| 本文已被：浏览 4397次 下载 8898次 |
码上扫一扫！ |
|
|
| 深度学习时代下的RGB-D显著性目标检测研究进展 |
|
丛润民1,2, 张晨1,2, 徐迈3, 刘鸿羽1,2, 赵耀1,2
|
|
1.北京交通大学 信息科学研究所, 北京 100044;2.现代信息科学与网络技术北京市重点实验室, 北京 100044;3.北京航空航天大学 电子信息工程学院, 北京 100191
|
|
| 摘要: |
| 受人类的视觉注意力机制启发, 显著性目标检测任务旨在定位给定场景中最吸引人注意的目标或区域. 近年来, 随着深度相机的发展和普及, 深度图像已经被成功应用于各类计算机视觉任务, 这也为显著性目标检测技术提供了新思路. 通过引入深度图像, 不仅能使计算机更加全面地模拟人类视觉系统, 而且深度图像所提供的结构、位置等补充信息也可以为低对比度、复杂背景等困难场景的检测提供新的解决方案. 鉴于深度学习时代下RGB-D显著目标检测任务发展迅速, 旨在从该任务关键问题的解决方案出发, 对现有相关研究成果进行归纳、总结和梳理, 并在常用RGB-D SOD数据集上进行不同方法的定量分析和定性比较. 最后, 对该领域面临的挑战及未来的发展趋势进行总结与展望. |
| 关键词: 显著性目标检测 RGB-D图像 跨模态信息交互 深度质量感知 |
| DOI：10.13328/j.cnki.jos.006700 |
| 分类号: |
| 基金项目:中央高校基本科研业务费专项资金(2022JBMC002); 北京市自然科学基金(4222013, JQ20020); 科技创新2030——“新一代人工智能”重大项目(2021ZD0112100); 北京市科技新星计划(Z201100006820016);国家自然科学基金(62002014, U1936212, 62120106009, 61922009, 61876013, 62050175); 中国科协青年人才托举工程(2020QNRC001); 北京市科协青年人才托举工程 |
|
| Research Progress of RGB-D Salient Object Detection in Deep Learning Era |
|
CONG Run-Min1,2, ZHANG Chen1,2, XU Mai3, LIU Hong-Yu1,2, ZHAO Yao1,2
|
|
1.Institute of Information Science, Beijing Jiaotong University, Beijing 100044, China;2.Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing 100044, China;3.School of Electronic and Information Engineering, Beihang University, Beijing 100191, China
|
| Abstract: |
| Inspired by the human visual attention mechanism, salient object detection (SOD) aims to detect the most attractive and interesting object or region in a given scene. In recent years, with the development and popularization of depth cameras, depth map has been successfully applied to various computer vision tasks, which also provides new ideas for the salient object detection task at the same time. The introduction of depth map not only enables the computer to simulate the human visual system more comprehensively, but also provides new solutions for the detection of some difficult scenes, such as low contrast and complex backgrounds by utilizing the structure information and location information of the depth map. In view of the rapid development of RGB-D SOD task in the era of deep learning, this studyaims to sort out and summarize the existing related research outputs from the perspective of key scientific problem solutions, and conduct the quantitative analysis and qualitative comparison of different methods on the commonly used RGB-D SOD datasets. Finally, the challenges and prospects are summarized for the future development trends. |
| Key words: salient object detection RGB-D images cross-modality information interaction depth quality perception |
