RGB‐D salient object detection via deep fusion of semantics and details

Abstract

In this paper, we address RGB-D salient object detection task by jointly leveraging semantics and contour details of salient objects. We propose a novel semantics-and-details complementary fusion network to adaptively integrate cross-model and multilevel features. Specifically, we employ two kinds of fusion modules in our model, which are designed for fusing high-level semantic features and integrating contour detail features of the scene components, respectively. The semantics fusion module aggregates high-level interdependent semantic relationships by a nonlinear weighted summation of small and medium receptive fields. Meanwhile, the details module integrates multi-level contour detail features to leverage expressive details of salient objects. We achieve new state-of-the-art salient object detection results on seven RGB-D datasets, that is, STERE, NJU2000, LFSD, NLPR, SSD, DES, and SIP2019 dataset. Experimental results demonstrate that our method outperforms eleven state-of-the-art salient object detection methods. K E Y W O R D S cross-model and multilevel features, feature fusion and deep fusion, RGB-D, salient object detection

Target Perception and Behavioral Recognition Algorithms Based on Saliency and Feature Extraction

“…𝑠(𝑟 ) = ∑ 𝑤 𝐷 (𝑟 , 𝑟 ) (2) By combining these priors, image processing algorithms can better adapt to complex environments. By combining information such as colour prior, centre prior, low-rank background, and region contrast to highlight saliency, the accuracy and robustness of image processing algorithms can be improved, making them more responsive to various complex scenes and environments [9][10][11].…”

“…(9) The background variance is 𝜎 . (10) The total image variance is 𝜎 . (11) where the grey level of the original image is L. where is the salient class mean: (12) The background mean: (13) That is, the overall mean of the whole image is μ.…”