[attachment=15442]
ABSTRACT
This project deals with the tracking and following of single object in a sequence of frames and its velocity determination. Algorithms are developed for improving the image quality, segmentation, feature extraction and for determining the velocity.
Segmentation is performed to detect the object after reducing the noise from that scene. The object is tracked by plotting a rectangular bounding box around it in each frame. The velocity of the object is determined by calculating the distance that the object moved in a sequence of frames with respect to the frame rate that the video is recorded. The algorithms developed can also be used for other applications (real time, object classification, etc.).
CHAPTER 1
INTRODUCTION
1.1 BACKGROUND
Even if we have not been able to teach a computer to process visual input in a complex sense, there is quite much a computer can do when it comes to following movement and performing easier recognitions. One of the key features in a computer vision system is for the computer
to extract interesting areas (foreground). Research on this has mainly two approaches. The first group uses advanced algorithms for pattern recognition to extract the foreground. Often these methods take little use of temporal redundancy, and are slow because of the large amount of computations needed. The second approach is different, often using pixel by pixel computations and only a few computations per pixel. In general the latter methods are fast
and may be implemented in real-time applications. The drawback of these methods is that they are, due to the lack of complexity in the algorithms, sensitive to noise and often need a static environment to be able to function.
1.2 OBJECTIVES
In the recent times number of theoretical and/or simulation studies were done on the topic of object-tracking. While these studies are useful, they are too general and provide little guidance for the actual deployment of networks for real-life tracking of an enemy. This thesis focuses on developing an object-tracking application and prescribes network configurations that work well with our algorithms. We implement our software using MATLAB software technology. The major issues addressed in this project are the evaluation and efficient use of a wired tracking network product with no changes, in a real-world application, and efficient ways to algorithmically analyze the collected raw data from the specific wired tracking networks product. it also provides be a great opportunity to explore the new area of security and surveillance.
1.3 MOTIVATION
The motivation behind this project is to develop software for tracking, the major application
in security, surveillance and vision analysis. The developed software must be capable
of tracking any single object moving in the frame and to implement on a hardware which
is capable of on board calculations with high performance and low power consumption.
This system might be useful for extending in real-time surveillance or object classification.
1.4 GOAL
Goal of this project is to develop an algorithm for tracking of an object and determining the
velocity of moving object in sequence of frames. All the evaluation has to be performed on
MATLAB/SIMULINK. It has features like internal memory and external memory on board to store instructions and doing evaluation on board. It has special functions for handling graphics up to ten-times faster than others. Algorithms can be extended for real time applications.
1.5 OUTLINE OF THE PROJECT
The implementation of object tracking and its velocity determination is explained step by step in this report. In chapter 2, few approaches are implemented in real-time for object tracking and velocity determination are explained. In chapter 3, algorithms that are developed to accomplish this project are explained. In chapter 4, implementation part which includes the logical approach of tracking done for the project is described. In chapter 5, evaluation part describes the interface between the hardware and workstation, converting the video into images and loading the images. In chapter 6, results are visualized and finally concluded.
CHAPTER 2
ANALYSIS
2.1 SINGLE OBJECT TRACKING
Object tracking is the process of locating and following the moving object in sequence of
video frames. Smart cameras are used as input sensors to record the video. The recorded
video may have some noise due to bad weather (light, wind, etc. or due to problems in
sensors). Few algorithms are tested to improve the image quality, to detect moving object,
calculation of distance and velocity of the moving object.
2.2 THE PRE-PROCESSING
The pre-processing performs some steps to improve the image quality. Few algorithms are
explained and filtering is done by using box-filter techniques. Box functionality : If we take an image with X*Y resolution, the pixels starting from 2nd row 2nd column to X-1 row Y-1 column are scanned with all the neighboring elements, they form a shape like box. The pixels from 2nd row 2nd column to X-1 row Y-1 column are taken into consideration since we need to scan all the surrounding elements and for the 1st row ,1st column, last row and last column elements are not possible to scan there surrounding elements as they don't have.
2.3 SEGMENTATION
Segmentation is the process of dividing digital image into multiple regions. Segmentation
shows the objects and boundaries in an image. Each Pixel in the region has some similar
characteristics like colour, intensity, etc. Few methods for segmenting the images are
explained below in chapter 4.
• Histogram Based Segmentation
• Single Gaussian Background Method