US 12,482,068 B2
Method and system for determining auto-exposure for high-dynamic range object detection using neural network
Emmanuel Luc Julien Onzon, Munich (DE); Felix Heide, Palo Alto, CA (US); and Fahim Mannan, Montreal (CA)
Assigned to TORC CND ROBOTICS, INC., Montreal (CA)
Filed by TORC CND ROBOTICS, INC., Montreal (CA)
Filed on Apr. 15, 2022, as Appl. No. 17/722,261.
Application 17/722,261 is a continuation in part of application No. 17/712,727, filed on Apr. 4, 2022, granted, now 11,783,231.
Application 17/712,727 is a continuation of application No. 16/927,741, filed on Jul. 13, 2020, granted, now 11,295,176, issued on Apr. 5, 2022.
Application 16/927,741 is a continuation of application No. 16/025,776, filed on Jul. 2, 2018, granted, now 10,713,537, issued on Jul. 14, 2020.
Claims priority of provisional application 63/175,505, filed on Apr. 15, 2021.
Claims priority of provisional application 62/528,054, filed on Jul. 1, 2017.
Prior Publication US 2022/0269910 A1, Aug. 25, 2022
Int. Cl. G06T 5/50 (2006.01); G06F 18/241 (2023.01); G06F 18/2413 (2023.01); G06N 3/045 (2023.01); G06N 3/084 (2023.01); G06N 20/00 (2019.01); G06T 5/60 (2024.01); G06T 5/73 (2024.01); G06V 10/44 (2022.01)
CPC G06T 5/50 (2013.01) [G06F 18/241 (2023.01); G06F 18/24133 (2023.01); G06N 3/045 (2023.01); G06N 3/084 (2013.01); G06N 20/00 (2019.01); G06T 5/60 (2024.01); G06T 5/73 (2024.01); G06V 10/454 (2022.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/20182 (2013.01)] 21 Claims
OG exemplary drawing
 
1. A computer-implemented method for determining an auto-exposure value of a low dynamic range (LDR) sensor for use in high dynamic range (HDR) object detection, the method comprising:
employing at least one hardware processor for:
forming an auto-exposure neural network for predicting exposure values for the LDR sensor driven by a downstream object detection neural network in real time;
training the auto-exposure neural network jointly, end-to-end together with (i) the object detection neural network and (ii) an image signal processing (ISP) pipeline, thereby yielding a trained auto-exposure neural network; and
using the trained auto-exposure neural network to generate an optimal exposure value for the LDR sensor and the downstream object detection neural network for the HDR object detection.