Target Detection Model of Corn Weeds in Field Environment Based on MSRCR Algorithm and YOLOv4-tiny

被引：0

作者：

Liu M. ^{[1
,2
]}

Gao T. ^{[1
]}

Ma Z. ^{[1
]}

Song Z. ^{[1
,3
]}

Li F. ^{[1
,3
]}

Yan Y. ^{[1
,2
]}

机构：

[1] College of Mechanical and Electronic Engineering, Shandong Agricultural University, Tai'an

[2] Shandong Engineering Laboratory of Agricultural Equipment Intelligence, Tai'an

[3] Shandong Provincial Key Laboratory of Horticultural Machinery and Equipment, Tai'an

来源：

Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery | 2022年 / 53卷 / 02期

关键词：

Embedded device; Model pruning; Multi-scale retinex with color restoration (MSRCR) enhancement algorithm; Weed recognition; YOLOv4-tiny model;

D O I：

10.6041/j.issn.1000-1298.2022.02.026

中图分类号：

学科分类号：

摘要：

To solve the problem of low accuracy and poor real-time performance of weed recognition in corn field, a detection method of weed based on multi-scale retinex with color restoration (MSRCR)and improved YOLOv4-tiny algorithm was proposed. Firstly, according to the image characteristics of weed in corn field environment, the MSRCR algorithm was used for image feature enhancement preprocessing to improve the image contrast and detail quality. Then, Mosaic online data augmentation method was used to enrich the object detection background, improve the training efficiency and the detection accuracy of small objects. Finally, The K-means++ was used for a priori anchor boxes clustering analysis and channel pruning for the YOLOv4-tiny model. The total parameters of the improved and simplified model were reduced by 45.3%, the model size was reduced by 45.8%, the mean average precision(mAP)was increased by 2.5 percentage points, and the average detection frame time on the Jetson Nano embedded platform was reduced by 22.4%. The proposed Prune-YOLOv4-tiny model was compared with Faster RCNN, YOLOv3-tiny, and YOLOv4, the experimental results showed that the mAP of the Prune-YOLOv4-tiny model was 96.6%, which was 22.1 percentage points and 3.6 percentage points higher than that of the Faster RCNN and YOLOv3-tiny, and 1.2 percentage points lower than that of the YOLOv4 model; the model size of the Prune-YOLOv4-tiny was 12.2 MB, which was 3.4% of the Faster RCNN, 36.9% of the YOLOv3-tiny, and 5% of the YOLOv4; the average detection frame time on the Jetson Nano embedded platform was 131 ms, which was 32.1% of the YOLOv3-tiny and 7.6% of YOLOv4. The optimization method proposed was superior to other commonly used object detection algorithms in model size, detection time and detection accuracy, which could provide a feasible real-time weed recognition method for the field precision weeding system with limited hardware resources. © 2022, Chinese Society of Agricultural Machinery. All right reserved.

引用

页码：246 / 255and335

共 34 条

[1] PATEL D, KUMBHAR B., Weed and its management: a major threats to crop economy, Journal of Pharmaceutical Science and Bioscientific Research, 6, 6, pp. 753-758, (2016)
[2] WU Tong, ZENG Shan, ZHAO Runmao, Et al., Analysis and study on intelligentialized technologies of intra-row weeding mechaninal control, Journal of Agricultural Mechanization Research, 41, 6, pp. 1-6, (2019)
[3] LI Xiangju, Main problems and management strategies of weeds in agricultural fields in China in recent years, Plant Protection, 44, 5, pp. 77-84, (2018)
[4] LIU B, BRUCH R., Weed detection for selective spraying: a review[J], Current Robotics Reports, 1, 1, pp. 19-26, (2020)
[5] SHANMUGAM S, ASSUNCAO E, MESQUITA R, Et al., Automated weed detection systems: a review, KnE Engineering, pp. 271-284, (2020)
[6] WANG Can, LI Zhiwei, Weed recognition using SVM model with fusion height and monocular image features, Transactions of the CSAE, 32, 15, pp. 165-174, (2016)
[7] LI Hui, QI Lijun, ZHANG Jianhua, Et al., Recognition of weed during cotton emergence based on principal component analysis and support vector machine, Transactions of the Chinese Society for Agricultural Machinery, 43, 9, pp. 184-189, (2012)
[8] BAI Jing, XU You, WEI Xinhua, Et al., Weed identification from winter rape at seedling stage based on spectrum characteristics analysis, Transactions of the CSAE, 29, 20, pp. 128-134, (2013)
[9] PULIDO C, SOLAQUE L, VELASCO N., Weed recognition by SVM texture feature classification in outdoor vegetable crop images, Ingeniería e Investigación, 37, 1, pp. 68-74, (2017)
[10] KRIZHEVSKY A, SUTSKEVER I, HINTON G E., ImageNet classification with deep convolutional neural networks, Advances in Neural Information Processing Systems, pp. 1097-1105, (2012)

← 1 2 3 4 →