# US 10,481,244 B2 · Method for classifying an object in an area surrounding a motor vehicle, driver assistance system and motor vehicle > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,481,244 B2 - Document ID: US10481244B2 - Status: Granted - Kind: B2 - Application number: 15/329,773 - Filed: 2015-07-27 - Published: 2017-09-07 - Granted: 2019-11-19 - Earliest claimed: 2014-07-29 - Assignees: Valeo Schalter und Sensoren GmbH - Applicants: VALEO Schalter und Sensoren GmbH - Inventors: Waqas Malik - Web page: https://patentgrep.com/patent/US10481244B2 ## CPC - G01S 7/412: {based on a comparison between measured values and known or stored values} - G01S 7/415: {Identification of targets based on measurements of movement associated with the target} - G01S 13/726: {Multiple target tracking} - G01S 13/931: of land vehicles - G01S 13/343: {using sawtooth modulation} - G01S 2013/93271: {in the front of the vehicles} - 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 ## Abstract The invention relates to a method for classifying an object (18) in a surrounding area (4) of a motor vehicle (1), having the steps of: a) transmission of radar signals (5) into the surrounding area (4) by at least one motor vehicle radar sensor (3) and reception of radar signals (6) reflected from the object (18), b) provision of the information obtained from the radar signals (5, 6) as radar data, c) production of a power spectrum (11) on the basis of at least one distance value (13) and/or speed value (14) and/or intensity value (12) that the radar data contain as information, d) comparison of at least one spectrum range (15) that the power spectrum (11) contains with an intensity threshold value and selection of the spectrum range (15) as a potential object (16) if the intensity (12) thereof is greater than the intensity threshold value, e) performance of a further cycle with steps a) to d), f) identification of the potential object (16) as an actual object (18) on the basis of whether the potential object (16) has been selected both in a first cycle according to steps a) to d) and at least in the second cycle according to step e), g) comparison of at least one feature (Vabs, Aabs, σ2V, σ2A, y, RC) of the identified object (18) with reference features (Vabs, Aabs, σ2V, σ2A, y, RC) of a reference object, h) assignment of the object (18) to a particular class (23, 24, 25) from multiple different classes (23, 24, 25) on the basis of the comparison according to step g). ## Claims ### Claim 1 A method for classifying an object in a surrounding area of a motor vehicle, the method comprising: a) transmission of radar signals into the surrounding area by at least one motor vehicle radar sensor and reception of radar signals reflected from the object; b) provision of the information obtained from the radar signals as radar data; c) production of a power spectrum on the basis of at least one distance value and/or speed value and/or intensity value that the radar data contain as information; d) comparison of at least one spectrum range that the power spectrum contains with an intensity threshold value and selection of the spectrum range as a potential object when the intensity thereof is greater than the intensity threshold value; e) performance of a further cycle with steps a) to d); f) identification of the potential object as an actual object on the basis of whether the potential object has been selected both in a first cycle according to steps a) to d) and at least in the second cycle according to step e); g) comparison of at least one feature of the identified object with reference features of a reference object; and h) assignment of the object to a class from multiple different classes on the basis of the comparison according to step g), wherein the at least one feature is an intensity range of the object from the power spectrum, wherein the intensity range of the object comprises multiple spectrum ranges, and wherein the intensity range of the object is taken into consideration on the basis of a rectangular detail from the power spectrum. ### Claim 2 (depends on 1) The method according to claim 1, further comprising in the first cycle, after selection of the potential object, determination of at least one parameter value characterizing the spectrum range; and in the second cycle, after selection of the potential object, determination of the at least one parameter value characterizing the spectrum range is performed and the identification of the potential object as an actual object according to step f) is effected on the basis of whether the parameter values have occurred in both cycles at least within a deviation interval defining a value range of the parameter values. ### Claim 3 (depends on 2) The method according to claim 2, wherein the parameter value taken into consideration is a distance value from the radar sensor to the object and/or a relative speed between the radar sensor and the object and/or an angle of azimuth from the radar sensor to the object. ### Claim 4 (depends on 1) The method according to claim 1, wherein the at least one feature taken into consideration further comprises one selected from the group consisting of: an absolute speed of the object, an absolute acceleration of the object, a variance in the speed of the object, a variance in the acceleration of the object, and an intensity of the object cumulated over the cycles. ### Claim 5 (depends on 4) The method according to claim 4, wherein the computation of the absolute speed of the object and of the absolute acceleration of the object is carried out on the basis of a speed of the motor vehicle and an acceleration of the motor vehicle, respectively. ### Claim 6 (depends on 4) The method according to claim 4, wherein an average filter that averages the intensity over the cycles is taken into consideration for the intensity of the object cumulated over the cycles. ### Claim 7 (depends on 6) The method according to claim 6, wherein the assignment to a class is performed on the basis of the intensity of the object cumulated over the cycles with at least one linear division of a feature space of the intensity cumulated over the cycles. ### Claim 8 (depends on 1) The method according to claim 1, wherein the different classes characterize different road users. ### Claim 9 (depends on 8) The method according to claim 8, wherein a road user taken into consideration is one selected from the group consisting of: a motor cycle, a car, a heavy goods vehicle, a pedestrian, and a bicycle. ### Claim 10 (depends on 1) The method according to claim 1, wherein step g) is taken as a basis for taking into consideration a confidence value that describes a reliability of the comparison. ### Claim 11 (depends on 1) The method according to claim 1, characterized in that the at least one feature is weighted. ### Claim 12 (depends on 1) The method according to claim 1, characterized in that step f) is performed using a prediction algorithm, particularly a Kalman filter. ### Claim 13 (depends on 1) A driver assistance system having at least one radar sensor for providing radar data from a surrounding area of a motor vehicle configured to perform a method according to claim 1. ### Claim 14 (depends on 13) A motor vehicle having a driver assistance system according to claim 13.