Method for Automatic Segmentation of Vehicles in Digital Images
https://doi.org/10.32603/1993-8985-2019-22-5-6-16
Abstract
Introduction. Modern systems for active vehicle safety are designed to significantly reduce the number of road accidents. Sensors based on monocular cameras are increasingly being introduced by the world's leading automakers as an effective tool for improving traffic safety. Modern methods of localisation and classification, combined with semantic segmentation algorithms, allow for image division into independent groups of pixels corresponding to each object. However, the problem of developing segmentation algorithms ensuring improved quality of image segmentation remains to be solved.
Aim. To develop an automatic method for segmenting a given object during image analysis.
Materials and methods. An automatic method for segmenting vehicles in an image was proposed. The method presented herein allows semantic segmentation of the object of interest, based upon a priori information about the bounding boxes, which frame the objects in the image. Bounding box information is used to transform an image into a polar coordinate system where the pixels of the image act as the edges of a weighted graph. A closed contour is obtained around the object of interest by using the shortest path search algorithm and inverse transformation to the Cartesian coordinate system.
Results. The experiments confirmed the correctness of the selected area of interest based on this algorithm. Jacquard’s similarity coefficient for the Carvana open database is 85 %. Furthermore, the proposed method was applied to different classes of images from the Pascal VOC database, thus demonstrating the ability to segment objects of other classes.
Conclusion. The main contribution of the proposed method was as follows: 1) segmentation of the object of interest at the level of modern methods, and in some cases in excess thereof; 2) the study presents a new look at the way of tracking object contours.
About the Author
Ilya G. Zubov
Ltd "Next"
Russian Federation
Russian Federation
Ilya G. Zubov, Master of Engineering and Technology (2016), Ltd "Next" algorithm programmer. The author of 4 scientific publications. Area of expertise: digital image processing; applied television systems.
15 Rochdelskaya st., bldg. 13, Moscow 123022, Russia
References
1. Dagan E., Mano O., Stein G. P., Shashua A. Forward Collision Warning with a Single Camera. Proc. of the IEEE Intelligent Vehicles Symp. Parma, Italy. 14–17 June 2004. Piscataway, IEEE, 2004, pp. 37–42. doi: 10.1109/IVS.2004.1336352
2. Deng J., Dong W., Socher R., Li L.-J., Li K., Fei-Fei L. Imagenet: A Large-Scale Hierarchical Image Database. IEEE Conf. on Computer Vision and Pattern Recognition 2009. Miami, FL, USA, 20–25 June 2009. Piscataway, IEEE, 2009, pp. 248–255. doi: 10.1109/CVPR.2009.5206848
3. Redmon J., Divvala S., Girshick R., Farhadi A. You Only Look Once: Unified, Real-Time Object Detection. 2015. Available at: https://arxiv.org/pdf/1506.02640.pdf (accessed 29.08.2019)
4. Girshick R. Fast R-CNN. IEEE Intern. Conf. on Computer Vision (ICCV), 2015. Available at: https://arxiv.org/pdf/1504.08083.pdf (accessed 29.08.2019)
5. Simonyan K., Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition. Available at: https://arxiv.org/pdf/1409.1556.pdf (accessed 02.09.2019)
6. Felzenszwalb P., Girshick R., McAllester D., Ramanan D. Object Detection with Discriminatively Trained Part Based Models. IEEE trans. on pattern analysis and machine intelligence (PAMI). 2010, no. 9. Available at: http://cs.brown.edu/people/pfelzens/papers/lsvm-pami.pdf (accessed 29.08.2019)
