自动化学报2016，Vol.42Issue(6)：834-847,14.DOI:10.16383/j.aas.2016.c150705
深度学习在视频目标跟踪中的应用进展与展望
Advances on Application of Deep Learning for Video Ob ject Tracking
摘要
Abstract
Video object tracking is an important research topic of computer vision with numerous applications including surveillance, robotics, human-computer interface, etc. The coming of big data era and the rise of deep learning methods have offered new opportunities for the research of tracking. Firstly, we present the general framework for video object tracking research. Then, we introduce new arisen datasets and evaluation methodology. We highlight the application of the rapid-developing deep-learning methods including stacked autoencoder and convolutional neural network on video ob ject tracking. Finally, we have a discussion and provide insights for future.关键词
目标跟踪/视频分析/在线学习/深度学习/大数据Key words
Ob ject tracking/video analysis/online learning/deep learning/big data引用本文复制引用
管皓,薛向阳,安志勇..深度学习在视频目标跟踪中的应用进展与展望[J].自动化学报,2016,42(6):834-847,14.基金项目
国家自然科学基金(61572138),上海市科技创新行动计划项目(15511104402)资助Supported by National Natural Science Foundation of China (61572138) and Science and Technology Commission of Shanghai Municipality (15511104402) （61572138）
