Counting spikelets from infield wheat crop images using fully convolutional networks

被引:16
作者
Alkhudaydi, Tahani [1 ]
De la Lglesia, Beatriz [2 ]
机构
[1] Univ Tabuk, Tabuk 71491, SA, Saudi Arabia
[2] Univ East Anglia, Norwich Res Pk, Norwich NR4 7TJ, Norfolk, England
关键词
Wheat; Spikelet counting; Plant phenotyping; Soft computing; Image analysis; CNN; Density estimation;
D O I
10.1007/s00521-022-07392-1
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Wheat is one of the world's three main crops, with global consumption projected to reach more than 850 million tons by 2050. Stabilising yield and quality of wheat cultivation is a major issue. With the use of remote sensing and non-invasive imaging technology, the Internet of things (IoT) has allowed us to constantly monitor crop development in agriculture. The output of such technologies may be analysed using machine-learning algorithms and image processing methods to extract useful information for crop management assistance. Counting wheat spikelets from infield images is considered one of the challenges related to estimating yield traits of wheat crops. For this challenging problem, we propose a density estimation approach related to crowd counting, SpikeCount. Our proposed counting methods are based on deep learning architectures as those have the advantage of being able to identify features automatically. Annotation of images with the ground truth is required for machine learning approaches, but those are expensive in terms of time and resources. We use transfer Learning in both tasks, segmentation and counting. Our results indicate the segmentation is beneficial as focusing only on the regions of interest improves counting accuracy in most scenarios. In particular, transfer learning from similar images produced excellent results for the counting task for most of the stages of wheat development.
引用
收藏
页码:17539 / 17560
页数:22
相关论文
共 51 条
  • [41] University ofBristol, 2011, WHEAT BIG PICTURE
  • [42] scikit-image: image processing in Python']Python
    van der Walt, Stefan
    Schonberger, Johannes L.
    Nunez-Iglesias, Juan
    Boulogne, Francois
    Warner, Joshua D.
    Yager, Neil
    Gouillart, Emmanuelle
    Yu, Tony
    [J]. PEERJ, 2014, 2
  • [43] COUNT Forest: CO-voting Uncertain Number of Targets using Random Forest for Crowd Density Estimation
    Viet-Quoc Pham
    Kozakaya, Tatsuo
    Yamaguchi, Osamu
    Okada, Ryuzo
    [J]. 2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, : 3253 - 3261
  • [44] Wang M, 2011, PROC CVPR IEEE
  • [45] Wang Y, 2016, IEEE IMAGE PROC, P3653, DOI 10.1109/ICIP.2016.7533041
  • [46] Wu B, 2005, IEEE I CONF COMP VIS, P90
  • [47] Xu BL, 2016, IEEE WINT CONF APPL
  • [48] Yosinski J, 2014, ADV NEUR IN, V27
  • [49] DECIMAL CODE FOR GROWTH STAGES OF CEREALS
    ZADOKS, JC
    CHANG, TT
    KONZAK, CF
    [J]. WEED RESEARCH, 1974, 14 (06) : 415 - 421
  • [50] Zhang C, 2015, PROC CVPR IEEE, P833, DOI 10.1109/CVPR.2015.7298684