DOI: 10.14704/nq.2018.16.6.1641

Convolutional Neural Network and the Recognition of Vehicle Types

Dewen Seng, Bin Lin, Jing Chen


In machine learning, a convolutional neural network (ConvNet) is a class of deep, feed-forward artificial neural networks. Featured by low computing load and fast convergence, the network has been successfully applied to pattern recognition. This paper gives a detailed introduction to the structure, working principles and advantages of ConvNet, and applies it to the recognition of vehicle types. In reference to previous research, two deep neural networks were created, namely VGG 16 and AlexNet. The experimental results show that our methods have performed well in vehicle classification in complex background images.


Convolutional Neural Network (ConvNet), Recognition Algorithm, Pattern Recognition, Pooling Layer, Vehicle Recognition

Full Text:



Akbari MG, Rezaei AH. Order statistics using fuzzy random variables. Statistics & Probability Letters 2009; 79(8):1031-37.

Arribas JI, Cid-Sueiro J, Adali T. Neural architectures for parametric estimation of a posteriori probabilities by constrained conditional density functions, neural networks for signal processing IX. Signal Processing Society Workshop IEEE 1999: 263-72.

Geismann P, Schneider G. A two-staged approach to visionbased pedestrian recognition using HAAR and HOG features. Intelligent Vehicles Symposium 2008; (5): 554-59.

Hasler S, Wersing H, Kirstein S, Körner E. Large-scale realtime object identification based on analytic features. International Conference on Artificial Neural Networks Springer Verlag 2009; (5): 663-72.

Huang Z, Liu X, Liu X. Accuracy and applicability analysis of Anatomical Landmarks point registration image guided surgery of neurosurgery. International Journal Bioautomation 2017; 21(S4): 293-304

Melorose J, Perroy R, Careas S. Efficient backprop. Neural Networks Tricks of the Trade 2015; 1524(1): 9-50.

Olshausen BA, Field DJ. Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature 1996; 381(6583): 607-09.

Serre T, Riesenhuber M, Louie J, Poggio T. On the role of object-specific features for real world object recognition in biological vision. International Workshop on Biologically Motivated Computer Vision 2002: 387-97.

Shamma S. On the role of space and time in auditory processing. Trends in Cognitive Science 2013; 5(8): 140-48.

Ström N. Sparse connection and pruning in large dynamic artificial neural networks. Fifth European Conference on Speech Communication and Technology 1997: 2807-10.

Sun C, Feng CB, Exponential periodicity and stability of delayed neural networks. Mathematics & Computers in Simulation 2004; 66(6): 469-78.

Szarvas M, Yoshizawa A, Yamamoto M, Ogata J. Pedestrian detection with convolutional neural networks. Intelligent Vehicles Symposium Proceedings IEEE 2005; 14(5): 224-29.

Pfister T, Charles J, Zisserman A. Flowing convnets for human pose estimation in videos. Proceedings of the IEEE International Conference on Computer Vision 2015: 1913-21.

Wang TC, Xie YZ, Yan H. Research of multi sensor information fusion technology based on extension neural network. Mathematical Modelling of Engineering Problems 2016; 3(3):129-34.

Won Y, Gader PD, Coffield PC. Morphological shared-weight networks with applications to automatic target recognition. IEEE Transactions on Neural Networks 1997; 8(5): 1195-203.

Yeung RW, Li SYR, Cai N, Zhang Z. Network coding theory: single sources. Foundations & Trends® in Communications & Information Theory 2005; 2(2): 241-329.

Supporting Agencies

| NeuroScience + QuantumPhysics> NeuroQuantology :: Copyright 2001-2019