| 基于高分辨率网络的行人重识别技术 |
| |
| 引用本文： | 董明超,黄伟,吴金明,徐怀宇. 基于高分辨率网络的行人重识别技术[J]. 计算机应用与软件, 2022, 39(3): 180-186. DOI: 10.3969/j.issn.1000-386x.2022.03.029 |
| |
| 作者姓名： | 董明超 黄伟 吴金明 徐怀宇 |
| |
| 作者单位： | 上海科技大学信息科学与技术学院 上海200120,中国科学院上海高等研究院 上海200120;中国科学院大学 北京 100049 |
| |
| 基金项目： | 中国科学院战略性先导科技专项(XDC02000000,XDC02070700)。 |
| |
| 摘 要： | 针对行人重识别特征提取过程中特征图分辨率不断下降,丢失大量空间信息和细节信息,导致特征鲁棒性较低的问题,提出一种基于高分辨率特征提取网络的行人重识别方法.采取变换背景的方法对训练数据集进行数据扩充,提高数据样本的多样性;通过构建高分辨率特征提取网络,使得在整个特征提取过程中网络里始终拥有高分辨特征;结合三元损失函数和改...
|
| 关 键 词： | 行人重识别 高分辨率 特征提取 数据增强 |
PEDESTRIAN RE-IDENTIFICATION METHOD BASED ON HIGH-RESOLUTION NETWORK |
| |
| Dong Mingchao,Huang Wei,Wu Jinming,Xu Huaiyu. PEDESTRIAN RE-IDENTIFICATION METHOD BASED ON HIGH-RESOLUTION NETWORK[J]. Computer Applications and Software, 2022, 39(3): 180-186. DOI: 10.3969/j.issn.1000-386x.2022.03.029 |
| |
| Authors: | Dong Mingchao Huang Wei Wu Jinming Xu Huaiyu |
| |
| Affiliation: | (School of Information Science and Technology,ShanghaiTech University,Shanghai 200120,China;Shanghai Advanced Research Institute,Chinese Academy of Sciences,Shanghai 200120,China;University of Chinese Academy of Sciences,Beijing 100049,China) |
| |
| Abstract: | The resolution of feature maps constantly decreases and a large amount of spatial and detail information is lost during the feature extraction process of pedestrian re-identification,which leads to low robustness.To solve this problem,we proposed a pedestrian re-identification method based on high-resolution feature extraction network.The training data set was expanded by changing the background of images to increase the diversity of data samples.We constructed a high-resolution feature extraction network,which had high-resolution features in the entire feature extraction process.The triplet loss and the improved cross-entropy loss function was adopted to train the network.The proposed method has Rank-1 of 94.6%and mAP of 86.0%on the Market1501 data set.On the DukeMTMC-reID data set,Rank-1 reaches 90.3%and mAP is 78.2%.The method performs well on two large data sets and has certain application value. |
| |
| Keywords: | Pedestrian re-identification High-resolution Feature extraction Data augmentation |
| 本文献已被 维普 万方数据 等数据库收录！ |
|
