Granted Patent B2

US 12,651,443 · App. 18/369,403 · Granted Jun 9, 2026

Inventors: Urs Zimmermann (Krefeld, DE); Dennis Müller (Moers, DE)

Assignee: Aptiv Technologies AG

G06V10/776G01S7/4802G01S17/42G01S17/58G01S17/931G06T7/246G06T7/73G06V10/764G06V10/98G06V20/70G06T2207/10028

Abstract

Claims (65)

1 . A computer implemented method for validating annotations of objects, the method comprising:

receiving a plurality of spatial datapoints acquired by a sensor, wherein the spatial datapoints are related to an external environment of the sensor,

receiving annotation data of objects associated with the acquired spatial datapoints, the annotation data including an identification of each respective object, and

validating, via a processing unit, the annotations of the objects by performing the steps of:

determining a target range for at least one property of the objects,

determining, from the acquired spatial datapoints and/or from the annotation data, a respective value of the at least one property for each respective object, and

for each object, identifying the object as an erroneous object if the respective value of the at least one property is outside the target range for the at least one property, the erroneous object being selected for review regarding erroneous annotation;

wherein:

the identification of each respective object includes a classification and a predefined geometrical shape, the predefined geometrical shape being associated with a subset of the acquired spatial datapoints for each respective object;

the target range is determined by performing the steps of:

selecting a portion of the spatial datapoints which include a respective subset of the spatial datapoints for each of a plurality of sample objects,

determining a respective value of the at least one property for each sample object based on the predefined geometrical shape and/or the respective subset of the spatial datapoints,

estimating at least one probability distribution for the property based on a statistical distribution for the values of the property for the sample objects,

deriving the target range for the at least one property of the respective objects from the at least one probability distribution;

a probability value is determined for the value of the at least one property based on at least one probability distribution,

the respective value of the at least one property is outside the target range if the probability value is smaller than a predetermined threshold;

a percentage share of a total number of objects is predefined for the review regarding erroneous annotation; and

one respective object having a lowest probability value is iteratively selected for the review until the number of selected objects is equal to the predefined percentage share of the total number of objects.

2 . The method according to claim 1 , wherein

the predefined geometrical shape is a cuboid.

3 . The method according to claim 1 , wherein

the classification of the respective object comprises that the respective object is associated with one of a plurality of object classes, and

estimating the at least one probability distribution for the at least one property comprises estimating a separate probability distribution for each of the plurality of object classes.

4 . The method according to claim 3 , wherein

each probability distribution is based on a Gaussian mixture model.

5 . The method according to claim 4 , wherein

the Gaussian mixture model includes a plurality of Gaussians distributions, and

for each Gaussian distribution:

a center is determined based on a median of the determined values of the at least one property for the respective object class, and

a standard deviation is determined based on a median of an absolute deviation for the determined values of the at least one property for the respective object class.

6 . The method according to claim 4 , wherein:

the Gaussian mixture model includes a plurality of Gaussians distributions; and

for each Gaussian distribution:

a center is determined based on a median of the determined values of the at least one property for the respective object class, and

a standard deviation is determined based on a median of an absolute deviation for the determined values of the at least one property for the respective object class.

7 . The method according to claim 1 , wherein

the at least one property is derived from a spatial distribution of the datapoints of the respective subset with respect to the predefined geometrical shape.

8 . The method according to claim 1 , wherein

the at least one property includes at least one statistical property of the datapoints of the respective subset.

9 . The method according to claim 1 , wherein

the at least one property of the objects includes parameters of a spatial location of the objects.

10 . The method according to claim 1 , wherein

the plurality of spatial datapoints is based on a sequence of Lidar scans for a predetermined time period, and

the at least one property includes a respective velocity of the objects with respect to the sensor, wherein the respective velocity is determined based on the sequence of Lidar scans.

11 . The method according to claim 1 , wherein

for each object being selected for the review regarding erroneous annotation, a potential annotation error is indicated.

12 . A computer system, configured to carry out the computer implemented method of claim 1 .

13 . A non-transitory computer readable medium comprising instructions for carrying out the computer implemented method of claim 1 .

14 . A computer implemented method for validating annotations of objects, the method comprising:

receiving a plurality of spatial datapoints acquired by a sensor, wherein the spatial datapoints are related to an external environment of the sensor,

receiving annotation data of objects associated with the acquired spatial datapoints, the annotation data including an identification of each respective object, and

validating, via a processing unit, the annotations of the objects by performing the steps of:

determining a target range for at least one property of the objects,

determining, from the acquired spatial datapoints and/or from the annotation data, a respective value of the at least one property for each respective object, and

for each object, identifying the object as an erroneous object if the respective value of the at least one property is outside the target range for the at least one property, the erroneous object being selected for review regarding erroneous annotation;

wherein:

the identification of each respective object includes a classification and a predefined geometrical shape, the predefined geometrical shape being associated with a subset of the acquired spatial datapoints for each respective object;

the target range is determined by performing the steps of:

selecting a portion of the spatial datapoints which include a respective subset of the spatial datapoints for each of a plurality of sample objects,

determining a respective value of the at least one property for each sample object based on the predefined geometrical shape and/or the respective subset of the spatial datapoints,

estimating at least one probability distribution for the property based on a statistical distribution for the values of the property for the sample objects, and

deriving the target range for the at least one property of the respective objects from the at least one probability distribution;

the classification of the respective object comprises that the respective object is associated with one of a plurality of object classes; and

estimating the at least one probability distribution for the at least one property comprises estimating a separate probability distribution for each of the plurality of object classes.

15 . The method according to claim 14 , wherein each probability distribution is based on a Gaussian mixture model.

Assignments (4)

Priority Claims (1)

Continuity (2)

References Cited (10)