Integrated convolutional neural network model with statistical moments layer for vehicle classification - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Integrated convolutional neural network model with statistical moments layer for vehicle classification

(1) , (1) , (2)
1
2

Résumé

Vehicle classification is an important topic which is still under research consideration because of its role in road surveillance, security system, traffic monitoring, and accident prevention. In this paper, we propose a deep learning model for vehicles classification using the Convolutional Neural Networks (CNN) integrated with a statistical moments layer. We referred to the model as ICNN. As an additional layer, the moments layer extracts statistical moments features from the feature maps obtained from convolutions layers. The moments layer is fed the fully-connected classifier of the network which is fine-tuned to get better results. Our Integrated CNN model (ICNN) achieves 97.1% accuracy compared to the most popular algorithms used in this field such as K Nearest Neighbour (KNN), and Support Vector Machine (SVM), which known as good tools for object classification.
Fichier non déposé

Dates et versions

hal-02465128 , version 1 (03-02-2020)

Identifiants

Citer

Amel Tuama, Hasan Abdulrahman, Baptiste Magnier. Integrated convolutional neural network model with statistical moments layer for vehicle classification. ICMV 2019 - the 12th International Conference on Machine Vision, Nov 2019, Amsterdam, Netherlands. pp.89, ⟨10.1117/12.2559375⟩. ⟨hal-02465128⟩
16 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook Twitter LinkedIn More