We present a new method for detecting interest points using histogram information. Unlike existing interest point detectors, which measure pixel-wise differences in image intensity, our detectors incorporate histogram-based representations, and thus can find image regions that present a distinct distribution in the neighborhood. The proposed detectors are able to capture large-scale structures and distinctive textured patterns, and exhibit strong invariance to rotation, illumination variation, and blur. The experimental results show that the proposed histogram-based interest point detectors perform particularly well for the tasks of matching textured scenes under blur and illumination changes, in terms of repeatability and distinctiveness. An extension of our method to space-time interest point detection for action classification is also presented.

我們提出利用直方圖資訊這個新方法來偵測影像上的特殊點，不像以前的方法是利用像素之間的亮度差距來偵測特殊點，而我們的方法包含直方圖表示法，因此可以從影像中找出直方圖分布相較於鄰近區域較為特殊的區域，而這個方法能夠捕捉到大範圍的結構以及特殊的紋理，並且對旋轉、亮度變化、模糊等現象展現出強大的不變性，在實驗中我們利用重複性以及特殊性來評估我們演算法的好壞，從實驗結果可以得知，我們的方法在模糊以及亮度變化的情形中比對含有紋理的圖片有十分好的效果，而我們的方法也可以延伸來偵測空間時間上的特殊點，並且用來做動作分類。

[1] H. Bay, T. Tuytelaars, and L. J. V. Gool. Surf: Speeded up robust features. In ECCV (1), pages 404–417, 2006.

[2] P. Beaudet. Rotationally invariant image operators. In 4th Int. Joint Conf. Patt. Recog., pages 579–583, 1978.

[3] A. Beygelzimer, S. Kakade, and J. Langford. Cover trees for nearest neighbor. In ICML, pages 97–104, 2006.

[4] A. Bhattacharyya. On a measure of divergence between two statistical populations defined by their probability distributions. Bull. Calcutta Math. Soc., 35:99–110, 1943.

[5] M. Brown and D. G. Lowe. Recognising panoramas. In ICCV, pages 1218–1227, 2003.

[6] D. Comaniciu, V. Ramesh, and P. Meer. Real-time tracking of non-rigid objects using mean shift. In CVPR (2), pages 142–149, 2000.

[7] N. Dalal and B. Triggs. Histograms of oriented gradients for human detection. In CVPR (1), pages 886–893, 2005.

[8] G. Dork´o and C. Schmid. Maximally stable local description for scale selection. In ECCV (4), pages 504–516, 2006.

[9] R. Fergus, F.-F. Li, P. Perona, and A. Zisserman. Learning object categories from google’s image search. In ICCV, pages 1816–1823, 2005.

[10] B. J. Frey and D. Dueck. Clustering by passing messages between data points. Science, 315:972–976, 2007.

[11] L. Gorelick, M. Blank, E. Shechtman, M. Irani, and R. Basri. Actions as space-time shapes. IEEE Trans. Pattern Anal. Mach. Intell., 29(12):2247–2253, 2007.

[12] C. Harris and M. Stephens. A combined corner and edge detection. IEEE Trans. Pattern Anal. Mach. Intell., pages 147–151, 1988.

[13] T. Kadir and M. Brady. Saliency, scale and image description. International Journal of Computer Vision, 45(2):83–105, 2001.

[14] T. Kadir, A. Zisserman, and M. Brady. An affine invariant salient region detector. In ECCV (1), pages 228–241, 2004.

[15] I. Laptev and T. Lindeberg. Space-time interest points. In ICCV, pages 432–439, 2003.

[16] T. Lindeberg. Feature detection with automatic scale selection. International Journal of Computer Vision, 30(2):79–116, 1998.

[17] D. G. Lowe. Object recognition from local scale-invariant features. In ICCV, pages 1150–1157, 1999.

[18] D. G. Lowe. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60(2):91–110, 2004.

[19] K. Mikolajczyk and C. Schmid. An affine invariant interest point detector. In ECCV (1), pages 128–142, 2002.

[20] K. Mikolajczyk and C. Schmid. Scale & affine invariant interest point detectors. International Journal of Computer Vision, 60(1):63–86, 2004.

[21] K. Mikolajczyk and C. Schmid. A performance evaluation of local descriptors. IEEE Trans. Pattern Anal. Mach. Intell., 27(10):1615–1630, 2005.

[22] K. Mikolajczyk, T. Tuytelaars, C. Schmid, A. Zisserman, J. Matas, F. Schaffalitzky, T. Kadir, and L. J. V. Gool. A comparison of affine region detectors. International Journal of Computer Vision, 65(1-2):43–72, 2005.

[23] P. Montesinos, V. Gouet, R. Deriche, and D. Pel´e. Matching color uncalibrated images using differential invariants. Image Vision Comput., 18(9):659–671, 2000.

[24] C. Schmid and R. Mohr. Local grayvalue invariants for image retrieval. IEEE Trans. Pattern Anal. Mach. Intell., 19(5):530–535, 1997.

[25] C. Schmid, R. Mohr, and C. Bauckhage. Evaluation of interest point detectors. International Journal of Computer Vision, 37(2):151–172, 2000.

[26] P. Scovanner, S. Ali, and M. Shah. A 3-dimensional sift descriptor and its application to action recognition. In ACM Multimedia, pages 357–360, 2007.

[27] E. Shechtman and M. Irani. Space-time behavior based correlation. In CVPR (1), pages 405–412, 2005.

[28] J. Sivic, F. Schaffalitzky, and A. Zisserman. Object level grouping for video shots. In ECCV (2), pages 85–98, 2004.

[29] T. Tuytelaars and K. Mikolajczyk. Local invariant feature detectors: A survey. Foundations and Trends in Computer Graphics and Vision, 3(3):177–280, 2007.