P.Chakik,‖Efficient object detection and Matching using Feature classification on Pattern Recognition‖,20
- F.Dornaika, san Sebastian, Bilbao
- International Conference on Pattern Recognition…
Intelligent video surveillance system has emerged as a very important topic of research in the field of computer vision in the recent years. It is well suited for a broad range of applications such as to monitor activities at traffic intersections for detecting congestions, and then predict the traffic flow which assists in regulating traffic. Manually reviewing the large amount of data they generate is often impractical. Moving object classification in the field of video surveillance is a key component of smart surveillance software. In this paper, we have proposed robust methodology and algorithms adopted for people and object classification in automated surveillance systems. Object motion can be detected using background subtraction model. The background subtraction and image segmentation based on morphological transformation for tracking and object classification on highways is proposed. This algorithm uses erosion followed by dilation on various frames. Proposed algorithm segments the image by preserving important edges which improves the adaptive background mixture model and makes the system learn faster and more accurately, as well as adapt effectively to changing environments. A probabilistic algorithm for object identification and visual tracking using twin comparison method that incorporates height width based classification method and robust SVM classifier with histogram oriented gradients is utilized for identifying human and vehicles. The experimental results demonstrate the effectiveness of the proposed approach in classifying human and other objects.