Download presentation
Presentation is loading. Please wait.
Published byAugustus Ryan Modified over 9 years ago
1
We are :- Soma Datta, Pramit Ghosh and Debotosh Bhattacherjee soma.datta@tcs.com, pramitghosh2002@yahoo.co.in, debotosh@indiatimes.com www.academypublisher.com/ijrte/vol02/no03/ijrte02033739.pdf
2
Unclaimed bag Security threats?
3
Answer:- ?
4
There are lots of security cameras inside the campus. So it is very difficult to checks all the images manually. Solution :- it will be helpful if the searching process is automatic.
6
using NTSC format where luminance(Y), hue(I), and saturation(Q)
7
The RGB image and corresponding Gray image
8
Laplacian Filter
9
correlation takes huge time……….. So selected correlation method is used here….
12
Unnecessary points
14
For a 600×800 image the total correlation time is 32.9220 second, where dimension of the mask is 39×49 and For the same input image and mask, 1.3590 second is required to detect the same object using proposed algorithm. 24 times faster !
15
In a campus there may be 100 or more security cameras so the number of images to be processed may exceed 100000. Single pc will take very long time to compute all the images…….. So…………….
16
But this type of processing is required very rarely. So it is not a good practice to deploy large number of computers for this. Better to ask 3 rd party (grid) to do the processing…..
17
The system can be thought as a single instruction multiple data set model where data sets are independent to each other.
18
How grid split and distribute user’s program among the nodes? Is there any standard protocol or guideline for writing c or java code that will run on grid?
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.