ABSTRACT
Image matching in large scale environments is challenging due to the large number of features used in typical representations. In this paper we investigate methods for reducing the number of SIFT (Scale invariant feature transform) features in an image based localization application. We find that reductions of up to 59% in the number of features can result in improved performance of a naive matching algorithm for highly redundant data sets. However, those improvements do not carry over to visual bag of words, where a more moderate feature reduction (up to 16%) is often needed to maintain performance similar to the non-reduced set. Our reduced features have performed better than other robust feature descriptors namely HoG, GIST and ORB on all data sets with naive matching. The main contribution of this paper is the compact feature representation of a large scale environment for robust 2D image matching.
- M. Aly, P. Welinder, M. Munich, and P. Perona. Scaling object recognition: Benchmark of current state of the art techniques. In Proc. of Workshop on Emergent Issues in Large Amounts of Visual Data, 2009.Google ScholarCross Ref
- R. Castle, G. Klein, and D. W. Murray. Video-rate localization in multiple maps for wearable augmented reality. In Proc. of IEEE International Symposium on Wearable Computers, pages 15--22, 2008. Google ScholarDigital Library
- N. Dalal and B. Triggs. Histograms of oriented gradients for human detection. In Proc. of Conference on Computer Vision and Pattern Recognition, pages 886--893, 2005. Google ScholarDigital Library
- A. Irschara, C. Zach, J.-M. Frahm, and H. Bischof. From structure-from-motion point clouds to fast location recognition. In Proc. of Conference of Computer Vision and Pattern Recognition, pages 2599--2606, 2009.Google ScholarCross Ref
- N. Khan. Indoor environment images of owheo building, dunedin, nz, 2012.Google Scholar
- N. Khan, B. McCane, and G. Wyvill. Homography based visual bag of word model for scene matching in indoor environments. In Proc. of Image and Vision Computing New Zealand, 2011.Google Scholar
- N. Khan, B. McCane, and G. Wyvill. Sift and surf performance evaluation against various image deformations on benchmark dataset. In Proc. of Conference on Diigital Image Computing Techniques and Applications, pages 501--506, 2011. Google ScholarDigital Library
- F. Li and J. Kosecka. Probabilistic location recognition using reduced feature set. In Proc. International Conference on Robotics and automation, pages 3405--3410, 2006.Google Scholar
- X. Li, C. Wu, C. Zach, S. Lazebnik, and J.-M. Frahm. Modeling and recognition of landmark image collections using iconic scene graphs. In Proc. of European Conference on Computer Vision, pages 427--440, 2008. Google ScholarDigital Library
- Y. Li, N. Snavely, and D. P. Huttenlocher. Location recognition using prioritized feature matching. In Proc. of European conference on Computer vision, 2011. Google ScholarDigital Library
- D. G. Lowe. Distinctive image features from scale-invariant keypoints. Interational Journal of Computer Vision, 60(2): 91--110, 2004. Google ScholarDigital Library
- D. Nistér and H. Stewénius. Scalable recognition with a vocabulary tree. In Proc. of Conference of Computer Vision and Pattern Recognition, pages 2161--2168, 2006. Google ScholarDigital Library
- A. Oliva and A. Torralba. Modeling the shape of the scene: A holistic representation of the spatial envelope. International Journal of Computer Vision, 42(3): 145--175, 2001. Google ScholarDigital Library
- D. Robertson and R. Cipolla. An image-based system for urban navigation. In Proc. of British Machine Vision Conference, pages 819--828, 2004.Google ScholarCross Ref
- E. Rublee, V. Rabaud, K. Konolige, and G. R. Bradski. Orb: An efficient alternative to sift or surf. In Proc. of International Conference on Computer Vision, pages 2564--2571, 2011. Google ScholarDigital Library
- T. Sattler, B. Leibe, and L. Kobbelt. Fast image-based localization using direct 2d-to-3d matching. pages 667--674, 2011. Google ScholarDigital Library
- N. Snavely, S. M. Seitz, and R. Szeliski. Photo tourism: exploring photo collections in 3d. In Proc. of SIGGRAPH, pages 835--846, 2006. Google ScholarDigital Library
- N. Snavely, S. M. Seitz, and R. Szeliski. Modeling the world from internet photo collections. International Journal of Computer Vision, 80: 189--210, 2008. Google ScholarDigital Library
- W. Zhang and J. Kosecka. Image based localization in urban environments. In Proc. International Symposium on 3D Data Processing, Visualization and Transmission, 2006. Google ScholarDigital Library
Index Terms
- Feature set reduction for image matching in large scale environments
Recommendations
Image feature point matching method based on improved BRISK
In order to improve the accuracy of the BRISK algorithm of feature point matching, an improved BRISK feature point matching method is proposed by combining the SIFT algorithm idea with high matching accuracy. Firstly, the Gaussian image pyramid is ...
Image matching with scale adjustment
In this paper we address the problem of matching two images with two different resolutions: a high-resolution image and a low-resolution one. The difference in resolution between the two images is not known and without loss of generality one of the ...
More effective image matching with scale invariant feature transform
SCCG '07: Proceedings of the 23rd Spring Conference on Computer GraphicsFeature matching is based on finding reliable corresponding points in the images. This requires to solve a twofold problem: detecting repeatable feature points and describing them as distinctive as possible. SIFT (Scale Invariant Feature Transform) has ...
Comments