计算机工程与应用 ›› 2020, Vol. 56 ›› Issue (5): 25-33.DOI: 10.3778/j.issn.1002-8331.1912-0176

• 热点与综述 • 上一篇    下一篇

基于深度学习的场景识别方法综述

李新叶,朱婧,麻丽娜   

  1. 1.华北电力大学 电子与通信工程系,河北 保定 071003
    2.华北电力大学 科技学院,河北 保定 071003
  • 出版日期:2020-03-01 发布日期:2020-03-06

Survey of Scene Recognition Methods Based on Deep Learning

LI Xinye, ZHU Jing, MA Lina   

  1. 1.Department of Electronics & Communication Engineering, North China Electric Power University, Baoding, Hebei 071003, China
    2.Science and Technology College, North China Electric Power University, Baoding, Hebei 071003, China
  • Online:2020-03-01 Published:2020-03-06

摘要:

随着深度学习的快速发展,基于深度学习的场景识别方法逐渐取代传统的基于手工特征的场景识别方法,成为未来研究的主要方向。针对基于深度学习的场景识别方法,对基本思想进行了总结,将其大体分为以下四类:深度学习与视觉词袋结合场景识别法、基于显著部分的场景识别法、多层特征融合场景识别法、融合知识表示的场景识别法,分析了各个方法的特点及局限性,并对识别效果进行了比较,最后对未来研究方向进行展望。

关键词: 场景识别, 深度学习, 视觉词袋, 显著目标, 多层特征融合, 语义关系

Abstract:

With the rapid development of deep learning, the scene recognition method based on deep learning gradually replaces the traditional scene recognition method based on manual features, and becomes the main research direction in the future. According to the method of scene recognition based on deep learning, this paper summarizes the basic ideas and divides it into four categories: the method of scene recognition based on deep learning and bag of visual words, the method of scene recognition based on salient part, the method of scene recognition based on multi-level feature fusion and the method of scene recognition based on knowledge representation. The characteristics and limitations of each method are analyzed, and the recognition effect is compared. Finally, the future research direction is prospected.

Key words: scene recognition, deep learning, bag-of-visual-words, salient object, multi-layer feature fusion, semantic relation