An Abstraction for Correspondence Search Using Task-Based Controls

详细信息    查看全文

• 作者：Gregor Miller (15)
  Sidney Fels (15)
  
  15. Human Communication Technologies Laboratory ; University of British Columbia ; Vancouver ; BC ; V6T 1Z4 ; Canada
  
• 刊名：Lecture Notes in Computer Science
• 出版年：2015
• 出版时间：2015
• 年：2015
• 卷：9009
• 期：1
• 页码：229-242
• 全文大小：9,011 KB
• 参考文献：1. Miller, G., Fels, S.: OpenVL: a task-based abstraction for developer-friendly computer vision. In: Proceedings of the 13th IEEE Workshop on the Applications of Computer Vision (WACV), WVM 2013, pp. 288鈥?95. IEEE (2013)
  2. Miller, G., Jang, D., Fels, S.: Developer-friendly segmentation using OpenVL, a high-level task-based abstraction. In: Proceedings of the 1st IEEE Workshop on User-Centred Computer Vision (UCCV), WVM 2013, pp. 31鈥?6. IEEE, New York City (2013)
  3. Oleinikov, G., Miller, G., Little, J.J., Fels, S.: Task-based control of articulated human pose detection for openvl. In: Proceedings of the 14th IEEE Winter Conference on Applications of Computer Vision, WACV 2014, pp. 682鈥?89. IEEE, New York City (2014)
  4. Jang, D., Miller, G., Fels, S., Oldridge, S.: User oriented language model for face detection. In: Proceedings of the 1st Workshop on Person-Oriented Vision (POV), WVM 2011, pp. 21鈥?6. IEEE, New York City (2011)
  5. Bradski, G, Kaehler, A (2008) Learning OpenCV: Computer Vision with the OpenCV Library. O鈥橰eilly Media, Inc., Sebastopol
  6. Matsuyama, T., Hwang, V.: SIGMA: a framework for image understanding integration of bottom-up and top-down analyses. In: Proceedings of the 9th International Joint Conference on Artificial Intelligence, vol. 2, pp. 908鈥?15. Morgan Kaufmann Publishers Inc. (1985)
  7. Kohl, C., Mundy, J.: The development of the image understanding environment. In: Proceedings of the Conference on Computer Vision and Pattern Recognition, CVPR 1994, pp. 443鈥?47. IEEE Computer Society Press, Los Alamitos (1994)
  8. Clouard, R, Elmoataz, A, Porquet, C, Revenu, M (1999) Borg: a knowledge-based system for automatic generation of image processing programs. Trans. Pattern Anal. Mach. Intell. 21: pp. 128-144 CrossRef
  9. Mundy, J (1995) The image understanding environment program. IEEE Expert Intell. Syst. Appl. 10: pp. 64-73
  10. Panin, G (2011) Model-based Visual Tracking: The OpenTL Framework. Wiley, Chichester CrossRef
  11. Konstantinides, K, Rasure, JR (1994) The Khoros software development environment for image and signal processing. IEEE Trans. Image Process. 3: pp. 243-252 CrossRef
  12. Peterson, J., Hudak, P., Reid, A., Hager, G.D.: FVision: a declarative language for visual tracking. In: Ramakrishnan, I.V. (ed.) PADL 2001. LNCS, vol. 1990, pp. 304鈥?21. Springer, Heidelberg (2001)
  13. Firschein, O, Strat, TM (1997) RADIUS: Image Understanding For Imagery Intelligence. Morgan Kaufmann, San Francisco
  14. Makarenko, A., Brooks, A., Kaupp, T.: On the benefits of making robotic software frameworks thin. In: Proceedings of the Workshop on Measures and Procedures for the Evaluation of Robot Architectures and Middleware, IROS 2007. IEEE, New York City (2007). Invited Presentation
  15. Lowe, DG (2004) Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60: pp. 91 CrossRef
  16. Bay, H, Ess, A, Tuytelaars, T, Gool, L (2008) Speeded-up robust features (surf). Comput. Vis. Image Underst. 110: pp. 346-359 CrossRef
  17. Rublee, E., Rabaud, V., Konolige, K., Bradski, G.: Orb: An efficient alternative to sift or surf. In: Proceedings of the 2011 International Conference on Computer Vision, ICCV 2011, pp. 2564鈥?571. IEEE Computer Society, Washington, DC (2011)
  18. Forss茅n, P.E., Lowe, D.: Shape descriptors for maximally stable extremal regions. In: IEEE International Conference on Computer Vision, vol. CFP07198-CDR. IEEE Computer Society, Rio de Janeiro (2007)
  19. Ortiz, R.: Freak: Fast retina keypoint. In: Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), CVPR 2012, pp. 510鈥?17. IEEE Computer Society, Washington, DC (2012)
  20. Bauer, J, S眉nderhauf, N, Protzel, P (2007) Comparing several implementations of two recently published feature detectors. Intell. Auton. Veh. 6: pp. 143-148
  21. Juan, L, Gwon, O (2009) A comparison of SIFT, PCA-SIFT and SURF. Int. J. of Image Process. 3: pp. 143-152
  22. Yu, G., Morel, J.M.: A fully affine invariant image comparison method. In: IEEE International Conference on Acoustics, Speech and Signal Processing, 2009, ICASSP 2009, pp. 1597鈥?600 (2009)
  23. Morel, JM, Yu, G (2009) Asift: a new framework for fully affine invariant image comparison. SIAM J. Img. Sci. 2: pp. 438-469 CrossRef
  24. Mikolajczyk, K, Tuytelaars, T, Schmid, C, Zisserman, A, Matas, J, Schaffalitzky, F, Kadir, T, Gool, LV (2005) A comparison of affine region detectors. Int. J. Comput. Vis. 65: pp. 43-72 CrossRef
  
• 作者单位：Computer Vision - ACCV 2014 Workshops
• 丛书名：978-3-319-16630-8
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349

文摘

The correspondence problem (finding matching regions in images) is a fundamental task in computer vision. While the concept is simple, the complexity of feature detectors and descriptors has increased as they provide more efficient and higher quality correspondences. This complexity is a barrier to developers or system designers who wish to use computer vision correspondence techniques within their applications. We have designed a novel abstraction layer which uses a task-based description (covering the conditions of the problem) to allow a user to communicate their requirements for the correspondence search. This is mainly based on the idea of variances which describe how sets of images vary in blur, intensity, angle, etc. Our framework interprets the description and chooses from a set of algorithms those that satisfy the description. Our proof-of-concept implementation demonstrates the link between the description set by the user and the result returned. The abstraction is also at a high enough level to hide implementation and device details, allowing the simple use of hardware acceleration.