Training An Embedded Object Detector For Industrial Settings Without Real Images - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Training An Embedded Object Detector For Industrial Settings Without Real Images

Résumé

In an industrial environment, object detection is a challenging task due to the absence of real images and real-time requirements for the object detector, usually embedded in a mobile device. Using 3D models, it is however possible to create a synthetic dataset to train a neural network, although the performance on real images is limited by the domain gap. In this paper, we study the performance of a Convolutional Neural Network (CNN) designed to detect objects in real-time: Single-Shot Detector (SSD) with a MobileNet backbone. We train SSD with synthetic images only, and apply extensive data augmentation to reduce the domain gap between synthetic and real images. On the T-LESS dataset, SSD performs better than Mask R-CNN trained on the same synthetic images, with MobileNet-V2 and MobileNet-V3 Large as backbone. Our results also show the huge improvement enabled by an adequate augmentation strategy.
Fichier principal
Vignette du fichier
ICIP2021Training.pdf (5.64 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03531483 , version 1 (18-01-2022)

Identifiants

Citer

Julia Cohen, Carlos F Crispim-Junior, Jean-Marc Chiappa, Laure Tougne. Training An Embedded Object Detector For Industrial Settings Without Real Images. 2021 IEEE International Conference on Image Processing (ICIP), Sep 2021, Anchorage, France. pp.714-718, ⟨10.1109/ICIP42928.2021.9506574⟩. ⟨hal-03531483⟩
44 Consultations
103 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More