Maize Tassel Detection Algorithm after Artificial Emasculation Based on Lightweight MLCE-RTMDet

LI Jinrui, DU Jianjun, ZHANG Hongming, GUO Xinyu, ZHAO Chunjiang

Abstract

Detecting missed tassels is crucial for assessing the quality of aritificial emasculation in maize seed production fields. Aiming at the problems of large parameter quantity, low detection efficiency and poor accuracy of the existing maize tassel detection models, a lightweight tassel detection model based on RTMDet-tiny, named MLCE-RTMDet, was proposed. The model used the lightweight MobileNetv3 as the feature extraction network to effectively reduce the model parameters. The CBAM attention module in the neck network was integrated to enhance multi-scale feature extraction capability for tassel objects, overcoming potential performance losses caused by the lightweight networks. Simultaneously, the EIOU Loss was adopted, replacing the GIOU Loss, which further improved the accuracy of tassel detection. Experiments on the self-built dataset showed that the improved MLCE-RTMDet model reduced model parameters to 3.9×106, while the number of floating point operations was lowered to 5.3×109, resulting in a 20.4% reduction in parameters and a 34.6% decrease in computational complexity compared with that of the original model. When evaluated on the test set, the model’s mean average precision (mAP) reached 92.2%, reflecting a 1.2 percentage points improvement over the original model. The inference speed was increased to 41.9 frames per second (FPS), representing a 12.6% enhancement. Compared with current mainstream detection models such as YOLO v6, YOLO v8, and YOLO X, MLCE-RTMDet demonstrated superior overall detection performance. The improved high-accuracy lightweight model offered technical support for tassel re-inspection and emasculation quality assessment in maize seed production fields following artificial emasculation.

 

Keyword: drone ; object detection ; artificial emasculation ; maize tassel ; RTMDet ; lightweight network

 

Download Full Text:

PDF


References


RANUM P, PENA-ROSAS J, GARCIA-CASAL M. Global maize production, utilization, and consumption [ J ]. Annals of the New York Academy of Science, 2014,1312( 1) : 105 - 112.

ERENSTEIN 0, JALETA M, SONDER K, et al. Global maize production, consumption and trade: trends and R&D implications[ J ]. Food Security ,2022 ,14(5 ); 1295 -1319.

CZEPAK M , KLIEMANN M , SCHMILDT 0, et al. Effect of artificial detasseling and defoliation on maize seed production [ J ]. International Journal of Plant & Soil Science, 2019, 20; 1 -9.

DING Shuaitao, SUN Qin, LUO Hongbing. Research progress on differentiation and development of tassel in maize[j] . Crop Research, 2014 , 28(1): 97 - 102.(in Chinese)

TANG W, ZHANG Y, ZHANG D, et al. Corn tassel detection based on image proeessing [ С ] //2012 International Workshop on Image Processing and Optical Engineering. SPIE, 2012; 123 - 129.

YE M, CAO Z, Y U Z, et al. An image-based approach for automatic detecting tasseling stage of maize using spatio-temporal saliency[ С] //Remote Sensing Image Processing, Geographic Information Systems, and other Applications, 2013: 8921.

KURTLLMU§ F, KAVDIR I. Detecting corn tassels using computer vision and support vector machines [ J ]. Expert Systems with Applications, 2014, 41(16) : 7390 -7397.

MA Zhongjie, LUO Chen, LUO Wei, et al. Tassel detection method of maize germplasm resources based on improved YOLO v7-tiny[J]. Transactions of the Chinese Society for Agricultural Machinery, 2024,55(7) :290 -297. (in Chinese)

CHANG Wanqiu, YAO Yu, XI Xiaojie, et al. Remote sensing identification for seed maize with integrated migration learning and unsupervised classification [J] . Transactions of the Chinese Society for Agricultural Machinery, 2024,55(8) : 181 - 195. ( in Chinese)

