Lightweight Network Model for Moving Object Recognition

doi:10.7652/xjtuxb202107014

您当前的位置：

首页 >

文章列表页 >

Lightweight Network Model for Moving Object Recognition

更新时间：2025-07-09

- Lightweight Network Model for Moving Object Recognition
- Vol. 55, Issue 7, Pages: 124-131(2021)
- 作者机构：
  
  西安工业大学电子信息工程学院,西安,710021
- 作者简介：
- 基金信息：
- DOI：10.7652/xjtuxb202107014
  CLC： TP391.9
- Online First：10 July 2021，
  
  Published：2021
- 稿件说明：
移动端阅览
Lightweight Network Model for Moving Object Recognition[J]. 2021, 55(7): 124-131.
DOI：

Lightweight Network Model for Moving Object Recognition[J]. 2021, 55(7): 124-131. DOI： 10.7652/xjtuxb202107014.

摘要

针对卷积神经网络模型体积大、运算量高

在体积小、资源有限的嵌入式平台上运行效率低

而现有轻量化模型无法兼顾检测速度和检测精度的问题

提出了一种基于Ghost模块的YOLO目标识别算法GS-YOLO。以YOLOv4模型为基础

基于Ghost模块重构目标识别网络

减少模型参数与卷积运算量

提升目标识别速率; 通过融入多个空间金字塔池化模块优化目标识别精度; 利用通道剪枝极限压缩方法剔除冗余参数

进一步减小模型体积与计算量; 利用微调技术提升剪枝后模型的精度。实验结果表明:在自主构建的测试集和相同的测试环境下

与YOLOv4相比

GS-YOLO将YOLOv4模型体积压缩96%

浮点型计算量减少91.2%

预测速度提升2.9倍

压缩后模型识别精度达到87.63%

精度仅损失2.43%。

Abstract

The convolutional neural network model with large volume and computation amount cannot be run by the embedded platform with small volume and limited resources

and the existing lightweight models are unable to juggle detection speed and accuracy. An object recognition algorithm of YOLO based on Ghost module(GS-YOLO)was proposed in this study. Following YOLOv4 model

the object recognition network was reconstructed based on Ghost module to reduce model parameters and convolution operations and improve object recognition rate. Multiple spatial pyramid pooling modules were incorporated to optimize the identification model and improve the accuracy of model identification. The channel pruning limit compression method was adopted to eliminate the redundant parameters and further reduce the model volume and calculation. The accuracy of pruning model was improved by fine tuning technique. Experimental data show that for the self-built test set and the same test environment

compared with YOLOv4 object recognition algorithm

GS-YOLO algorithm reduces the volume of YOLOv4 model by 96%

reduces the amount of floating point calculation by 91.2%

and increases the prediction speed by 2.9 times. After compression

the model recognition accuracy achieves 87.63%

and the accuracy loss is only 2.43%.

关键词

Keywords

references

乔梦雨, 王鹏, 吴娇, 等. 面向陆战场目标识别的轻量级卷积神经网络 [J]. 计算机科学, 2020, 47(5): 161-165.

QIAO Mengyu, WANG Peng, WU Jiao, et al. Lightweight convolutional neural networks for land battle target recognition [J]. Computer Science, 2020, 47(5): 161-165.

赵永强, 饶元, 董世鹏, 等. 深度学习目标检测方法综述 [J]. 中国图象图形学报, 2020, 25(4): 629-654.

ZHAO Yongqiang, RAO Yuan, DONG Shipeng, et al. Survey on deep learning object detection [J]. Journal of Image and Graphics, 2020, 25(4): 629-654.

WANG Peng, SUN Mengyu, WANG Haiyan, et al. Convolution operators for visual tracking based on spatial-temporal regularization [J]. Neural Computing and Applications, 2020, 32(10): 5339-5351.

SHARKEY N. The ethical frontiers of robotics [J]. Science, 2008, 322(5909): 1800-1801.

刘俊, 孟伟秀, 余杰, 等. 面向军事目标识别的DRFCN深度网络设计及实现 [J]. 光电工程, 2019, 46(4): 180307.

