Person Re-identification Based on Fusion Relationship Learning Network

被引：0

作者：

Wu Z. ^{[1
]}

Chang H. ^{[1
,2
]}

Ma B. ^{[1
]}

机构：

[1] School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing

[2] Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing

来源：

Moshi Shibie yu Rengong Zhineng/Pattern Recognition and Artificial Intelligence | 2021年 / 34卷 / 09期

基金：

中国国家自然科学基金;

关键词：

Attention Mechanism; Graph Convolutional Network; Person Re-identification; Similarity Metric; Structural Relationship;

D O I：

10.16451/j.cnki.issn1003-6059.202109003

中图分类号：

学科分类号：

摘要：

There are two problems in person re-identification methods based on graph convolutional network(GCN). While graphs are built for feature maps, the semantic information represented by graph node is not salient. The process of selecting feature blocks to build graph just relies on the relative distance among feature blocks, and the content similarity is ignored. To settle these two problems, an algorithm of person re-identification based on fusion relationship learning network(FRLN) is proposed in this paper. By employing attention mechanism, the maximum attention model makes the most important feature block more salient and assigns semantic information to it. The affinities of feature blocks are evaluated by the fusion similarity metric in the aspect of distance and content, and thus the metric is more comprehensive. By the proposed algorithm, the neighbor feature blocks are selected comprehensively and better input graph structures are provided for GCN. Hence, more robust structure relationship features are extracted by GCN. Experiments on iLIDS-VID and MARS datasets verify the effectiveness of FRLN. © 2021, Science Press. All right reserved.

引用

页码：798 / 808

页数：10

共 46 条

[1] GRAY D, BRENNAN S, TAO H., Evaluating Appearance Models for Recognition, Reacquisition, and Tracking
[2] LIAO S C, HU Y, ZHU X Y, Et al., Person Re-identification by Local Maximal Occurrence Representation and Metric Learning
[3] MA B P, SU Y, JURIE F., Local Descriptors Encoded by Fisher Vectors for Person Re-identification, Proc of the European Conference on Computer Vision, pp. 413-422, (2012)
[4] WANG P, SONG X N, WU X J, Et al., Multi-type Features Network for Person Re-identification, Pattern Recognition and Artificial Intelligence, 33, 10, pp. 879-888, (2020)
[5] JIANG H H, ZHANG R, LI X B, Et al., Pedestrian Re-identification Fusing Direct Metric and Indirect Metric, Pattern Recognition and Artificial Intelligence, 31, 2, pp. 167-174, (2018)
[6] KOSTINGER M, HIRZER M, WOHLHART P, Et al., Large Scale Metric Learning from Equivalence Constraints, Proc of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2288-2295, (2012)
[7] SUN Y F, ZHENG L, YANG Y, Et al., Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline), Proc of the European Conference on Computer Vision, pp. 501-518, (2018)
[8] ZHAO L M, LI X, ZHUANG Y T, Et al., Deeply-Learned Part-Aligned Representations for Person Re-identification, Proc of the IEEE International Conference on Computer Vision, pp. 3239-3248, (2017)
[9] ZHENG Z D, YANG X D, YU Z D, Et al., Joint Discriminative and Generative Learning for Person Re-identification, Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2133-2142, (2019)
[10] CHEN W H, CHEN X T, ZHANG J G, Et al., Beyond Triplet Loss: A Deep Quadruplet Network for Person Re-identification, Proc of the IEEE Conference on Computer Vision and Pattern Re-cognition, pp. 1320-1329, (2017)

← 1 2 3 4 5 →