Issue |
JNWPU
Volume 42, Number 6, December 2024
|
|
---|---|---|
Page(s) | 1135 - 1143 | |
DOI | https://doi.org/10.1051/jnwpu/20244261135 | |
Published online | 03 February 2025 |
RGB-D salient object detection based on BC2 FNet network
基于BC2FNet 网络的RGB-D显著性目标检测 network
1
School of Physics and Electrical Engineering, Weinan Normal University, Weinan 714099, China
2
Engineering Research Center of X-ray Imaging and Detection, University of Shaanxi Province, Weinan 714099, China
3
School of Automation, Northwestern Polytechnical University, Xi'an 710072, China
Received:
11
October
2023
In the face of complex scene images, the introduction of depth information can greatly improve the performance of salient object detection. However, up-sampling and down-sampling operations in neural networks maybe blur the boundaries of objects in the saliency map, thereby reducing the performance of salient object detection. Aiming at this problem, a boundary-driven cross-modal and cross-layer fusion network (BC2FNet) for RGB-D salient object detection is proposed in this paper, which preserves the boundary of the object by adding the guidance of boundary information to the cross-modal and cross-layer fusion, respectively. Firstly, a boundary generation module is designed to extract two kinds of boundary information from low-level features of RGB and depth modalities, respectively. Secondly, a boundary-driven feature selection module is designed, which is dedicated to simultaneously focusing on important feature information and preserving boundary details in the process of RGB and depth modality fusion. Finally, a boundary-driven cross-layer fusion module is proposed which simultaneously adds two kinds of boundary information in the process of up-sampling fusion on adjacent layers. By embedding this module into the top-down information fusion flow, the predicted saliency map can contain accurate objects and sharp boundaries. Simulation results on five standard RGB-D data sets show that the proposed model can achieve better performance.
摘要
面对复杂的场景图像, 深度信息的引入可以大大提高显著性目标检测的性能。然而, 神经网络的上采样和下采样操作会模糊显著图中目标的边界, 从而降低显著性目标检测性能。针对此问题, 提出了一种基于边界驱动跨模态跨层融合网络(BC2FNet)的RGB-D显著性目标检测方法。该网络在跨模态和跨层融合中分别加入边界信息引导来保持目标区域。设计了边界生成模型, 分别从RGB和深度模态的低层特征中提取2种边界信息; 设计边界驱动的特征选择模块, 在RGB与深度模态融合过程中, 聚焦重要特征信息并保留边界细节; 提出了一种边界驱动的跨层融合模块, 在相邻层的上采样融合过程中加入2种边界信息。通过将该模块嵌入到自顶向下的信息融合流中, 预测出包含精确目标和清晰边界的显著性图。在5种标准RGB-D数据集上进行仿真实验, 结果证明所提出的模型具有较好的性能。
Key words: salient object detection / boundary-driven / cross-modal fusion / cross-layer fusion
关键字 : 显著性目标检测 / 边界驱动 / 跨模态融合 / 跨层融合
© 2024 Journal of Northwestern Polytechnical University. All rights reserved.
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.