WO2021069130A1 - Verfahren und eine vorrichtung zur klassifizierung eines objektes, insbesondere im umfeld eines kraftfahrzeugs - Google Patents
Verfahren und eine vorrichtung zur klassifizierung eines objektes, insbesondere im umfeld eines kraftfahrzeugs Download PDFInfo
- Publication number
- WO2021069130A1 WO2021069130A1 PCT/EP2020/072518 EP2020072518W WO2021069130A1 WO 2021069130 A1 WO2021069130 A1 WO 2021069130A1 EP 2020072518 W EP2020072518 W EP 2020072518W WO 2021069130 A1 WO2021069130 A1 WO 2021069130A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- feature
- ultrasonic
- pedestrian
- received
- ultrasonic sensors
- Prior art date
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
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/52—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S15/00
- G01S7/523—Details of pulse systems
- G01S7/526—Receivers
- G01S7/53—Means for transforming coordinates or for evaluating data, e.g. using computers
-
- 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
- G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
- G01S15/02—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems using reflection of acoustic waves
- G01S15/06—Systems determining the position data of a target
- G01S15/46—Indirect determination of position data
-
- 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
- G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
- G01S15/02—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems using reflection of acoustic waves
- G01S15/06—Systems determining the position data of a target
- G01S15/08—Systems for measuring distance only
- G01S15/10—Systems for measuring distance only using transmission of interrupted, pulse-modulated waves
-
- 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
- G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
- G01S15/02—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems using reflection of acoustic waves
- G01S15/06—Systems determining the position data of a target
- G01S15/42—Simultaneous measurement of distance and other co-ordinates
-
- 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
- G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
- G01S15/02—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems using reflection of acoustic waves
- G01S15/50—Systems of measurement, based on relative movement of the target
- G01S15/52—Discriminating between fixed and moving objects or between objects moving at different speeds
-
- 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
- G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
- G01S15/87—Combinations of sonar systems
-
- 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
- G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
- G01S15/88—Sonar systems specially adapted for specific applications
- G01S15/93—Sonar systems specially adapted for specific applications for anti-collision purposes
- G01S15/931—Sonar 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
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/52—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S15/00
- G01S7/523—Details of pulse systems
- G01S7/526—Receivers
- G01S7/527—Extracting wanted echo signals
-
- 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
- G01S7/52—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S15/00
- G01S7/539—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S15/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
-
- 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
- G01S7/52—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S15/00
- G01S7/54—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S15/00 with receivers spaced apart
-
- 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
- G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
- G01S15/02—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems using reflection of acoustic waves
- G01S15/06—Systems determining the position data of a target
- G01S15/46—Indirect determination of position data
- G01S2015/465—Indirect determination of position data by Trilateration, i.e. two transducers determine separately the distance to a target, whereby with the knowledge of the baseline length, i.e. the distance between the transducers, the position data of the target is determined
-
- 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
- G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
- G01S15/88—Sonar systems specially adapted for specific applications
- G01S15/93—Sonar systems specially adapted for specific applications for anti-collision purposes
- G01S15/931—Sonar systems specially adapted for specific applications for anti-collision purposes of land vehicles
- G01S2015/932—Sonar systems specially adapted for specific applications for anti-collision purposes of land vehicles for parking operations
-
- 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
- G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
- G01S15/88—Sonar systems specially adapted for specific applications
- G01S15/93—Sonar systems specially adapted for specific applications for anti-collision purposes
- G01S15/931—Sonar systems specially adapted for specific applications for anti-collision purposes of land vehicles
- G01S2015/937—Sonar systems specially adapted for specific applications for anti-collision purposes of land vehicles sensor installation details
- G01S2015/938—Sonar systems specially adapted for specific applications for anti-collision purposes of land vehicles sensor installation details in the bumper area
Definitions
- the invention relates to a method and a device for classifying an object, in particular in the vicinity of a motor vehicle, by means of an ultrasonic sensor system, the ultrasonic sensor system having a plurality of spatially distributed ultrasonic sensors.
- a device for detecting a dynamic object in the vicinity of a motor vehicle by means of ultrasound which comprises a sensor array with at least two sensor elements which are arranged at a predetermined distance from one another and which act as both a transmitter and a receiver.
- a detected moving object is classified based on its trajectory and speed by comparison with given models, e.g. as a pedestrian.
- a vehicle control device which comprises an ultrasonic sensor designed to detect an obstacle in front of the vehicle and a monocular camera designed to record an image of an area in front of the vehicle.
