Videos play an ever increasing role in our everyday lives with applications ranging from news, entertainment, scientific research, security, and surveillance. Coupled with the fact that cameras and storage media are becoming less expensive, it has resulted in people producing more video content than ever before. Analysis of human activities in video is important for several important applications. Interpretation and identification of human activities requires approaches that address the following questions (a) what are the appropriate atomic primitives for human activities, (b) how to combine primitives to produce complex activities, (c) what are the required invariances for inference algorithms, and (d) how to build computational models for each of these. In this chapter, we provide a broad overview and discussion of these issues. We shall review state-of-the-art computer vision algorithms that address these issues and then provide a unified perspective from which specific algorithms can be derived. We will then present supporting experimental results.
ASJC Scopus subject areas
- Computer Science(all)