Activity Recognition based on a Magnitude-Orientation Stream Network

08/22/2017
by   Carlos Caetano, et al.
0

The temporal component of videos provides an important clue for activity recognition, as a number of activities can be reliably recognized based on the motion information. In view of that, this work proposes a novel temporal stream for two-stream convolutional networks based on images computed from the optical flow magnitude and orientation, named Magnitude-Orientation Stream (MOS), to learn the motion in a better and richer manner. Our method applies simple nonlinear transformations on the vertical and horizontal components of the optical flow to generate input images for the temporal stream. Experimental results, carried on two well-known datasets (HMDB51 and UCF101), demonstrate that using our proposed temporal stream as input to existing neural network architectures can improve their performance for activity recognition. Results demonstrate that our temporal stream provides complementary information able to improve the classical two-stream methods, indicating the suitability of our approach to be used as a temporal video representation.

READ FULL TEXT

page 3

page 5

page 6

research
02/27/2018

ReHAR: Robust and Efficient Human Activity Recognition

Designing a scheme that can achieve a good performance in predicting sin...
research
03/11/2019

Investigation on Combining 3D Convolution of Image Data and Optical Flow to Generate Temporal Action Proposals

In this paper, a novel two-stream architecture for the task of temporal ...
research
12/07/2022

DroneAttention: Sparse Weighted Temporal Attention for Drone-Camera Based Activity Recognition

Human activity recognition (HAR) using drone-mounted cameras has attract...
research
03/30/2017

TS-LSTM and Temporal-Inception: Exploiting Spatiotemporal Dynamics for Activity Recognition

Recent two-stream deep Convolutional Neural Networks (ConvNets) have mad...
research
07/13/2020

Fusing Motion Patterns and Key Visual Information for Semantic Event Recognition in Basketball Videos

Many semantic events in team sport activities e.g. basketball often invo...
research
11/10/2022

SWTF: Sparse Weighted Temporal Fusion for Drone-Based Activity Recognition

Drone-camera based human activity recognition (HAR) has received signifi...
research
08/30/2016

Motion Representation with Acceleration Images

Information of time differentiation is extremely important cue for a mot...

Please sign up or login with your details

Forgot password? Click here to reset