[1]周文进,李凡,薛峰.基于YOLOv3和注意力机制的野外蝴蝶种类识别[J].郑州大学学报(工学版),2022,43(01):34-40.[doi:10.13705/j.issn.1671-6833.2022.01.007]
 ZHOU Wenjin,LI Fan,XUE Feng.Identification of Butterfly Species in the Wild Based on YOLOv3 and Attention Mechanism[J].Journal of Zhengzhou University (Engineering Science),2022,43(01):34-40.[doi:10.13705/j.issn.1671-6833.2022.01.007]
点击复制

基于YOLOv3和注意力机制的野外蝴蝶种类识别()
分享到:

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
43
期数:
2022年01期
页码:
34-40
栏目:
出版日期:
2022-01-09

文章信息/Info

Title:
Identification of Butterfly Species in the Wild Based on YOLOv3 and Attention Mechanism
作者:
周文进李凡薛峰
昆明理工大学信息工程与自动化学院;

Author(s):
ZHOU Wenjin LI Fan XUE Feng
Faculty of Information Engineering and Automation,Kunming University of Science and Technology, Kunming 650500, China
关键词:
Keywords:
butterflies automatic identification YOLOv3 channel attention multiscale
分类号:
TP391.41
DOI:
10.13705/j.issn.1671-6833.2022.01.007
文献标志码:
A
摘要:
蝴蝶,作为昆虫纲中一个庞大的分支,其种类多样性强、生物形态特性突出并且呈现较强的拟态性,一直是昆虫分类学研究的重难点问题之一。通过蝴蝶数字图像对蝴蝶种类进行辨别,是目前在不影响研究对象及周边环境的情况下,最具效率的一种分类方法。然而,蝴蝶分类粒度极为细致,现有模型难以在图像样本缺乏的情况下对蝴蝶的外部形态特征进行有效学习。此外,由于蝴蝶的强拟态性,通过野外拍摄的图像对蝴蝶具体种类进行准确分辨,更是对模型的局部细节特征提取能力提出了巨大挑战。因此,本文以野外蝴蝶图像的种类自动识别为目标,在自建混合数据集基础上,对Yolo v3模型的主干网络进行了改进,构建出一种内嵌通道注意力MutiSE1D识别网络,该网络使用多尺度提取高维特征,使网络具有多种感受野,更好地关注了蝴蝶众多子类间、周围环境间存在的局部细微差异;并使用一维卷积代替压缩激励层,避免通道特征降维的同时,有效降低模型参数量,提升模型运行效率。根据上述方法在本文自建数据集上实验,模型最终的mAP达到了83.2%。结果表明,本文改进的识别网络可以有效提升原模型提取蝴蝶图像特征的准确性及细节特征的学习能力,能为野外蝴蝶数字图像的种类识别问题提供有效的解决方案。
Abstract:
To solve the problems of fine granularity of butterfly classification, low recognition efficiency and poor accuracy of existing models in the field environment, aim at the automatic recognition of butterfly species in the field, an embedded channel attention MultSE1D recognition network was proposed to improve the backbone network of YOLOv3 model on the basis of self-built hybrid data set. The network used multiscale to extract high-dimensional features, so that the network had a variety of receptive fields, and paid more attention to the local subtle differences between many subclasses of butterflies and the surrounding environment. One dimensional convolution was used to replace the compressed excitation layer to avoid dimensionality reduction of channel features, to reduce the model parameters and to improve the operation efficiency of the model. According to the above method, the final mean average precision (mAP) of the model was 83.2%. The results showed that the improved recognition network could effectively improve the accuracy of the original model to extract the butterfly image features and the learning ability of the detail features, and could provide an effective solution to the problem of identifying the species of butterfly digital images in the wild.

参考文献/References:

[1] 寿建新,周尧,李宇飞.世界蝴蝶分类名录[M].西 安: 陕西科学技术出版社,2006. 

[2] WANG J N,JI L Q,LIANG A P,et al.The identification of butterfly families using content-based image retrieval [J].Biosystems engineering,2012,111( 1) : 24-32. 
[3] LI F,XIONG Y. Automatic identification of butterfly species based on HoMSC and GLCMoIB[J].The visual computer,2018,34( 11) : 1525-1533. 
[4] CHEN X,WANG B,GAO Y S. Gaussian convolution angles: invariant vein and texture descriptors for butterfly species identification [ C ]/ /2020 25th International Conference on Pattern Recognition ( ICPR) .Piscataway: IEEE,2021: 5798-5803. 
[5] 谢娟英,侯琦,史颖欢,等.蝴蝶种类自动识别研究 [J].计算机研究与发展,2018,55( 8) : 1609-1618. 
[6] XIE J Y,LU Y Y,WU Z Z,et al.Investigations of butterfly species identification from images in natural environments[J]. International journal of machine learning and cybernetics,2021,12( 8) : 2431-2442.
 [7] 魏宏彬,张端金,杜广明,等.基于改进型 YOLOv3 的 蔬菜识别算法[J].郑州大学学报( 工学版) ,2020, 41( 2) : 7-12,31.
 [8] REDMON J,FARHADI A. YOLOv3: an incremental improvement[EB/OL]. ( 2018 - 04 - 08) [2021 - 05 - 01]. https: / /arxiv.org /abs/1804. 027672. 
[9] HU J,SHEN L,SUN G. Squeeze-and-excitation networks[C]/ /2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE,2018: 7132-7141. 
[10] WOO S,PARK J,LEE J Y,et al.CBAM: convolutional block attention module [ C ]/ /15th European Conference on Computer Vision( ECCV 2018) .Cham: Springer,2018: 3-19. 
[11] LI X,WANG W H,HU X L,et al.Selective kernel networks[C]/ /2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition ( CVPR) .Piscataway:IEEE,2019: 510-519.
 [12] WANG Q L,WU B G,ZHU P F,et al. ECA-net: efficient channel attention for deep convolutional neural networks[C]/ /2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition ( CVPR) .Piscataway: IEEE,2020: 11531-11539. 
[13] HE T,ZHANG Z,ZHANG H,et al. Bag of tricks for image classification with convolutional neural networks [C]/ /2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition ( CVPR) .Piscataway: IEEE,2019: 558-567. 
[14] XIN D J,CHEN Y W,LI J J. Fine-grained butterfly classification in ecological images using squeeze-andexcitation and spatial attention modules[J]. Applied sciences,2020,10( 5) : 1681. 
[15] CAO Y,XU J R,LIN S,et al. GCNet: non-local networks meet squeeze-excitation networks and beyond [C]/ /2019 IEEE/CVF International Conference on Computer Vision Workshop ( ICCVW) . Piscataway: IEEE,2019: 1971-1980. 
[16] REN S Q,HE K M,GIRSHICK R,et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE transactions on pattern analysis and machine intelligence,2017,39( 6) : 1137 -1149. 
[17] LIU W,ANGUELOV D,ERHAN D,et al. SSD: single shot MultiBox detector[C]/ /ECCV 2016: European Conference on Computer Vision.Cham: Springer,2016: 21-37. 
[18] TAN M X,PANG R M,LE Q V.EfficientDet: scalable and efficient object detection[C]/ /2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition ( CVPR) . Piscataway: IEEE,2020: 10778 -10787. 
[19] BOCHKOVSKIY A,WANG C Y,LIAO H Y MARK. YOLOv4: optimal speed and accuracy of object detection[EB/OL]. ( 2020-04-23) [2021-05-01]. https: / /arxiv.org /abs/2004. 10934.

更新日期/Last Update: 2022-01-09