Video Action Recognition Using spatio-temporal optical flow video frames

TL;DR

This paper presents a deep neural network approach for human action recognition in videos, utilizing RGB and optical flow data to achieve high accuracy despite challenges like cluttered backgrounds and camera movement.

Contribution

It introduces a deep learning model that combines spatial and temporal features from RGB and optical flow videos for improved action classification.

Findings

Achieved approximately 94% recognition accuracy.

Effectively handled background clutter and viewpoint variations.

Utilized combined RGB and optical flow inputs for better performance.

Abstract

Recognizing human actions based on videos has became one of the most popular areas of research in computer vision in recent years. This area has many applications such as surveillance, robotics, health care, video search and human-computer interaction. There are many problems associated with recognizing human actions in videos such as cluttered backgrounds, obstructions, viewpoints variation, execution speed and camera movement. A large number of methods have been proposed to solve the problems. This paper focus on spatial and temporal pattern recognition for the classification of videos using Deep Neural Networks. This model takes RGB images and Optical Flow as input data and outputs an action class number. The final recognition accuracy was about 94%.