LIANG Yinhao, CHEN Quan, DONG Caixia, et al. Application of deep-learning and UAV for field surveying corn tassel [ J ] . Fujian Journal of Agricultural Sciences, 2020, 35(4) : 456 -464. (in Chinese)

ZHANG Xiaomeng, ZIIU Deli, YU Maosheng. Lightweight detection model of maize tassel in UAV remote sensing image[ J ]. Acta Agriculturae Universitatis Jiangxiensis, 2022, 44(2) : 461 -472. (in Chinese)

HU Zhen, MA Zongjun, HUANG Chuanbao, et al. PSOS — YOLO v5s; a lightweight maize tassel rapid detection algorithm [J/OL] . Radio Engineering, https://link.cnki. net/urlid/13. 1097. TN. 2023091 5. 1739.002. (in Chinese)

LIU W, QUIJANO K, CRAWFORD M. YOLO v5-Tassel; detecting tassels in RGB UAV imagery with improved YOLO v5 based on transfer learning [ J ]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2022,15 ; 8085 -8094.

SONG C, ZHANG F, LI J, et al. Detection of maize tassels for UAV remote sensing image with an improved YOLO X model [J] . Journal of Integrative Agriculture, 2023,22(6) ; 1671 - 1683.

SHORTEN G, KHOSHGOFTAAR T. A survey on image data augmentation for deep learningf J !. Journal of Big Data, 2019, 6( 1) :60 - 108.

LIN T Y, MAIRE M, BELONGIE S,et al. Microsoft COCO: common objects in context [ С ] // Proceedings of European Conference on Computer Vision, 2014: 740 -755.

LYU C, ZHANG W, HUANG H, et al. RTMDet; an empirical study of designing real-time object detectors [J] . arXiv Preprint, arXiv; 2212.07784,2022.

HOWARD A G, ZHU M, CHEN B, et al. MobileNets; efficient convolutional neural networks for mobile vision applications [J] . arXiv Preprint, arXiv: 1704.04861,2017.

SANDLER M, HOWARD A, ZHU M, et al. MobileNetV2: inverted residuals and linear bottlenecks [ J ]. arXiv Preprint, arXiv: 1801.04381 ,2019.

HOWARD A, SANDLER M, CIIU G, et al. Searching for MobileNetV3 [ J ]. arXiv Preprint, arXiv: 1905.02244,2019.

PRAJIT R, BARRET Z, QUOC V. Searching for activation functions [J]. arXiv Preprint, arXiv; 1710.05941,2017.

WOO S, PARK J, LEE J, et al. CBAM; convolutional block attention module [J] . arXiv Preprint, arXiv; 1807. 06521 ,2018.

LI X, WANG W, WU L, et al. Generalized focal loss: learning qualified and distributed bounding boxes for dense object detection [J] . arXiv Preprint, arXiv: 2006.04388,2020.

HAMID R, NATHAN T, JUNY G, et al. Generalized intersection over union: a metric and a loss for bounding box regression [J]. arXiv Preprint, arXiv: 1902.09630,2019.

ZHENG Z, WANG P, LIU W , et al. Distance — IoU Loss: faster and better learning for bounding box regression [ J ]. arXiv Preprint, arXiv: 1911. 08287 ,2019.

ZHENG Z, W ANG P, REN D,et al. Enhancing geometric factors in model learning and inference for object detection and instance segmentation[ J ]. arXiv Preprint, arXiv; 2005.03572,2020.

ZHANG Y, REN W, ZHANG Z, et al. Focal and efficient IOU loss for accurate bounding box regression[ J ]. arXiv, Preprint arXiv : 2101.08158,2022.

CHATTOPADHAY A, SARKAR A, HOWLADER P, et al. Grad-cam + + generalized gradient-based visual explanations for deep convolutional networks [C] /2018 IEEE W inter Conferenceon Applications of Computer Vision (WACV). IEEE, 2018; 839 -847.


Refbacks

  • There are currently no refbacks.