5.1 Simulation
5.1 Simulation
5.1.1 System description
To conduct the experiment, as a data set we used different videos from outdoor places which comprise of both normal and abnormal motions. The experimental results of one of the videos have been presented in figure 5.1-5.8. The video consists of 100 frames where both normal and abnormal motion exists.
Figure: 5.8.1 System block diagram
5.2 Results
Figure: 5.9.1 Normal motion of the Truck
Figure: 5.2.2 Abnormal motion of the Truck
Figure: 5.2.3 Abnormal motion of the Truck
Figure: 5.2.4 Detect normal motion
Figure: 5.2.5 Human detect abnormal motion
Figure: 5.2.6 Detect normal motion
Figure: 5.2.7 Detect abnormal object motion
Chapter-6
Conclusion
Conclusion
Various existing normal
and abnormal motion detection algorithms available to video surveillance systems are studied. Other than in most of the algorithm that does not completely detect the moving object because it causes some shadow and it requires large memory to store the video. The studies proved that the initial object mask problem are responsible for shadow present in the detecting abnormal moving object it will lead to degrade the accuracy of the system whereas the noisy region is dominant part of accuracy degradation. In this paper, abnormal motion detection for video surveillance system. Thus motion based change detection in .avi video format was completed and successfully implemented. The proposed algorithm extracted the background from the all frames of video and detected the foreground effectively. This algorithm also dynamically updating the background frame by frame. Finally this algorithm works for On-line (Real time) and Off-line video processing and its computational complexity is low.
5.1.1 System description
To conduct the experiment, as a data set we used different videos from outdoor places which comprise of both normal and abnormal motions. The experimental results of one of the videos have been presented in figure 5.1-5.8. The video consists of 100 frames where both normal and abnormal motion exists.
Figure: 5.8.1 System block diagram
5.2 Results
Figure: 5.9.1 Normal motion of the Truck
Figure: 5.2.2 Abnormal motion of the Truck
Figure: 5.2.3 Abnormal motion of the Truck
Figure: 5.2.4 Detect normal motion
Figure: 5.2.5 Human detect abnormal motion
Figure: 5.2.6 Detect normal motion
Figure: 5.2.7 Detect abnormal object motion
Chapter-6
Conclusion
Conclusion
Various existing normal
and abnormal motion detection algorithms available to video surveillance systems are studied. Other than in most of the algorithm that does not completely detect the moving object because it causes some shadow and it requires large memory to store the video. The studies proved that the initial object mask problem are responsible for shadow present in the detecting abnormal moving object it will lead to degrade the accuracy of the system whereas the noisy region is dominant part of accuracy degradation. In this paper, abnormal motion detection for video surveillance system. Thus motion based change detection in .avi video format was completed and successfully implemented. The proposed algorithm extracted the background from the all frames of video and detected the foreground effectively. This algorithm also dynamically updating the background frame by frame. Finally this algorithm works for On-line (Real time) and Off-line video processing and its computational complexity is low.