19-09-2014, 11:09 AM
An Advanced Video Surveillance for Theft Detection
[attachment=68158]
Abstract:
In 21st Century terrorism, Naxalism, Robbery has increased to a large extent. Today, Video Surveillance is having a lot of significance. Video Surveillance is used where higher security is required such as banks, Jewellery shops, Sensitive zones, for traffic control etc. Now everywhere CCTV cameras are fixed for the monitoring but they are passive.The camera only records the video stream but never alert user when theft is carried out. The purpose of this paper is realtime theft detection and alert to owner and police station, So that act of burglary or theft can be prevented. This technique uses camera connected to PC hence it reduces cost to a large extent and also can be implemented anywhere. Owner will get informed by voice call . A detailed video clip of theft detection can be recorded and stored on the PC so that it can be used as evidence against thieves.
Keywords: Video Surveillance, Real Time Monitoring, Canny Edge Detection, White Pixel Count, Attention Commands, Alert Generation .
I. INTRODUCTION
For real time theft detection people generally use sensors, electronic devices . The cost of such system is very high and not affordable to all shopkeepers and small scale industries. Basically Security is one of the important aspect. Extreme care should taken for protecting our assets. Here we will see one example. When owner closes his office/shop and returns home and by chance if any thief enters his premises then CCTV cameras will capture the videos but cannot guarantee to convey message to owner. Now a days everyone uses CCTV camera in their workplace to monitor the things around. It is practically not possible for anyone to continuously observe the video and detect the theft, another case, if we just record the video, then abnormal things like intrusion will not be detected. The main drawback of all systems is that they are passive systems. There is need to develop an active technique so that it will work in real time. It will not only record the abnormal activities but also raise alert to the owner so that owner can prevent the theft at the same time. This increases the stability and reliability of a system.
We are developing a system which overcomes the all drawbacks of existing system.The proposed system is efficient and helpful to the owner as well as police for preventing loss as well as catching the thief. In our system we have used a camera for monitoring purpose, which is connected to computer. When we will start the system the area under surveillance of camera can be monitored. Frames will be generated from the video and frames will be selected at the interval of time the current frame will be selected and white pixel of the frame will be calculated using canny edge algorithm. Then same procedure will be followed to next frame. Now previous frame will be compared to current frame then no. of white pixel difference is checked. If there is considerable white pixel difference then system will inform to the owner and police .
This paper organized as literature survey in section 2, overview of the proposed work in section 3, Canny edge detection 4,set theory of a system 5 and section 6 concludes the paper.
D. Double thresholding
The edge-pixels remaining after the non-maximum suppression step are marked with their strength pixel-by-pixel. Many of these will probably be true edges in the image, but some may be caused by noise or color variations for instance due to rough surfaces. The simplest way to discern between these would be to use a threshold, so that only edges stronger that a certain value would be preserved. The Canny edge detection algorithm uses double thresholding. Edge pixels stronger than the high threshold are marked as strong; edge pixels weaker than the low threshold are suppressed and edge pixels between the two thresholds are marked as weak. The effect on the test image with thresholds of 20 and 80.
E. Edge tracking by hysteresis
Strong edges are interpreted as certain edges, and can immediately be included in the final edge image. Weak edges are included if and only if they are connected to strong edges. The logic is of course that noise and other small variations are unlikely to result in a strong edge (with proper adjustment of the threshold levels). Thus strong edges will (almost) only be due to true edges in the original image. The weak edges can either be due to true edges or noise/color variations. The latter type will probably be distributed independently of edges on the entire image, and thus only a small amount will be located adjacent to strong edges. Weak edges due to true edges are much more likely to be connected directly to strong edges.
Edge tracking can be implemented by BLOB-analysis (Binary Large OBject). The edge pixels are divided into connected BLOB’s using 8-connected neighbourhood. BLOB’s containing at least one strong edge pixel are then preserved, while other BLOB’s are suppressed.
VI. CONCLUSION
This system will help to increase in security of users property. This system is affordable to everyone and is suitable for any real tine applications. This system is a good substitute for costlier sensor systems. Real time theft detection is a key feature of this system hence it will definitely help the user as well as police to prevent theft and save the valuable assets.
