An Integration of Bottom-up and Top-Down Salient Cues on RGB-D Data: Saliency from Objectness vs. Non-Objectness

TL;DR

This paper proposes a novel RGB-D saliency detection framework that combines bottom-up and top-down cues from space-based and object-based features, leveraging pre-trained CNNs to improve salient object detection.

Contribution

It introduces an integrated approach combining space and object-based salient cues from RGB-D data, utilizing pre-trained CNNs for enhanced top-down saliency extraction.

Findings

Significant improvement in salient object detection accuracy.

Effective integration of color and depth cues.

Outperforms several state-of-the-art models.

Abstract

Bottom-up and top-down visual cues are two types of information that helps the visual saliency models. These salient cues can be from spatial distributions of the features (space-based saliency) or contextual / task-dependent features (object based saliency). Saliency models generally incorporate salient cues either in bottom-up or top-down norm separately. In this work, we combine bottom-up and top-down cues from both space and object based salient features on RGB-D data. In addition, we also investigated the ability of various pre-trained convolutional neural networks for extracting top-down saliency on color images based on the object dependent feature activation. We demonstrate that combining salient features from color and dept through bottom-up and top-down methods gives significant improvement on the salient object detection with space based and object based salient cues. RGB-D saliency integration framework yields promising results compared with the several state-of-the-art-models.