公开(公告)号：US20240420356A1

公开(公告)日：2024-12-19

申请号：US18743696

申请日：2024-06-14

Applicant: Torc Robotics, Inc.

Inventor： Felix Heide ,  Fahim Mannan ,  Mario Bijelic

IPC: G06T7/593 ,  G01S17/89

Abstract: A perception system including at least one memory, and at least one processor configured to: (i) compute, in a stereo branch, disparity from a pair of stereo images including a left image and a right image; (ii) based on the computed disparity from the pair of stereo images, output, by the stereo branch, a depth for the left image and a depth for the right image; (iii) compute an absolute depth for the left image in a first monocular branch and an absolute depth for the right image in a second monocular branch; (iv) compute, in a first fusion branch, a depth map for the left image; (v) compute, in a second fusion branch, a depth map for the right image; and (vi) generate a single fused depth map based on the depth map for the left image and the depth map for the right image, is disclosed.

公开(公告)号：US20240331366A9

公开(公告)日：2024-10-03

申请号：US18526787

申请日：2023-12-01

Applicant: Torc Robotics, Inc.

Inventor： Emmanuel Luc Julien Onzon ,  Felix Heide ,  Maximilian Rufus Bömer ,  Fahim Mannan

IPC: G06V10/776 ,  G06T5/40 ,  G06T5/50 ,  G06T7/11 ,  G06V10/77 ,  G06V10/80 ,  G06V10/94 ,  G06V20/00

CPC classification number: G06V10/776 ,  G06T5/40 ,  G06T5/50 ,  G06T7/11 ,  G06V10/7715 ,  G06V10/806 ,  G06V10/955 ,  G06V20/38 ,  G06T2207/10144 ,  G06T2207/20161

Abstract: A computer-vision pipeline is organized as a closed loop of a sensor-processing phase, an image-processing phase, and an object-detection phase, each comprising a respective phase processor coupled to a master processor. The sensor-processing phase creates multiple exposure images, and derives multi-exposure multi-scale zonal illumination-distributions, to be processed independently in the image-processing phase. In a first implementation of the object-detection phase, extracted exposure-specific features are pooled prior to overall object detection. In a second implementation, exposure-specific objects, detected from the exposure-specific features, are fused to produce the sought objects of a scene under consideration. The two implementations enable detecting fine details of a scene under diverse illumination conditions. The master processor performs loss-function computations to derive updated training parameters of the processing phases. Several experiments applying a core method of operating the computer-vision pipelines, and variations thereof, ascertain performance gain under challenging illumination conditions.

公开(公告)号：US20240233351A1

公开(公告)日：2024-07-11

申请号：US18545874

申请日：2023-12-19

Applicant: Torc Robotics, Inc.

Inventor： Emmanuel Luc Julien Onzon ,  Felix Heide ,  Maximilian Rufus Bömer ,  Fahim Mannan

IPC: G06V10/80 ,  G06T5/70 ,  G06V10/60 ,  G06V10/82

CPC classification number: G06V10/806 ,  G06T5/70 ,  G06V10/60 ,  G06V10/82

Abstract: Departing from conventional HIDR image fusion approach, a learned task-driven fusion in the feature domain is disclosed. Instead of using a single companded image, the disclosed method exploits semantic features from all exposures learned in an end-to-end fashion with supervision from downstream detection losses. The method outperforms all tested conventional HDR exposure fusion and auto-exposure methods in challenging automotive HIDR scenarios.

公开(公告)号：US20240127584A1

公开(公告)日：2024-04-18

申请号：US18526787

申请日：2023-12-01

Applicant: Torc Robotics, Inc.

Inventor： Emmanuel Luc Julien Onzon ,  Felix Heide ,  Maximilian Rufus Bömer ,  Fahim Mannan

IPC: G06V10/776 ,  G06T5/40 ,  G06T5/50 ,  G06T7/11 ,  G06V10/77 ,  G06V10/80 ,  G06V10/94 ,  G06V20/00

CPC classification number: G06V10/776 ,  G06T5/40 ,  G06T5/50 ,  G06T7/11 ,  G06V10/7715 ,  G06V10/806 ,  G06V10/955 ,  G06V20/38 ,  G06T2207/10144 ,  G06T2207/20161

Abstract: A computer-vision pipeline is organized as a closed loop of a sensor-processing phase, an image-processing phase, and an object-detection phase, each comprising a respective phase processor coupled to a master processor. The sensor-processing phase creates multiple exposure images, and derives multi-exposure multi-scale zonal illumination-distributions, to be processed independently in the image-processing phase. In a first implementation of the object-detection phase, extracted exposure-specific features are pooled prior to overall object detection. In a second implementation, exposure-specific objects, detected from the exposure-specific features, are fused to produce the sought objects of a scene under consideration. The two implementations enable detecting fine details of a scene under diverse illumination conditions. The master processor performs loss-function computations to derive updated training parameters of the processing phases. Several experiments applying a core method of operating the computer-vision pipelines, and variations thereof, ascertain performance gain under challenging illumination conditions.