SKSVMA Charitable Trust (Regd.
)
Smt Kamala & Sri Venkappa M Agadi College of Engineering & Technology
Lakshmeshwar 582116 Dist: Gadag
Department of Information Science and Engineering
Date: 07/10/2024
“Intelligent Agricultural Equipment for Pest And
Disease Management Using Image Processing
And RGB-D SLAM with CNN”
ABSTRACT
Agriculture plays an important role in human survival and the economy of the nation; hence
heavy investment is made by the farmers to protect crops from pests and diseases. Early
detection of pests prevents severe damage to crop yield and ensures high yields. Here, we
propose an automatic approach for early pest detection using some preprocessing techniques
on images with MATLAB. By applying pre-processing, modification, and clustering of
images of leaves, computer vision algorithms can efficiently assess crop health. Features are
extracted in order to feed the image into an SVM classifier with a decision towards the
presence of pests, which gives an efficient and reliable solution in pest management. Besides
this, loop closure detection plays a very significant role in constructing reliable maps in
intelligent agricultural machinery. This process is more precise and faster with the
introduction of CNN than the traditional ways. The problem in using small embedded devices
in agricultural equipment is rapid response time and real-time performance. With such
problems, we are proposing a lightweight CNN-based approach for further enhancement of
accuracy using GhostNet, combining high-dimensional semantic information with low-
dimensional geometric features. In addition to this, we use Multi-Probe Random Hyperplane
Local Sensitive Hashing to optimize the detection speed. Experimental results on public and
proprietary greenhouse datasets show that the combined approach can effectively satisfy the
precision as well as real-time requirements of both early pest detection and agricultural loop
closure detection systems.
Key Words:
Agricultural Automation
Pest Detection System
Crop Yield Management
Intelligent Agricultural Machinery
Multi-Probe Random Hyperplane Local Sensitive Hashing
References:
[1] Press Trust of India. (2009, Feb 26). India loses Rs 90k- cr crop yield to pest attacks every year
[Online].Available0: http://www.financialexpress.comlnews/indiaIoses-rs-90kcr-cropyield-to-pestattacks-
every-year 14280911.
[2] Ganesh Bhadane, Sapana Sharma and Vijay B. Nerkar,"Early Pest Identification in Agricultural Crops
using Image Processing Techniques", International Journal of Electrical, Electronics and Computer
Engineering, 2(2), 2013, pp. 77-82.
[3] Pan, Z.; Hou, J.; Yu, L. Optimization RGB-D 3-D Reconstruction Algorithm Based on Dynamic
SLAM. IEEE Trans. Instrum. Meas. 2023, 72, 1–13. [CrossRef]
[4] Nguyen, D.D.; Elouardi, A.; Florez, S.A.; Bouaziz, S. HOOFR SLAM system: An embedded vision
SLAM algorithm and its hardware-software mapping-based intelligent vehicles applications. IEEE Trans.
Intell. Transp. Syst. 2018, 20, 4103–4118. [CrossRef]
Students Name: Guide Signature: HOD Signature:
Anish R C (2KA22IS004)
M R Zeeshan (2KA22IS021)
Shivaraj B Y (2KA22IS048)
Suhil I I (2KA22IS057)