- a control device determines the presence or absence of an obstacle in front of the vehicle based on images captured by the monocular camera while the vehicle is traveling, and controls the driving force of the vehicle according to a combination of detecting or not detecting an object by the ultrasonic sensor and presence or Absence of an obstacle that is determined based on the image taken with the monocular camera.
- DE 102016124157 A1 shows a method for determining a need for braking for a motor vehicle as a function of a possible collision object, for example a pedestrian, in an area surrounding the motor vehicle.
- the object of the invention can be seen in realizing the most reliable possible pedestrian detection in the vicinity of a motor vehicle based on an ultrasonic sensor system.
- a method for classifying an object, in particular in the vicinity of a motor vehicle, by means of an ultrasonic sensor system, the ultrasonic sensor system having a plurality of spatially distributed ultrasonic sensors.
- the ultrasonic sensor system can, for example, be part of a driving or parking assistance system provided on a motor vehicle.
- the ultrasonic sensors can be arranged, for example, in a distributed manner on a front and / or rear bumper of the motor vehicle.
- Each of the ultrasonic sensors can be designed to transmit ultrasonic signals and to receive ultrasonic signals reflected on an object.
- the distance to the object can be determined in a known manner by means of the transit time of a received ultrasonic signal reflected on an object.
- Extended and structured objects can generate so-called multiple echoes.
- the emitted ultrasonic signal is reflected at different points on the object and it For example, several echo signals with different transit times can be received by an ultrasonic sensor from a transmitted ultrasonic signal.
- the procedure consists of the following steps:
- a plurality of measurements are carried out, in particular continuously, with an ultrasonic signal being transmitted by one of the ultrasonic sensors in each case during a measurement, a signal being received by at least one of the ultrasonic sensors which has a plurality of reflected echo signals, so-called multiple echoes, and the received echo signals Echo signals are assigned to an object.
- a number of features can be determined from the echo signals received:
- a third feature which represents a distribution of the number of received echo signals per measurement via the ultrasonic sensors
- a fourth feature which represents the alignment of the ultrasonic sensors with respect to the object
- a fifth feature which represents a variance of first object distances over a number of measurements, an associated first object distance being calculated for each specific first time echo signal received, with an approach of the object in particular being taken into account when determining the variance;
- a sixth feature which represents a correlation of a received echo signal with the transmitted ultrasonic signal;
- a seventh feature representing an amplitude of an echo signal
- an eighth feature which represents a distribution of reflex points, each reflex point indicating a measured object position.
- the object is classified as a function of a combination of at least two of these features, in particular as a pedestrian.
- a combination is understood here to mean that features are evaluated to determine whether, for example, certain threshold values are exceeded or undershot, or certain distributions or variances of distributions of the features are observed in a plurality of, for example, successive measurements. Each characteristic under consideration can then provide a specific contribution to the determination of the classification, for example by indicating a probability that the object is a pedestrian.
- the features can be used as input signals of a so-called classifier (e.g. a neural network, a decision tree, etc.) trained via a database for machine learning.
- a so-called classifier e.g. a neural network, a decision tree, etc.
- the first and the third feature can be combined to reliably classify the object as a pedestrian as follows: If the frequency according to the first feature with which a distance d between the The first recorded echo signal and the last recorded echo signal of a multiple echo exceeds a predetermined distance threshold value, i.e. it exceeds a frequency threshold value and the distribution according to the third feature shows that only certain of the ultrasonic sensors, in particular only one of the ultrasonic sensors or only a few, in particular adjacent arranged ultrasonic sensors have received a plurality of echo signals per measurement, the object is classified as a pedestrian.
- the invention is based on the knowledge that a pedestrian as a structured object reflects ultrasound at different points, e.g. on the foot, torso, head and / or arms. Due to this peculiarity, a single ultrasonic measurement usually gives several echo signals (reflections, multiple echoes) that lie behind one another in time or at a distance. It is characteristic that the distance d between the temporally first received signal and the temporally last received signal is often relatively large, in particular greater than in the case of low objects such as curbs. This can be due, for example, to the fact that different body parts reflect the transmitted ultrasonic signal which, as seen from the ultrasonic sensor, are at a great distance from one another. As a result of the movement of the pedestrian, this relative distance d can also fluctuate greatly, especially if a sequence of successive measurements is considered. This effect is also due to the fact that the same points on the pedestrian do not reflect the transmitted ultrasonic signal for each measurement.
- the first characteristic used to classify the reflecting object is how often multiple echoes are measured in relation to the total number of measurements assigned to the object and how often the distance d is large, i.e. greater than a certain threshold value (first characteristic) .
