Invertebrates Detection with YOLOv5: Towards Study of Soil Organisms Using Deep Learning - IMT Mines Alès Access content directly
Conference Poster Year : 2022

Invertebrates Detection with YOLOv5: Towards Study of Soil Organisms Using Deep Learning

Emma Pruvost
  • Function : Author
Hadrien Tulet
  • Function : Author
Etienne Delort
  • Function : Author
Ghulam-Sakhi Shokouh
  • Function : Author
Baptiste Magnier
Christophe Jourdan
Emma Belaud
  • Function : Author
Mickael Hedde

Abstract

The investigation of the complicated underground life via automatic technique is in high demand in recent days. Using Convolutional Neural Network (CNN) to detect soil in- vertebrates is an interesting approach, although most studies on the topic have focused on other solutions. The creation of state-of-the-art technique through this work will be a significant step in soil ecology, bio-science and agriculture in effectively exploring the different types of invertebrates, their behaviors and interactions. In this paper, generating and annotating images containing seven classes of invertebrates is firstly presented. Then various automatic detections of the invertebrates using YOLOv5 algorithm on these images are performed and evaluated. Index Terms—Soil fauna, invertebrate detection, small object detection, invertebrate dataset, YOLOv5, cluttered background
Fichier principal
Vignette du fichier
[Poster]_invertebrates-detection-with-yolov5.pdf (769.08 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03790169 , version 1 (04-10-2022)

Identifiers

  • HAL Id : hal-03790169 , version 1

Cite

Emma Pruvost, Hadrien Tulet, Etienne Delort, Ghulam-Sakhi Shokouh, Philippe Montesinos, et al.. Invertebrates Detection with YOLOv5: Towards Study of Soil Organisms Using Deep Learning. EUVIP 2022 - The 10th European Workshop on Visual Information Processing, Sep 2022, Lisbone, Portugal. , 2022. ⟨hal-03790169⟩
67 View
165 Download

Share

Gmail Mastodon Facebook X LinkedIn More