US 2022/0189178 A1Published application

Signal-to-noise ratio (snr) identification within a scene

AssigneeMobileye Vision Technologies Ltd.

InventorGabriel Bowers

Life of this patent

Estimating the term…

Loading patent…

Abstract

Techniques are disclosed for generating a two-dimensional (2D) map of signal-to-noise ratio (SNR) values for sensor-acquired images. The techniques leverage the use of lookup tables (LUTs) to generate a transformation LUT that functions to map pixel values to SNR values. The transformation LUT may be generated by first generating an intermediate LUT that uses the operating parameters identified with the sensor to map pixel values to light level values. The light level values are then used together with an SNR model that outputs a prediction of electrons identified with a signal portion and a noise portion of images acquired by the sensor to thus map the pixel values to SNR values. The 2D map may be used to improve upon the accuracy of the classification of objects and/or scene characteristics for various applications.

Claims24

Dependent claims

A computing device, comprising:

a memory configured to store computer-readable instructions;
and
processing circuitry configured to execute the computer-readable instructions to cause the computing device to:
receive a first set of pixel values identified with a first image acquired by a sensor, each one of the first set of pixel values corresponding to a respective pixel of the first image,
generate a first LUT based upon one or more operating parameters identified with the sensor such that entries of the first LUT represent light levels mapped to respective pixel values;
generate a second LUT based upon (i) a signal-to-noise ratio (SNR) model associated with the sensor, and (ii) the light levels mapped to the respective pixel values, such that entries of the second LUT represent SNR levels mapped to respective pixel values;
transform a second set of pixel values, each one of the second set of pixel values corresponding to a respective pixel of a second image acquired by the sensor, to a two-dimensional (2D) SNR map associated with the second image by mapping the second set of pixel values to entries in the second LUT;
and
classify, using the 2D SNR map, an object or a characteristic of a scene identified by the second image.

6 more elements

A computer-readable medium having instructions stored thereon that, when executed by processing circuitry of a vehicle, cause the vehicle to:

receive a first set of pixel values identified with a first image acquired by a sensor, each one of the first set of pixel values corresponding to a respective pixel of the first image,
generate a first LUT based upon one or more operating parameters identified with the sensor such that entries of the first LUT represent light levels mapped to respective pixel values;
generate a second LUT based upon (i) a signal-to-noise ratio (SNR) model associated with the sensor, and (ii) the light levels mapped to the respective pixel values, such that entries of the second LUT represent SNR levels mapped to respective pixel values;
transform a second set of pixel values, each one of the second set of pixel values corresponding to a respective pixel of a second image acquired by the sensor, to a two-dimensional (2D) SNR map associated with the second image by mapping the second set of pixel values to entries in the second LUT;
and
classify, using the 2D SNR map, an object or a characteristic of a scene identified by the second image.

3 more elements

A vehicle, comprising:

a sensor configured to acquire images;
a data interface configured to receive a first set of pixel values identified with a first image acquired by the sensor, each one of the first set of pixel values corresponding to a respective pixel of the first image;
and
processing circuitry configured to:
generate a first LUT based upon one or more operating parameters identified with the sensor such that entries of the first LUT represent light levels mapped to respective pixel values;
generate a second LUT based upon (i) a signal-to-noise ratio (SNR) model associated with the sensor, and (ii) the light levels mapped to the respective pixel values, such that entries of the second LUT represent SNR levels mapped to respective pixel values;
transform a second set of pixel values, each one of the second set of pixel values corresponding to a respective pixel of a second image acquired by the sensor, to a two-dimensional (2D) SNR map associated with the second image by mapping the second set of pixel values to entries in the second LUT;
and
classify, using the 2D SNR map, an object or a characteristic of a scene identified by the second image.

6 more elements

Dependencies are inferred from the claim text.

Facts

Application: 17/550,042Filed 14 Dec 2021
Priority: 15 Dec 2020
Published: 16 Jun 2022
Term ends: Not estimatedThe source records don’t support an estimate.

Classification10 codes

G06V 20/56
Context or environment of the image: exterior to a vehicle by using sensors mounted on the vehicle
G06V 20/90
Scenes; Scene-specific elements: identifying an image sensor based on its output data
G06T 3/4053
Scaling of whole images or parts thereof, e.g. expanding or contracting: based on super-resolution, i.e. the output image resolution being higher…
G06T 7/194
Segmentation; Edge detection: involving foreground-background segmentation