- an increased occurrence of the typical multiple echoes can be detected in pedestrians, especially with only one of the ultrasonic sensors or with two adjacent ultrasonic sensors, whereas such a distribution cannot be observed, for example, with a curb as a reflective object.
- a distribution of the number of received echo signals per measurement via the ultrasonic sensors is thus recorded as a third feature. It is thus detected which of the ultrasonic sensors receive a plurality of echo signals per measurement and which do not.
- a reflective object is preferably classified as a pedestrian if the distribution according to the third feature shows that only certain of the ultrasonic sensors, in particular only one of the ultrasonic sensors or only a few, in particular adjacent ultrasonic sensors, have received a plurality of echo signals per measurement that are related to the contributed to the object to be classified.
- the other ultrasonic sensors can also detect echo signals, but not echo signals that are assigned to the object to be classified due to their position in space, which can be determined for example by trilateration.
- the alignment of the ultrasonic sensors with respect to the object can be determined. It can thus also be taken into account that the multiple echo signals are often very weak and can only be recognized at all by sensor systems that are set to be very sensitive. The reception of these ultrasonic signals (multiple echoes) can therefore be between the various ultrasonic sensors vary greatly.
- the statistics ie in particular to determine the distance d, to determine the frequency with which the distance d exceeds a certain threshold value according to the first feature and / or to determine the variance of d according to the second feature in particular to evaluate only the measurement data of those ultrasonic sensors that are aligned with the object, that is, have a good viewing angle or, preferably, to use only that ultrasonic sensor that has the best viewing angle to the object in comparison.
- the angle of the main axis of each ultrasonic sensor relative to the detected object can be taken into account here.
- the object distance, which results from the first received reflected echo signal (first reflex) varies greatly, especially in comparison with a geometrically simple, stable reflector such as a curb.
- the variance of the object distance that results from the first received reflected echo signal (first reflex) can therefore be used as a further, fifth feature. In particular if this variance exceeds a second variance threshold value, the object can be classified as a pedestrian.
- the echo signals are acoustically superimposed. If an ultrasonic sensor sends out encoded ultrasonic signals, e.g. by using a characteristic frequency curve, and the receiving ultrasonic sensor evaluates the curve of the received echo signal in order to determine a correlation, then the superimposition of the echo signals leads to a disruptive influence on the correlation, i.e. the correlation drops from. In the case of, for example, a curb, on the other hand, very high correlations can be observed that can never occur with a pedestrian.
- the sixth feature is therefore the correlation of the received echo signal with the transmitted ultrasonic signal.
- a classification of the object as a pedestrian is preferably excluded if for one certain number of measurements the correlation value is greater than a certain correlation threshold value.
- an amplitude of at least one received echo signal can be evaluated. Since the clothing of a pedestrian usually strongly absorbs acoustic signals, the reflected sound energy of an ultrasonic signal reflected from a pedestrian is rather low to moderately pronounced. In this respect, the amplitude can in particular be evaluated in such a way that particularly high amplitudes reduce the probability of classification as a pedestrian. In particular, the classification of an object as a pedestrian can be excluded if the amplitude of at least one received ultrasonic signal is greater than a specific amplitude threshold value.
- a so-called reflex point can also be determined, which indicates a position in space from which the received ultrasonic signal was reflected.
- a reflex point can, for example, be determined in a known manner by trilateration.
- the reflex points received from one measurement to the next jump locally strongly, i.e. that the coordinates that are assigned to the pedestrian as an object in space during a measurement vary in a certain way. This results from the complex geometric structure of the pedestrian and from the fact that the pedestrian can move.
- the spatial distribution of the reflex points which represent a spatial assignment of several measurements via trilateration, in a sequence of measurements can thus be used as a further, eighth feature.
- the spatial distribution of the reflex points according to the eighth feature has a characteristic shape, in particular an accumulation of reflex points at a probable object position and scatter in the lateral direction, the object can be classified as a pedestrian.
- the features mentioned enable pedestrians and curbs or other objects that are not relevant to braking to be separated with a certain degree of probability. No single characteristic is unambiguous on its own enough to make a reliable statement possible without adding further features. Therefore, according to the invention, the features mentioned are combined with one another in particular logically or statistically.
- the features can also be used as input signals of a classifier trained via a database (neural network, decision tree, ...) for machine learning.
- the type of logical combination is not primarily decisive, rather it is the characteristics that are decisive for recognizing a pedestrian.
