Real-Time Detection of Low-Textured Objects Based on Deep Learning - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Real-Time Detection of Low-Textured Objects Based on Deep Learning

Résumé

In this paper, a custom Single Shot Multi-box Detector (SSD) [1] is proposed for object detection on difficult scenes. The fruit 360 dataset [2], with low-textured images of different fruits and vegetables, is used as a training and validation data set. The purpose of this research is to implement the detector on mobile devices for mixed and augmented reality experiences, so a lighter weight SSD [1] model was designed while retaining its performance. The custom model is 4 times faster than the original SSD [1] model and the tests showed that it is even more accurate on the designated data set. The model is implemented in Python using Tensorflow and will soon be available on GitHub for public use.
Fichier non déposé

Dates et versions

hal-04396248 , version 1 (15-01-2024)

Identifiants

Citer

Salah-Eddine Laidoudi, Madjid Maidi, Samir Otmane. Real-Time Detection of Low-Textured Objects Based on Deep Learning. 25th IEEE International Workshop on Multimedia Signal Processing (MMSP 2023), Sep 2023, Poitiers, France. pp.1-6, ⟨10.1109/MMSP59012.2023.10337653⟩. ⟨hal-04396248⟩
28 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More