期刊文献+

基于多层次深度学习网络的行人重识别 被引量:1

MULTI-LEVEL DEEP LEARNING NETWORK FOR PERSON RE-IDENTIFICATIOIN
下载PDF
导出
摘要 提出了多层级特征融合模型,该模型利用深度学习网络提取行人图像的全局特征和局部特征,并将全局和局部特征联合起来,以生成更具辨识度的描述符.在模型中,基于部分的多层级网络用于提取不同网络深度的局部特征,从而将网络底层到高层中提取的局部特征组合起来.全局—局部网络分支则提取网络深层的局部特征和全局特征,用于识别行人.该模型在三个数据集上进行了实验并得到了更好的结果. This paper proposes a Multi-level Feature Fusion(MFF)model,which uses deep learning networks to extract the global and local features of pedestrian images and combines global and local features to generate more discriminative pedestrian descriptors.In MFF model,Part-based Multi-level Net(PMN)is used to extract local features of different depths of network and combine local features extracted from shallow to deep layers of the network,while Global-Local Branches(GLB)extract the local and global features at the highest level of the network to identify pedestrians.This model has been tested on three widely-used datasets and obtained better results.
作者 吴绍君 高玲 李强 Wu Shaojun;Gao Ling;Li Qiang(School of Information Science and Engineering, Shandong Normal University, 250358, Jinan, China)
出处 《山东师范大学学报(自然科学版)》 CAS 2020年第2期208-216,共9页 Journal of Shandong Normal University(Natural Science)
基金 国家自然科学基金资助项目(61672329).
关键词 图像识别 深度学习 行人重识别 image identification deep learning person re-identification
  • 引文网络
  • 相关文献

参考文献3

二级参考文献13

  • 1曾国荪.改善神经网络反向传播算法的训练时间[J].小型微型计算机系统,1996,17(11):69-72. 被引量:2
  • 2陈晓娟,卜乐平,李其修.基于图像处理的明火火灾探测研究[J].海军工程大学学报,2007,19(3):6-11. 被引量:15
  • 3McCllum Andrew. Multi -label text classification with a mixture model trained by EM [ C ]. AAAI' 99 Workshop on Text Learning, 1999:1 -7.
  • 4Wang M,Ni B, Hua X S, et al. Assistive tagging:A survey of multimedia tagging with human -computer joint exploration [ Jl. ACM Computing Surveys, 2012,44(4) :25.
  • 5Kim H J, Choi Y H. A novel echo hiding scheme with backward and forward kernels[ J]. IEEE Trans Circuits Syst, Video Teehno1,2003 ,13 :885 -889.
  • 6Le Cun Y, Bottou L, Bengio Y, et al. Gradient -based learning applied to document recognition [ J]. Proceedings of the IEEE, 1998,86 (11 ) : 2278 - 2324.
  • 7Socher R, Lin C C, Manning C,et ah Parsing natural scenes and natural language with recursive neural network [ C ]. Proceedings of the 28th International Conference on Machine Learning. Washington, USA : ICML,2011 : 129 - 136.
  • 8Wang W, Ooi B C, Zhang D. Effective multi - modal retrieval based on stacked auto - encoders [ C ]. Proceedings of International Conference on Very Large Data Bases. Hangzhou, China: VLDB, 2014:649 - 660.
  • 9郑希源,张化祥.基于局部近邻相关性的多标记算法[J].计算机科学,2014,41(2):123-126. 被引量:4
  • 10杨阳,张文生.基于深度学习的图像自动标注算法[J].数据采集与处理,2015,30(1):88-98. 被引量:26

共引文献14

同被引文献3

引证文献1

二级引证文献4

;
使用帮助 返回顶部