- a device designed for classifying an object, in particular in the vicinity of a motor vehicle comprising:
- ultrasonic sensor system • an ultrasonic sensor system, wherein the ultrasonic sensor system has a plurality of spatially distributed, in particular arranged on a body of a motor vehicle, ultrasonic sensors,
- An evaluation device which is designed to carry out the steps according to a method designed as described above.
- the evaluation device is designed to determine two or more of the features described above from the measurement data recorded by the ultrasonic sensors and to combine at least two of the features in order to determine a classification of an object in the vicinity of the device.
- the device can be part of a driver assistance system of a motor vehicle.
- the ultrasonic sensors are preferably on a bumper of the Arranged motor vehicle and aligned such that they can capture an area in the direction of travel in front of or behind the motor vehicle.
- the device can in particular be part of a brake assistance system, for example emergency braking can be triggered if an object is classified as a pedestrian and the object is detected, for example, in the direction of travel of the motor vehicle at a distance closer than a certain minimum distance.
- emergency braking can be triggered if an object is classified as a pedestrian and the object is detected, for example, in the direction of travel of the motor vehicle at a distance closer than a certain minimum distance.
- a motor vehicle which has a device according to the invention.
- Figure 1 shows a device according to a possible embodiment of the invention when detecting a pedestrian.
- FIG. 2 shows, by way of example, according to the invention, distance data acquired during a plurality of measurements following one another in time.
- FIG. 3 shows by way of example according to the invention, distance data acquired during several consecutive measurements taking into account multiple echoes, a distance d corresponding to a distance between a first received echo signal and a last received echo signal of a measurement being determined for each measurement.
- FIG. 4 shows schematically a motor vehicle designed according to the invention and a pedestrian, as well as, superimposed, a distribution of reflex points from a plurality of measurements.
- FIG 1 the front part of a motor vehicle 1 is shown schematically.
- the motor vehicle 1 comprises a device 10 for classifying an object 70 in the vicinity of the motor vehicle 1.
- the device 10 comprises an ultrasonic sensor system, the ultrasonic sensor system having four ultrasonic sensors 12.1, 12.2, 12.3 and 12.4 arranged along the front of the motor vehicle 1.
- the device 10 also includes an evaluation device 11 which is designed to evaluate the measurement data from the ultrasonic sensors 12.1-12.4 and to classify the object 70 based thereon.
- the evaluation device is designed to control each of the ultrasonic sensors 12.1-12.4, so that the ultrasonic sensors 12.1-12.4 send ultrasonic signals and receive ultrasonic signals reflected on the object 70 and assign the received signals to the object 70.
- the object 70 is a pedestrian 80.
- the probability is high that at least one of the ultrasonic sensors 12.1-12.4 will receive a signal which has a plurality of reflected echo signals.
- a hand 82 and a foot 84 of the pedestrian 80 reflect the transmitted ultrasonic signal of the ultrasonic sensor 12.3.
- the foot 84 can have a smaller distance 24 from the ultrasonic sensor 12.3 than the distance 22 from the hand 82.
- the ultrasonic sensor 12.3 will therefore receive at least two echo signals during a measurement.
- the echo signal that was reflected from the foot 84 is received as the first echo signal in time and the echo signal that was reflected from the hand 82 is received as the last echo signal in time.
- a distance d between the first received echo signal and the last received echo signal in time can be determined from the echo signals. For this purpose, for example, a transit time difference between these echo signals is first determined, which can be calculated in a known manner with knowledge of the speed of sound of the ultrasonic signals, a spatial distance d.
- a plurality of measurements can now be used to observe how the respectively determined distance d behaves. If, for example, a distance d is determined for a certain minimum portion of the measurements which exceeds a certain threshold value, then this fact can serve as an indicator that the object 70 is a pedestrian. Movement, for example of the arms and legs, and / or different orientations of a pedestrian 80 relative to the ultrasonic sensors also cause strong fluctuations in the distance d. If a variance of the distance d is considered, then, for example, if the variance exceeds a certain threshold value, it can be used as a further indicator that the object 70 is a pedestrian.
- the first received echo signal 210 and the last received echo signal 220 and the distance d determined therefrom are shown as an example in a diagram 200 for a plurality of measurements i.
- the measurement time t is plotted on the x-axis and the measured distance s from the ultrasonic sensor is plotted on the y-axis.
- a comparison can be made for each measurement as to whether the distance d exceeds a predefined distance threshold value, and a frequency based on the number of measurements carried out with which the distance d exceeds the predefined distance threshold value can thus be determined.
