Abstract
[Objective] To achieve accurate and efficient detection of pig carcasses' segmentation features, which are hard to distinguish and relatively small. [Methods] The Ghost Conv module and C 3Ghost module are introduced into the Backbone layer to replace the ordinary convolution and C 2 modules in the original YOLOv 8n feature extraction network, aiming to reduce the computational amount and model complexity.The SPPF module is replaced with the SPPELAN module, so that the model can more effectively cope with multi -scale and small target features.Finally, parameter -free attention SimAM is introduced in front of the three detection heads to improve the ability to recognize the small target features of the lower pig carcass in a complex environment. [Results] The mAP 50 of the improved YOLOv 8n model on the self-made dataset is 97.3%, which is 5.3% higher than that of the original YOLOv 8n.The parameter Params, computational FLOPs, and the model size of the improved model are 1.5 M, 4.9 G, and 3.5 MB, respectively, which are only 50.0%, 60.5% and 55.6% of YOLOv 8n.The FPS of the model inference speed is 120.2 frames/s, which is increased by 20.7 frames/s. [Conclusion] The improved YOLOv 8n model has advantages in detection accuracy and lightweight, and can effectively identify the small target segmentation features of pig carcasses.
Publication Date
12-11-2025
First Page
76
Last Page
83
DOI
10.13652/j.spjx.1003.5788.2024.81250
Recommended Citation
Chunshan, LIU; Zhiang, LI; Wenbin, DENG; Tao, SHANG; and Xuecai, XIAO
(2025)
"Segmentation feature detection method of pig carcass based on improved YOLOv 8n,"
Food and Machinery: Vol. 41:
Iss.
11, Article 11.
DOI: 10.13652/j.spjx.1003.5788.2024.81250
Available at:
https://www.ifoodmm.cn/journal/vol41/iss11/11
References
[1] 国家统计局.中华人民共和国 2023 年国民经济和社会发展统计公报 [J].中国统计,2024 (3):4-21.NBSPRC.Statistical Communiqué of the People's Republic of China on the 2023 national economic and social development[J].China Statistics,2024 (3):4-21.
[2] 赵文豪.我国猪肉产业国际竞争力研究 [D].福州:福州大学,2019.ZHAO W H.Study on improving international competitiveness of pork industry in China [D].Fuzhou:Fuzhou University,2019.
[3] 国家市场监督管理总局,国家标准化管理委员会.畜禽肉分割技术规程 猪肉:GB/T 40466 —2021 [S].北京:中国标准出版社,2021.State Administration for Market Regulation,Standardization Administration of the People's Republic of China.Code of practice for livestock and poultry meat fabrication:pork:GB/T 40466 —2021 [S].Beijing:Standards Press of China,2021.
[4] 王志伟,王志刚,陈静.推进生猪屠宰业转型升级的思考与建议[J].猪业科学,2020,37(9):122-123.WANG Z W,WANG Z G,CHEN J.Thoughts and suggestions on promoting the transformation and upgrade of the pig slaughtering industry [J].Swine Industry Science,2020,37(9):122-123.
[5] 高胜普,温晓辉,孟庆阳,等.中国畜禽屠宰加工装备产业发展现状及趋势 [J].肉类工业,2021 (1):23-27.GAO S P,WEN X H,MENG Q Y,et al.Development status and trend of slaughtering and processing equipment industry of livestock and poultry in China [J].Meat Industry,2021 (1):23-27.
[6] 刘银,郑丽敏,朱虹,等.改进的 Canny 算法对猪胴体特征有效分割的研究 [J].农业网络信息,2014 (4):56-60.LIU Y,ZHENG L M,ZHU H,et al.Research on the effective segmentation of pig carcass characteristics based on improved canny algorithm [J].Agriculture Network Information,2014 (4):56-60.
[7] 赵世达.羊骨架关键部位识别方法及自动切割系统研发 [D].武汉:华中农业大学,2022.ZHAO S D.Identification method of key parts of sheep skeleton and research and development of automatic cutting system [D].Wuhan:Huazhong Agricultural University,2022.
[8] 江一宇,杨耀国.基于机器学习的生猪胴体分割方法及系统:CN113643401 A[P].2021 -11-12.JIANG Y Y,YANG Y G.Pig carcass segmentation method and system based on machine learning:CN 113643401 A[P].2021 -11-12.
[9] 李 春 保,高 廷 轩,陈 玉 仑,等.一 种 猪 半 胴 体 智 能 分 割 方 法:CN114342986 B[P].2023 -03-28.LI C B,GAO T X,CHEN Y L,et al.An intelligent segmentation method for pig semi-carcass:CN 114342986 B[P].2023 -03-28.
[10] 赵世达,王树才,李振强,等.基于 U型卷积神经网络的羊肋排图像分割 [J].食品与机械,2020,36(9):116-121,154.ZHAO S D,WANG S C,LI Z Q,et al.Image segmentation of sheep ribs based on U-shaped convolutional neural network [J].Food & Machinery,2020,36(9):116-121,154.
[11] ZHANG X R,WANG Y L,FANG H S.Steel surface defect detection algorithm based on ESI-YOLOv 8[J].Materials Research Express,2024,11(5):056509.
