Visual saliency detection: a Kalman filter based approach

TL;DR

This paper introduces a Kalman filter-based model for static image saliency detection, leveraging the idea that salient regions are visually surprising compared to expectations, and demonstrates its superior performance on benchmark datasets.

Contribution

The paper presents a novel Kalman filter aided saliency detection model that effectively predicts salient regions in static images and can be extended to space-time saliency.

Findings

Outperforms existing saliency models on benchmark datasets

Saliency regions are identified as visually surprising compared to expectations

Model can be extended for space-time saliency prediction

Abstract

In this paper we propose a Kalman filter aided saliency detection model which is based on the conjecture that salient regions are considerably different from our "visual expectation" or they are "visually surprising" in nature. In this work, we have structured our model with an immediate objective to predict saliency in static images. However, the proposed model can be easily extended for space-time saliency prediction. Our approach was evaluated using two publicly available benchmark data sets and results have been compared with other existing saliency models. The results clearly illustrate the superior performance of the proposed model over other approaches.