Video object detection using inter-frame correlation based background subtraction

In this paper the problem of video object detection under illumination variation is addressed. Many algorithms have been proposed to cope to this situation. But the major draw back in most of them is misclassified object and background area. Thereby object recognition and tracking process fails many a times due to failure of the detection algorithms. In our previous work we have proposed a supervised approach to increase the correct classification of the object and background regions. Although the results obtained were as per expectation but the model parameters estimation; such as the threshold selection process was manually done. In order to make it adaptive to the scene, we have proposed a classification algorithm which takes the histogram of correlation matrix into account and classify the object. The proposed algorithm computes the inter-plane correlation between three consecutive R, G and B planes by using a correlation function. The correlation matrix obtained is then used to construct a segmented image which gives a rough estimate of the object. The segmentation of the correlation plane is done by a threshold. This threshold selection is made adaptive to the video sequence considered. This segmented plane along with the moving edge image is then taken into consideration to improvise the correct classification of the moving object in the video. It is observed that the proposed algorithm yields quite manageable results in terms of correct classification.