Person Reidentification Based on Multiscale Convolutional Feature Fusion

Longzhuang Xu; Li Peng

doi:10.3788/LOP56.141504

Journals >Laser & Optoelectronics Progress >Volume 56 >Issue 14 >Page 141504 > Article

Laser & Optoelectronics Progress
Vol. 56, Issue 14, 141504 (2019)

Person Reidentification Based on Multiscale Convolutional Feature Fusion

Longzhuang Xu and Li Peng^*

Author Affiliations

Engineering Research Center of Internet of Things Technology Applications of the Ministry of Education, School of Internet of Things Engineering, Jiangnan University, Wuxi, Jiangsu 214122, China

show less

DOI: 10.3788/LOP56.141504 Cite this Article Set citation alerts

Longzhuang Xu, Li Peng. Person Reidentification Based on Multiscale Convolutional Feature Fusion[J]. Laser & Optoelectronics Progress, 2019, 56(14): 141504 Copy Citation Text

show less

Fig. 1. Network structure

Download full size

Fig. 2. Comparison of our blocking strategy with PCB blocking strategy

Download full size

Fig. 3. Geometric diagram of the second classification. (a) Original softmax loss; (b) softmax loss with normalized weights and features

Download full size

Fig. 4. Results of recognition algorithm. (a) Baseline; (b) PCB (out RPP); (c) baseline+SPP (1+2+6); (d) ours

Download full size

Model	Market-1501		DukeMTMC-reID
Model	rank-1	mAP	rank-1	mAP
Baseline	86.88	69.59	72.62	54.93
Baseline+SPP	89.31	71.41	80.83	64.99
Baseline+L2_softmax	88.72	72.42	76.93	60.18
Ours	91.36	75.46	82.05	65.97
Ours+Re-ranking	93.29	88.81	86.49	81.93

Table 1. Effects of two methods for improving baseline model

Model	Market-1501		DukeMTMC-reID
Model	rank-1	mAP	rank-1	mAP
Baseline	86.88	69.59	72.62	54.93
PCB(out RPP)	88.48	69.89	80.21	64.27
Baseline+SPP(1+2+3)	89.31	71.41	80.83	64.99
Baseline+SPP(1+2+4)	89.41	70.68	79.35	62.55
Baseline+SPP(1+2+6)	88.09	68.75	80.05	64.89

Table 2. Performance comparison of different block models

Method	Market-1501		DukeMTMC-reID
Method	rank-1	mAP	rank-1	mAP
PSE	87.7	69.0	79.8	62.0
GLAD	89.9	73.9	—	—
SVDNet	82.3	62.1	76.7	56.8
MultiScale	88.9	73.1	79.2	60.6
MLFN	90.0	74.3	81.0	62.8
HA-CNN	91.2	75.7	80.5	63.8
DPFL	88.9	72.6	79.2	60.6
Ours	91.4	75.5	82.1	66.0
Ours+Re-ranking	93.3	88.9	86.5	81.9

Table 3. Performance comparison of our algorithm with mainstream algorithms

Longzhuang Xu, Li Peng. Person Reidentification Based on Multiscale Convolutional Feature Fusion[J]. Laser & Optoelectronics Progress, 2019, 56(14): 141504

Download Citation

Set citation alerts for the article

Tools

Set citation alerts for the article

Save the article for my favorites

Paper Information