Vehicle type classification using an enhanced sparse-filtered convolutional neural network with layer-skipping strategy

• Main Authors: Suryanti, Awang, Nik Mohamad Aizuddin, Nik Azmi, Rahman, Md. Arafatur
• Format: Article
• Language: English
• Published: IEEE 2020
• Subjects: T Technology (General)
• Online Access: http://umpir.ump.edu.my/id/eprint/30744/8/Vehicle%20Type%20Classification%20Using%20an%20Enhanced%20Sparse-Filtered%20Convolutional%20Neural%20Network%20with%20Layer-Skipping%20Strategy.pdf; http://umpir.ump.edu.my/id/eprint/30744/; https://doi.org/10.1109/ACCESS.2019.2963486; https://doi.org/10.1109/ACCESS.2019.2963486

In this paper, a vehicle type classification approach is proposed by using an enhanced feature extraction technique based on Sparse-Filtered Convolutional Neural Network with Layer-Skipping strategy (SF-CNNLS). To extract rich and discriminant vehicle features, we introduce Three-Channels of SF-CNNL...