Object Tracking Automated Camera
No Thumbnail Available
Date
2013
Journal Title
Journal ISSN
Volume Title
Publisher
Uva Wellassa University of Sri Lanka
Abstract
Because of the advance in surveillance systems, object tracking has been an active research
topic in the computer vision community over the last two decades as it is an essential
prerequisite for analyzing and understanding video data. Tracking an object is to get its spatial-
tempo information by estimating its trajectory in the image plane as it moves around a scene,
which in turn helps to study and predict its future behavior. Enhancement of object tracking
systems is building up a pan tilt moving cameras based on the movements of the detected object
by combining the object tracking and computer vision technologies with microcontrollers.
These systems are capable of continuing the tracking even though the object runs away from the
boundaries of the normal still camera. Therefore, this research project was carried out to
develop an object tracking Pan Tilt moving automatic camera with a low cost and better
performance.
Methodology
This proposed system mainly consists of two modules such as a hardware module and a
Software module. The Software module comprises of image processing algorithms and tracking
algorithms. The hardware module consists with a Pan Tilt moving camera that was used to take
video inputs and a Microcontroller to pass the control instructions to the Servo motors attached
to the Pan Tilt mechanism.
In this proposed system the video from the camera was processed using Digital Image
Processing (Kirillov, 2008). The video was read as frames (Kirillov, 2009)and frame was a still
image. The user was allowed to click on any object in this image using a mouse pointer. Then
the color of the selected point was read as RGB values. The colors of the image were filtered
out according to the selected color. Using a Color filtering algorithm it was able to filter the
colors of the selected color and filled the rest of the image with black color.
After the above process, developed algorithm was able to find the blobs with same color in the
image and saved each and every blob in an array sorted by the size of the blobs. Then the largest
blob was selected and drawn a rectangle around largest blob to clearly point out the selected
object, and calculated the X and Y coordinates of the center of the rectangle with respect to the
display pane. The above scenario was repeated for every frame. Thus any object in the frame
can be tracked by its color, using the above algorithm.
Universal Serial Bus (USB) communication was very important to read and write data to the
external hardware. First the USB port which was used to communicated with the implemented
hardware and the Software had to be configured. Once the baud rate was specified in the
system, the serial port started to perform the communication. The Microcontroller attached to
the serial port was programmed to read the data from the USB port, and the program run in a
Computer was able to read the data from the Microcontroller via USB.
In this proposed system, two servo motors were used and initially they were set to 90 degrees.
Then in tracking algorithm two variables X and Y were declared and they were used to hold the
values which were going to pass to the Microcontroller. Above X and Y variables also set to 90
degrees initially. Then calculated the display pane’s center X and Y coordinates. Subtracted the
display pane’s center X coordinates from the largest blob’s center X coordinate, if the value was
a negative value, and then decreased the variable value which hold the X value and wrote it to
the serial port. If the subtract value was positive increased the variable value which hold the X
value and wrote it to the serial port. If it equal to 0 did nothing. With parallel to the above
process, subtracted the display pane’s center Y coordinates from the largest blob’s center Y
coordinate, if the value was negative value, and then increased the variable value which hold the
Y value and wrote it to the serial port. If the subtract value was positive decreased the variable
value which hold the Y value and wrote it to the serial port. If it equal to 0 did nothing. These
two parallel processes executed until the program stopped inside an infinite loop. The
Microcontroller was programmed to accept those two values and it was programmed to identify
the X and Y values uniquely and pass correct values to relevant servo motors. This algorithm
and the programmed microcontroller kept the tracked object in the center of the display pane
always by rotating the camera towards the object.
Description
Keywords
Computer Science, Science and Technology, Technology, Automation, System, Software Developing