Anticipating Human Activities from Surveillance Videos

Sensors

Recognition of human actions form videos has been an active area of research because it has applications in various domains. The results of work in this field are used in video surveillance, automatic video labeling and human-computer interaction, among others. Any advancements in this field are tied to advances in the interrelated fields of object recognition, spatio- temporal video analysis and semantic segmentation. Activity recognition is a challenging task since it faces many problems such as occlusion, view point variation, background differences and clutter and illumination variations. Scientific achievements in the field have been numerous and rapid as the applications are far reaching. In this survey, we cover the growth of the field from the earliest solutions, where handcrafted features were used, to later deep learning approaches that use millions of images and videos to learn features automatically. By this discussion, we intend to highlight the major breakthroughs and ...

International Journal of Advanced Science and Engineering, 2019

Nowadays automated detection and recognition of human beings and their actions in surveillance videos is gaining importance. The paper presented is divided into different segments which include methods of extraction of images of different moving objects from surveillance videos, identification and face and action recognition. The smart surveillance system proposes information processing techniques for CCTV based surveillance systems. It gives information about the advanced surveillance cameras having the property of identifying and providing real time notification. This paper is a study on the methods and applications of the human action recognition through surveillance system. It can be most effectively used in surveillance of crowded public places, finding missing and suspicious people and recognizing their actions, human computer interaction and automated refereeing.

Recognition and analysis of Human actions is an important task in the area of computer vision. There are many applications of this research which include surveillance systems, patient monitoring systems, human performance analysis, contentbased image/video retrieval/storage, virtual reality and a variety of systems that involve interactions between persons or interactions between person and devices, etc. The need for such systems is increasing day-by-day, with the increase in number of surveillance cameras deployed in public spaces. Automated systems are required that can detect, categorize and recognize human activities and request the human attention only when necessary.

International Journal for Research in Applied Science and Engineering Technology IJRASET, 2020

The goal of this project is to develop a Human Action Recognition system with a video classification approach. Data is gathered by downloading images from google, analyze the frames of the video and predict the actions being performed. This is achieved by using Computer vision-a field of computer science that works on enabling computers to see, identify and process images similar to human vision, and then provide appropriate results. It is like imparting human intelligence and instincts to a computer.

2006

In this paper, we propose a new system for human action recognition with a view to applications in security systems, man-machine communications and intelligent environments. Our system is based on very simple features in order to achieve high-speed recognition in real-world applications. We have chosen three main techniques to build a system that can work in real-time. Firstly, we choose Motion History Images and related features. Secondly, we use a template matching methods instead of state-space methods that need expensive modelling processes; finally, we use linear classifier support vector machine (SVM) for fast classification. Experimental results show that this system can achieve good performance in human action recognition in realtime embedded applications, such as intelligent environments.

2021 3rd International Conference on Sustainable Technologies for Industry 4.0 (STI), 2021

Crime rate is increasing proportionally with the increasing rate of the population. The most prominent approach was to introduce Closed-Circuit Television (CCTV) camerabased surveillance to tackle the issue. Video surveillance cameras have added a new dimension to detect crime. Several research works on autonomous security camera surveillance are currently ongoing, where the fundamental goal is to discover violent activity from video feeds. From the technical viewpoint, this is a challenging problem because analyzing a set of frames, i.e., videos in temporal dimension to detect violence might need careful machine learning model training to reduce false results. This research focuses on this problem by integrating state-ofthe-art Deep Learning methods to ensure a robust pipeline for autonomous surveillance for detecting violent activities, e.g., kicking, punching, and slapping. Initially, we designed a dataset of this specific interest, which contains 600 videos (200 for each action). Later, we have utilized existing pre-trained model architectures to extract features, and later used deep learning network for classification. Also, We have classified our models' accuracy, and confusion matrix on different pre-trained architectures like VGG16, InceptionV3, ResNet50, Xception and MobileNet V2 among which VGG16 and MobileNet V2 performed better.

Advancements in Computer Vision and Image Processing, 2018

Computer vision techniques are capable of detecting human behavior from video sequences. Several state-of-the-art techniques have been proposed for human behavior detection and analysis. However, a collective framework is always required for intelligent human behavior analysis. Therefore, in this chapter, the authors provide a comprehensive understanding towards human behavior detection approaches. The framework of this chapter is based on human detection, human tracking, and human activity recognition, as these are the basic steps of human behavior detection process. The authors provide a detailed discussion over the human behavior detection framework and discuss the feature-descriptor-based approach. Furthermore, they have provided qualitative and quantitative analysis for the detection framework and demonstrate the results for human detection, human tracking, and human activity recognition.

International Journal of Advance Research in Computer Science and Management Studies [IJARCSMS] ijarcsms.com, 2020

Gotten from fast advances in computer vision and AI, video investigation errands have been moving from inferring the present state to anticipating the future state. Vision-based activity acknowledgment and forecast from recordings are such assignments, where activity acknowledgment is to human actions in light of complete activity executions, and activity expectation to foresee human actions in view of fragmented activity executions. These two undertakings have become especially predominant subjects as of late on account of their violently developing genuine applications, for example, visual reconnaissance, self-sufficient driving vehicle, amusement, and video recovery, and so forth. Numerous endeavors have been dedicated in the last a couple of decades so as to manufacture a strong and successful structure for activity acknowledgment and expectation. This paper, overview the total best in class systems in the activity acknowledgment andforecast.

The Research work Human activity recognisation district of interest a portion of video with mixture method and upgrade of Non –region of interest part is examined in this work. As of late, programmed human movement acknowledgment has attracted much consideration the field of video examination innovation because of the developing requests from numerous applications, for example, reconnaissance situations, amusement situations and medicinal services frameworks. In an observation domain, the programmed recognition of anomalous exercises can be utilized to alarm the related power of potential criminal or risky practices, for example, programmed reporting of a man with a sack dallying at an airplane terminal or station. There are SVM and KNN is studied to segment the human action on MAD dataset and accuracy is calculated on this dataset after the action recognisation.

—Analysis of human activities from video is currently one of the ongoing research areas in computer science. Recognition of human activity from video has gained lot of attention because of its increasing demand in many real life applications, for e.g. video surveillance, entertainment, healthcare, child and old age homes, etc. In this paper, several steps involved in automatic human activity recognition systems, such as segmentation, tracking of motion, pose estimation and recognition of activities are studied. Common segmentation techniques such as background subtraction and Gaussian Mixture Model (GMM) are also discussed. Two different approaches for tracking of motion in video, i.e. representation and localization of the target and filtering and data association are also discussed. Finally some of the commonly available datasets used in automatic analysis of human activities from video are also mentioned in detail.