Hybrid convolution neural network model for a quicker detection of infested maize plants with fall armyworms using UAV-based images

被引:22
作者
Ishengoma, Farian S. [1 ,3 ]
Rai, Idris A. [2 ]
Ngoga, Said Rutabayiro [1 ]
机构
[1] Univ Rwanda, Coll Sci Technol, African Ctr Excellence Internet Things ACEIoT, POB 3900, Kigali, Rwanda
[2] State Univ Zanzibar, Sch Nat & Social Sci, Dept Comp Sci, POB 146, Zanzibar, Tanzania
[3] Sokoine Univ Agr, Coll Nat & Appl Sci, Dept Informat & Informat Technol, POB 3000, Morogoro, Tanzania
关键词
Maize; Fall armyworms; Unmanned aerial vehicle; Convolutional neural network; IDENTIFICATION;
D O I
10.1016/j.ecoinf.2021.101502
中图分类号
Q14 [生态学(生物生态学)];
学科分类号
071012 ; 0713 ;
摘要
Visual detection of plants diseases over a large area is time-consuming, and the results are prone to errors due to the subjective nature of human evaluations. Several automatic disease detection techniques that improve detection time and improve accuracy compared to visual methods exist, yet they are not suitable for immediate detection. In this paper, we propose a hybrid convolution neural network (CNN) model to speed up the detection of fall armyworms (faw) infested maize leaves. Specifically, the proposed system combines unmanned aerial vehicle (UAV) technology, to autonomously capture maize leaves, and a hybrid CNN model, which is based on a parallel structure specifically designed to take advantage of the benefits of both individual models, namely VGG16 and InceptionV3. We compare the performance of the proposed model in terms of accuracy and training time to four existing CNN models, namely VGG16, InceptionV3, XceptionNet, and Resnet50. The results show that compared to existing models, the proposed hybrid model reduces the training time by 16% to 44% compared to other models while exhibiting the most superior accuracy of 96.98%.
引用
收藏
页数:7
相关论文
共 24 条
[1]  
Alehegn E, 2017, International Journal of Innovative Research in Computer and Communication Engineering, V5
[2]  
[Anonymous], 2019, Meat market review, P1
[3]  
[Anonymous], 2015, P 3 INT C LEARN REPR
[4]  
Barmpoutis P, 2019, INT CONF ACOUST SPEE, P8291, DOI 10.1109/ICASSP.2019.8683128
[5]   Identification of Diseases in Corn Leaves using Convolutional Neural Networks and Boosting [J].
Bhatt, Prakruti ;
Sarangi, Sanat ;
Shivhare, Anshul ;
Singh, Dineshkumar ;
Pappula, Srinivasu .
ICPRAM: PROCEEDINGS OF THE 8TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION APPLICATIONS AND METHODS, 2019, :894-899
[6]   A survey on feature selection methods [J].
Chandrashekar, Girish ;
Sahin, Ferat .
COMPUTERS & ELECTRICAL ENGINEERING, 2014, 40 (01) :16-28
[7]   Counting Apples and Oranges With Deep Learning: A Data-Driven Approach [J].
Chen, Steven W. ;
Shivakumar, Shreyas S. ;
Dcunha, Sandeep ;
Das, Jnaneshwar ;
Okon, Edidiong ;
Qu, Chao ;
Taylor, Camillo J. ;
Kumar, Vijay .
IEEE ROBOTICS AND AUTOMATION LETTERS, 2017, 2 (02) :781-788
[8]   Xception: Deep Learning with Depthwise Separable Convolutions [J].
Chollet, Francois .
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :1800-1807
[9]   Fall armyworm threatens food security in southern Africa [J].
Devi, Sharmila .
LANCET, 2018, 391 (10122) :727-727
[10]  
Ebrahimi M.S, 2021, Study of residual networks for image recognition, P754, DOI [10.1007/978-3-030-80126-7_53, DOI 10.1007/978-3-030-80126-7_53]