An explainable CNN-based approach for classifying Desert Lions from camera trap images

Jack  Pears; Gelayol Golcarenarenji

doi:10.1109/ICARAI67046.2025.11137832

An explainable CNN-based approach for classifying Desert Lions from camera trap images

Jack Pears^*
, Gelayol Golcarenarenji

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

8 Downloads (Pure)

Abstract

The Desert Lion population plays a significant role in promoting tourism and is of considerable ecological interest. Camera traps are used to monitor the lions; however, manually evaluating this data is labor-intensive and time-consuming for conservationists. Hence, this study developed a computer vision system that improves upon the InceptionV3 architecture to classify Desert Lions from camera trap data, with a final accuracy of 97.7 percent on the Desert Lion dataset. The final system is validated on unseen data, achieving an accuracy of 85.9 percent. Grad-CAM was also included for explainability of the model output.

Original language	English
Title of host publication	Proceedings of 2025 5th International Conference on Robotics, Automation, and Artificial Intelligence
Publisher	Institute of Electrical and Electronics Engineers Inc.
Number of pages	6
ISBN (Electronic)	9781665465663
ISBN (Print)	9781665465670
DOIs	https://doi.org/10.1109/ICARAI67046.2025.11137832
Publication status	Published - 3 Sept 2025
Event	International Conference Automatics, Robotics & Artificial Intelligence - Faculty of Automatics of the Technical Universiy of Sofia, Sozopol, Bulgaria Duration: 13 Jun 2025 → 15 Jun 2025 https://icarai.tu-sofia.bg/

Conference

Conference	International Conference Automatics, Robotics & Artificial Intelligence
Abbreviated title	ICARAI
Country/Territory	Bulgaria
City	Sozopol
Period	13/06/25 → 15/06/25
Internet address	https://icarai.tu-sofia.bg/

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 12 Responsible Consumption and Production
SDG 15 Life on Land

Keywords

Camera trap
Desert lion
Explainability
Wildlife conservation
Deep learning

Access to Document

10.1109/ICARAI67046.2025.11137832

An explainable CNN-based approach for classifying Desert Lions from camera trap images
© © 2050 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript (Post-print), 526 KB

Cite this

@inproceedings{a53d5856da3d438faf8dd929571306db,

title = "An explainable CNN-based approach for classifying Desert Lions from camera trap images",

abstract = "The Desert Lion population plays a significant role in promoting tourism and is of considerable ecological interest. Camera traps are used to monitor the lions; however, manually evaluating this data is labor-intensive and time-consuming for conservationists. Hence, this study developed a computer vision system that improves upon the InceptionV3 architecture to classify Desert Lions from camera trap data, with a final accuracy of 97.7 percent on the Desert Lion dataset. The final system is validated on unseen data, achieving an accuracy of 85.9 percent. Grad-CAM was also included for explainability of the model output. ",

keywords = "Camera trap, Desert lion, Explainability, Wildlife conservation, Deep learning",

author = "Jack Pears and Gelayol Golcarenarenji",

year = "2025",

month = sep,

day = "3",

doi = "10.1109/ICARAI67046.2025.11137832",

language = "English",

isbn = "9781665465670",

booktitle = "Proceedings of 2025 5th International Conference on Robotics, Automation, and Artificial Intelligence",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "International Conference Automatics, Robotics \& Artificial Intelligence, ICARAI ; Conference date: 13-06-2025 Through 15-06-2025",

url = "https://icarai.tu-sofia.bg/",

}

Pears, J & Golcarenarenji, G 2025, An explainable CNN-based approach for classifying Desert Lions from camera trap images. in Proceedings of 2025 5th International Conference on Robotics, Automation, and Artificial Intelligence. Institute of Electrical and Electronics Engineers Inc., International Conference Automatics, Robotics & Artificial Intelligence, Sozopol, Bulgaria, 13/06/25. https://doi.org/10.1109/ICARAI67046.2025.11137832

An explainable CNN-based approach for classifying Desert Lions from camera trap images. / Pears, Jack ; Golcarenarenji, Gelayol.
Proceedings of 2025 5th International Conference on Robotics, Automation, and Artificial Intelligence. Institute of Electrical and Electronics Engineers Inc., 2025.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - An explainable CNN-based approach for classifying Desert Lions from camera trap images

AU - Pears, Jack

AU - Golcarenarenji, Gelayol

PY - 2025/9/3

Y1 - 2025/9/3

N2 - The Desert Lion population plays a significant role in promoting tourism and is of considerable ecological interest. Camera traps are used to monitor the lions; however, manually evaluating this data is labor-intensive and time-consuming for conservationists. Hence, this study developed a computer vision system that improves upon the InceptionV3 architecture to classify Desert Lions from camera trap data, with a final accuracy of 97.7 percent on the Desert Lion dataset. The final system is validated on unseen data, achieving an accuracy of 85.9 percent. Grad-CAM was also included for explainability of the model output.

AB - The Desert Lion population plays a significant role in promoting tourism and is of considerable ecological interest. Camera traps are used to monitor the lions; however, manually evaluating this data is labor-intensive and time-consuming for conservationists. Hence, this study developed a computer vision system that improves upon the InceptionV3 architecture to classify Desert Lions from camera trap data, with a final accuracy of 97.7 percent on the Desert Lion dataset. The final system is validated on unseen data, achieving an accuracy of 85.9 percent. Grad-CAM was also included for explainability of the model output.

KW - Camera trap

KW - Desert lion

KW - Explainability

KW - Wildlife conservation

KW - Deep learning

U2 - 10.1109/ICARAI67046.2025.11137832

DO - 10.1109/ICARAI67046.2025.11137832

M3 - Conference contribution

SN - 9781665465670

BT - Proceedings of 2025 5th International Conference on Robotics, Automation, and Artificial Intelligence

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - International Conference Automatics, Robotics & Artificial Intelligence

Y2 - 13 June 2025 through 15 June 2025

ER -

An explainable CNN-based approach for classifying Desert Lions from camera trap images

Abstract

Conference

UN SDGs

Keywords

Access to Document

Fingerprint

Cite this