抄録
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 propose a novel method of discriminating moving objects, such as a person or a vehicle. We use only a narrow and tall area of the video called the Strip Frame Image for detecting 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 stored reference patterns in the database for all possible classes (person, 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. We test both a moving object speed independent and a speed based method for constructing patterns for the passing objects. The results show that the relatively simple method of pattern classification by DP matching can be successfully applied for classifying graphic objects of a certain degree of complexity. Finally, non-homogeneity of people's patterns and their subsequent frequent misclassification is addressed by not producing reference patterns for people, and differentiating them from correctly classified bicycles by the DP distance to the first candidate.
