TY - GEN
T1 - Automatic Detection and Classification of Ladybird Beetles in Wildlife Images
AU - Granizo, Sebastián
AU - Pérez-Pérez, Noel
AU - Benítez, Diego S.
AU - Herrera, Marco
AU - Camacho, Oscar
AU - Baldeon-Calisto, Maria
N1 - Publisher Copyright:
© 2025 IEEE.
PY - 2025
Y1 - 2025
N2 - This work aims to improve the early detection of ladybird beetles (Coccinellidae), which are important natural predators of agricultural pests, but can also become invasive, by evaluating lightweight YOLO-based object detection models on wildlife images. We hypothesize that small YOLO architectures can achieve high detection accuracy with an efficiency suitable for real-world monitoring. As a contribution, we tested three compact models (YOLOv10, YOLOv11, YOLOv12) trained and validated on 2,899 images from the iNaturalist database, collected in Ecuador, Colombia, Chile, Peru, and Bolivia. YOLOv11 achieved the best performance at a 0.6 confidence threshold, with mAP@50 of 0.876 and 0.868 in training and test sets, respectively, demonstrating comparable results to state-of-the-art methods and robust generalization to realworld conditions.
AB - This work aims to improve the early detection of ladybird beetles (Coccinellidae), which are important natural predators of agricultural pests, but can also become invasive, by evaluating lightweight YOLO-based object detection models on wildlife images. We hypothesize that small YOLO architectures can achieve high detection accuracy with an efficiency suitable for real-world monitoring. As a contribution, we tested three compact models (YOLOv10, YOLOv11, YOLOv12) trained and validated on 2,899 images from the iNaturalist database, collected in Ecuador, Colombia, Chile, Peru, and Bolivia. YOLOv11 achieved the best performance at a 0.6 confidence threshold, with mAP@50 of 0.876 and 0.868 in training and test sets, respectively, demonstrating comparable results to state-of-the-art methods and robust generalization to realworld conditions.
KW - YOLO detector
KW - computer vision
KW - deep learning
KW - ladybird beetle detection
KW - wildlife insects
UR - https://www.scopus.com/pages/publications/105033339361
U2 - 10.1109/C366505.2025.11340178
DO - 10.1109/C366505.2025.11340178
M3 - Contribución a la conferencia
AN - SCOPUS:105033339361
T3 - C3 2025 - IEEE Colombian Caribbean Conference
BT - C3 2025 - IEEE Colombian Caribbean Conference
A2 - Gomez, Yesica Beltran
A2 - Mendoza, Paul Sanmartin
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2025 IEEE Colombian Caribbean Conference, C3 2025
Y2 - 17 September 2025 through 20 September 2025
ER -