Event and Activity Recognition in Video Surveillance for Cyber-Physical Systems

Abstract

In this chapter, we aim to aid the development of Cyber-Physical Systems (CPS) in automated understanding of events and activities in various applications of videosurveillance. These events are mostly captured by drones, CCTVs or novice and unskilled individuals on low-end devices. Being unconstrained in nature, these videos are immensely challenging due to a number of quality factors. We present an extensive account of the various approaches taken to solve the problem over the years. This ranges from methods as early as Structure from Motion (SFM) based approaches to recent solution frameworks involving deep neural networks. We show that the long-term motion patterns alone play a pivotal role in the task of recognizing an event. Consequently each video is significantly represented by a fixed number of key-frames using a graph-based approach. Only the temporal features are exploited using a hybrid Convolutional Neural Network (CNN) + Recurrent Neural Network (RNN) architecture. The results we obtain are encouraging as they outperform standard temporal CNNs and are at par with those using spatial information along with motion cues. Further exploring multistream models, we conceive a multi-tier fusion strategy for the spatial and temporal wings of a network. A consolidated representation of the respective individual prediction vectors on video and frame levels is obtained

An Effective Video Event Classification by Optimizing the Hyper-Parameters Using Improved Pelican Optimization and Bi-LSTM Classifier

“…The recognition of events is considered one of the active areas in the field of computer vision due to the wide range of applications like the interaction between humans and computers, analysis of motion, analysis of medical images, etc [1]. The main goal of event recognition is to recognize the events such as parties, weddings, graduation, and also daily activities like shaving the beard, jogging, riding a bike, and so on [2]. In recognition of events, feature extraction plays a significant role in extracting the essential features from the videos [3,4].…”

Recent Trends in 2D Object Detection and Applications in Video Event Recognition

“…The task of video event recognition [2] is to predict the ongoing event or activity in a video throughout its duration. The prevalent approach is to obtain a global video-level feature representation [3] from 3D CNNs and classify the video using the same.…”