Video object processing is a challenging and highly important area of research in today’s world. There are various research applications which seek the attention of researchers. Among those applications video object tracking and action recognition is interesting as well as diversified.Thus, it seeks attention of researchers, institutions and commercial companies. Our motivation of studying this problem is to create a visual surveillance system with real-time moving object detection, classification, tracking and data insertion on that path. The system handles all the above methods, with few conditions imposed, except activity recognition which will likely to be the future step of this work.
Whole work is explained in figure 4.1 where block diagram shows the extraction of feature from the input embedding video.
As video is the collection of images which is called as frame. Here these collections of images are display in so fast sequence that human eyes could not judge that it actually see one image at a time. As contents of the consecutive frames are mostly same but change in object position is new information of the frame. So reading of video means conversion of video in sequence of frames of RGB format.
Original Video: As shown in block diagram first block will read original video. This reading means covert that video into collection of sequential frames. Now all frames are in form of two dimensional matrix and complete video is of three dimensional matrix. One dimension for row, second for the column and third for the frames.
|Doc||Complete Project word file document|
|Read me||Complete read me text file|
|Source Code||Complete Code files|