A security system for monitoring trespass in an environment with obstacles

We are developing the security system for detecting and notifying a trespass. This system doesn't need security staffs because the trespass is detected by the automatic operation, and it notifies via e-mail. The trespass is detected by the time-varying image processing. In the existing methods of a moving object detection using image recognition technology, they have processed an obtained whole image, and have detected a moving object in a picture. However, when a moving portion in the scene is hidden by some obstacles, the recognition of a moving object is sometimes difficult. In this study, we present a novel method of discriminating moving objects, such as a human or a vehicle. We use only a narrow and tall area of the video called Slit Frame Image to detect moving portions. By using this method, we are able to obtain the patterns of moving objects while avoiding the obstacles in a picture. Then we classify them by DP matching against previously registered reference patterns in the database of all possible classes (human, bicycle, car, and bus). In this paper, we compare several variations of an algorithm used to detect and classify objects passing laterally in front of a security camera. Non-homogeneity of people's patterns and their subsequent frequent misclassification is addressed by not producing reference patterns of people, and differentiating them from correctly classified bicycles by the DP distance to the first candidate.