ActionXPose: A Novel 2D Multi-view Pose-based Algorithm for Real-time Human Action Recognition

10/29/2018
by   Federico Angelini, et al.
12

We present ActionXPose, a novel 2D pose-based algorithm for posture-level Human Action Recognition (HAR). The proposed approach exploits 2D human poses provided by OpenPose detector from RGB videos. ActionXPose aims to process poses data to be provided to a Long Short-Term Memory Neural Network and to a 1D Convolutional Neural Network, which solve the classification problem. ActionXPose is one of the first algorithms that exploits 2D human poses for HAR. The algorithm has real-time performance and it is robust to camera movings, subject proximity changes, viewpoint changes, subject appearance changes and provide high generalization degree. In fact, extensive simulations show that ActionXPose can be successfully trained using different datasets at once. State-of-the-art performance on popular datasets for posture-related HAR problems (i3DPost, KTH) are provided and results are compared with those obtained by other methods, including the selected ActionXPose baseline. Moreover, we also proposed two novel datasets called MPOSE and ISLD recorded in our Intelligent Sensing Lab, to show ActionXPose generalization performance.

READ FULL TEXT

page 1

page 4

page 7

page 12

research
12/14/2018

Action Machine: Rethinking Action Recognition in Trimmed Videos

Existing methods in video action recognition mostly do not distinguish h...
research
05/22/2018

Pose-Based Two-Stream Relational Networks for Action Recognition in Videos

Recently, pose-based action recognition has gained more and more attenti...
research
05/02/2023

Cross-view Action Recognition via Contrastive View-invariant Representation

Cross view action recognition (CVAR) seeks to recognize a human action w...
research
07/01/2021

Action Transformer: A Self-Attention Model for Short-Time Human Action Recognition

Deep neural networks based purely on attention have been successful acro...
research
09/14/2020

Collaborative Attention Mechanism for Multi-View Action Recognition

Multi-view action recognition (MVAR) leverages complementary temporal in...
research
11/16/2020

DARE: AI-based Diver Action Recognition System using Multi-Channel CNNs for AUV Supervision

With the growth of sensing, control and robotic technologies, autonomous...

Please sign up or login with your details

Forgot password? Click here to reset