Affiliation:
1. School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China
2. Chengdu Union Big Data Technology Incorporation, Chengdu 610041, China
Abstract
The human visual system can rapidly focus on prominent objects in complex scenes, significantly enhancing information processing efficiency. Salient object detection (SOD) mimics this biological ability, aiming to identify and segment the most prominent regions or objects in images or videos. This reduces the amount of data needed to process while enhancing the accuracy and efficiency of information extraction. In recent years, SOD has made significant progress in many areas such as deep learning, multi-modal fusion, and attention mechanisms. Additionally, it has expanded in real-time detection, weakly supervised learning, and cross-domain applications. Depth images can provide three-dimensional structural information of a scene, aiding in a more accurate understanding of object shapes and distances. In SOD tasks, depth images enhance detection accuracy and robustness by providing additional geometric information. This additional information is particularly crucial in complex scenes and occlusion situations. This survey reviews the substantial advancements in the field of RGB-Depth SOD, with a focus on the critical roles played by attention mechanisms and cross-modal fusion methods. It summarizes the existing literature, provides a brief overview of mainstream datasets and evaluation metrics, and quantitatively compares the discussed models.
Funder
Key Research and Development Project of Sichuan
Major Program of National Natural Science Foundation of China
Reference106 articles.
1. Learning to detect a salient object;Liu;IEEE Trans. Pattern Anal. Mach. Intell.,2010
2. H-DenseUNet: Hybrid densely connected UNet for liver and tumor segmentation from CT volumes;Li;IEEE Trans. Med. Imaging,2018
3. Zhang, L., Gonzalez-Garcia, A., Weijer, J.V.D., Danelljan, M., and Khan, F.S. (2019, January 27–28). Learning the model update for siamese trackers. Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea.
4. Global contrast based salient region detection;Cheng;IEEE Trans. Pattern Anal. Mach. Intell.,2014
5. A model of saliency-based visual attention for rapid scene analysis;Itti;IEEE Trans. Pattern Anal. Mach. Intell.,1998