In this thesis we present an operational computer video system for moving
object detection and tracking . The system captures monocular frames of
background as well as moving object and to detect tracking and identifies
those moving objects. An approach to statistically modeling of moving object
developed using Background Subtraction Algorithms. There are many
methods proposed for Background Subtraction algorithm in past years.
Background subtraction algorithm is widely used for real time moving object
detection in video surveillance system. In this paper we have studied and
implemented different types of methods used for segmentation in Background
subtraction algorithm with static camera. This paper gives good understanding
about procedure to obtain foreground using existing common methods of
Background Subtraction, their complexity, utility and also provide basics which
will useful to improve performance in the future . First, we have explained the
basic steps and procedure used in vision based moving object detection.
Then, we have debriefed the common methods of background subtraction like
Simple method, statistical methods like Mean and Median filter, Frame
Differencing and W4 System method , Running Gaussian Average and
Gaussian Mixture Model and last is Eigenbackground Model. After that we
have implemented all the above techniques on MATLAB software and show
some experimental results for the same and compare them in terms of speed
and complexity criteria. Also we have improved one of the GMM algorithm by
combining it with optical flow method, which is also good method to detect
moving elements.
Table of Contents
1. INTRODUCTION
1.1 OBJECTIVE
1.2 APPLICATIONS
1.3 LITERATURE SURVEY
1.4 ORGANIZATION OF THE REPORT
2. BLOCK DIAGRAM AND CHALLANGES
2.1 GENERAL STEPS FOR OBJECT DETECTION
2.2 CHALLENGES
3. STUDY OF DIFFERENT BACKGROUND SUBTRACTION ALGORITHMS
3.1 SIMPLE BACKGROUND SUBTRACTION METHOD
3.2 MEAN FILTERING METHOD
3.3 MEDIAN FILTERING METHOD
3.4 W4 SYSTEM METHOD
3.5 FRAME DIFFERENCING METHOD
3.6 RUNNING GAUSSIAN AVERAGE MODEL
3.7 GAUSSIAN MIXTURE MODEL
3.8 EIGENBACKGROUND
4. COMPARISION OF BACKGROUND SUBTRACTION ALGORITHMS
5. OPTICAL FLOW
5.1 THE SMOOTHNESS CONSTRAINT
5.2 DETERMINING OPTICAL FLOW USING HORN - SCHUNCK
5.3 ESTIMATION OF CLASSICAL PARTIAL DERIVATIVES
5.4 EXPERIMENT RESULTS
6. COMBINE GMM & OPTICAL FLOW
7. SHADOW DETECTION
7.1 HSV/HSI MODE
7.2 SHADOW DETECTION
8. CONCLUSION AND FUTURE WORK
Research Objectives and Core Themes
The primary objective of this dissertation is to present an operational computer video system designed for real-time moving object detection and tracking. The research focuses on evaluating, implementing, and improving various background subtraction algorithms to address challenges such as illumination changes, noise, and the requirement for high-accuracy tracking in surveillance applications.
- Systematic review and performance evaluation of common background subtraction algorithms.
- Implementation of motion detection techniques on the MATLAB software platform.
- Comparative analysis of algorithms based on speed, memory usage, and detection accuracy.
- Development of a combined GMM and Optical Flow approach to improve detection robustness against lighting variations.
- Application of HSV color space modeling for effective shadow detection and removal.
Book Excerpt
3.1 Simple Background Subtraction Method
In basic method for Background subtraction, the static background image without object is taken first as a reference image. After that the current image of the video is subtracted pixel by pixel from the background image and resultant image is converted into binary image using threshold value. This binary image is worked as a foreground mask. For conversion in binary image threshold is required. From [1] we can write |It(x,y) - B(x,y)| > T (1)
Where, It(x,y) is pixel intensity of frame at time t, B(x,y) is mean intensity on background pixel and T is threshold. When difference reaches beyond threshold the pixel categorize as a foreground pixel.
So the effectiveness of the object detection is depends on the threshold value. Although this method is very fast, it is very sensitive to illumination changes and noise.
Summary of Chapters
1. INTRODUCTION: This chapter introduces the necessity of motion detection in surveillance and outlines the organization of the research report.
2. BLOCK DIAGRAM AND CHALLANGES: This chapter details the general workflow of object detection systems and identifies critical challenges such as illumination changes and moving shadows.
3. STUDY OF DIFFERENT BACKGROUND SUBTRACTION ALGORITHMS: This chapter discusses various segmentation methods, ranging from Simple Background Subtraction to more complex techniques like GMM and Eigenbackground.
4. COMPARISION OF BACKGROUND SUBTRACTION ALGORITHMS: This chapter provides a quantitative comparative analysis of the studied algorithms in terms of computational speed and memory requirements.
5. OPTICAL FLOW: This chapter explains the theoretical basis of optical flow methods and their application in motion estimation using the Horn-Schunck algorithm.
6. COMBINE GMM & OPTICAL FLOW: This chapter introduces a hybrid approach that integrates GMM and Optical Flow to mitigate the negative effects of sudden illumination changes.
7. SHADOW DETECTION: This chapter explores the use of HSV color space to identify and suppress shadows that otherwise cause false detections.
8. CONCLUSION AND FUTURE WORK: This chapter summarizes the experimental findings and suggests future improvements, such as the use of pyramid approaches and handling moving camera scenarios.
Keywords
Background Subtraction, Moving Object Detection, Optical Flow, Gaussian Mixture Model, Surveillance Systems, Image Segmentation, Shadow Detection, MATLAB, Horn-Schunck Algorithm, Principal Component Analysis, Eigenbackground, Motion Tracking, Computer Vision, Thresholding, Illumination Changes
Frequently Asked Questions
What is the primary focus of this dissertation?
The dissertation focuses on the development and evaluation of computer vision systems for real-time moving object detection and tracking using various background subtraction algorithms.
What are the core thematic areas covered in this report?
The core themes include algorithmic performance analysis, comparative studies on computational complexity, motion detection methods (GMM, Optical Flow), and techniques for shadow suppression in surveillance environments.
What is the main research goal?
The goal is to analyze existing moving object detection algorithms and improve upon their limitations, specifically regarding their sensitivity to noise and sudden lighting fluctuations.
Which scientific methods are primarily utilized?
The research utilizes statistical modeling, background subtraction techniques, optical flow estimation based on the Horn-Schunck algorithm, and color-space analysis (HSV) for image processing.
What does the main body of the work cover?
The main body examines several algorithms (Simple BS, Mean/Median Filtering, W4, Frame Differencing, GMM, Eigenbackground), compares their performance metrics, and proposes a combined GMM-Optical Flow method.
Which keywords characterize this research?
The work is characterized by terms such as Background Subtraction, GMM, Optical Flow, Surveillance, and Shadow Detection.
How does the proposed combined approach improve performance?
The combined approach merges the accurate segmentation capabilities of GMM with the motion-robustness of Optical Flow to minimize false detections caused by illumination changes.
What role does the HSV color space play in this study?
HSV modeling is used specifically for shadow detection, as it effectively separates color information from intensity, allowing for the isolation of shadows that are often misidentified as moving objects.
- Arbeit zitieren
- Priyank Shah (Autor:in), 2014, Moving Object Detection Using Background Subtraction Algorithms, München, GRIN Verlag, https://www.grin.com/document/275108
