06-01-2016, 04:44 PM
Abstract
When we enter into any new society we are asked to make an entry each time. So the queue is formed sometimes for making entry. Sometimes people are in big hurry that they could not get time to sign in entry book. So for avoiding such kind of problem, when people used to visit their friends, relatives, etc. its time consuming waiting out there and make an entry. For solving such a problem we people come up with an solution which sounds too much costly and difficult to implement but we can implement it once we get specific devices which includes programmable Camera
Survey: Generally outside each and every society or any company building there is a security guard who always stop the people and ask them for their identity. If that person coming for the first time or not the employee of the comapany or not living in the apartment then he has to make entry first then he will be allowed to enter.
Keywords: Image processing, OpenCV library, Programmable Camera, Database, Alert System
Introduction: In today's world time is most important factor in everyone's life. For saving this time we are ready to do anything right from taking notes for reading them further to breaking traffic signals which should be avoided.
Study Area and Data Collection:
Study Area: Study for this problem has been carried out outside the societies(apartments) where security is the indivisible part.
Every vehicle was getting stopped for checking purpose and were getting asked about their identity.
Data Collection:
Average amount of time taken for security check outside the society was about 30 secs. So if we are going to consider 15 vehicles coming every minute then surely some of them really going to be panic and if they are in hurry then it will be a big loverload for them.
OpenCV:
OpenCV (Open Source Computer Version)
OpenCV is released under a BSD license and hence it’s free for both academic and commercial use. It has C++, C, Python and Java interfaces and supports Windows, Linux, Mac OS, iOS and Android. OpenCV was designed for computational efficiency and with a strong focus on real-time applications. Written in optimized C/C++, the library can take advantage of multi-core processing. Enabled with OpenCL, it can take advantage of the hardware acceleration of the underlying heterogeneous compute platform. Adopted all around the world, OpenCV has more than 47 thousand people of user community and estimated number of downloads exceeding 9 million. Usage ranges from interactive art, to mines inspection, stitching maps on the web or through advanced robotics.
Programmable Camera:
With the help of programmable camera we can alert the guards seating inside slight away from the gate. The idea behind using this camera is we will be able to configure according to our needs. Its basic functionality will be like:
1. It will first capture the image of the vehicle coming inside then it will search for specific area in the image where the number plate is resided. This can be accomplished using the template matching feature of the OpenCV library. Once the number is elicited from the image it will get compared with the database where the authorized residents alongwith thier vehicles are registered.
If the entry is not found in the database it will inform to the security person using some alert system. Then the actual security check will be made rather than doing it for every vehicle.
http://news.stanford.edu/pr/98/980422digicam.html
http://www.tigeneral/docs/litabsmultiple...er=spra651
Flow and Implementation:
Template matching for face detection:
This method can be used for searching and finding the location of a template image in a larger image. In OpenCV we do have a function called cv2.matchTemplate() for this purpose.
:Messi Image
Template matching with multiple objects is also possible. It can be done using the method cv2.minMaxLoc().
:Mario Image
http://opencv-python-tutroals.readthedoc...e-matching
Corner detection to determine what kind of vehicle it is:
This feature of OpenCV can be used to determine the vehicle type two wheeler or foru wheeler. Then under four wheeler category we can determine whether its. For this purpose we can make use of FAST(Features from Accelerated Segment Test) algorithm. This algorithm was proposed by Edward Rosten and Tom Drummond in their paper "Machine learning for high-speed corner detection" in 2006.
It is called as any other feature detector in OpenCV. If you want, you can specify the threshold, whether non-maximum suppression to be applied or not, the neighborhood to be used etc.
REF:
1. Edward Rosten and Tom Drummond, “Machine learning for high speed corner detection” in 9th European Conference on Computer Vision, vol. 1, 2006, pp. 430–443.
2. Edward Rosten, Reid Porter, and Tom Drummond, “Faster and better: a machine learning approach to corner detection” in IEEE Trans. Pattern Analysis and Machine Intelligence, 2010, vol 32, pp. 105-119.
http://opencv-python-tutroals.readthedoc....html#fast
Feature matching:
In feature matching, Brute Force matcher is simple to use. It takes the descriptor of one feature in first set and is matched with all other features in second set using some distance calculation. And the closest one is returned.
http://opencv-python-tutroals.readthedoc...ml#matcher
Feature Matching + Homography to find Objects
http://opencv-python-tutroals.readthedoc...homography
Scope:
Conclusion and references:
So in order to reduce waiting time outside the apartment or any big company building we should implement these kind of projects so that there won't any wastage of anybody's important time.
Papers:
Image processing
OpenCV Lib
Pragrammable Camera