An Automatic Method for Interest Point Detection
https://doi.org/10.32603/1993-8985-2020-23-6-6-16
Abstract
Introduction. Computer vision systems are finding widespread application in various life domains. Monocularcamera based systems can be used to solve a wide range of problems. The availability of digital cameras and large sets of annotated data, as well as the power of modern computing technologies, render monocular image analysis a dynamically developing direction in the field of machine vision. In order for any computer vision system to describe objects and predict their actions in the physical space of a scene, the image under analysis should be interpreted from the standpoint of the basic 3D scene. This can be achieved by analysing a rigid object as a set of mutually arranged parts, which represents a powerful framework for reasoning about physical interaction.
Objective. Development of an automatic method for detecting interest points of an object in an image.
Materials and methods. An automatic method for identifying interest points of vehicles, such as license plates, in an image is proposed. This method allows localization of interest points by analysing the inner layers of convolutional neural networks trained for the classification of images and detection of objects in an image. The proposed method allows identification of interest points without incurring additional costs of data annotation and training.
Results. The conducted experiments confirmed the correctness of the proposed method in identifying interest points. Thus, the accuracy of identifying a point on a license plate achieved 97%.
Conclusion. A new method for detecting interest points of an object by analysing the inner layers of convolutional neural networks is proposed. This method provides an accuracy similar to or exceeding that of other modern methods.
About the Author
I. G. Zubov
Ltd "Next"
Russian Federation
Ilya G. Zubov, Master of Engineering and Technology (2016), Ltd "Next" algorithm programmer. The author of 6 scientific publications. Area of expertise: digital image processing; applied television systems. Address: Ltd "Next", 15 Rochdelskaya St., bld. 1
Russian Federation
Ilya G. Zubov, Master of Engineering and Technology (2016), Ltd "Next" algorithm programmer. The author of 6 scientific publications. Area of expertise: digital image processing; applied television systems. Address: Ltd "Next", 15 Rochdelskaya St., bld. 1
References
1. Zeiler M. D., Fergus R. Visualizing and understanding convolutional networks. Proc. of the 13th Europ. Conf. on Computer Vision, Zurich, Switzerland, 6–12 Sept. 2014. Berlin: Springer, 2014, pp. 818–833. doi: 10.1007/978-3-319-10590-1_53
2. Simonyan K., Vedaldi A., Zisserman A. Deep inside convolutional networks: Visualising image classification models and saliency maps. Proc. of the ICLR Intern. Conf. on Learning Representations, Banff, Canada, apr. 2014. Available at: https://arxiv.org/abs/1312.6034 (accessed 15.11.2020)
3. Simon M., Rodner E., Denzler J. Part Detector Discovery in Deep Convolutional Neural Networks. Proc. of the ACCV Asian Conf. on Computer Vision, Singapore, 1–5 Nov. 2014. Berlin: Springer, 2014. Pt. 2, pp. 162–177. doi: 10.1007/978-3-319-16808-1_12
4. Zhou B., Khosla A., Lapedriza A., Oliva A., Torralba A. Object Detectors Emerge in Deep Scene CNNs. Intern. Conf. on Learning Representations, San Diego, USA, May 2015. Available at: http://hdl.handle.net/1721.1/96942 (accessed 15.11.2020)
5. Chen K., Wang J., Pang J., Cao Yu., Xiong Yu, Li X., Sun Sh., Feng W., Liu Z., Xu J., Zhang Zh., Cheng D., Zhu Ch., Cheng T., Zhao Q., Li B., Lu X., Zhu R., Wu Y., Dai J., Wang J., Shi J., Ouyang W., Change Loy Ch., Lin D. MMDetection: open MMLab Detection Toolbox and Benchmark, 13 p. Available at: https://arxiv.org/pdf/1906.07155.pdf (accessed 02.06.2020)
6. He K., Zhang X., Ren S., Sun J. Deep Residual Learning for Image Recognition. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, Las Vegas, USA, 27–30 June 2016. Piscataway: IEEE, 2016, art. 16541111. doi: 10.1109/CVPR.2016.90
7. Simonyan K., Zisserman A. Very Deep Convolutional Networks for large-Scale Image Recognition. Apr. 2015, 14 p. Available at: https://arxiv.org/abs/1409.1556 (accessed 02.06.2020)
8. Howard A. G., Zhu M., Chen B., Kalenichenko D., Wang W., Weyand T., Andreetto M., Adam H. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. Available at: https://arxiv.org/abs/1704.04861 (accessed 02.06.2020)
9. Iandola F. N., Han S., Moskewicz M. W., Ashraf K., Dally W. J., Keutzer K. SqueezeNet: AlexNet-Level Accuracy with 50x Few-er Parameters and <0.5MB Model Size. Available at: https://arxiv.org/abs/1602.07360 (accessed 02.06.2020)
10. Redmon J., Farhadi A. YOLOv3: An Incremental Improvement. Available at: https://arxiv.org/abs/1804.02767 (accessed 02.06.2020)
11. Carvana Image Masking Challenge. Available at: https://www.kaggle.com/c/carvana-image-masking-challenge (accessed 02.06.2020)
12. Viola P., Jones M. Rapid object detection using a boosted cascade of simple features. Proc. of the IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, Kauai, USA, 8–14 Dec. 2001. Piscataway: IEEE, 2001, art. 7176899. doi: 10.1109/CVPR.2001.990517
13. Silva S. M., Jung C. R. License Plate Detection and Recognition in unconstrained Scenarios // Computer Vision, ECCV 2018, 15th Europ. Conf. 8–14 Sept. 2018, Munich, Germany. Berlin: Springer, 2018, pp. 593–609. doi: 10.1007/978-3-030-01258-8_36
14. He K., Gkioxari G., Dollar P., Girshick R. Mask R-Cnn.IEEE Int. Conf. on Computer Vision (ICCV). Venice, Italy, 22–29 Oct. 2017. Piscataway: IEEE, 2017, art. 17467816. doi: 10.1109 /ICCV.2017.322
15. Haar Cascad license plate detection. Weights for the model. Available at: https://github.com/opencv/opencv/blob/master/data/haarcascades/haarcascade_licence_plate_rus_16stages.xml (accessed 15.11.2020)
16. Silva S. M., Jung C. R. License Plate Detection and Recognition in Unconstrained Scenarios. Available at: http://sergiomsilva.com/pubs/alpr-unconstrained/ (accessed 31.05.2020)
17. Nomeroff Net. A Open Source Python License Plate Recognition Framework. Available at: https://nomeroff.net.ua/ (accessed 31.05.2020)
18. PyTorch implementation of YOLOv3. Available at: https://docs.openvinotoolkit.org/latestomz_models_intel_person_vehicle_bike_detection_crossroad_1016_description_person_vehicle_bike_detection_crossroad_1016.html (accessed 31.05.2020)
19. Xu Z., Yang W., Meng A., Lu N., Huang H., Ying C., Huang L. Towards End-to-End License Plate Detection and Recognition: A Large Dataset and Baseline. Com-puter Vision, ECCV 2018, 15th Europ. Conf. Munich, Germany, 8–14 Sep. 2018. Berlin: Springer, pp. 261–277. doi: 10.1007/978-3-030-01261-8_16
Review
For citations:
Zubov I.G. An Automatic Method for Interest Point Detection. Journal of the Russian Universities. Radioelectronics. 2020;23(6):6-16. (In Russ.) https://doi.org/10.32603/1993-8985-2020-23-6-6-16
Views:
575
Email this article 