Advances in Video-Based Human Activity Analysis: Challenges and Approaches

Pavan Turaga, Rama Chellappa, Ashok Veeraraghavan

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

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.

Original languageEnglish (US)
Pages (from-to)237-290
Number of pages54
JournalAdvances in Computers
Volume80
Issue numberC
DOIs
StatePublished - Jan 1 2010
Externally publishedYes

Fingerprint

Invariance
Computer vision
Cameras

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Advances in Video-Based Human Activity Analysis : Challenges and Approaches. / Turaga, Pavan; Chellappa, Rama; Veeraraghavan, Ashok.

In: Advances in Computers, Vol. 80, No. C, 01.01.2010, p. 237-290.

Research output: Contribution to journalArticle

Turaga, Pavan ; Chellappa, Rama ; Veeraraghavan, Ashok. / Advances in Video-Based Human Activity Analysis : Challenges and Approaches. In: Advances in Computers. 2010 ; Vol. 80, No. C. pp. 237-290.
@article{6d7d44b80a954c3a8540e4a1fa95afb1,
title = "Advances in Video-Based Human Activity Analysis: Challenges and Approaches",
abstract = "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.",
author = "Pavan Turaga and Rama Chellappa and Ashok Veeraraghavan",
year = "2010",
month = "1",
day = "1",
doi = "10.1016/S0065-2458(10)80007-5",
language = "English (US)",
volume = "80",
pages = "237--290",
journal = "Advances in Computers",
issn = "0065-2458",
publisher = "Academic Press Inc.",
number = "C",

}

TY - JOUR

T1 - Advances in Video-Based Human Activity Analysis

T2 - Challenges and Approaches

AU - Turaga, Pavan

AU - Chellappa, Rama

AU - Veeraraghavan, Ashok

PY - 2010/1/1

Y1 - 2010/1/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=84999288385&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84999288385&partnerID=8YFLogxK

U2 - 10.1016/S0065-2458(10)80007-5

DO - 10.1016/S0065-2458(10)80007-5

M3 - Article

AN - SCOPUS:84999288385

VL - 80

SP - 237

EP - 290

JO - Advances in Computers

JF - Advances in Computers

SN - 0065-2458

IS - C

ER -