7. Vedaldi A., Gulshan V., Varma M., Zisserman A. Multiple Kernels for Object Detection. 2009 IEEE 12th Intern. Conf. on Comp. Vision. Kyoto, Japan, 29 Sept.–2 Oct. 2009. Piscataway, IEEE, 2009, pp. 606–613. doi: 10.1109/ICCV.2009.5459183
8. Viola P., Jones M. Rapid Object Detection Using a Boosted Cascade of Simple Features. CVPR, 2001. Kauai, HI, USA, 8–14 Dec. 2001. Piscataway, IEEE, 2001. Available at: https://www.cs.cmu.edu/~efros/courses/LBMV07/Papers/viola-cvpr-01.pdf (accessed 27.08.2019)
9. Girshick R., Donahue J., Darrell T., Malik J. Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. In Proc. of the IEEE Conf. on Comp. vision and pattern recognition. Columbus, USA, 23–28 June 2014. Piscataway, IEEE, 2014, pp. 580–587. doi: 10.1109/CVPR.2014.81
10. Overfeat: Integrated Recognition, Localization and Detection Using Convolutional Networks. Available at: https://arxiv.org/pdf/1312.6229v4.pdf (accessed 20.08.2019)
11. A Review of Computer Vision Segmentation Algorithms. Available at: https://courses.cs.washington.edu/courses/cse576/12sp/notes/remote.pdf (accessed 20.08.2019)
12. Yuheng S., Yan Hao. Image Segmentation Algorithms Overview. Computer Vision and Pattern Recognition. 2017. Available at: https://arxiv.org/ftp/arxiv/papers/1707/1707.02051.pdf (accessed 20.08.2019)
13. Jyotsana M., Nirvair N. A Brief Review: Super-Pixel Based Image Segmentation Methods. Imperial J. of Interdisciplinary Research. 2016, vol. 2, iss. 9, pp. 8–12. Available at: https://pdfs.semanticscholar.org/4aee/70a322c01bc4dfd51c3164e480c3984b8071.pdf (accessed 20.08.2019)
14. Shcherba E. V. Application Analysis of Interpolation and Extrapolation Methods as Used for Image Restoration. Computer Optics. 2009, vol. 33, no. 3, pp. 336–339. Available at: http://www.computeroptics.smr.ru/KO/PDF/KO33-3/33313.pdf (accessed 20.08.2019). (In Russ.)
15. Gonsales R., Vuds R. Tsifrovaya obrabotka izobrazhenii [Digital Image Processing]. Moscow, Tekhnosfera, 2012, 834 p. (In Russ.)
16. Dechter R., Pearl J. Generalized Best-First Search Strategies and the Optimality of A*. Journal of the ACM (JACM). 1985, vol. 32, no. 3, pp. 505–536. Available at: http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.89.3090&rep=rep1&type=pdf (accessed 20.08.2019)
17. Bandyopadhyay S., Maulik U. An Evolutionary Technique Based on K-Means Algorithm for Optimal Clustering in RN. Information Sciences. 2002, vol. 146, iss. 1–4, pp. 221–237. doi: 10.1016/S0020-0255(02)00208-6
18. Rother C., Kolmogorov V., Blake A. “GrabCut” - Interactive Foreground Extraction Using Iterated Graph Cuts. ACM Trans. on Graphics. 2004, vol. 23, pp. 309–314.
19. He K., Gkioxari G., Dollar P., Girshick R. Mask R-CNN. Computer Vision and Pattern Recognition. Available at: https://arxiv.org/pdf/1703.06870.pdf (accessed 20.08.2019)
20. Graph cut based image segmentation with connectivity priors. Available at: https://pub.ist.ac.at/~vnk/papers/connectedGC-CVPR08.pdf (accessed 28.10.2019)
21. Deep Residual Learning for Image Recognition. Available at: https://arxiv.org/pdf/1512.03385.pdf(accessed 20.08.2019)
22. Carvana Image Masking Challenge. Available at: https://www.kaggle.com/c/carvana-image-masking-challenge (accessed 20.08.2019)
23. The PASCAL Visual Object Classes Challenge (VOC2007). URL: http://www.pascal-network.org/challenges/VOC/voc2007/index.html (accessed 20.08.2019)
Review
For citations:
Zubov I.G. Method for Automatic Segmentation of Vehicles in Digital Images. Journal of the Russian Universities. Radioelectronics. 2019;22(5):6-16. https://doi.org/10.32603/1993-8985-2019-22-5-6-16
Views:
851
Email this article 