US 11,790,682 B2
Image analysis using neural networks for pose and action identification
Razwan Ghafoor, Sutton Coldfield (GB); Peter Rennert, Sutton Coldfield (GB); and Hichame Moriceau, London (GB)
Assigned to STANDARD COGNITION, CORP., San Francisco, CA (US)
Filed by STANDARD COGNITION, CORP., San Francisco, CA (US)
Filed on Jul. 29, 2021, as Appl. No. 17/388,260.
Application 17/388,260 is a continuation of application No. 16/492,781, abandoned, previously published as PCT/GB2018/050614, filed on Mar. 9, 2018.
Claims priority of application No. 1703914 (GB), filed on Mar. 10, 2017.
Prior Publication US 2022/0012478 A1, Jan. 13, 2022
Int. Cl. G06V 40/10 (2022.01)
CPC G06V 40/103 (2022.01) 20 Claims
OG exemplary drawing
 
1. An apparatus for performing image analysis to identify human actions represented in an image, comprising:
a joint-determination module configured to analyse an image depicting one or more people using a first computational neural network to determine a set of joint candidates for the one or more people depicted in the image,
wherein the first computational neural network processes, as input, the image on a pixel-by-pixel basis to generate, an output vector containing a number of elements, each element within the number of elements storing a probability that a respective pixel within the image depicts a joint, and wherein the output vector is evaluated to determine the set of joint candidates;
a pose-estimation module configured to derive pose estimates from the set of joint candidates that estimate a body configuration for the one or more people depicted in the image; and
an action-identification module configured to analyse a region of interest within the image identified from the derived pose estimates using a second computational neural network to identify an action performed by a person depicted in the image.