Deep Learning-Based Vehicle Classification for Low Quality Images

被引:12
作者
Tas, Sumeyra [1 ]
Sari, Ozgen [1 ]
Dalveren, Yaser [2 ]
Pazar, Senol [3 ,4 ]
Kara, Ali [5 ]
Derawi, Mohammad [6 ]
机构
[1] Atilim Univ, Grad Sch Nat & Appl Sci, TR-06830 Ankara, Turkey
[2] Atilim Univ, Dept Avion, TR-06830 Ankara, Turkey
[3] Biruni Univ, Dept Comp Programming, TR-34010 Istanbul, Turkey
[4] Yildiz Tech Univ Ikitelli Technopk, Ankageo Co Ltd, TR-34220 Istanbul, Turkey
[5] Gazi Univ, Dept Elect & Elect Engn, TR-06570 Ankara, Turkey
[6] Norwegian Univ Sci & Technol, Dept Elect Syst, N-2815 Gjovik, Norway
关键词
vehicle classification; convolutional neural network; deep learning; low resolution; low quality; SYSTEMS;
D O I
10.3390/s22134740
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
This study proposes a simple convolutional neural network (CNN)-based model for vehicle classification in low resolution surveillance images collected by a standard security camera installed distant from a traffic scene. In order to evaluate its effectiveness, the proposed model is tested on a new dataset containing tiny (100 x 100 pixels) and low resolution (96 dpi) vehicle images. The proposed model is then compared with well-known VGG16-based CNN models in terms of accuracy and complexity. Results indicate that although the well-known models provide higher accuracy, the proposed method offers an acceptable accuracy (92.9%) as well as a simple and lightweight solution for vehicle classification in low quality images. Thus, it is believed that this study might provide useful perception and understanding for further research on the use of standard low-cost cameras to enhance the ability of the intelligent systems such as intelligent transportation system applications.
引用
收藏
页数:12
相关论文
共 35 条
[1]   End-to-End View-Aware Vehicle Classification via Progressive CNN Learning [J].
Cao, Jiawei ;
Wang, Wenzhong ;
Wang, Xiao ;
Li, Chenglong ;
Tang, Jin .
COMPUTER VISION, PT I, 2017, 771 :729-737
[2]   Vision-Based Occlusion Handling and Vehicle Classification for Traffic Surveillance Systems [J].
Chang, Jianlong ;
Wang, Lingfeng ;
Meng, Gaofeng ;
Xiang, Shiming ;
Pan, Chunhong .
IEEE INTELLIGENT TRANSPORTATION SYSTEMS MAGAZINE, 2018, 10 (02) :80-92
[3]  
Chauhan MS, 2019, PROCEEDINGS OF THE TENTH INTERNATIONAL CONFERENCE ON INFORMATION AND COMMUNICATION TECHNOLOGIES AND DEVELOPMENT (ICTD), DOI [10.1145/3287098.3287118, 10.1109/southeastcon42311.2019.9020511]
[4]   VIDEO-BASED VEHICLE DETECTION AND CLASSIFICATION IN CHALLENGING SCENARIOS [J].
Chen, Yiling ;
Qin, GuoFeng .
INTERNATIONAL JOURNAL ON SMART SENSING AND INTELLIGENT SYSTEMS, 2014, 7 (03) :1077-1094
[5]   Vehicle Type Classification Using a Semisupervised Convolutional Neural Network [J].
Dong, Zhen ;
Wu, Yuwei ;
Pei, Mingtao ;
Jia, Yunde .
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2015, 16 (04) :2247-2256
[6]   Vehicle Classification in Intelligent Transport Systems: An Overview, Methods and Software Perspective [J].
Gholamhosseinian, Ashkan ;
Seitz, Jochen .
IEEE OPEN JOURNAL OF INTELLIGENT TRANSPORTATION SYSTEMS, 2021, 2 :173-194
[7]   Detection and classification of vehicles [J].
Gupte, S ;
Masoud, O ;
Martin, RFK ;
Papanikolopoulos, NP .
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2002, 3 (01) :37-47
[8]   A Super-Learner Ensemble of Deep Networks for Vehicle-Type Classification [J].
Hedeya, Mohamed A. ;
Eid, Ahmad H. ;
Abdel-Kader, Rehab F. .
IEEE ACCESS, 2020, 8 :98266-98280
[9]  
Hicham B, 2018, 2018 IEEE 5TH INTERNATIONAL CONGRESS ON INFORMATION SCIENCE AND TECHNOLOGY (IEEE CIST'18), P313, DOI 10.1109/CIST.2018.8596500
[10]  
Huilgol P., 2020, Top 4 pretrained models for image classification with Python code