Subsequence-Wise Approach for Online Tracking

Subsequence-Wise Approach for Online Tracking

Bin Shen (Tsinghua University, China) and Yu-Jin Zhang (Tsinghua University, China)
Copyright: © 2009 |Pages: 10
DOI: 10.4018/978-1-60566-298-5.ch009
OnDemand PDF Download:


This chapter is concerned with online object tracking, which aims to locate a given object in each of the consecutive frames. Many algorithms have been proposed to deal with this problem. Most make a decision in each frame, failing to consider the inner relationship among these decisions. However, the relation among these decisions is important if they can be fused together. Intuitively, human beings do not make a decision in a single frame and always explore the temporal information contained in neighboring frames, and then make decisions for all these neighboring frames. This chapter proposes a novel framework, which views the tracking as a sequence of decisions, with each subsequence of decisions corresponding to a subsequence of the video. Such an approach is described as a subsequence-wise approach. This framework considers the relation among the states in different frames, and it is ready to be incorporated into many related tracking techniques.
Chapter Preview

1. Introduction

With the development of computer vision, online object tracking is becoming a more and more active research area. It plays an important role in a lot of applications, such as area surveillance, navigation, video compression, and human computer interfaces. Besides, tracking paves the way for further process of videos, such as object classification or recognition.

1.1 Existing Approaches

Lots of algorithms have been proposed to deal with this task, from the simple feature point matching method to non-rigid object tracking. The general idea inside these approaches can be simply described as two steps: (1) make use of the information available to model the target object or both the target and background; (2) decide where the target is in the current frame. For example, particle filter based tracking algorithm (Arulampalam, 2002, Isard, 1998) adopts the information available in the past frames to get the priori probability of the target’s state for the current frame, and then the measurements are used to get the posterior probability distribution function via Bayesian Theorem. Based on the posterior the state in the current frame of the target is estimated. Mean shift based tracking algorithm (Cheng, 1995, Comaniciu, 2000) treats tracking as a mode seeking process. The model of the target for tracking is constructed based on the passed frames, and then it deploys the mean shift method to search the optimal mode the current frame. These algorithms make a decision based on the feature extracted from the current frame, while they fail to take into account the constraint among the decisions in consecutive frames, which we call a subsequence. Some other algorithms (Grabner, 2006, Nguyen, 2006) are aimed to explore not only the spatial context of the object but also the temporal spatial context. However, they still make one decision at a time, which is for the current frame, and do not consider the innate relation among the decisions in neighboring frames.

Now, to express our idea clearly, we introduce the term tracking unit. Here, we call a repeated component of a video sequence a tracking unit, if and only if the tracking algorithm treats each such component equivalently. For example, these algorithms listed above treat every frame equivalently, and make a decision in an individual frame, no matter whether they make use of the temporal context. Therefore, the tracking unit for them is a single frame. While experiences tell us that when we humans track a target using our eyes, we do not make decisions about the states in several continuous frames separately. Or rather, we will explore some inner relation among these decisions and fuse them before releasing the decision result. For instance, we are able to estimate the occluded target states if we know how the target enters occlusion and how it gets out. Therefore, it is intuitive that the constraint among decisions in consecutive frames will be helpful for our final better decisions if we can make use of it. From this example, we can further see that choosing a frame as the tracking unit may be not a good choice, for it probably fails to estimate the target’s state when it is occluded. Before seeking a better choice for tracking unit, we denote these algorithms mentioned above as frame-wise approach, since they take a single frame as the tracking unit.

