Abstract
The advance of technology makes video acquisition devices better and less costly, thereby increasing the number of applications that can effectively utilize digital video. Compared to still images, video sequences provide more information about how objects and scenarios change over time. However, video needs more space for storage and wider bandwidth for transmission. Hence is raised the topic of video compression. The MPEG 4 compression standard suggests the usage of object planes. If the object planes are segmented correctly and the motion parameters are derived for each object plane accordingly, a better compression ratio can be expected. Therefore, to take full advantage of the MPEG 4 standard, algorithms for tracking objects are needed. It is also obvious that there is great interest in moving object tracking algorithms in the fields of reconnaissance, robot technology, etc. So, we propose an algorithm to track moving objects in video sequences. The algorithm first separates the moving objects from the background in each frame. Then, four sets of variables are computed based on the positions, the sizes, the grayscale distributions and the presence of textures of the objects. A rule-based method is developed to track the objects between frames, based on the values of the variables. Preliminary experimental results show that the algorithm performs well. The tests also show that the algorithm obtains success in indicating new tracks (object starts moving), ceased tracks (object stops moving) and possible collisions (objects move together)

---

Presented By:
Yiwei Wang and John F. Doherty
Department of Electrical Engineering
The Pennsylvania State University
University Park, PA16802,

Robert E. Van Dyck
National Institute of Standards and Technology

---

read full report
http://citeseerx.ist.psu.edu/viewdoc/dow...1&type=pdf

[attachment=5389]

---

This article is presented by:
Anusha.R
Bhagyasree B
Swathi priyanka
Bhargavi S

Real-Time Moving Object Tracking

INTRODUCTION


The use of video is becoming prevalent in many applications such as monitoring of traffic, detection of pedestrians,identification of anomalous behaviour in a parking lot or near an ATM, etc. While a single image provides a snap of scene, the different frames of a video taken over time reprents the dynamics in the scene,making it possible to capture motion in the sequence.
In this project the real time tracking system, which detect an object entering the field of view of a camera and execute tracking of the detected object. In this, we allow the model of the target to vary dynamically during the tracking process so that it can assimilate varatiations of shape and intensities of the target object. The tracking history can then be encoded into state parameters of kalman filter.
A stationary background is taken as reference image. Then every frame is compared with this image. If the number of pixels whose grey-level differs significantly from the reference image, then we can confirm that there is an object entering. This algorithm is Inter-frame differentiation algorithm.

The goal of our design is real time tracking with fairly good accuracy. More over since the algorithm is very efficient, we can process almost every frame in real time, amounting to a processing rate of 30 frames per second. This enables correct detection and tracking of very rapid moving object.

Hardware and software requirements for the project:
Hardware: web cam
Software: Matlab 7.0.4 software

If the concept of tracking real-time moving objects can be developed effectively then it can be used for decreasing the number of crimes happening nowadays. For example if there is a burglar in a shop then the camera can be used to focus him only. Thus if he steals, we can catch him at the moment itself. Same is the case with drivers. If a camera is installed in a vehicle then it will be focusing the driver only. This will prevent him from falling asleep because he will always be cautious that he is being watched.