[attachment=68158]
Abstract:
In 21st Century terrorism, Naxalism, Robbery has increased to a large extent. Today, Video Surveillance is having a lot of significance. Video Surveillance is used where higher security is required such as banks, Jewellery shops, Sensitive zones, for traffic control etc. Now everywhere CCTV cameras are fixed for the monitoring but they are passive.The camera only records the video stream but never alert user when theft is carried out. The purpose of this paper is realtime theft detection and alert to owner and police station, So that act of burglary or theft can be prevented. This technique uses camera connected to PC hence it reduces cost to a large extent and also can be implemented anywhere. Owner will get informed by voice call . A detailed video clip of theft detection can be recorded and stored on the PC so that it can be used as evidence against thieves.
Keywords: Video Surveillance, Real Time Monitoring, Canny Edge Detection, White Pixel Count, Attention Commands, Alert Generation .
I. INTRODUCTION
For real time theft detection people generally use sensors, electronic devices . The cost of such system is very high and not affordable to all shopkeepers and small scale industries. Basically Security is one of the important aspect. Extreme care should taken for protecting our assets. Here we will see one example. When owner closes his office/shop and returns home and by chance if any thief enters his premises then CCTV cameras will capture the videos but cannot guarantee to convey message to owner. Now a days everyone uses CCTV camera in their workplace to monitor the things around. It is practically not possible for anyone to continuously observe the video and detect the theft, another case, if we just record the video, then abnormal things like intrusion will not be detected. The main drawback of all systems is that they are passive systems. There is need to develop an active technique so that it will work in real time. It will not only record the abnormal activities but also raise alert to the owner so that owner can prevent the theft at the same time. This increases the stability and reliability of a system.
We are developing a system which overcomes the all drawbacks of existing system.The proposed system is efficient and helpful to the owner as well as police for preventing loss as well as catching the thief. In our system we have used a camera for monitoring purpose, which is connected to computer. When we will start the system the area under surveillance of camera can be monitored. Frames will be generated from the video and frames will be selected at the interval of time the current frame will be selected and white pixel of the frame will be calculated using canny edge algorithm. Then same procedure will be followed to next frame. Now previous frame will be compared to current frame then no. of white pixel difference is checked. If there is considerable white pixel difference then system will inform to the owner and police .
This paper organized as literature survey in section 2, overview of the proposed work in section 3, Canny edge detection 4,set theory of a system 5 and section 6 concludes the paper.
D. Double thresholding
The edge-pixels remaining after the non-maximum suppression step are marked with their strength pixel-by-pixel. Many of these will probably be true edges in the image, but some may be caused by noise or color variations for instance due to rough surfaces. The simplest way to discern between these would be to use a threshold, so that only edges stronger that a certain value would be preserved. The Canny edge detection algorithm uses double thresholding. Edge pixels stronger than the high threshold are marked as strong; edge pixels weaker than the low threshold are suppressed and edge pixels between the two thresholds are marked as weak. The effect on the test image with thresholds of 20 and 80.
E. Edge tracking by hysteresis
Strong edges are interpreted as certain edges, and can immediately be included in the final edge image. Weak edges are included if and only if they are connected to strong edges. The logic is of course that noise and other small variations are unlikely to result in a strong edge (with proper adjustment of the threshold levels). Thus strong edges will (almost) only be due to true edges in the original image. The weak edges can either be due to true edges or noise/color variations. The latter type will probably be distributed independently of edges on the entire image, and thus only a small amount will be located adjacent to strong edges. Weak edges due to true edges are much more likely to be connected directly to strong edges.
Edge tracking can be implemented by BLOB-analysis (Binary Large OBject). The edge pixels are divided into connected BLOB’s using 8-connected neighbourhood. BLOB’s containing at least one strong edge pixel are then preserved, while other BLOB’s are suppressed.
VI. CONCLUSION
This system will help to increase in security of users property. This system is affordable to everyone and is suitable for any real tine applications. This system is a good substitute for costlier sensor systems. Real time theft detection is a key feature of this system hence it will definitely help the user as well as police to prevent theft and save the valuable assets.