Complete Chapter List

Search this Book:
Editorial Advisory Board
Table of Contents
Olaf Diegel
Judith Symonds, John Ayoade, David Parry
Chapter 1
Chin Boo Soon
This chapter describes the history and development of Radio Frequency Identification (RFID). Key information on RFID such as the ratification of the... Sample PDF
Radio Frequency Identification History and Development
Chapter 2
John Garofalakis, Christos Mettouris
The continuous evolution of wireless technologies has made them ideal for use in many different applications, including user positioning. Until now... Sample PDF
Using Bluetooth for Indoor User Positioning and Informing
Chapter 3
John Ayoade, Judith Symonds
Standards organisations such as EPC Global work to provide global compatibility between RFID readers and tags (EPCGlobal, 2007). This is essential... Sample PDF
RFID for Identification of Stolen/Lost Items
Chapter 4
Filippo Gandino, Erwing Ricardo Sanchez, Bartolomeo Montrucchio, Maurizio Rebaudengo
This chapter deals with the use of RFID technology for improving management and security of agri-food products. In order to protect health and to... Sample PDF
RFID Technology for Agri-Food Tracability Management
Chapter 5
Lena Mamykina, Elizabeth Mynatt
In the last decade, novel sensing technologies enabled development of applications that help individuals with chronic diseases monitor their health... Sample PDF
Interpreting Health and Wellness Information
Chapter 6
Bryan Houliston
Hospitals are traditionally slow to adopt new information systems (IS). However, health care funders and regulators are demanding greater use of IS... Sample PDF
RFID in Hospitals and Factors Restricting Adoption
Chapter 7
David Parry, Judith Symonds
Radio-frequency Identification (RFID) offers a potentially flexible and low cost method of locating objects and tracking people within buildings.... Sample PDF
RFID and Assisted Living for the Elderly
Chapter 8
Ashir Ahmed, Ly-Fie Sugianto
This chapter introduces an activity-based framework for the adoption of radio frequency identification (RFID) in emergency management. The framework... Sample PDF
RFID in Emergency Management
Chapter 9
Bin Shen, Yu-Jin Zhang
This chapter is concerned with online object tracking, which aims to locate a given object in each of the consecutive frames. Many algorithms have... Sample PDF
Subsequence-Wise Approach for Online Tracking
Chapter 10
John Ayoade
The aim of Fixed-Mobile Convergence (FMC) is to provide both fixed-line and mobile telephony services to users through the same handset which could... Sample PDF
From Fixed to Mobile Convergence
Chapter 11
Sarita Pais, Judith Symonds
RFID tags can store more data and can update this data through local processing. This is in contrast to the EPC global standard of data-on-network.... Sample PDF
Handling RFID Data Using a Data-on-Tag Approach
Chapter 12
Maryam Purvis, Toktam Ebadi, Bastin Tony Roy Savarimuthu
The objective of this research is to describe a mechanism to provide an improved library management system using RFID and agent technologies. One of... Sample PDF
An Agent-Based Library Management System Using RFID Technology
Chapter 13
Tommaso Di Noia, Eugenio Di Sciascio, Francesco Maria Donini, Michele Ruta, Floriano Scioscia, Eufemia Tinelli
We propose a novel object discovery framework integrating the application layer of Bluetooth and RFID standards. The approach is motivated and... Sample PDF
Semantic-Based Bluetooth-RFID Interaction for Advanced Resource Discovery in Pervasive Contexts
Chapter 14
Indranil Bose, Chun Wai Lam
Radio frequency identification (RFID) has generated vast amounts of interest in the supply chain, logistics, and the manufacturing area. RFID can be... Sample PDF
Facing the Challenges of RFID Data Management
Chapter 15
Masoud Mohammadian, Ric Jentzsch
The cost of health care continues to be a world wide issue. Research continues into ways and how the utilization of evolving technologies can be... Sample PDF
A Mobile Computing Framework for Passive RFID Detection System in Healthcare
Chapter 16
Masoud Mohammadian, Ric Jentzsch
When dealing with human lives, the need to utilize and apply the latest technology to help in saving and maintaining patients’ lives is quite... Sample PDF
Intelligent Agents Framework for RFID Hospitals
Chapter 17
David Wyld
We are in the midst of what may become one of the true technological transformations of our time. RFID (radio frequency identification) is by no... Sample PDF
Radio Frequency Identification (RFID) Technology
About the Contributors