- Another feature is the number of echo signals received per measurement using the ultrasonic sensors.
- the two middle ultrasonic sensors 12.2 and 12.3 receive stronger echo signals than the two outer ultrasonic sensors 12.1 and 12.4 due to their proximity and alignment with respect to the pedestrian 80.
- the reception of multiple echoes by the middle ultrasonic sensors 12.2 and 12.3 is correspondingly more likely.
- the distribution of the number of received echo signals per measurement will therefore have an accumulation in the case of the ultrasonic sensors 12.2 and 12.3 arranged adjacent to one another.
- a distance between the pedestrian 80 and the ultrasonic sensor determined from a respective first received echo signal can vary greatly, in particular in comparison with a geometrically simple, stable reflector such as a curb.
- FIG. 2 a measurement diagram 100.
- the measurement time t is plotted on the x-axis and the measured distance s from the ultrasonic sensor is plotted on the y-axis.
- a distance 90 between the reflecting object 70 and the measuring ultrasonic sensor is determined by means of the first received echo signal.
- a relative, linear approach between the measuring ultrasonic sensor and the reflective object 70 is visible, as is shown by the straight line 95.
- the straight line 95 can be calculated. If the state of motion of the object 70 is not known, the straight line 95 can be determined from the measured values 90 (for example using customary fit methods). To determine the fifth feature, a variance of the measured values 90 representing the respective object distance is determined over several measurements with respect to the straight line 95, whereby an approach of the object 70 to the vehicle 1 or the measuring ultrasonic sensor is taken into account. If the variance determined in this way according to the fifth feature exceeds a second variance threshold value, this can be assessed as a further indication that the reflective object 70 is a pedestrian 80.
- FIG. 4 shows schematically, using a possible example, how the eighth feature according to the invention can be determined, which represents a distribution of reflex points 60. In FIG.
- the front of a vehicle 1 is shown schematically, which has an ultrasonic sensor system 12 with four ultrasonic sensors 12.1, 12.2, 12.3 and 12.4.
- An object 70 is located in front of the vehicle 1.
- Coordinates of reflex points 60 are determined by a large number of measurements using the ultrasonic sensors, for example by means of trilateration.
- a spatial distribution of the reflex points is formed, as indicated in FIG. 4 by the coordinate system. It has been found that a pedestrian 80 has a characteristic distribution of reflex points 60 which, on the one hand, has an accumulation at a probable object position, as well as a certain scatter of the reflex points 60 in the lateral direction, i.e. in a direction perpendicular to the main measuring direction.
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Measurement Of Velocity Or Position Using Acoustic Or Ultrasonic Waves (AREA)
- Traffic Control Systems (AREA)
Abstract
Description
Claims
Priority Applications (5)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
MX2022003941A MX2022003941A (es) | 2019-10-08 | 2020-08-11 | Metodo y dispositivo para clasificar un objeto, en particular en el entorno de un vehiculo de motor. |
KR1020227014935A KR20220070320A (ko) | 2019-10-08 | 2020-08-11 | 특히 자동차 주변에 있는 물체를 분류하기 위한 방법 및 장치 |
CN202080071027.3A CN114556146A (zh) | 2019-10-08 | 2020-08-11 | 用于将尤其是在机动车环境中的对象分类的方法和设备 |
US17/764,672 US20220342061A1 (en) | 2019-10-08 | 2020-08-11 | Method and a device for classifying an object, in particular in the surroundings of a motor vehicle |
JP2022521080A JP7385026B2 (ja) | 2019-10-08 | 2020-08-11 | 特に自動車周辺における、物体を分類するための方法及び装置 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE102019215393.3 | 2019-10-08 | ||
