[1]余 咏,吴建平,何旭鑫,等.基于改进 YOLOv4-tiny 的节肢动物目标检测模型[J].计算机技术与发展,2024,34(01):114-120.[doi:10. 3969 / j. issn. 1673-629X. 2024. 01. 017]
　YU Yong,WU Jian-ping,HE Xu-xin,et al.Arthropod Object Detection Model Based on Improved YOLOv4-tiny[J].,2024,34(01):114-120.[doi:10. 3969 / j. issn. 1673-629X. 2024. 01. 017]
点击复制

基于改进 YOLOv4-tiny 的节肢动物目标检测模型()
分享到：

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

卷:
34
期数:
2024年01期
页码:
114-120
栏目:
人工智能
出版日期:
2024-01-10

文章信息/Info

Title:
Arthropod Object Detection Model Based on Improved YOLOv4-tiny
文章编号:
1673-629X(2024)01-0114-07
作者:
余 咏1 ; 吴建平1; 2 ; 何旭鑫1 ; 韦 杰1 ; 高雪豪1
1. 云南大学 信息学院,云南 昆明 650504;
2. 云南省电子计算中心,云南 昆明 650223
Author(s):
YU Yong1 ; WU Jian-ping1; 2 ; HE Xu-xin1 ; WEI Jie1 ; GAO Xue-hao1
1. School of Information Science & Engineering,Yunnan University,Kunming 650504,China;
2. Yunnan Provincial Electronic Computing Center,Kunming 650223,China
关键词:
节肢动物; 目标检测; 可变形卷积; YOLOv4-tiny; 双向特征金字塔
Keywords:
arthropods; object detection; deformable convolution; YOLOv4-tiny; bidirectional feature pyramid
分类号:
TP312
DOI:
10. 3969 / j. issn. 1673-629X. 2024. 01. 017
摘要:
针对自然环境下节肢动物背景复杂、形态万千、遮挡目标和目标尺度多样等因素,导致模型检测效率不高、边界框定位不准确的情况,提出一种基于改进 YOLOv4 -tiny 的节肢动物目标检测模型。 首先,结合空间、通道卷积注意力机制(CBAM) ,抑制背景噪声;其次,引入可变形卷积( DCN) 以及改进的加权双向特征金字塔,重塑卷积和特征融合方式进行多尺度预测;最后,在 FPN 网络中引出一层 Feat@ 3,嵌入空间金字塔池化结构,有效提取节肢动物的各种显著特征,使模型泛化能力更强,将改进后的模型命名为 YOLOv4-tiny-ATO。 实验结果表明,该模型在大小仅为 54. 6 Mb 的前提下,很好地平衡了检测速度和检测精度,检测精度为 0. 725,检测速度达到 89. 6 帧·s -1 ,召回率为 0. 585,较改进前相比 YOLOv4-tiny模型,检测精度提高 0. 426,模型在模型大小、检测速度上更适用于移动端部署,模型检测精度也能达到应用标准,满足对节肢动物的检测需求。
Abstract:
Aiming at the situation that the model detection efficiency is not high,and the bounding box prediction is wrong caused by thecomplex background, variety of morphology, occlusion target and diverse target scale of arthropods in the natural environment, anarthropod target detection model based on improved YOLOv4 - tiny is proposed. Firstly,combining spatial and channel convolutionalattention mechanism ( CBAM ) , the background noise is suppressed. Secondly, deformable convolution ( DCN ) and an improvedweighted bidirectional feature pyramid are introduced to reshape the convolution and feature fusion methods for multiscale prediction.Finally,a layer of Feat@ 3 is extracted in the FPN network,and a spatial pyramid pool structure is embedded to effectively extract varioussignificant features of arthropods,so as to enhance the generalization ability of the model. The improved model is named YOLOv4-tiny-ATO. The experimental results show that the proposed model balances detection speed and accuracy well with a size of only 54. 6 Mb.The detection accuracy is 0. 725,the detection speed reaches 89. 6 frames per second,and the recall rate reaches 0. 585,which is 0. 426higher than that of the YOLOv4 - tiny model before the improvement. The model is more suitable for mobile deployment in terms ofmodel size and detection speed,and the model detection accuracy can also meet the application standards to meet the detection needs ofarthropods.

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,(01):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,(01):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,(01):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,(01):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(01):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(01):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(01):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(01):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(01):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(01):36.

更新日期/Last Update: 2024-01-10