完整搜尋頁面 →

關鍵點定位

選讀・IP 12・特徵擷取 的補充資料(第 8/10 則)。主線不依賴這則補充;引用編號對應本頁底部的參考文獻。

導覽:本頁與本系列: 導覽:本頁與本系列

極值是在離散格點上找到的。為了精修位置,用泰勒展開對樣本點附近的 DD 擬合三維二次函數,

D(x)≈D+∂D∂xTx+12xT∂2D∂x2x,x^=−(∂2D∂x2)−1∂D∂x,D(\mathbf{x}) \approx D + \frac{\partial D}{\partial \mathbf{x}}^{\mathsf T} \mathbf{x} + \frac{1}{2}\mathbf{x}^{\mathsf T} \frac{\partial^2 D}{\partial \mathbf{x}^2}\mathbf{x}, \qquad \hat{\mathbf{x}} = -\left(\frac{\partial^2 D}{\partial \mathbf{x}^2}\right)^{-1} \frac{\partial D}{\partial \mathbf{x}},

其中 x=(x,y,σ)T\mathbf{x} = (x, y, \sigma)^{\mathsf T} 是相對於樣本點的偏移,x^\hat{\mathbf{x}} 是極值在次像素、次尺度上的位置。接著用兩個測試剔除不穩定的點 [6]:

  • 低對比:若 ∣D(x^)∣<0.03|D(\hat{\mathbf{x}})| < 0.03(強度範圍為 [0,1][0, 1] 時)就捨棄。
  • 邊緣響應:DoG 在邊緣上也有反應,但邊緣上的位置定不準。用 DD 的 2×22 \times 2 空間 Hessian 矩陣 H\mathbf{H},只有在
tr⁡(H)2det⁡(H)<(r+1)2r\frac{\operatorname{tr}(\mathbf{H})^2}{\det(\mathbf{H})} < \frac{(r + 1)^2}{r}

時才保留,其中 rr 限制兩個主曲率的比值;Lowe 使用 r=10r = 10。這和 Harris 的想法相同:好的點必須在兩個方向上都彎得厲害。

參考文獻

  1. R. C. Gonzalez and R. E. Woods, Digital Image Processing, 4th ed., Pearson, 2018, Ch. 12. publisher page
  2. M.-K. Hu, “Visual pattern recognition by moment invariants,” IRE Transactions on Information Theory, vol. 8, no. 2, pp. 179–187, 1962. doi
  3. R. M. Haralick, K. Shanmugam, and I. Dinstein, “Textural features for image classification,” IEEE Transactions on Systems, Man, and Cybernetics, vol. SMC-3, no. 6, pp. 610–621, 1973. doi
  4. C. Harris and M. Stephens, “A combined corner and edge detector,” in Proc. Alvey Vision Conference, pp. 23.1–23.6, 1988. doi
  5. J. Matas, O. Chum, M. Urban, and T. Pajdla, “Robust wide-baseline stereo from maximally stable extremal regions,” Image and Vision Computing, vol. 22, no. 10, pp. 761–767, 2004. doi
  6. D. G. Lowe, “Distinctive image features from scale-invariant keypoints,” International Journal of Computer Vision, vol. 60, no. 2, pp. 91–110, 2004. doi
  7. H. Bay, A. Ess, T. Tuytelaars, and L. Van Gool, “Speeded-up robust features (SURF),” Computer Vision and Image Understanding, vol. 110, no. 3, pp. 346–359, 2008. doi
  8. E. Rublee, V. Rabaud, K. Konolige, and G. Bradski, “ORB: An efficient alternative to SIFT or SURF,” in Proc. IEEE International Conference on Computer Vision (ICCV), pp. 2564–2571, 2011. doi
  9. D. Zhang and G. Lu, “Review of shape representation and description techniques,” Pattern Recognition, vol. 37, no. 1, pp. 1–19, 2004. doi
  10. T. Tuytelaars and K. Mikolajczyk, “Local invariant feature detectors: A survey,” Foundations and Trends in Computer Graphics and Vision, vol. 3, no. 3, pp. 177–280, 2008. doi
  11. L. Liu, J. Chen, P. Fieguth, G. Zhao, R. Chellappa, and M. Pietikäinen, “From BoW to CNN: Two decades of texture representation for texture classification,” International Journal of Computer Vision, vol. 127, pp. 74–109, 2019. arXiv
  12. J. Ma, X. Jiang, A. Fan, J. Jiang, and J. Yan, “Image matching from handcrafted to deep features: A survey,” International Journal of Computer Vision, vol. 129, pp. 23–79, 2021. doi
  13. Y. Jin, D. Mishkin, A. Mishchuk, J. Matas, P. Fua, K. M. Yi, and E. Trulls, “Image matching across wide baselines: From paper to practice,” International Journal of Computer Vision, 2021. doi · arXiv
  14. D. DeTone, T. Malisiewicz, and A. Rabinovich, “SuperPoint: Self-supervised interest point detection and description,” arXiv:1712.07629, 2017. arXiv
  15. P.-E. Sarlin, D. DeTone, T. Malisiewicz, and A. Rabinovich, “SuperGlue: Learning feature matching with graph neural networks,” arXiv:1911.11763, 2019. arXiv
  16. M. J. Tyszkiewicz, P. Fua, and E. Trulls, “DISK: Learning local features with policy gradient,” arXiv:2006.13566, 2020. arXiv
  17. J. Sun, Z. Shen, Y. Wang, H. Bao, and X. Zhou, “LoFTR: Detector-free local feature matching with Transformers,” arXiv:2104.00680, 2021. arXiv
  18. P. Lindenberger, P.-E. Sarlin, and M. Pollefeys, “LightGlue: Local feature matching at light speed,” arXiv:2306.13643, 2023. arXiv
  19. M. Oquab, T. Darcet, T. Moutakanni, et al., “DINOv2: Learning robust visual features without supervision,” arXiv:2304.07193, 2023. arXiv
  20. J. Edstedt, Q. Sun, G. Bökman, M. Wadenbäck, and M. Felsberg, “RoMa: Robust dense feature matching,” in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024. arXiv
  21. M. A. Fischler and R. C. Bolles, “Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography,” Communications of the ACM, vol. 24, no. 6, pp. 381–395, 1981. doi
  22. scikit-image contributors, “skimage.measure.ransac,” scikit-image 0.26 documentation (API reference). docs