A Critical Analysis on Machine Learning Techniques for Video-based Human Activity Recognition of Surveillance Systems: A Review

TL;DR

This review critically examines machine learning and deep learning techniques for video-based human activity recognition in surveillance, highlighting current methods, challenges, and future research directions to improve anomaly detection.

Contribution

It provides a comprehensive analysis of various machine learning and deep learning approaches for HAR, comparing their effectiveness and identifying key challenges and future prospects.

Findings

CNN and RNN are effective for feature extraction.

Deep learning techniques outperform traditional methods.

Challenges include real-time processing and diverse activity recognition.

Abstract

Upsurging abnormal activities in crowded locations such as airports, train stations, bus stops, shopping malls, etc., urges the necessity for an intelligent surveillance system. An intelligent surveillance system can differentiate between normal and suspicious activities from real-time video analysis that will enable to take appropriate measures regarding the level of an anomaly instantaneously and efficiently. Video-based human activity recognition has intrigued many researchers with its pressing issues and a variety of applications ranging from simple hand gesture recognition to crucial behavior recognition in a surveillance system. This paper provides a critical survey of video-based Human Activity Recognition (HAR) techniques beginning with an examination of basic approaches for detecting and recognizing suspicious behavior followed by a critical analysis of machine learning and deep learning techniques such as Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Hidden Markov Model (HMM), K-means Clustering etc. A detailed investigation and comparison are done on these learning techniques on the basis of feature extraction techniques, parameter initialization, and optimization algorithms, accuracy, etc. The purpose of this review is to prioritize positive schemes and to assist researchers with emerging advancements in this field's future endeavors. This paper also pragmatically discusses existing challenges in the field of HAR and examines the prospects in the field.