Acta Metrologica Sinica  2024, Vol. 45 Issue (11): 1665-1670    DOI: 10.3969/j.issn.1000-1158.2024.11.10
Current Issue | Archive | Adv Search |
Lightweight Target Detection Method Based on Adaptive Feature Fusion of Optimized RetinaNet
ZHANG Liguo1,2, JI Xinye1,2, ZHANG Yupeng1,2, GENG Xingshuo1,2, ZHANG Sheng1,2
1. Hebei Key Laboratory of Meas Tech and Instrument, Yanshan University, Qinhuangdao, Hebei 066000, China
2.School of Electrical Engineering, Yanshan University, Qinhuangdao, Hebei 066000, China
Download: PDF (450 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  Aiming at the problems of large amount of computation and complex model in target detection algorithm, which make it difficult to deploy in application scenarios with limited computing resources on embedded platform. The lightweight target detection method based on optimized RetinaNet is proposed with adaptive feature fusion. Firstly, the proposed algorithm refers to the Ghost Module in GhostNet to reduce the number of model parameters. By means of a spatial feature fusion mechanism, the scale invariance of features is improved. Secondly, the idea of structural reparameterization is integrated to increase the depth of training, realize multi-branch training, single-branch training, and better improve the detecting performance of the model. The method is evaluated on two common target detection datasets, PASCAL VOC2007 and COCO. With an average accuracy of 54.1%, better than that of RetinaNet. The experimental results show that the memory taken by the proposed method is 170.71MByte, which is 44.27% of the memory taken by the RetinaNet, indicating that the proposed algorithm can greatly improve the network inference speed without ensuring the accuracy.
Key wordsmachine vision      target detection      optimized RetinaNet      feature fusion      lightweight      structure reparameterization     
Received: 28 March 2023      Published: 29 November 2024
PACS:  TB96  
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
ZHANG Liguo
JI Xinye
ZHANG Yupeng
GENG Xingshuo
ZHANG Sheng
Cite this article:   
ZHANG Liguo,JI Xinye,ZHANG Yupeng, et al. Lightweight Target Detection Method Based on Adaptive Feature Fusion of Optimized RetinaNet[J]. Acta Metrologica Sinica, 2024, 45(11): 1665-1670.
URL:  
http://jlxb.china-csm.org:81/Jwk_jlxb/EN/10.3969/j.issn.1000-1158.2024.11.10     OR     http://jlxb.china-csm.org:81/Jwk_jlxb/EN/Y2024/V45/I11/1665
Copyright © Editorial Board of Acta Metrologica Sinica
Supported by:Beijing Magtech