Device and a method for extracting dynamic information on a scene using a convolutional neural network

C Nunn, W Zhu, Y Su - US Patent 11,195,038, 2021 - Google Patents
(57) ABSTRACT A device for extracting dynamic information comprises a convolutional
neural network, wherein the device is config ured to receive a sequence of data blocks …

Parametric top-view representation of complex road scenes

B Liu, B Zhuang, S Schulter, M Chandraker - US Patent 11,455,813, 2022 - Google Patents
Abstract Systems and methods are provided for producing a road layout model. The method
includes capturing digital images having a perspective view, converting each of the digital …

Method of processing image data in a connectionist network

W Zhu, J Siegemund - US Patent 11,386,329, 2022 - Google Patents
A method of processing image data in a connectionist network includes: determining, a
plurality of offsets, each offset representing an individual location shift of an underlying one …

Obstacle detection and notification for motorcycles

CL Oesterling, DH Clifford - US Patent App. 17/822,593, 2022 - Google Patents
[0001] The technical field generally relates to obstacle detection and notification for
motorcycles, and more par ticularly relates to use of computer vision and machine learning …

Obstacle detection and notification for motorcycles

CL Oesterling, DH Clifford - US Patent App. 17/822,578, 2022 - Google Patents
An obstacle detection and notification system for a motor cycle. The system includes a
forward looking thermal cam era and a backward looking thermal camera mountable to the …

Multimodal input processing system

MM Maher, BJ Theobald, NE Apostoloff - US Patent 11,663,514, 2023 - Google Patents
US11663514B1 - Multimodal input processing system - Google Patents US11663514B1 -
Multimodal input processing system - Google Patents Multimodal input processing system …

Method of processing image data in a connectionist network

W Zhu, J Siegemund - US Patent 11,645,851, 2023 - Google Patents
(57) ABSTRACT A method of processing image data in a connectionist network includes:
determining, a plurality of offsets, each offset representing an individual location shift of an …

System and method for providing unsupervised domain adaptation for spatio-temporal action localization

YT Chen, B Dariush, N Agarwal, MH Yang - US Patent 11,580,743, 2023 - Google Patents
US11580743B2 - System and method for providing unsupervised domain adaptation for
spatio-temporal action localization - Google Patents US11580743B2 - System and method for …

Traffic prediction with reparameterized pushforward policy for autonomous vehicles

P Vernaza, N Rhinehart - US Patent 11,189,171, 2021 - Google Patents
Abstract Systems and methods for vehicle behavior prediction include an imaging device
that captures images of a vehicle in traffic. A processing device including policy stored in a …

System and method for providing unsupervised domain adaptation for spatio-temporal action localization

YT Chen, B Dariush, N Agarwal, MH Yang - US Patent 11,403,850, 2022 - Google Patents
A system and method for providing unsupervised domain adaption for spatio-temporal
action localization that includes receiving video data associated with a surrounding …