A New Lightweight Hybrid Graph Convolutional Neural Network -- CNN Scheme for Scene Classification using Object Detection Inference
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909262960132096 |
|---|---|
| author | Beghdadi, Ayman Beghdadi, Azeddine Ullah, Mohib Cheikh, Faouzi Alaya Mallem, Malik |
| author_facet | Beghdadi, Ayman Beghdadi, Azeddine Ullah, Mohib Cheikh, Faouzi Alaya Mallem, Malik |
| contents | 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/Aymanbegh/Hybrid-GCNN-CNN. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_14658 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A New Lightweight Hybrid Graph Convolutional Neural Network -- CNN Scheme for Scene Classification using Object Detection Inference Beghdadi, Ayman Beghdadi, Azeddine Ullah, Mohib Cheikh, Faouzi Alaya Mallem, Malik Computer Vision and Pattern Recognition Artificial Intelligence 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/Aymanbegh/Hybrid-GCNN-CNN. |
| title | A New Lightweight Hybrid Graph Convolutional Neural Network -- CNN Scheme for Scene Classification using Object Detection Inference |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2407.14658 |