DE102019215393.3A DE102019215393A1 (de) | 2019-10-08 | 2019-10-08 | Verfahren und eine Vorrichtung zur Klassifizierung eines Objektes, insbesondere im Umfeld eines Kraftfahrzeugs |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2021069130A1 true WO2021069130A1 (de) | 2021-04-15 |
Family
ID=72050881
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/EP2020/072518 WO2021069130A1 (de) | 2019-10-08 | 2020-08-11 | Verfahren und eine vorrichtung zur klassifizierung eines objektes, insbesondere im umfeld eines kraftfahrzeugs |
Country Status (7)
Country | Link |
---|---|
US (1) | US20220342061A1 (de) |
JP (1) | JP7385026B2 (de) |
KR (1) | KR20220070320A (de) |
CN (1) | CN114556146A (de) |
DE (1) | DE102019215393A1 (de) |
MX (1) | MX2022003941A (de) |
WO (1) | WO2021069130A1 (de) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102021212067A1 (de) * | 2021-10-26 | 2023-04-27 | Robert Bosch Gesellschaft mit beschränkter Haftung | Verfahren zur Klassifizierung von wenigstens einem Objekt in einer Umgebung eines Fahrzeugs mittels eines Ultraschallsensorsystem sowie Steuereinrichtung, Ultraschallsensorsystem und Fahrzeug |
DE102022202524B4 (de) * | 2022-03-15 | 2024-04-18 | Continental Autonomous Mobility Germany GmbH | Verfahren zur Objektklassifizierung |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102005021225A1 (de) * | 2005-05-09 | 2006-11-16 | Robert Bosch Gmbh | Verfahren und Vorrichtung zur Erkennung der Oberflächenbeschaffenheit von Objekten des Straßenverkehrs oder Personen |
EP2908153A2 (de) | 2014-02-14 | 2015-08-19 | Volkswagen Aktiengesellschaft | Erkennung dynamischer Objekte mittels Ultraschall |
DE112016003462T5 (de) | 2015-08-25 | 2018-05-03 | Mazda Motor Corporation | Fahrzeugsteuervorrichtung |
DE102016124157A1 (de) | 2016-12-13 | 2018-06-14 | Valeo Schalter Und Sensoren Gmbh | Ermitteln einer Bremsnotwendigkeit zum Vermeiden einer Kollision eines Kraftfahrzeugs mit einem Fußgänger |
WO2018210966A1 (de) * | 2017-05-16 | 2018-11-22 | Elmos Semiconductor Aktiengesellschaft | Verfahren zur übertragung von daten über einen fahrzeugdatenbus von einem ultraschallsystem zu einer datenverarbeitungsvorrichtung |
Family Cites Families (28)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6178141B1 (en) * | 1996-11-20 | 2001-01-23 | Gte Internetworking Incorporated | Acoustic counter-sniper system |
US6268803B1 (en) * | 1998-08-06 | 2001-07-31 | Altra Technologies Incorporated | System and method of avoiding collisions |
DE19856974C1 (de) * | 1998-12-10 | 2000-09-07 | Bosch Gmbh Robert | Verfahren und Vorrichtung zur Erfassung eines Hindernisses |
US6615138B1 (en) * | 2002-05-30 | 2003-09-02 | Delphi Technologies, Inc. | Collision detection system and method of estimating miss distance employing curve fitting |
US6943727B2 (en) * | 2002-10-29 | 2005-09-13 | Volkswagen Ag | Length measurement with radar |
DE10323144A1 (de) * | 2003-05-22 | 2004-12-09 | Robert Bosch Gmbh | Verfahren und Vorrichtung zur Detektion von Objekten in der Umgebung eines Fahrzeugs |
DE10344299B4 (de) * | 2003-09-23 | 2016-08-04 | Volkswagen Ag | Klassifizierung der in einer Umgebung eines Kraftfahrzeugs befindlichen Objekte |
DE102007042220A1 (de) * | 2007-09-05 | 2009-03-12 | Robert Bosch Gmbh | Objektklassifizierungsverfahren, Einparkhilfeverfahren und Einparkhilfesystem |
DE102007061235A1 (de) * | 2007-12-19 | 2009-06-25 | Robert Bosch Gmbh | Verfahren zur Klassifizierung von Abstandsdaten und korrespondierende Abstandsmessvorrichtung |
US8428305B2 (en) * | 2008-04-24 | 2013-04-23 | GM Global Technology Operations LLC | Method for detecting a clear path through topographical variation analysis |
US8384531B2 (en) * | 2009-04-02 | 2013-02-26 | GM Global Technology Operations LLC | Recommended following distance on full-windshield head-up display |
