تشخیص درب مبتنی بر بینایی ماشین در صحنههای بیرونی
محورهای موضوعی : عمومى
عباس وفایی
1
(دانشگاه اصفهان)
مهدی طالبی
2
(داشجوی دکتری)
سید امیرحسن منجمی
3
(-)
کلید واژه: بینایی کامپیوتر, تشخیص درب, استخراج خطوط, رنگ, بافت,
چکیده مقاله :
دربها نشانه‌ی مهمی جهت ورود و خروج از ساختمان برای افراد نابینا و رباتها میباشند. تشخیص درب در محیطهای بیرونی به یکی از مسایل دشوار در بینایی کامپیوتر تبدیل شده است؛ زیرا معمولا̎ در دربهای محیطهای بیرونی، ویژگیهای یک درب ساده مانند دستگیره، گوشهها و فضای خالی بین درب و زمین آشکار نیستند. در این مقاله، روشی برای تشخیص درب در محیطهای بیرونی ارائه می شود. پس از استخراج خطوط و حذف خطوط اضافی، ناحیه ی بین خطوط عمودی تشکیل میشود و ویژگیهای هر ناحیه شامل ارتفاع، عرض، محل، رنگ، بافت و تعداد خطوط داخل ناحیه استخراج می گردند. سپس از دانش اضافی مانند وجود درب در پایین تصویر، ارتفاع و عرض معقول درب و اختلاف رنگ و بافت درب با ناحیه‌ی اطراف، برای تصمیمگیری وجود درب استفاده می شود. این روش بر روی مجموعه تصاویر eTRIMS و مجموعه تصاویر خودمان شامل دربهای منازل، آپارتمانها و فروشگاهها امتحان شده است و نتایج ارائه‌شده، برتری روش پیشنهادی نسبت به روش‌های پیشین را نشان می‌دهد.
Doors are an important sign for blind people and robots to enter and leave the building. Detection of doors in outdoor environments has become one of the most difficult issues in computer vision; Because usually in outdoor doors, the features of a simple door such as handles, corners and empty space between the door and the floor are not obvious. In this article, a method for detecting doors in outdoor environments is presented. After extracting the lines and removing the extra lines, the area between the vertical lines is formed and the characteristics of each area including height, width, location, color, texture and number of lines inside the area are extracted. Additional knowledge such as the presence of the door at the bottom of the image, the reasonable height and width of the door, and the difference in color and texture of the door with the surrounding area are then used to determine the presence of the door. This method has been tested on our eTRIMS image collection and our image collection, including doors of houses, apartments and shops, and the presented results show the superiority of the proposed method over the previous methods.
1. R. Szeliski, Computer Vision: Algorithms and Applications, Springer, London, 2011.
2. D. Anguelov, D. Koller, E. Parker, and S. Thrun, “Detecting and Modeling Doors with Mobile Robots,” Proc. Int. Conf. on Robotics and Automation, USA, pp. 3777-3784, 2004.
3. Z. Chen, Y. Li, and S.T. Birchfield, “Visual Detection of Lintel-Occluded Doors by Integrating Multiple Cues Using Data-Driven Markov Chain Monte Carlo Process,” Robotics and Autonomous Systems, Vol. 59, No. 11, pp. 966-976, 2011.
4. J. Hensler, M. Blaich, and O. Bittel, “Real-Time Door Detection Based on Adaboost Learning Algorithm,” Proc. Int. Conf. on Research and Education in Robotics, France, pp. 61-73, 2009.
5. A.C. Murillo, J. Kosecka, J.J. Guerrero, and C. Sagues, “Visual Door Detection Integrating Appearance and Shape Cues,” Robotics and Autonomous Systems, Vol. 56, No. 6, pp. 512-521, 2008.
6. R. Sekkal, F. Pasteau, M. Babel, B. Brun, and I. Leplumey, “Simple Monocular Door Detection and Tracking,” Proc. Int. Conf. on Image Processing, Australia, pp. 3929-3933, 2013.
7. J. Liu, T. Korah, V. Hedau, V. Parameswaran, R. Grzeszczuk, and Y. Liu, “Entrance Detection from Street-View Images,” Proc. Int. Conf. on Computer Vision and Pattern Recognition Workshop (CVPR), USA, 2014.
8. S.J. Kang, H.H. Trinh, D.N. Kim, and K.H. Jo, “Entrance Detection of Buildings Using Multiple Cues,” Proc. Int. Conf. on Intelligent Information and Database Systems, Vietnam, pp. 251-260, 2010.
9. O. Teboul, I. Kokkinos, L. Simon, P.
Koutsourakis, and N. Paragios, “ShapeGrammar Parsing via Reinforcement Learning,” Proc. Int. Conf. on Computer Vision and Pattern Recognition (CVPR), USA, pp. 2273-2280, 2011.
10. H. Riemenschneider, U. Krispel, W. Thaller, M. Donoser, S. Havemann, D. Fellner, and H. Bischof, “Irregular Lattices for Complex
Shape Grammar Facade Parsing,” Proc. Int. Conf. on Computer Vision and Pattern Recognition (CVPR), USA, pp. 1640-1647, 2012.
