Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon openaccess Car detection and classification using cascade model

  • Author(s): Jun Liang 1 ; Xu Chen 1 ; Mei-ling He 1 ; Long Chen 1 ; Tao Cai 2 ; Ning Zhu 3
    • View affiliations
  • Source: Volume 12, Issue 10, December 2018, p. 1201 – 1209
    DOI:  10.1049/iet-its.2018.5270 , Print ISSN 1751-956X, Online ISSN 1751-9578
This is an open access article published by the IET under the Creative Commons Attribution-NonCommercial-NoDerivs License (http://creativecommons.org/licenses/by-nc-nd/3.0/)
Received 13/09/2017, Accepted 07/06/2018, Revised 23/05/2018, Published 30/07/2018

In recent years, a number of vision-based classification methods have been proposed. However, a few of them were paid attention to vehicle-type classification in a real-world image, which is an important part of the intelligent transportation system. Owing to the large variances of the car appearance in images, it is critical to capture the discriminative object parts that can provide key information about the car pose. In the authors’ project, the traditional convolutional neural network (CNN) models are modified and experiments are followed as well. The model has two main contributions. First, the output shows a confidence score of how likely this box contains a car for each predicted box, which has some certain advantages compared with other models and is quite different from traditional approaches. Another contribution is the fine-grained classification of the makers and models of a car, which need to train the bounding box predictors as part of the network training. The experiment results show that data enhancement and pre-train of CNNs with original images can classify the vehicle makes and models with a high accuracy of nearly 80%. Cropping images by cascade methods can increase the precision to 86.6%.

Inspec keywords: neural nets; learning (artificial intelligence); object detection; computer vision; feature extraction; pattern classification; image classification; traffic engineering computing

Other keywords: discriminative object parts; intelligent transportation system; predicted box; vehicle-type classification; bounding box predictors; real-world image; traditional approaches; key information; vision-based classification methods; traditional convolutional neural network models; fine-grained classification; confidence score; original images; network training; car appearance; cascade model; cascade methods; authors

Subjects: Neural computing techniques; Image recognition; Optical, image and video signal processing; Computer vision and image processing techniques; Other topics in statistics

