US 11,858,504 B2
Stereo-assist network for determining an object's location
Nadav Shaag, Jerusalem (IL); and Ofer Springer, Jerusalem (IL)
Assigned to Mobileye Vision Technologies Ltd., Jerusalem (IL)
Filed by MOBILEYE VISION TECHNOLOGIES LTD., Jerusalem (IL)
Filed on Oct. 27, 2022, as Appl. No. 17/974,789.
Claims priority of provisional application 63/272,862, filed on Oct. 28, 2021.
Prior Publication US 2023/0138686 A1, May 4, 2023
Int. Cl. G06V 20/58 (2022.01); B60W 30/095 (2012.01)
CPC B60W 30/095 (2013.01) [G06V 20/58 (2022.01); B60W 2420/42 (2013.01); B60W 2554/4029 (2020.02); B60W 2554/4041 (2020.02); B60W 2554/4049 (2020.02)] 26 Claims
OG exemplary drawing
 
1. A navigation system for a host vehicle, the navigation system comprising:
at least one processor comprising circuitry and having access to at least one memory, wherein the at least one memory includes instructions that when executed by the circuitry cause the at least one processor to:
receive a first image acquired by a first camera onboard the host vehicle, the first image having been acquired from an environment of the host vehicle;
receive a second image acquired by a second camera onboard the host vehicle, the second image having been acquired from the environment of the host vehicle;
identify a first representation of an object in the first image and a second representation of the object in the second image;
input to a first trained model at least a portion of the first image, where the at least a portion of the first image includes at least a portion of the first representation of the object, and wherein the first trained model is configured to determine a first signature encoding using at least the first representation of the object;
input to a second trained model at least a portion of the second image, wherein the at least a portion of the second image includes at least a portion of the second representation of the object, and wherein the second trained model is configured to determine a second signature encoding using at least the second representation of the object;
receive the first signature encoding determined by the first trained model;
receive the second signature encoding determined by the second trained model;
input to a third trained model the first signature encoding and the second signature encoding, wherein the third trained model is configured to determine a location of the object within the environment of the host vehicle based on at least the first signature encoding and the second signature encoding; and
receive an indicator of the location of the object determined by the third trained model.