公开(公告)号：US12050664B2

公开(公告)日：2024-07-30

申请号：US17494979

申请日：2021-10-06

Applicant: NEC Laboratories America, Inc.

Inventor： Murugan Sankaradas ,  Kunal Rao ,  Yi Yang ,  Biplob Debnath ,  Utsav Drolia ,  Srimat Chakradhar ,  Amit Redkar ,  Ravi Kailasam Rajendran

IPC: G06F18/25 ,  G06F18/214 ,  G06N3/045 ,  G06T7/50 ,  G06T11/00 ,  G06V10/40 ,  G06V20/00

CPC classification number: G06F18/253 ,  G06F18/2148 ,  G06N3/045 ,  G06T7/50 ,  G06T11/00 ,  G06V10/40 ,  G06V20/00 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/20221 ,  G06T2210/12

Abstract: A method for real-time cross-spectral object association and depth estimation is presented. The method includes synthesizing, by a cross-spectral generative adversarial network (CS-GAN), visual images from different data streams obtained from a plurality of different types of sensors, applying a feature-preserving loss function resulting in real-time pairing of corresponding cross-spectral objects, and applying dual bottleneck residual layers with skip connections to accelerate real-time inference and to accelerate convergence during model training.

公开(公告)号：US20220114380A1

公开(公告)日：2022-04-14

申请号：US17494979

申请日：2021-10-06

Applicant: NEC Laboratories America, Inc.

Inventor： Murugan Sankaradas ,  Kunal Rao ,  Yi Yang ,  Biplob Debnath ,  Utsav Drolia ,  Srimat Chakradhar ,  Amit Redkar ,  Ravi Kailasam Rajendran

IPC: G06K9/62 ,  G06T7/50 ,  G06K9/00 ,  G06T11/00 ,  G06K9/46 ,  G06N3/04

Abstract: A method for real-time cross-spectral object association and depth estimation is presented. The method includes synthesizing, by a cross-spectral generative adversarial network (CS-GAN), visual images from different data streams obtained from a plurality of different types of sensors, applying a feature-preserving loss function resulting in real-time pairing of corresponding cross-spectral objects, and applying dual bottleneck residual layers with skip connections to accelerate real-time inference and to accelerate convergence during model training.