Density based Image Background Removal with Relevance Vector Machine

Abstract

Image background modeling and removal is a natural technique for object detection in videos. A pixel wise background modeling and removal technique using various gradients is involved in classification. A pixel wise background model is obtained for each feature efficiently and effectively by Kernel Density Approximation method (KDA). The proposed RVM algorithm is more robust to shadow, illumination changes, spatial variations of background comparing with SVM. Background removal is performed in a discriminative way based on Relevance Vector Machines (RVMs). Nearly, the equal classification accuracy as SVM is obtained using RVM based classification, with a significantly smaller Relevance Vector Rate and, therefore, much faster testing time, compared with Support Vector Machine (SVM) based classification. This feature makes the RVM-based Background modeling and removal approach more suitable for Applications that require low convolution and probably real-time classification.