System and method for evaluating the perception system of an autonomous vehicle
First Claim
1. An apparatus for optimizing object detection performed by an autonomous vehicle, the apparatus comprising:
- a memory operative to store;
a plurality of images captured by an autonomous vehicle using a plurality of object detection parameters;
a first plurality of object label parameters determined by the autonomous vehicle; and
a second plurality of object label parameters applied by a reviewer having reviewed the plurality of images captured by the autonomous vehicle, the first and second pluralities of object label parameters defining a shape bounding a detected object; and
a processor in communication with the memory, the processor operative to;
determine whether to optimize the plurality of object detection parameters based on a comparison of the first plurality of object label parameters with the second plurality of object label parameters; and
perform an operation on the plurality of object detection parameters based on the comparison of the first plurality of object label parameters with the second plurality of object label parameters, wherein the operation comprises;
identifying a plurality of object detection values, wherein each object detection value corresponds to at least one object detection parameter in the plurality of object detection parameters;
for each combination of the plurality of object detection values, performing an object detection routine on the plurality of images captured by the autonomous vehicle using the plurality of object detection values; and
selecting the combination of the plurality of object detection values that resulted in an optimal object detection routine.
3 Assignments
0 Petitions
Accused Products
Abstract
A method and apparatus are provided for optimizing one or more object detection parameters used by an autonomous vehicle to detect objects in images. The autonomous vehicle may capture the images using one or more sensors. The autonomous vehicle may then determine object labels and their corresponding object label parameters for the detected objects. The captured images and the object label parameters may be communicated to an object identification server. The object identification server may request that one or more reviewers identify objects in the captured images. The object identification server may then compare the identification of objects by reviewers with the identification of objects by the autonomous vehicle. Depending on the results of the comparison, the object identification server may recommend or perform the optimization of one or more of the object detection parameters.
-
Citations
20 Claims
-
1. An apparatus for optimizing object detection performed by an autonomous vehicle, the apparatus comprising:
-
a memory operative to store; a plurality of images captured by an autonomous vehicle using a plurality of object detection parameters; a first plurality of object label parameters determined by the autonomous vehicle; and a second plurality of object label parameters applied by a reviewer having reviewed the plurality of images captured by the autonomous vehicle, the first and second pluralities of object label parameters defining a shape bounding a detected object; and a processor in communication with the memory, the processor operative to; determine whether to optimize the plurality of object detection parameters based on a comparison of the first plurality of object label parameters with the second plurality of object label parameters; and perform an operation on the plurality of object detection parameters based on the comparison of the first plurality of object label parameters with the second plurality of object label parameters, wherein the operation comprises; identifying a plurality of object detection values, wherein each object detection value corresponds to at least one object detection parameter in the plurality of object detection parameters; for each combination of the plurality of object detection values, performing an object detection routine on the plurality of images captured by the autonomous vehicle using the plurality of object detection values; and selecting the combination of the plurality of object detection values that resulted in an optimal object detection routine. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. An method for optimizing object detection performed by an autonomous vehicle, the method comprising:
-
storing, in a memory, a plurality of images captured by an autonomous vehicle using a plurality of object detection parameters, receiving, by one or more computing devices having one or more processors, a first plurality of object label parameters determined by the autonomous vehicle and a second plurality of object label parameters applied by a reviewer having reviewed the plurality of images captured by the autonomous vehicle, the first and second pluralities of object label parameters defining a shape bounding a detected object; determining, by the one or more computing devices, whether to optimize the plurality of object detection parameters based on a comparison of the first plurality of object label parameters with the second plurality of object label parameters; performing, by the one or more computing devices, an operation on the plurality of object detection parameters based on the comparison of the first plurality of object label parameters with the second plurality of object label parameters; identifying, by the one or more computing devices, a plurality of object detection values, wherein each object detection value corresponds to at least one object detection parameter in the plurality of object detection parameters; performing, by the one or more computing devices, an object detection routine on the plurality of images captured by the autonomous vehicle using the plurality of object detection values for each combination of the plurality of object detection values; and selecting, by the one or more computing devices, the combination of the plurality of object detection values that resulted in an optimal object detection routine. - View Dependent Claims (9, 10, 11, 12, 13, 14)
-
-
15. A non-transitory, tangible recording medium on which instructions are stored, the instructions, when executed by one or more processors of one or more computing devices, causes the one or more processor to perform a method for optimizing object detection performed by an autonomous vehicle, the method comprising:
-
storing a plurality of images captured by an autonomous vehicle using a plurality of object detection parameters, receiving a first plurality of object label parameters determined by the autonomous vehicle and a second plurality of object label parameters applied by a reviewer having reviewed the plurality of images captured by the autonomous vehicle; determining whether to optimize the plurality of object detection parameters based on a comparison of the first plurality of object label parameters with the second plurality of object label parameters; performing an operation on the plurality of object detection parameters based on the comparison of the first plurality of object label parameters with the second plurality of object label parameters, the first and second pluralities of object label parameters defining a shape bounding a detected object; identifying a plurality of object detection values, wherein each object detection value corresponds to at least one object detection parameter in the plurality of object detection parameters; performing an object detection routine on the plurality of images captured by the autonomous vehicle using the plurality of object detection values for each combination of the plurality of object detection values; and selecting the combination of the plurality of object detection values that resulted in an optimal object detection routine. - View Dependent Claims (16, 17, 18, 19, 20)
-
Specification