Skip to main content
main-content

Über dieses Buch

This work proposes a complete sensor-independent visual system that provides robust target motion detection. First, the way sensors obtain images, in terms of resolution distribution and pixel neighbourhood, is studied. This allows a spatial analysis of motion to be carried out. Then, a novel background maintenance approach for robust target motion detection is implemented. Two different situations are considered: a fixed camera observing a constant background where objects are moving; and a still camera observing objects in movement within a dynamic background. This distinction lies on developing a surveillance mechanism without the constraint of observing a scene free of foreground elements for several seconds when a reliable initial background model is obtained, as that situation cannot be guaranteed when a robotic system works in an unknown environment. Other problems are also addressed to successfully deal with changes in illumination, and the distinction between foreground and background elements.

Inhaltsverzeichnis

Frontmatter

Chapter 1. Introduction

Abstract
One of the most challenging issues in computer vision is image segmentation. The reason lies on the information it can provide about the elements in the scene from the automatic image division based on pixel similarities. Therefore, what makes a pixel interesting depends on the object's features to be considered. Thus, due to segmentation of countless applications, a wide range of solutions have been proposed and tested by the scientific community during the previous years. However, considering motion as a primary cue for target detection, background subtraction (BS) methods are commonly used. In this chapter, we overview the method in general terms as well as its different variants with the aim to analyze the problems remaining to be solved.
Ester Martínez-Martín, Ángel P. del Pobil

Chapter 2. Motion Detection in Static Backgrounds

Abstract
Motion detection plays a fundamental role in any object tracking or video surveillance algorithm, to the extent that nearly all such algorithms start with motion detection. Actually, the reliability with which potential foreground objects in movement can be identified, directly impacts on the efficiency and performance level achievable by subsequent processing stages of tracking or object recognition. However, detecting regions of change in images of the same scene is not a straightforward task since it does not only depend on the features of the foreground elements, but also on the characteristics of the background such as, for instance, the presence of vacillating elements. So, in this chapter, we have focused on the motion detection problem in the basic case, i.e., when all background elements are motionless. The goal is to solve different issues referred to the use of different imaging sensors, the adaptation to different environments, different motion speed, the shape changes of the targets, or some uncontrolled dynamic factors such as, for instance, gradual/sudden illumination changes. So, first, a brief overview of previous related approaches is presented by analyzing factors which can make the system fail. Then, we propose a motion segmentation algorithm that successfully deals with all the arisen problems. Finally, performance evaluation, analysis, and discussion are carried out.
Ester Martínez-Martín, Ángel P. del Pobil

Chapter 3. Motion Detection in General Backgrounds

Abstract
Once the basic case of the motion detection problem has been studied and solved the issues referred to the use of different imaging sensors, the adaptation to different environments, different motion speed, the shape changes of the targets, and some uncontrolled dynamic factors (e.g. gradual/sudden illumination changes), we have focused on motion detection when real scenes are considered. Therefore, in this chapter, the goal is to design a perfect segmentation technique based on motion in environments without any constraint about the environment and the targets to be identified. With that aim, different issues such as, for instance, the presence of vacillating background elements or the distinction between targets and background objects in terms of motion and motionless situations, have been studied and solved. Thus, a brief review of the previous work is carried out in order to introduce our approach. Then, a deeper analysis of the problems as well as the proposed solutions are explained. Finally, experimental results, from qualitative and quantitative points of view, are presented and discussed. As it will be demonstrated, compared with classical techniques, the proposed algorithm is faster, more robust, and sensor-independent.
Ester Martínez-Martín, Ángel P. del Pobil

Chapter 4. Applications

Abstract
Motion detection is of widespread interest due to a large number of applications in various disciplines such as, for instance, video surveillance [14], remote sensing [58], medical diagnosis and treatment [911], civil infrastructure [1214], underwater sensing [1517], objective measures of intervention effectiveness in team sports [18], and driver assistance system [1921], to name some. Among the diversity, some real applications have been implemented to evaluate approach’s performance. These real applications as well as their performance results are presented and discussed through this chapter.
Ester Martínez-Martín, Ángel P. del Pobil

Chapter 5. Computer Vision Concepts

Abstract
In this chapter, we will introduce some of the concepts and techniques of Computer Vision that are used throughout this book. This description does not represent an exhaustive introduction into the Computer Vision field, but it is addressed to clarify those terms to a reader unfamiliar with them.
Ester Martínez-Martín, Ángel P. del Pobil
Weitere Informationen

Premium Partner

    Bildnachweise