深度学习及其在目标和行为识别中的新进展  

Deep learning and its new progress in object and behavior recognition

作　　者：郑胤[1] 陈权崎 章毓晋[1] 

机构地区：[1]清华大学电子工程系,北京100084

出　　处：《中国图象图形学报》2014年第2期175-184,共10页Journal of Image and Graphics

基　　金：国家自然科学基金项目(61171118);教育部高等学校博士学科点专项科研基金项目(SRFDP-20110002110057)

摘　　要：目的深度学习是机器学习中的一个新的研究领域。通过深度学习的方法构建深度网络来抽取特征是目前目标和行为识别中得到关注的研究方向。为引起更多计算机视觉领域研究者对深度学习进行探索和讨论,并推动目标和行为识别的研究,对深度学习及其在目标和行为识别中的新进展给予概述。方法首先介绍深度学习领域研究的基本状况、主要概念和原理;然后介绍近期利用深度学习在目标和行为识别应用中的一些新进展。结果阐述了深度学习与神经网络之间的关系,深度学习的优缺点,以及目前深度学习理论需要解决的主要问题。结论该文对拟将深度学习应用于目标和行为识别的研究人员有所帮助。Objective Deep learning is a new research area in machine learning. Currently, extracting features by deep learning for visual object recognition and behavior recognition capture many attentions. To draw more attention from research community about deep learning, and to push forward the research frontier of object and behavior recognition, we give a general progress overview for deep learning and its application to visual object and behavior recognition. Method First, we give a general introduction to deep learning, including the basic situation, main concepts and principle. Then, some new progresses on using deep learning in visual object recognition and behavior recognition are presented. Result A discussion about the differences between deep learning and neural network as well as the advantage and disadvantage of deep learning are given, the main existing problems that should be solved for deep learning theory are pointed. Conclusion This paper should provide some help for the research community on applying the deep learning to the visual object and behavior recog-

关 键 词：深度学习 目标识别 行为识别 计算机视觉 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]