30-03-2012, 03:23 PM
video stream data
content.docx (Size: 149.11 KB / Downloads: 31)
INTRODUCTION
1.1 OVERVIEW
Identifying moving objects from a video sequence is a fundamental and
critical task in many computer-vision applications. A common approach is to perform background
subtraction, which identifies moving objects from the portion of a video frame that differs
significantly from a background model. There are many challenges in developing a good
background subtraction algorithm. First, it must be robust against changes in illumination.
Second, it should avoid detecting non-stationary background objects such as moving leaves, rain,
snow, and shadows cast by moving objects.
OBJECTIVE
• Find the foreground objects in live video when background scene textures change over time.
• Get the high robustness for nonstationarity region
• Implement the global algorithm for object Vs background
• Implement the algorithm on online (real time) videos
• Make the Computationally efficient algorithm for real time videos
1.3 LITERATURE SURVEY
1.Li Cheng, Member, IEEE, Minglun Gong, Member, IEEE, Dale Schuurmans, and Terry Caelli,
Fellow, IEEE, Real-Time Discriminative Background Subtraction. IEEE TRANSACTIONS ON
IMAGE PROCESSING, VOL. 20, NO. 5, MAY 2011
This paper examine the problem of segmenting foreground objects in live video when background
scene textures change over time. In particular, we formulate background subtraction as
minimizing a penalized instantaneous risk functional— yielding a local online discriminative
algorithm that can quickly adapt to temporal changes.
Input video
The video which is going to be processed in order to detect moving object is given as the input.
2.3. Frame separation
Frame separation is the foremost step in motion detection. Actually the input is given to
the entire network in the form of a video. Next the frames are extracted from the input video and
converted to images. This process includes store the input video (avi file), fix the information
about the no. of frames, width and height of the frame, image quality etc.
Learning with kernels
Background subtraction is generally based on a static background hypothesis which is
often not applicable in real environments. With indoor scenes, reflections or animated images on
screens lead to background changes. In a same way, due to wind, rain or illumination changes
brought by weather, static backgrounds methods have difficulties with outdoor scenes.