Skip to main navigation Skip to search Skip to main content

Automatic Detection and Classification of Ladybird Beetles in Wildlife Images

  • Universidad San Francisco de Quito

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

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.

Original languageEnglish
Title of host publicationC3 2025 - IEEE Colombian Caribbean Conference
EditorsYesica Beltran Gomez, Paul Sanmartin Mendoza
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798331571429
DOIs
StatePublished - 2025
Event2025 IEEE Colombian Caribbean Conference, C3 2025 - Santa Marta, Colombia
Duration: 17 Sep 202520 Sep 2025

Publication series

NameC3 2025 - IEEE Colombian Caribbean Conference

Conference

Conference2025 IEEE Colombian Caribbean Conference, C3 2025
Country/TerritoryColombia
CitySanta Marta
Period17/09/2520/09/25

Keywords

  • YOLO detector
  • computer vision
  • deep learning
  • ladybird beetle detection
  • wildlife insects

Fingerprint

Dive into the research topics of 'Automatic Detection and Classification of Ladybird Beetles in Wildlife Images'. Together they form a unique fingerprint.

Cite this