References

    1. 1)
      • 17. Hsieh, J.W., Chen, L.C., Chen, D.Y., et al: ‘Vehicle make and model recognition using symmetrical SURF’. IEEE Int. Conf. Advanced Video and Signal Based Surveillance, 2013, pp. 472–477.
    2. 2)
      • 3. Kong, X., Song, X., Xia, F., et al: ‘LoTAD: long-term traffic anomaly detection based on crowd sourced bus trajectory data’, World Wide Web-Internet Web Inf. Syst., 2017, 21, (3), pp. 1–23.
    3. 3)
      • 11. Sande, K.E.A.V.D., Uijlings, J.R.R., Gevers, T., et al: ‘Segmentation as selective search for object recognition’. Proc./IEEE Int. Conf. Computer Vision, 2011, pp. 1879–1886.
    4. 4)
      • 23. Wang, L., Guo, S., Huang, W., et al: ‘Places205-VGGNet models for scene recognition’, arXiv:1508.01667.
    5. 5)
      • 27. Yang, F., Choi, W., Lin, Y.: ‘Exploit all the layers: fast and accurate CNN object detector with scale dependent pooling and cascaded rejection classifiers’. Computer Vision and Pattern Recognition, 2016, pp. 2129–2137.
    6. 6)
      • 33. Zhou, Y., Cheung, N.M.: ‘Vehicle classification using transferable deep neural network features’, arXiv preprint arXiv: (1601.01145), 2016.
    7. 7)
      • 14. Gu, C., Ren, X.: ‘Discriminative mixture-of-templates for viewpoint classification’. Computer Vision – ECCV 2010 – European Conf. Computer Vision, Proc. DBLP, Heraklion, Crete, Greece, 5–11 September 2010, pp. 408–421.
    8. 8)
      • 12. Girshick, R.B., Felzenszwalb, P.F., Mcallester, D.: ‘Object detection with grammar models’. Int. Conf. Neural Information Processing Systems, 2011, pp. 442–450.
    9. 9)
      • 31. Krause, J., Stark, M., Jia, D., et al: ‘3D object representations for fine-grained categorization’. IEEE Int. Conf. Computer Vision Workshops, 2014, pp. 554–561.
    10. 10)
      • 32. Donahue, J., Jia, Y., Vinyals, O., et al: ‘DeCAF: a deep convolutional activation feature for generic visual recognition’ (University of California Berkeley Brigham Young University, 2013), pp. 647–655.
    11. 11)
      • 6. Hoai, M., Zisserman, A.: ‘Discriminative sub-categorization’. IEEE Conf. Computer Vision and Pattern Recognition, 2013, pp. 1666–1673.
    12. 12)
      • 9. Martins, J.C., Caeiro, J.J., Sousa, L.A.: ‘Nonlinear system identification using constellation based multiple model adaptive estimators’. Signal Processing Conf., 2014, pp. 1217–1221.
    13. 13)
      • 8. Simon, M., Rodner, E.: ‘Neural activation constellations: unsupervised part model discovery with convolutional networks’, Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), Washington, DC, USA, 2015, pp. 1143–1151.
    14. 14)
      • 13. Simonyan, K., Zisserman, A.: ‘Very deep convolutional networks for large-scale image recognition’, Comput. Sci., 2014.
    15. 15)
      • 1. Kong, X., Xia, F., Ning, Z., et al: ‘Mobility dataset generation for vehicular social networks based on floating car data’, IEEE Trans. Veh. Technol., 2018, PP, (99), p. 1.
    16. 16)
      • 19. Hsiao, E., Sinha, S.N., Ramnath, K., et al: ‘Car make and model recognition using 3D curve alignment’. Applications of Computer Vision, 2014, p. 1.
    17. 17)
      • 29. Ren, J., Chen, X., Liu, J., et al: ‘Accurate single stage detector using recurrent rolling convolution’, arXiv:1704.05776, 2017.
    18. 18)
      • 30. Chabot, F., Chaouch, M., Rabarisoa, J., et al: ‘Deep MANTA: a coarse-to-fine many-task network for joint 2D and 3D vehicle analysis from monocular image’. IEEE Conf. Computer Vision and Pattern Recognition, 2017, pp. 1827–1836.
    19. 19)
      • 4. Felzenszwalb, P.F., Girshick, R.B., Mcallester, D., et al: ‘Object detection with discriminatively trained part-based models’, IEEE Trans. Pattern Anal. Mach. Intell., 2010, 32, (9), p. 1627.
    20. 20)
      • 16. Pedersoli, M., Gonzalez, J., Hu, X., et al: ‘Toward real-time pedestrian detection based on a deformable template model’, IEEE Trans. Intell. Transp. Syst., 2014, 15, (1), pp. 355–364.
    21. 21)
      • 24. Krizhevsky, A., Sutskever, I., Hinton, G.E.: ‘ImageNet classification with deep convolutional neural networks’, Adv. Neural. Inf. Process. Syst., 2012, 25, p. 2012.
    22. 22)
      • 21. Cai, Y., Wang, H., Chen, L., et al: ‘Robust vehicle recognition algorithm using visual saliency and deep convolutional neural networks’, Jiangsu Daxue Xuebao, 2015, 36, (3), pp. 331–336.
    23. 23)
      • 2. Rahim, A., Kong, X., Xia, F., et al: ‘Vehicular social networks: a survey’, Pervasive Mob. Comput., 2017, 43, pp. 96–113.
    24. 24)
      • 18. Saravi, S., Edirisinghe, E.A.: ‘Vehicle make and model recognition in CCTV footage’. Int. Conf. Digital Signal Processing, 2013, pp. 1–6.
    25. 25)
      • 15. Sermanet, P., Kavukcuoglu, K., Chintala, S., et al: ‘Pedestrian detection with unsupervised multi-stage feature learning’. Computer Vision and Pattern Recognition, 2013, pp. 3626–3633.
    26. 26)
      • 10. Krause, A., Guestrin, C. E.: ‘Near-optimal nonmyopic value of information in graphical models’, Comput. Sci., 2012, 35, (1), pp. 557–591.
    27. 27)
      • 28. Cai, Z., Fan, Q., Feris, R.S., et al: ‘A unified multi-scale deep convolutional neural network for fast object detection’, 14th European Conference on Computer Vision, Amsterdam, The Netherlands, 2016, pp. 354–370.
    28. 28)
      • 25. Prior, I.S.D.: ‘3D object proposals for accurate object class detection’, Lect. Notes Bus. Inf. Process., 2015, 122, pp. 34–45.
    29. 29)
      • 5. Pepik, B., Stark, M., Gehler, P., et al: ‘Teaching 3D geometry to deformable part models’. IEEE Conf. Computer Vision and Pattern Recognition, 2012, pp. 3362–3369.
    30. 30)
      • 20. Zhang, H.B., Hai-Ling, L.I., Huang, X.T., et al: ‘Research and implementation of vehicle-type recognition method based on HOG features of vehicle frontal face’, Comput. Simul., 2015.
    31. 31)
      • 26. Chen, X., Kundu, K., Zhang, Z., et al: ‘Monocular 3D object detection for autonomous driving’. IEEE Conf. Computer Vision and Pattern Recognition, 2016, pp. 2147–2156.
    32. 32)
      • 22. Jia, Y.: ‘Caffe: an open source convolutional architecture for fast feature embedding’, 2014. Available at http://caffe.berkeleyvision.org/, accessed January 2017.
    33. 33)
      • 7. Balthazor, R.L., Mcharg, M.G., Enloe, C.L., et al: ‘Methodology of evaluating the science benefit of various satellite/sensor constellation orbital parameters to an assimilative data forecast model’, Radio Sci., 2016, 50, (4), pp. 318–326.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-its.2018.5270
Loading

Related content

content/journals/10.1049/iet-its.2018.5270
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address