * | 1995-12-07 | 1997-06-12 | Horsch Maschinen Gmbh | Verfahren und Einrichtung zum Vermessen landwirtschaftlicher Nutzflächen unter Verwendung von GPS |
| DE102014210770A1 (de) * | 2014-06-05 | 2015-12-17 | Conti Temic Microelectronic Gmbh | Verfahren und system zur bestimmung einer fahrzeugposition eines fahrzeuges |
| DE102015003115A1 (de) * | 2015-03-11 | 2016-09-15 | Audi Ag | Verfahren zur Ermittlung einer Fahrbahnzustandsinformation und Kraftfahrzeug |
| DE102017103969A1 (de) * | 2016-02-25 | 2017-08-31 | Ford Global Technologies, Llc | Autonome Fahrzeugsteuerung mit Risikofaktor |
Non-Patent Citations (1)
| Title |
|---|
| See also references of WO2019076812A1 * |
Also Published As
| Publication number | Publication date |
|---|---|
| US11500087B2 (en) | 2022-11-15 |
| US20200256980A1 (en) | 2020-08-13 |
| WO2019076812A1 (de) | 2019-04-25 |
| DE102017123969A1 (de) | 2019-04-18 |
| CN111491845B (zh) | 2024-04-16 |
| DE102017123969B4 (de) | 2019-11-28 |
| CN111491845A (zh) | 2020-08-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| DE102017123969B4 (de) | Verfahren zur Klassifikation von flächigen Strukturen | |
| DE102015100134B4 (de) | Verfahren zum Detektieren und Verfolgen von Objekten unter Verwendung mehrerer Radarsensoren | |
| EP3175256B1 (de) | Verfahren zum klassifizieren eines objektes in einem umgebungsbereich eines kraftfahrzeugs, fahrerassistenzsystem und kraftfahrzeug | |
| EP1554602B1 (de) | Verfahren zur abstands- und geschwindigkeitsmessung an mehreren objekten mittels fmcw-radar | |
| DE102012107445B4 (de) | 2Verfahren zur Klassifizierung von fahrenden Fahrzeugen | |
| DE102018118528B4 (de) | Verfahren und Vorrichtung zur Segment-übergreifenden Erfassung in einem Lidar-System | |
| EP3485290B1 (de) | Verfahren und system zur abtastung eines objekts | |
| EP1929331B1 (de) | Kraftfahrzeug-radarverfahren und -radarsystem | |
| WO1999036796A1 (de) | Radarsignal-verarbeitungsverfahren | |
| DE102018202289A1 (de) | Winkelauflösender breitbandiger Radarsensor für Kraftfahrzeuge | |
| DE102014009648A1 (de) | Verfahren und Vorrichtung zum Abtasten einer Straßenumgebung basierend auf einem frequenzmodulierten Dauerstrichradar | |
| DE102015207804A1 (de) | Verfahren zum Erkennen von Parkflächen und/oder Freiflächen | |
| DE19532597A1 (de) | System und Verfahren zur Objektverfolgung unter Verwendung eines Detektorsystems | |
| EP1380854A2 (de) | Verfahren und Radarsystem zur Bestimmung der Richtungswinkel von Radarobjekten | |
| DE102015105080B4 (de) | Radarvorrichtung | |
| DE102018123170A1 (de) | Verfahren und vorrichtung zur frameratenerhöhung in lidar-arrays | |
| DE102017130659A1 (de) | Radarvorrichtung und Fahrzeuggeschwindigkeitskorrekturverfahren | |
| DE102018115372A1 (de) | Verfahren und vorrichtung zur parallelen beleuchtung durch ein vcsel-array | |
| DE102010045980A1 (de) | Radarverfahren und Radarsystem | |
| DE102018217533A1 (de) | Verfahren zur Klassifikation eines Objekts | |
| WO2022117161A1 (de) | Verfahren zur erkennung von parklücken mittels ultraschallsensoren | |
| EP3663881A1 (de) | Verfahren zur steuerung eines autonomen fahrzeugs auf der grundlage von geschätzten bewegungsvektoren | |
| WO2019170347A1 (de) | Verfahren zur eindeutigen bestimmung der geschwindigkeit eines objekts an einem radar messsystem | |
| DE102018115895B4 (de) | Verfahren und System zur Erkennung von Hindernissen | |
| WO2023104617A1 (de) | Verfahren zum vermessen einer umgebung eines kraftfahrzeugs |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: UNKNOWN |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE |
|
| PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
| 17P | Request for examination filed |
Effective date: 20200213 |
|
| AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
| AX | Request for extension of the european patent |
Extension state: BA ME |
|
| RAP1 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: VOLKSWAGEN AG Owner name: CONTI TEMIC MICROELECTRONIC GMBH |
|
| RBV | Designated contracting states (corrected) |
Designated state(s): AL AT BE BG CH CY CZ DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
| REG | Reference to a national code |
Ref country code: DE Ref legal event code: R108 |
|
| RAP1 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: VOLKSWAGEN AG Owner name: CONTI TEMIC MICROELECTRONIC GMBH |
|
| DAV | Request for validation of the european patent (deleted) | ||
| DAX | Request for extension of the european patent (deleted) | ||
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
| 17Q | First examination report despatched |
Effective date: 20211103 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE APPLICATION HAS BEEN WITHDRAWN |
|
| 18W | Application withdrawn |
Effective date: 20230927 |