DE102009046158A1 (de) * | 2009-10-29 | 2011-05-05 | Robert Bosch Gmbh | Verfahren zur Erkennung von Objekten mit geringer Höhe |
ES2532142T3 (es) * | 2010-08-25 | 2015-03-24 | Frankfurt University Of Applied Sciences | Dispositivo y procedimiento para el reconocimiento de personas |
JP5500121B2 (ja) * | 2011-04-25 | 2014-05-21 | 株式会社デンソー | 歩行者検出装置、歩行者検出方法およびプログラム |
JP5630377B2 (ja) * | 2011-05-25 | 2014-11-26 | 株式会社デンソー | 物体識別装置、および物体識別プログラム |
DE102012212894A1 (de) * | 2012-07-24 | 2014-01-30 | Robert Bosch Gmbh | Verfahren zum Betrieb eines Umfelderfassungssystems eines Fahrzeugs mit zumindest zwei Sende-/Empfangseinheiten und Umfelderfassungssystem |
DE102014114999A1 (de) * | 2014-10-15 | 2016-04-21 | Valeo Schalter Und Sensoren Gmbh | Verfahren zum Erfassen zumindest eines Objekts in einem Umgebungsbereich eines Kraftfahrzeugs, Fahrerassistenzsystem sowie Kraftfahrzeug |
JP6392152B2 (ja) * | 2015-03-24 | 2018-09-19 | パナソニック株式会社 | レーダ装置および走行車両検知方法 |
JP6777403B2 (ja) * | 2016-02-26 | 2020-10-28 | 株式会社デンソー | 物体認識装置及びプログラム |
DE102016113736A1 (de) * | 2016-07-26 | 2018-02-01 | Valeo Schalter Und Sensoren Gmbh | Verfahren zum Erfassen eines Objekts in einer Umgebung eines Fahrzeugs mit Höhenbestimmung, Fahrerassistenzsystem sowie Fahrzeug |
US20210197834A1 (en) * | 2016-11-21 | 2021-07-01 | George Shaker | System and method for sensing with millimeter waves for sleep position detection, vital signs monitoring and/or driver detection |
DE102017201219A1 (de) * | 2017-01-26 | 2018-07-26 | Robert Bosch Gmbh | Verfahren und System zum Erkennen von Objekten anhand von Ultraschallsignalen |
US20190197497A1 (en) * | 2017-12-22 | 2019-06-27 | Lyft, Inc. | Responses to detected impairments |
DE102018103551B4 (de) * | 2018-02-16 | 2022-09-22 | Valeo Schalter Und Sensoren Gmbh | Verfahren zum Charakterisieren eines Objekts in einem Umgebungsbereich eines Kraftfahrzeugs anhand von zuvor gelernten Kurvenparametern, Sensorvorrichtung sowie Fahrerassistenzsystem |
DE102019207688A1 (de) * | 2019-05-26 | 2020-11-26 | Robert Bosch Gmbh | Verfahren und Fahrerassistenzsystem zur Klassifizierung von Objekten in der Umgebung eines Fahrzeugs |
US20210064030A1 (en) * | 2019-08-27 | 2021-03-04 | Yu-Sian Jiang | Driver assistance for a vehicle and method for operating the same |
US12039785B2 (en) * | 2019-10-23 | 2024-07-16 | Lyft, Inc. | Approaches for encoding environmental information |
US11816900B2 (en) * | 2019-10-23 | 2023-11-14 | Lyft, Inc. | Approaches for encoding environmental information |
-
2019
- 2019-10-08 DE DE102019215393.3A patent/DE102019215393A1/de active Pending
-
2020
- 2020-08-11 CN CN202080071027.3A patent/CN114556146A/zh active Pending
- 2020-08-11 MX MX2022003941A patent/MX2022003941A/es unknown
- 2020-08-11 JP JP2022521080A patent/JP7385026B2/ja active Active
- 2020-08-11 KR KR1020227014935A patent/KR20220070320A/ko unknown
- 2020-08-11 US US17/764,672 patent/US20220342061A1/en active Pending
- 2020-08-11 WO PCT/EP2020/072518 patent/WO2021069130A1/de active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102005021225A1 (de) * | 2005-05-09 | 2006-11-16 | Robert Bosch Gmbh | Verfahren und Vorrichtung zur Erkennung der Oberflächenbeschaffenheit von Objekten des Straßenverkehrs oder Personen |
EP2908153A2 (de) | 2014-02-14 | 2015-08-19 | Volkswagen Aktiengesellschaft | Erkennung dynamischer Objekte mittels Ultraschall |
DE112016003462T5 (de) | 2015-08-25 | 2018-05-03 | Mazda Motor Corporation | Fahrzeugsteuervorrichtung |
DE102016124157A1 (de) | 2016-12-13 | 2018-06-14 | Valeo Schalter Und Sensoren Gmbh | Ermitteln einer Bremsnotwendigkeit zum Vermeiden einer Kollision eines Kraftfahrzeugs mit einem Fußgänger |
WO2018210966A1 (de) * | 2017-05-16 | 2018-11-22 | Elmos Semiconductor Aktiengesellschaft | Verfahren zur übertragung von daten über einen fahrzeugdatenbus von einem ultraschallsystem zu einer datenverarbeitungsvorrichtung |
