TY - GEN
T1 - Unmanned Aerial Vehicle-Based Animal Detection via Hybrid CNN and LSTM Model
AU - Gaurav, Akshat
AU - Gupta, Brij B.
AU - Chui, Kwok Tai
AU - Arya, Varsha
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - In this paper, we present a novel approach for wildlife animal detection in natural habitats using a deep learning model. Our model leverages a combination of Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks, trained on aerial imagery captured by unmanned aircraft. We conducted a comprehensive 50-epoch training and testing regimen, and the results reveal the model's learning trajectory and performance. The findings demonstrate a progressive increase in testing accuracy, indicative of the model's improved ability to recognize and classify a diverse range of animal species. This research contributes to wildlife conservation and monitoring efforts, particularly in remote or inaccessible areas, by providing an automated and accurate means of animal detection. The model's proficiency in real-world scenarios is highlighted, making it a valuable tool for ecological research and conservation initiatives.
AB - In this paper, we present a novel approach for wildlife animal detection in natural habitats using a deep learning model. Our model leverages a combination of Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks, trained on aerial imagery captured by unmanned aircraft. We conducted a comprehensive 50-epoch training and testing regimen, and the results reveal the model's learning trajectory and performance. The findings demonstrate a progressive increase in testing accuracy, indicative of the model's improved ability to recognize and classify a diverse range of animal species. This research contributes to wildlife conservation and monitoring efforts, particularly in remote or inaccessible areas, by providing an automated and accurate means of animal detection. The model's proficiency in real-world scenarios is highlighted, making it a valuable tool for ecological research and conservation initiatives.
KW - Aerial Image Anal-ysis
KW - CNN-LSTM Hybrid Model
KW - Unmanned Aerial Vehicles
KW - Wildlife Detection
UR - https://www.scopus.com/pages/publications/85202802272
U2 - 10.1109/ICC51166.2024.10622970
DO - 10.1109/ICC51166.2024.10622970
M3 - Conference contribution
AN - SCOPUS:85202802272
T3 - IEEE International Conference on Communications
SP - 2586
EP - 2591
BT - ICC 2024 - IEEE International Conference on Communications
A2 - Valenti, Matthew
A2 - Reed, David
A2 - Torres, Melissa
T2 - 59th Annual IEEE International Conference on Communications, ICC 2024
Y2 - 9 June 2024 through 13 June 2024
ER -