11.M. Mathias, A. Martinovic, and L. Van Gool,“ATLAS: A Three-Layered Approach to Facade Parsing,” Int. Journal of Computer Vision (IJCV), Vol. 118, No. 1, pp. 22-48, 2016.
12.A. Cohen, A.G. Schwing, and M. Pollefeys, “Efficient Structured Parsing of Facades Using Dynamic Programming,” Proc. Int. Conf. on Computer Vision and Pattern Recognition (CVPR), USA, pp. 3206-3213, 2014.
13. R. Gadde, R. Marlet, and N. Paragios, “Learning
Grammars for Architecture-Specific Façade
Parsing,” Int. Journal of Computer Vision (IJCV), Vol. 117, No. 3, pp. 290-316, 2016. 14.C. Zhou and C. Liu, “Semantic Image
Segmentation using Low-Level Features and Contextual Cues,” Computers and Electrical Engineering, Vol. 40, pp. 844-857, 2014.
15. S. Gould and X. He, “Scene Understanding by Labeling Pixels,” Communications of the ACM, Vol. 57, No. 11, pp. 68-77, 2014.
16. J. Xiao, T. Fang, P. Zhao, M. Lhuillier, and L. Quan, “Image-based Street-side City Modeling,” ACM Transactions on Graphics, Vol. 28, No. 5, 2009.
17.B. Shuai, Z. Zuo, G. Wang, and B. Wang, “Scene Parsing with Integration of Parametric and Non-parametric Models,” IEEE Trans. on Image Processing, Vol. 25, No. 5, pp. 2379-2391, 2016.
18. P.F. Felzenszwalb and D.P. Huttenlocher, “Efficient Graph-Based Image Segmentation,” Int. Journal of Computer Vision (IJCV), Vol. 59, No. 2, pp. 167-181, 2004.
19. J. Tighe and S. Lazebnik, “Superparsing: Scalable Nonparametric Image Parsing with Superpixels,” Int. Journal of Computer Vision (IJCV), Vol. 101, No. 2, pp. 329-349, 2013.
20. C. Liu, J. Yuen, and A. Torralba, “Nonparametric Scene Parsing via Label Transfer,” IEEE Trans. on Pattern Analysis and Machine Intelligence (PAMI), Vol. 33, No. 12, pp. 2368-2382, 2011.
21. P. Razzaghi and S. Samavi, “A New Fast Approach to Nonparametric Scene Parsing,” Pattern Recognition Letters, Vol. 42, pp. 56-64, 2014.
22. M. Najafi, S. Taghavi Namin, M. Salzmann, and L. Petersson, “Sample and Filter: Nonparametric Scene Parsing via Efficient Filtering, Proc. Int. Conf. on Computer Vision and Pattern Recognition (CVPR), USA, pp. 607-615, 2016.
23. R.G. Von Gioi, J. Jakubowicz, J.M. Morel, and G. Randall, “LSD: A Fast Line Segment Detector with a False Detection Control,” IEEE Trans. on Pattern Analysis and Machine Intelligence (PAMI), Vol. 32, No. 4, pp. 722-732, 2010.
24. F. Korc and W. Forstner, “eTRIMS Image Database for Interpreting Images of Man-Made Scenes,” Technical Report, University of Bonn, 2009.
25.R.G. Von Gioi, J. Jakubowicz, J.M. Morel, and G. Randall, “LSD: a Line Segment Detector,” Image Processing On Line, Vol. 2, pp. 35-55, 2012.
26.T. Leung and J. Malik, “Representing and Recognizing the Visual Appearance of Materials using Three-dimensional Textons,” Int. Journal of Computer Vision (IJCV), Vol. 43, No. 1, pp. 29-44, 2001.
27. A.K. Jain and F. Farrokhnia, “Unsupervised Texture Segmentation using Gabor Filters,” Pattern Recognition, Vol. 24,
No. 12, pp. 1167-1186, 1991.Code available:
28. A.K. Jain and F. Farrokhnia, “Unsupervised Texture Segmentation using Gabor Filters,” Pattern Recognition, Vol. 24, No. 12, pp. 1167-1186, 1991.Code available: http://note.sonots.com/SciSoftware.html
29. D. Hoiem, A.A. Efros, and M. Hebert, “Recovering Surface Layout from an Image,” Int. Journal of Computer Vision (IJCV), Vol. 75, No. 1, pp. 151-172, 2007.
29. S. Bu, P. Han, Z. Liu, and J. Han, “Scene Parsing using Inference Embedded Deep Networks,” Pattern Recognition, Vol. 59, pp. 188-198, 2016.
30. Y. Guo, Y. Liu, A. Oerlemans, S. Lao, S. Wu, and M . S . Lew , “Deep Learning for Visual Understanding: A Review,” Neurocomputing, Vol. 187. 27-48, 2016.
31. E. Shelhamer, J. Long, and T. Darrell, “Fully Convolutional Networks for Semantic Segmentation,” IEEE Trans. on Pattern Analysis and Machine Intelligence (PAMI), Vol. 39, No. 4, pp. 640-651, 2017.
