Method for determining a confidence value of an object of a class
AssigneeRobert Bosch GmbH
InventorsStephanie Abrecht, Oliver Willers
Life of this patent
Estimating the term…
Abstract
A method is described for determining a confidence value for an object of a class determined by a neural network in an input image. The method includes: preparing an activation signature with the aid of a multiplicity of output images of a layer of the neural network for the class of the object, with the input image being provided to the input of the neural network; scaling the activation signature to the size of the input image; comparing an overlapping area portion of an area of the activation signature with an area of an object frame in relation to the area of the activation signature in order to determine the confidence value.
Claims11
A method for determining a confidence value for an object of a class determined by a neural network in an input image, the method comprising the following steps:
- preparing an activation signature using a multiplicity of output images of a layer of the neural network for the class of the object, with the input image being provided to an input of the neural network;
- scaling the activation signature to a size of the input image;
- and
- comparing an overlapping area portion of an area of the activation signature with an area of an object frame in relation to the area of the activation signature to determine the confidence value.
A device configured to determine a confidence value for an object of a class determined by a neural network in an input image, the device comprising:
- a processor, wherein the processor is programmed to:
- prepare an activation signature using a multiplicity of output images of a layer of the neural network for the class of the object, with the input image being provided to an input of the neural network;
- scale the activation signature to a size of the input image;
- and
- compare an overlapping area portion of an area of the activation signature with an area of an object frame in relation to the area of the activation signature to determine the confidence value.
A non-transitory machine-readable memory medium on which is stored a computer program for determining a confidence value for an object of a class determined by a neural network in an input image, the computer program, when executed by a computer, causing the computer to perform the following steps:
- preparing an activation signature using a multiplicity of output images of a layer of the neural network for the class of the object, with the input image being provided to an input of the neural network;
- scaling the activation signature to a size of the input image;
- and
- comparing an overlapping area portion of an area of the activation signature with an area of an object frame in relation to the area of the activation signature to determine the confidence value.
Dependencies are inferred from the claim text.