Also Published As
Publication number | Publication date |
---|---|
KR20220070320A (ko) | 2022-05-30 |
US20220342061A1 (en) | 2022-10-27 |
MX2022003941A (es) | 2022-04-25 |
JP2022552228A (ja) | 2022-12-15 |
DE102019215393A1 (de) | 2021-04-08 |
JP7385026B2 (ja) | 2023-11-21 |
CN114556146A (zh) | 2022-05-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
DE102004016025B4 (de) | Verfahren zur Klassifizierung eines Objektstandorts eines 3D-Objekts an einer Seite eines Transportfahrzeugs | |
DE102004016023B4 (de) | Verfahren zur Objektklassifizierung aus Daten eines seitwärts gerichteten Sensors | |
EP3485290B1 (de) | Verfahren und system zur abtastung eines objekts | |
DE102004016024B4 (de) | Ausfilterung eines stillstehenden Objekts für ein Seitenobjekterfassungssystem | |
EP1417509B1 (de) | Echosignalüberwachungsvorrichtung und -verfahren | |
DE102015220329B4 (de) | Objekterfassungsvorrichtung | |
DE112016001530T5 (de) | Fahrzeugsteuerungsvorrichtung und Fahrzeugsteuerungsverfahren | |
EP3250943B1 (de) | Verfahren zum erfassen eines objekts in einem umgebungsbereich eines kraftfahrzeugs durch überprüfen einer räumlichen abweichung von messpunkten, steuereinrichtung, fahrerassistenzsystem sowie kraftfahrzeug | |
DE10233163A1 (de) | Anordnung und Verfahren zur Vorhersage einer Kollision mit integriertem Radar und aktivem Transponder | |
DE102005026386A1 (de) | Verfahren und Vorrichtung zum Bestimmen von Freiflächen in der Umgebung eines Fahrzeugs | |
DE102014202752B4 (de) | Erkennung dynamischer Objekte mittels Ultraschall | |
EP2339374A2 (de) | Verfahren zur Objekterfassung und Wandleranordnung hierfür | |
WO2019038174A1 (de) | Vermeidung von totwinkelwarnungen durch gischt | |
WO2021069137A1 (de) | Verfahren und fahrerassistenzsystem zum klassifizieren von objekten in der umgebung eines fahrzeugs | |
WO2021069130A1 (de) | Verfahren und eine vorrichtung zur klassifizierung eines objektes, insbesondere im umfeld eines kraftfahrzeugs | |
EP2895880B1 (de) | Verfahren zur funktionsüberwachung von ultraschallsensoren | |
WO2020239351A1 (de) | Verfahren und fahrerassistenzsystem zur klassifizierung von objekten in der umgebung eines fahrzeugs | |
EP3602119B1 (de) | Verfahren zum erfassen eines objekts in einem umgebungsbereich eines kraftfahrzeugs mit klassifizierung des objekts, ultraschallsensorvorrichtung sowie kraftfahrzeug | |
EP3791205A1 (de) | Ultraschallsensorsystem und verfahren zum erkennen von objekten im umfeld eines fahrzeugs, sowie fahrzeug mit einem ultraschallsensorsystem | |
EP1762861B1 (de) | Verfahren und Vorrichtung zur Ermittlung der Geometrie und Position einer Parklücke | |
EP3252502A1 (de) | Verfahren zum erkennen einer neigung in einer fahrbahn eines kraftfahrzeugs, fahrerassistenzsystem sowie kraftfahrzeug | |
DE102021212901B4 (de) | Verfahren zur Charakterisierung eines Objekts in einer Umgebung eines Kraftfahrzeugs | |
WO2022033980A1 (de) | Verfahren zum erkennen von verkehrsteilnehmern in einer umgebung eines fahrzeugs anhand von messungen eines radarsensors durch identifizieren von stördetektionen sowie recheneinrichtung | |
DE102018117516B3 (de) | Erkennung und Eliminierung von Störsignalen durch kodierte Ultraschallemissionen an einem Ultraschallsensor | |
WO2023072477A1 (de) | Verfahren zur klassifizierung von wenigstens einem objekt in einer umgebung eines fahrzeugs mittels eines ultraschallsensorsystem sowie steuereinrichtung, ultraschallsensorsystem und fahrzeug |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 20754745 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2022521080 Country of ref document: JP Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 20227014935 Country of ref document: KR Kind code of ref document: A |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20754745 Country of ref document: EP Kind code of ref document: A1 |