[12] 唐兴萍,王白娟,杨红欣,等.基于 YOLOv 8的水果外观检测与分类方法 [J].食品与机械,2024,40(7):103-110.TANG X P,WANG B J,YANG H X,et al.Research on fruit appearance detection and classification method based on YOLOv 8[J].Food & Machinery,2024,40(7):103-110.
[13] 刘颖,刘红燕,范九伦,等.基于深度学习的小目标检测研究与应用综述 [J].电子学报,2020,48(3):590-601.LIU Y,LIU H Y,FAN J L,et al.A survey of research and application of small object detection based on deep learning [J].Acta Electronica Sinica,2020,48(3):590-601.
[14] 张志凯,韩红章,赵雪芊,等.基于改进 YOLOv 3模型的软包装食品自动识别方法 [J].食品与机械,2023,39(5):95-100.ZHANG Z K,HAN H Z,ZHAO X Q,et al.Automatic recognition method for soft packaged food based on improved |YOLOv 3 model [J].Food & Machinery,2023,39(5):95-100.
[15] HAN K,WANG Y H,TIAN Q,et al.GhostNet:more features from cheap operations [C]// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR ).Seattle,WA:IEEE,2020:1 577-1 586.
[16] 崔家乐,曾祥峰,任政威,等.基于轻量化 Ghost-YOLOv 8和智能手机的田间水稻有效分蘖检测方法 [J].智慧农业 (中英文),2024,6(5):98-107.CUI J L,ZENG X F,REN Z W,et al.Detection method of effective tillering of rice in field based on lightweight ghost-YOLOv 8 and smart phone [J].Smart Agriculture,2024,6(5):98-107.
[17] 王福奇,王志峰,金建成,等.基于 GSL-YOLO 模型的综放工作面混矸率检测方法 [J].工矿自动化,2024,50(9):59-65,137.WANG F Q,WANG Z F,JIN J C,et al.Detection method for gangue mixed ratio in fully mechanized caving faces based on the GSL-YOLO model [J].Journal of Mine Automation,2024,50(9):59-65,137.
[18] YANG L X,ZHANG R Y,LI L D,et al.Simam:a simple,parameter-free attention module for convolutional neural networks [C]// Proceeding of the 38th International Conference on Machine Learning.Virtual:PMLR,2021:11 863-11 874.
[19] CHENG G,CHAO P Z,YANG J,et al.SGST-YOLOv 8:an improved lightweight YOLOv 8 for real-time target detection for campus surveillance [J].Applied Sciences,2024,14(12):5 341.
[20] JIANG P Y,ERGU D,LIU F Y,et al.A review of yolo algorithm developments [J].Procedia Computer Science,2022,199:1 066-1 073.
[21] MA S B,LIU Y N,ZHANG Y P.Fabric defect detection based on improved lightweight YOLOv 8n[J].Applied Sciences,2024,14(17):8 000.
[22] MA S Z,LU H M,LIU J,et al.LAYN:lightweight multi-scale attention YOLOv 8 network for small object detection [J].IEEE Access,2024,12:29 294-29 307.
[23] JOOSHIN H K,NANGIR M,SEYEDARABI H.Inception-YOLO:computational cost and accuracy improvement of the YOLOv 5 model based on employing modified CSP,SPPF,and inception modules [J].IET Image Processing,2024,18(8):1 985-1 999.
[24] HE K M,ZHANG X Y,REN S Q,et al.Spatial pyramid pooling in deep convolutional networks for visual recognition[C]// Computer Vision-ECCV 2014.Cham:Springer International Publishing,2014:346-361.
[25] LIN T Y,DOLLÁR P,GIRSHICK R,et al.Feature pyramid networks for object detection [C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR ).Honolulu,HI:IEEE,2017:936-944.
[26] LIU S,QI L,QIN H F,et al.Path aggregation network for instance segmentation [C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City,UT:IEEE,2018:8 759-8 768.
[27] LIN T Y,MAIRE M,BELONGIE S,et al.Microsoft COCO:common objects in context [M]// Computer Vision-ECCV 2014.Cham:Springer International Publishing,2014:740-755.
[28] TANG R,ADHIKARI A,LIN J.FLOPs as a direct optimization objective for learning sparse neural networks [EB/OL].(2018 -11-07) [2025 -02-26].https://arxiv.org/abs/ 1811.03060 v2.
[29] HE K M,ZHANG X Y,REN S Q,et al.Deep residual learning for image recognition [C]// 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR ).Las Vegas,NV:IEEE,2016:770-778.
[30] REDMON J,DIVVALA S,GIRSHICK R,et al.You only look once:unified,real-time object detection [C]// 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR ).Las Vegas,NV:IEEE,2016:779-788.
[31] HAN Y Z,HUANG G,SONG S J,et al.Dynamic neural networks:a survey [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2022,44(11):7 436-7 456.
[32] POWERS D M W.Evaluation:from precision,recall and F-measure to ROC,informedness,markedness and correlation[J].Journal of Machine Learning Technologies,2011,2(1):2 229.
