Communication Dans Un Congrès Année : 2024

A New Lightweight Hybrid Graph Convolutional Neural Network - CNN Scheme for Scene Classification Using Object Detection Inference

Résumé

Scene understanding plays an important role in several high-level computer vision applications, such as autonomous vehicles, intelligent video surveillance, or robotics. However, too few solutions have been proposed for indoor/outdoor scene classification to ensure scene context adaptability for computer vision frameworks. We propose the first Lightweight Hybrid Graph Convolutional Neural Network (LH-GCNN)-CNN framework as an add-on to object detection models. The proposed approach uses the output of the CNN object detection model to predict the observed scene type by generating a coherent GCNN representing the semantic and geometric content of the observed scene. This new method, applied to natural scenes, achieves an efficiency of over 90% for scene classification in a COCO-derived dataset containing a large number of different scenes, while requiring fewer parameters than traditional CNN methods. For the benefit of the scientific community, we will make the source code publicly available: https://github.com/Avmanbe2h/Hvbrid-GCNN-CNN.

Fichier non déposé

Dates et versions

hal-05196305 , version 1 (01-08-2025)

Identifiants

Citer

Ayman Beghdadi, Azeddine Beghdadi, Mohib Ullah, Faouzi Alaya Cheikh, Malik Mallem. A New Lightweight Hybrid Graph Convolutional Neural Network - CNN Scheme for Scene Classification Using Object Detection Inference. 12th European Workshop on Visual Information Processing (EUVIP 2024), Sep 2024, Geneva, Switzerland. pp.1-6, ⟨10.1109/EUVIP61797.2024.10772944⟩. ⟨hal-05196305⟩
128 Consultations
0 Téléchargements

Altmetric

Partager

  • More