Fu Y. (ed.) Human Activity Recognition and Prediction

Springer, 2016. — 179.Automatic human activity sensing has drawn much attention in the field of video analysis technology due to the growing demands from many applications, such as surveillance environments, entertainments, and healthcare systems. Human activity recognition and prediction is closely related to other computer vision tasks such as human gesture analysis, gait recognition, and event recognition. Very recently, the US government funded many major research projects on this topic; in industry, commercial products such as the Microsoft’s Kinect are good examples that make use of human action recognition techniques. Many commercialized surveillance systems seek to develop and exploit video-based detection, tracking and activity recognition of persons, and vehicles in order to infer their threat potential and provide automated alerts.
This book focuses on the recognition, prediction of individual activities and interactions from videos that usually involves several people. This provides a unique view of: human activity recognition, especially fine-grained human activity structure learning, human interaction recognition, RGB-D data-based recognition temporal decomposition, and casually learning in unconstrained human activity videos. These techniques will significantly advance existing methodologies of video content understanding by taking advantage of activity recognition. As a professional reference and research monograph, this book includes several key chapters covering multiple emerging topics in this new field. It links multiple popular research fields in computer vision, machine learning, human-centered computing, humancomputer interaction, image classification, and pattern recognition. Contributed by top experts and practitioners of the Synergetic Media Learning (SMILE) Lab at Northeastern University, these chapters complement each other from different angles and compose a solid overview of the human activity recognition and prediction techniques. Well-balanced contents and cross-domain knowledge for both methodology and real-world applications will benefit readers from different level of expertise in broad fields of science and engineering.Action Recognition and Human Interaction.
Subspace Learning for Action Recognition.
Multimodal Action Recognition.
RGB-D Action Recognition.
Activity Prediction.
Actionlets and Activity Prediction.
Time Series Modeling for Activity Prediction.