LIU Jun, MENG Weixiu, YU Jie, et al. Design and implementation of DRFCN in-depth network for military target identification [J]. Opto-Electronic Engineering, 2019, 46(4): 180307.

WANG Peng, WU Jiao, WANG Haiyan, et al. Low-light-level image enhancement algorithm based on integrated networks [J]. Multimedia Systems, 2020(10): 1-11.

LI Xiaoyan, LV Zhigang, WANG Peng, et al. Combination weighted clustering algorithms in cognitive radio networks [J]. Concurrency and Computation: Practice and Experience, 2020, 32(23): e5516.

LEMLEY J, BAZRAFKAN S, CORCORAN P. Deep learning for consumer devices and services: pushing the limits for machine learning, artificial intelligence, and computer vision [J]. IEEE Consumer Electronics Magazine, 2017, 6(2): 48-56.

HOWARD A G, ZHU M, CHEN B, et al. MobileNets: efficient convolutional neural networks for mobile vision applications [EB/OL].(2017-04-17)[2021-03-04]. https: ∥arxiv.org/abs/1704.04861.

LEE Y, PARK J. CenterMask: real-time anchor-free instance segmentation [C]∥Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, NJ, USA: IEEE, 2020: 13903-13912.

LIN T Y, MAIRE M, BELONGIE S, et al. Microsoft COCO: common objects in context [C]∥Proceedings of the 2014 European Conference on Computer Vision(ECCV). Cham, Germany: Springer, 2014: 740-755.

TAN Mingxing, PANG Ruoming, LE Q V. EfficientDet: scalable and efficient object detection [C]∥Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, NJ, USA: IEEE, 2020: 10781-10790.

HAN Kai, WANG Yunhe, TIAN Qi, et al. GhostNet: more features from cheap operations [C]∥Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, NJ, USA: IEEE, 2020: 1577-1586.

BOCHKOVSKIY A, WANG C Y, LIAO H Y M. YOLOv4: optimal speed and accuracy of object detection [EB/OL]. [2021-03-04]. https: ∥arxiv.org/abs/2004.10934.

WANG C Y, LIAO H Y M, WU Y H, et al. CSPNet: a new backbone that can enhance learning capability of CNN [C]∥Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops(CVPRW). Piscataway, NJ, USA: IEEE, 2020: 390-391.

LIN T Y, DOLLÁR P, GIRSHICK R, et al. Feature pyramid networks for object detection [C]∥Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, NJ, USA: IEEE, 2017: 936-944.

LIU Shu, QI Lu, QIN Haifang, et al. Path aggregation network for instance segmentation [C]∥Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2018: 8759-8768.

HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1904-1916.

IOFFE S, SZEGEDY C. Batch normalization: accelerating deep network training by reducing internal covariate shift [C]∥Proceedings of the 32nd International Conference on Machine Learning(ICML). Princeton, NJ, USA: IMLS, 2015: 448-456.

LIU Zhuang, LI Jianguo, SHEN Zhiqiang, et al. Learning efficient convolutional networks through network slimming [C]∥Proceedings of the 2017 IEEE International Conference on Computer Vision(ICCV). Piscataway, NJ, USA: IEEE, 2017: 2736-2744.

ZHANG Pengyi, ZHONG Yunxin, LI Xiaoqiong. SlimYOLOv3: narrower, faster and better for real-time UAV applications [C]∥Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision Workshop(ICCVW). Piscataway, NJ, USA: IEEE, 2019: 37-45.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Numerical Simulation of Heat-Moisture Barrier Performance of a Horizontal Air Curtain in Cold Storage

Electrothermal Coupling Research on the Evolutionary Law of Anti-Corona Performance for High-Altitude Air-Cooled Generators

Turbulent Kinetic Energy Dissipation Mechanism of Supercritical Carbon Dioxide Leakage Flow in a Scallop Bionic Seal Cavity

Bi-Level Multi-Obj ective Optimization of a Wind-Solar Coupled Hydrogen Production System Based on the Synergy of Hybrid Electrolyzer Arrays

A Structure-Semantics-Residual Collaborative Image Compression Framework：Towards Privacy Protection and High-Fidelity Reconstruction

Related Author

No data

Related Institution

No data

⁰