[1]许 伟,熊卫华.一种改进的轻量级垃圾目标检测算法[J].计算机技术与发展,2022,32(02):63-68.[doi:10. 3969 / j. issn. 1673-629X. 2022. 02. 010]
　XU Wei,XIONG Wei-hua.An Improved Lightweight Garbage Target Detection Algorithm[J].,2022,32(02):63-68.[doi:10. 3969 / j. issn. 1673-629X. 2022. 02. 010]
点击复制

一种改进的轻量级垃圾目标检测算法()

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
32
期数:
2022年02期
页码:
63-68
栏目:
图形与图像
出版日期:
2022-02-10

文章信息/Info

Title:
An Improved Lightweight Garbage Target Detection Algorithm
文章编号:
1673-629X(2022)02-0063-08
作者:
许 伟; 熊卫华
浙江理工大学 机械与自动控制学院,浙江 杭州 310018
Author(s):
XU Wei; XIONG Wei-hua
Faculty of Mechanical Engineering & Automation,Zhejiang Sci-Tech University,Hangzhou 310018,China
关键词:
垃圾分类; 目标检测; 轻量化; YOLOv3; GhostNet
Keywords:
garbage classification; target detection; lightweight; YOLOv3; GhostNet
分类号:
TP391. 4
DOI:
10. 3969 / j. issn. 1673-629X. 2022. 02. 010
摘要:
垃圾分类问题的解决方法目前主要依靠垃圾处理厂人工分拣,其工作环境较差且自动化程度不高。 为了提高垃圾分拣的速度与精度,以及为自动垃圾分拣设备提供算法解决参考方案,文章提出一种面向低功耗设备的轻量级垃圾目标检测算法 Ghost-YOLO,该算法在保证轻量化的同时具有较高的垃圾检测精度。 Ghost-YOLO 算法是基于 YOLOv3 算法通过一系列轻量化改进方案进行改进。 首先,通过引入 Ghost bottleneck 轻量级模块的特征提取网络对输入图片进行特征提取。 其次,通过改进的轻量级特征融合层,增加降采样链路,将特征进行二次融合,使得网络对小物体的检测能力更强以及回归框的位置更为精确。 通过实验表明,Ghost-YOLO 算法模型的参数量相比原 YOLOv3 减少了 95. 96% ,,大大降低了计算量和网络参数量,整体算法压缩至 9. 5 MB。 在垃圾数据集下的平均精度均值能达到 89. 02% 。
Abstract:
At present,the solution to the problem of garbage classification mainly relies on manual sorting of garbage treatment plant,which has poor working environment and low degree of automation. In order to improve the speed and accuracy of garbage sorting,andto provide an algorithm solution reference scheme for automatic garbage sorting equipment, we propose a lightweight garbage targetdetection algorithm Ghost-YOLO for low-power devices,which has high precision of garbage detection while ensuring lightweight. TheGhost-YOLO algorithm is based on the YOLOv3 algorithm through a series of lightweight improvements. Firstly,feature extraction isperformed on the input image by introducing the feature extraction network of the Ghost bottleneck lightweight module. Secondly,through the improved lightweight feature fusion layer, the down - sampling link is added,and the features are fused twice, so that thenetwork has a stronger ability to detect small objects and the position of the regression box is more accurate. Experiments show that the amount of parameters of the Ghost - YOLO algorithm model is reduced by 95. 96% compared to the original YOLOv3, which greatlyreduces the amount of calculation and network parameters,and the overall algorithm is compressed to 9. 5 MB. The mAP of the garbagedata set can reach 89. 02% .

相似文献/References:

[1]刘晓明 李毓蕙 高燕 郑华强.基于目标区域清晰显示的H.264编码策略[J].计算机技术与发展,2010,(06):29.
　LIU Xiao-ming,LI Yu-hui,GAO Yan,et al.A Coding Strategy of H.264 Based on High-definition Display of Target Region[J].,2010,(02):29.
[2]刘翔 吴谨 祝愿博 康晓晶.基于视频序列的目标检测与跟踪技术研究[J].计算机技术与发展,2009,(11):179.
　LIU Xiang,WU Jin,ZHU Yuan-bo,et al.A Study of Object Detecting and Tracking Based on Video Sequences[J].,2009,(02):179.
[3]曙光 张超 蔡则苏.基于改进的混合高斯模型的目标检测方法[J].计算机技术与发展,2012,(07):60.
　SHU Guang,ZHANG Chao,CAI Ze-su.Target Detection Method Based on Improved Gaussian Mixture Model[J].,2012,(02):60.
[4]刘洁,李目,周少武.一种混沌混合粒子群优化RBF神经网络算法[J].计算机技术与发展,2013,(08):181.
　LIU Jie[],LI Mu[],ZHOU Shao-wu[].An Algorithm of Chaotic Hybrid Particle Swarm Optimization Based on RBF Neural Network[J].,2013,(02):181.
[5]蒋翠清,孙富亮,吴艿芯. 基于相对欧氏距离的背景差值法视频目标检测[J].计算机技术与发展,2015,25(01):37.
　JIANG Cui-qing,SUN Fu-liang,WU Nai-xin. Video Object Detection of Background Subtraction Method Based on Relative Euclidean Distance[J].,2015,25(02):37.
[6]卢官明,衣美佳. 步态识别关键技术研究[J].计算机技术与发展,2015,25(07):100.
　LU Guan-ming,YI Mei-jia. Research on Critical Techniques in Gait Recognition[J].,2015,25(02):100.
[7]高翔,朱婷婷,刘洋. 多摄像头系统的目标检测与跟踪方法研究[J].计算机技术与发展,2015,25(07):221.
　GAO Xiang,ZHU Ting-ting,LIU Yang. Research of Target Detection and Tracking Method for Multi-camera System[J].,2015,25(02):221.
[8]章文洁[][],黄旻[],张桂峰[]. 滤光片多光谱成像中运动目标场景误配准修正[J].计算机技术与发展,2016,26(01):18.
　ZHANG Wen-jie[][],HUANG Min[],ZHANG Gui-feng[]. Misregistration Correction for Moving Object Scene in Filter-type Multispectral Imaging[J].,2016,26(02):18.
[9]施泽浩,赵启军.基于全卷积网络的目标检测算法[J].计算机技术与发展,2018,28(05):55.[doi:10.3969/j.issn.1673－629X.2018.05.013]
　SHI Ze-hao,ZHAO Qi-jun.Object Detection Algorithm Based on Fully Convolutional Neural Network[J].,2018,28(02):55.[doi:10.3969/j.issn.1673－629X.2018.05.013]
[10]张夏清,茅耀斌. 一种改进的ViBe背景提取算法[J].计算机技术与发展,2016,26(07):36.
　ZHANG Xia-qing,MAO Yao-bin. An Improved ViBe Background Generation Method[J].,2016,26(02):36.
[11]李 威,李 楠,于清玲.基于 Faster RCNN 的可回收物自动分类算法研究[J].计算机技术与发展,2021,31(增刊):100.[doi:10. 3969 / j. issn. 1673-629X. 2021. S. 020]
　LI Wei,LI Nan,YU Qing-ling.Research on Automatic Classification Algorithm of Recyclables Based on Faster RCNN[J].,2021,31(02):100.[doi:10. 3969 / j. issn. 1673-629X. 2021. S. 020]

更新日期/Last Update: 2022-02-10