基于改进YOLOv8的草原巡检机器人障碍物识别方法

doi:10.11896/jsjkx.241100065

摘要/Abstract

摘要： 为解决草原巡检机器人的障碍物识别算法受限于外部环境复杂和自身算力不足等在准确率与实时性上难以兼顾的问题,提出了一种基于YOLOv8的草原障碍物轻量化检测模型,利用高效多尺度注意力机制(Efficient Multi-Scale Attention Module)增强网络特征提取能力。同时在网络颈部结构添加1X1卷积进行降维映射处理,降低网络的参数量;还将原网络的损失函数替换为WIoU,降低了低质量图像在训练过程中对模型的影响。在自建数据集上进行了实验,结果表明,改进后模型的F1分数、平均精度值(mAP)分别为93%和96.2%,比原模型提高了1个百分点和1.9个百分点;模型参数量为1.96×10⁶,比原模型降低了34.7%,最后将模型移植到嵌入式平台并进行FP16量化,运行帧率提升了35%。提出的方法能兼顾准确率和实时性,是一种适用于嵌入式平台的轻量化检测方法,为草原巡检机器人的障碍物检测提供了技术支持。

关键词: 草原巡检机器人, 障碍物识别, 注意力机制, 轻量化, 嵌入式平台

Abstract: In order to solve the problem of difficulty in balancing accuracy and real-time performance of obstacle recognition algorithms for grassland inspection robots due to complex external environments and insufficient computing power,a lightweight detection model for grassland obstacles based on YOLOv8 is proposed,which utilizes an efficient multi-scale attention module to enhance network feature extraction capabilities.At the same time,1X1 convolution is added to the neck structure of the network for dimensionality reduction mapping processing,reducing the number of parameters in the network.This paper also replaced the loss function of the original network with WIoU,reducing the impact of low-quality images on the model during training.Experiments conducted on self-built datasets have shown that the improved model has an F1 score of 93% and an average accuracy value(mAP) of 96.2%,which is 1 and 1.9 percentage points higher than the original model.The model parameter size is 1.96×10⁶,which is 34.7% lower than the original model.Finally,the model was ported to an embedded platform and FP16 quantization was performed,resulting in a 35% increase in running frame rate.The proposed method can balance accuracy and real-time performance,and is a lightweight detection method suitable for embedded platforms,providing technical support for obstacle detection of grassland inspection robots.

Key words: Grassland inspection robot, Obstacle recognition, Attention mechanism, Lightweight detection methods, Embedded platform

中图分类号:

TP391

窦琢仑, 于春战, 张佳林, 李玉龙. 基于改进YOLOv8的草原巡检机器人障碍物识别方法[J]. 计算机科学, 2025, 52(11A): 241100065-6. https://doi.org/10.11896/jsjkx.241100065

DOU Zhuolun, YU Chunzhan, ZHANG Jialin, LI Yulong. Obstacle Recognition Method for Grassland Inspection Robot Based on Improved YOLOv8[J]. Computer Science, 2025, 52(11A): 241100065-6. https://doi.org/10.11896/jsjkx.241100065

参考文献

[1]CHANG S,WANG L,JIANG J,et al.Developments Course and Prospect of Grassland Survey and Monitoring Domestic and Abroad[J].Acta Agrestia Sinica,2023,31(5):1281.
[2]ZHENG Y L,TIAN Z,GUAN P,et al.Development of an intelligent monitoring system for vegetation coverage and phenology in grassland[J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE),2023,39(18):162-171.
[3]JIANG B,XIA J,MENG T,et al.ROD-YOLO:improvedYOLOv8 semantic segmentation of obstacles in complex road scenes based on Swin Transformer[C]//Third International Symposium on Computer Applications and Information Systems(ISCAIS 2024).SPIE,2024,13210:561-566.
[4]LALAK M,WIERZBICKI D.Automated detection of atypicalaviation obstacles from UAV images using a YOLO algorithm[J].Sensors,2022,22(17):6611.
[5]XUAN W,JIAN S G,BO J H,et al.A lightweight modified YOLOX network using coordinate attention mechanism for PCB surface defect detection[J].IEEE Sensors Journal,2022,22(21):20910-20920.
[6]WANG W,LI S,SHAO J,et al.LKC-Net:large kernel convolution object detection network[J].Scientific Reports,2023,13(1):9535.
[7]YIN Q J,YANG W Z,RAN M Y,et al.FD-SSD:An improved SSD object detection algorithm based on feature fusion and dilated convolution[J].Signal Processing:Image Communication,2021,98,116402.
[8]WANG Z,LING Y M,WANG X L,et al.An improved Faster R-CNN model for multi-object tomato maturity detection in complex scenarios[J].Ecological Informatics,2022,72:101886.
[9]HOWARD A G,ZHU M,CHEN B,et al.Mobilenets:Efficient convolutional neural networks for mobile vision applications[J].arXiv:1704.04861,2017.
[10]LI R Y,QIAN H F,GUO J H.Lightweight target detection al-gorithm based on M- YOLOV4 model[J].Foreign ElectronicMeasurement Technology,2022,41(4):15-21.
[11]ZHANG X,ZHOU X,LIN M,et al.Shufflenet:An extremelyefficient convolutional neural network for mobile devices[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:6848-6856.
[12]CHEN W WILSON J,TYREE S,et a1.Compressing neural networks with the hashing trick[C]//International Conference on Machine Learning.2015:2285-2294.
[13]LAVIN A,GRAY S.Fast algorithms for convolutional neural networks[C]//Proceedings of the IEEE Conference on Compu-ter Vision and Pattern Recognition.2016:4013-4021.
[14]OUYANG D,HE S,ZHANG G,et al.Efficient multi-scale attention module with cross-spatial learning[C]//2023 IEEE International Conference on Acoustics,Speech and Signal Processing(ICASSP 2023).IEEE,2023:1-5.
[15]TONG Z,CHEN Y,XU Z,et al.Wise-IoU:bounding box regression loss with dynamic focusing mechanism[J].arXiv:2301.10051,2023.
[16]REDMON J,FARHADI A.Yolov3:An incremental improvement[J].arXiv:1804.02767,2018.
[17]SZEGEDY C,LIU W,JIA Y,et al.Going deeper with convolutions[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2015:1-9.
[18]ZHENG Z,WANG P,LIU W,et al.Distance-IoU loss:Fasterand better learning for bounding box regression[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2020:12993-13000.
[19]JACOB B,KLIGYS S,CHEN B,et al.Quantization and training of neural networks for efficient integer-arithmetic-only inference[C]//Procee-dings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:2704-2713.
[20]WANG Q,WU B,ZHU P,et al.ECA-Net:Efficient channel attention for deep convolutional neural networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:11534-11542.
[21]WOO S,PARK J,LEE J Y,et al.Cbam:Convolutional block attention module [C]//Proceedings of the European Conference on Computer Vision(ECCV).2018:3-19.
[22]SRINIVAS A,LIN T Y,PARMAR N,et al.Bottleneck transformers for visual recognition [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021:16519-16529.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed