Going deeper into action recognition

Understanding human actions in visual data is tied to advances in complementary research areas including object recognition, human dynamics, domain adaptation and semantic segmentation. Over the last decade, human action analysis evolved from earlier schemes that are often limited to controlled environments to nowadays advanced solutions that can learn from millions of videos and apply to almost all daily activities. Given the broad range of applications from video surveillance to human-computer interaction, scientific milestones in action recognition are achieved more rapidly, eventually leading to the demise of what used to be good in a short time. This motivated us to provide a comprehensive review of the notable steps taken towards recognizing human actions. To this end, we start our discussion with the pioneering methods that use handcrafted representations, and then, navigate into the realm of deep learning based approaches. We aim to remain objective throughout this survey, touching upon encouraging improvements as well as inevitable fallbacks, in the hope of raising fresh questions and motivating new research directions for the reader.

Going Deeper into Action Recognition: A Survey

This paper provides a comprehensive survey for activity recognition in video surveillance. It starts with a description of simple and complex human activity, and various applications. The applications of activity recognition are manifold, ranging from visual surveillance through content based retrieval to human computer interaction. The organization of this paper covers all aspects of the general framework of human activity recognition. Then it summarizes and categorizes recent-published research progresses under a general framework. Finally, this paper also provides an overview of benchmark databases for activity recognition, the market analysis of video surveillance, and future directions to work on for this application.

A survey on activity recognition and behavior understanding in video surveillance

Although widely used in many applications, accurate and efficient human action recognition remains a challenging area of research in the field of computer vision. Most recent surveys have focused on narrow problems such as human action recognition methods using depth data, 3D-skeleton data, still image data, spatiotemporal interest point-based methods, and human walking motion recognition. However, there has been no systematic survey of human action recognition. To this end, we present a thorough review of human action recognition methods and provide a comprehensive overview of recent approaches in human action recognition research, including progress in hand-designed action features in RGB and depth data, current deep learning-based action feature representation methods, advances in human⁻object interaction recognition methods, and the current prominent research topic of action detection methods. Finally, we present several analysis recommendations for researchers. This survey paper provides an essential reference for those interested in further research on human action recognition.

A Comprehensive Survey of Vision-Based Human Action Recognition Methods.

https://ro.uow.edu.au/cgi/viewcontent.cgi?article=7172&context=eispapers

RGB-D-based action recognition datasets

ideo surveillance has gained importance in law enforcement, security and military applications The system consists of processing steps such as object detection, movement tracking, and activity monitoring The paper contribution is to present the human activity analysis system that both detect a human with carrying or abandoning an object and segments the object from the human so that it can be tracked Segmentation of objects is done from the background using advance Gaussian mixture model The tracking algorithm considers the human as whole from frame to frame, it does not track the human parts such as limbs Object features such as center of mass, size, and bounding box are used in this paper to estimate a matching between objects in consecutive frames As the object is segmented and tracked, Bayesian inference framework is used for event analysis This system uses a single camera view and unusual activity is detected using the detected objects and object tracking result The operator is notified if an unusual activity is detected

Unusual activity detection for video surveillance

In this paper we propose a framework for activity recognition based on space-time interest point in video surveillance. Single type interest point feature is not sufficient to identify the activity therefore we have considered multi-class activities fussed in three dimensional (spatial & time) coordinate to achieve our objective with maximum accuracy. Our experiment shows that fusing multi class activity using global feature provides a copious representation of human daily action when compared to the use of a single feature type. This paper model the spatial temporal distribution of interest points for identification of various short or long duration activities. It is scalable in nature and work efficiently under conditions of dynamic background, changing camera view angle or zooming, front and sidelong activities. It assumes that human being is performing action. The experiment on two benchmark datasets show propitious results when compared with the state-of-the-art methods.

Action recognition using cuboids of interest points

https://air.unimi.it/bitstream/2434/778842/2/imavis20.pdf

I-SOCIAL-DB: A labeled database of images collected from websites and social media for iris recognition

Biometric systems based on touchless and less-constrained palmprint are being increasingly studied since they allow a favorable trade-off between high-accuracy and high usability recognition. Another advantage is that with a palmar hand acquisition, it is possible to extract the palmprint as well as the Inner Finger Texture (IFT) and increase the recognition accuracy without requiring further biometric acquisitions. Recently, most methods in the literature consider Deep Learning (DL) and Convolutional Neural Networks (CNN), due to their high recognition accuracy and the capability to adapt to biometric samples captured in heterogeneous and less-constrained conditions. However, current methods based on DL do not consider the fusion of palmprint with IFT. In this work, we propose the first novel method in the literature based on a CNN to perform the fusion of palmprint and IFT using a single hand acquisition. Our approach uses an innovative procedure based on training the same CNN topology separately on the palmprint and the IFT, adapting the neural model to the different biometric traits, and then performing a feature-level fusion. We validated the proposed methodology on a public database captured in touchless and less-constrained conditions, with results showing that the fusion enabled to increase the recognition accuracy, without requiring multlple biometric acquisltions.

/pdf/touchless-palmprint-and-finger-texture-recognition-a-deep-1qr87guuri.pdf

Sarvesh Vishwakarma

Papers

A survey on activity recognition and behavior understanding in video surveillance

Unusual activity detection for video surveillance

Action recognition using cuboids of interest points

I-SOCIAL-DB: A labeled database of images collected from websites and social media for iris recognition

Touchless Palmprint and Finger Texture Recognition: A Deep Learning Fusion Approach