Identification and Counting of Sugarcane Seedlings in the Field Using Improved Faster R-CNN

被引:19
作者
Pan, Yuyun [1 ]
Zhu, Nengzhi [1 ,2 ]
Ding, Lu [1 ]
Li, Xiuhua [1 ,3 ]
Goh, Hui-Hwang [1 ]
Han, Chao [1 ]
Zhang, Muqing [3 ,4 ,5 ]
机构
[1] Guangxi Univ, Sch Elect Engn, Nanning 530004, Peoples R China
[2] Anhui Transportat Holding Grp Co Ltd, Hefei 230088, Peoples R China
[3] Guangxi Univ, Guangxi Key Lab Sugarcane Biol, Nanning 530004, Peoples R China
[4] Guangxi Univ, State Key Lab Conservat & Utilizat Subtrop Agrobi, Nanning 530004, Peoples R China
[5] Univ Florida, IRREC IFAS, Ft Pierce, FL 34945 USA
基金
中国国家自然科学基金;
关键词
sugarcane seedling; convolutional neural network; object detection; unmanned aerial vehicle; faster RCNN; PRECISION AGRICULTURE;
D O I
10.3390/rs14225846
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Sugarcane seedling emergence is important for sugar production. Manual counting is time-consuming and hardly practicable for large-scale field planting. Unmanned aerial vehicles (UAVs) with fast acquisition speed and wide coverage are becoming increasingly popular in precision agriculture. We provide a method based on improved Faster RCNN for automatically detecting and counting sugarcane seedlings using aerial photography. The Sugarcane-Detector (SGN-D) uses ResNet 50 for feature extraction to produce high-resolution feature expressions and provides an attention method (SN-block) to focus the network on learning seedling feature channels. FPN aggregates multi-level features to tackle multi-scale problems, while optimizing anchor boxes for sugarcane size and quantity. To evaluate the efficacy and viability of the proposed technology, 238 images of sugarcane seedlings were taken from the air with an unmanned aerial vehicle. Outcoming with an average accuracy of 93.67%, our proposed method outperforms other commonly used detection models, including the original Faster R-CNN, SSD, and YOLO. In order to eliminate the error caused by repeated counting, we further propose a seedlings de-duplication algorithm. The highest counting accuracy reached 96.83%, whilst the mean absolute error (MAE) reached 4.6 when intersection of union (IoU) was 0.15. In addition, a software system was developed for the automatic identification and counting of cane seedlings. This work can provide accurate seedling data, thus can support farmers making proper cultivation management decision.
引用
收藏
页数:18
相关论文
共 41 条
  • [1] Aerial Imagery Paddy Seedlings Inspection Using Deep Learning
    Anuar, Mohamed Marzhar
    Halin, Alfian Abdul
    Perumal, Thinagaran
    Kalantar, Bahareh
    [J]. REMOTE SENSING, 2022, 14 (02)
  • [2] Machine Learning Regression Analysis for Estimation of Crop Emergence Using Multispectral UAV Imagery
    Banerjee, Bikram P.
    Sharma, Vikas
    Spangenberg, German
    Kant, Surya
    [J]. REMOTE SENSING, 2021, 13 (15)
  • [3] Bhatt R., 2020, RESOURCES USE EFFICI, P650, DOI DOI 10.1007/978-981-15-6953-1_18
  • [4] Elsharif A.A., 2019, INT J ACAD ENG RES I, V3, P19
  • [5] Evaluation of cotton emergence using UAV-based imagery and deep learning
    Feng, Aijing
    Zhou, Jianfeng
    Vories, Earl
    Sudduth, Kenneth A.
    [J]. COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2020, 177
  • [6] The impact of climate change and climate extremes on sugarcane production
    Flack-Prain, Sophie
    Shi, Liangsheng
    Zhu, Penghui
    da Rocha, Humberto R.
    Cabral, Osvaldo
    Hu, Shun
    Williams, Mathew
    [J]. GLOBAL CHANGE BIOLOGY BIOENERGY, 2021, 13 (03): : 408 - 424
  • [7] Automated Detection of Conifer Seedlings in Drone Imagery Using Convolutional Neural Networks
    Fromm, Michael
    Schubert, Matthias
    Castilla, Guillermo
    Linke, Julia
    McDermid, Greg
    [J]. REMOTE SENSING, 2019, 11 (21)
  • [8] Deep Residual Learning for Image Recognition
    He, Kaiming
    Zhang, Xiangyu
    Ren, Shaoqing
    Sun, Jian
    [J]. 2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, : 770 - 778
  • [9] DeepSeedling: deep convolutional network and Kalman filter for plant seedling detection and counting in the field
    Jiang, Yu
    Li, Changying
    Paterson, Andrew H.
    Robertson, Jon S.
    [J]. PLANT METHODS, 2019, 15 (01)
  • [10] Deep learning in agriculture: A survey
    Kamilaris, Andreas
    Prenafeta-Boldu, Francesc X.
    [J]. COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2018, 147 : 70 - 90