TY - GEN
T1 - Automated Pest Control
T2 - 7th International Conference on Computational Intelligence and Intelligent Systems, CIIS 2024
AU - Crossling, Cleveland J.
AU - Vadapalli, Hima
AU - Van Der Haar, Dustin
N1 - Publisher Copyright:
© 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.
PY - 2025/2/7
Y1 - 2025/2/7
N2 - The integration of artificial intelligence in agriculture has revolutionized farming practices, enhancing crop yields and resource efficiency. However, existing machine learning systems primarily focus on livestock, overlooking the impact of wildlife on agricultural productivity. This study addresses the gap by introducing two classification pipelines utilizing VGG16 and ResNet50 models for identifying five major classes of wildlife (foxes, rats, pigeons, raccoons, and squirrels) affecting agricultural sectors. A comprehensive dataset, comprising existing datasets and trail-camera footage, is compiled for training and validation. The results show that models trained on clear images struggle to generalize to real-world environments (the best accuracy being 48.19%). Grey-scaled models perform worse with a 2-6% decrease. Training on the training dataset and evaluating the validation set yields better average results for the weaker-performing model. This study contributes to invasive animal control in agriculture, providing a foundation for effective wildlife management with computer vision.
AB - The integration of artificial intelligence in agriculture has revolutionized farming practices, enhancing crop yields and resource efficiency. However, existing machine learning systems primarily focus on livestock, overlooking the impact of wildlife on agricultural productivity. This study addresses the gap by introducing two classification pipelines utilizing VGG16 and ResNet50 models for identifying five major classes of wildlife (foxes, rats, pigeons, raccoons, and squirrels) affecting agricultural sectors. A comprehensive dataset, comprising existing datasets and trail-camera footage, is compiled for training and validation. The results show that models trained on clear images struggle to generalize to real-world environments (the best accuracy being 48.19%). Grey-scaled models perform worse with a 2-6% decrease. Training on the training dataset and evaluating the validation set yields better average results for the weaker-performing model. This study contributes to invasive animal control in agriculture, providing a foundation for effective wildlife management with computer vision.
KW - agriculture
KW - classification pipelines
KW - computer vision
KW - invasive species detection
KW - wildlife management
UR - http://www.scopus.com/inward/record.url?scp=85219522268&partnerID=8YFLogxK
U2 - 10.1145/3708778.3708784
DO - 10.1145/3708778.3708784
M3 - Conference contribution
AN - SCOPUS:85219522268
T3 - CIIS 2024 - 2024 the 7th International Conference on Computational Intelligence and Intelligent Systems
SP - 38
EP - 43
BT - CIIS 2024 - 2024 the 7th International Conference on Computational Intelligence and Intelligent Systems
PB - Association for Computing Machinery, Inc
Y2 - 22 November 2024 through 24 November 2024
ER -