
Research Article
A Multi-level Smart Monitoring System by Combining an E-Nose and Image Processing for Early Detection of FAW Pest in Agriculture
@INPROCEEDINGS{10.1007/978-3-030-51051-0_2, author={S\'{e}m\'{e}vo Arnaud R. M. Ahouandjinou and Manhougb\^{e} P. A. F. Kiki and Prince E. N. Amoussouga Badoussi and Kokou M. Assogba}, title={A Multi-level Smart Monitoring System by Combining an E-Nose and Image Processing for Early Detection of FAW Pest in Agriculture}, proceedings={Innovations and Interdisciplinary Solutions for Underserved Areas. 4th EAI International Conference, InterSol 2020, Nairobi, Kenya, March 8-9, 2020, Proceedings}, proceedings_a={INTERSOL}, year={2020}, month={8}, keywords={Smart farming Fall Armyworm (FAW) Multi-level monitoring Early detection E-nose Image processing}, doi={10.1007/978-3-030-51051-0_2} }
- Sèmèvo Arnaud R. M. Ahouandjinou
Manhougbé P. A. F. Kiki
Prince E. N. Amoussouga Badoussi
Kokou M. Assogba
Year: 2020
A Multi-level Smart Monitoring System by Combining an E-Nose and Image Processing for Early Detection of FAW Pest in Agriculture
INTERSOL
Springer
DOI: 10.1007/978-3-030-51051-0_2
Abstract
Fall Armyworm whose scientific name is Spodoptera frugiperda is a pest which have a large destructive activity of cornfields in sub-Saharan Africa. Fall Armyworm is a pest causing significant economic harm in Africa. In this work, we proposed to develop a smart monitoring system through several level. Each level of the proposed monitoring system is used to control and to detect the pest early. The aim is therefore to develop a system for the early detection of fall armyworm, these eggs, larvae and its adult form on image in order to anticipate the damage it can cause and to prevent its proliferation. First of all, the proposed monitoring system is based on an e-nose to analyze the odors that are released in the environment by fall armyworm. Then, we use image processing techniques based on image segmentation to detect the presence of pest through the damage caused to the plants and leaves its environment. We offers through this work, a smart monitoring system for Early Detection of FAW (EDFaw) by combining an e-nose and the plant leaf image segmentation. Several experiments have been done to test the proposed system and the results of the image segmentation.