A Comparative Analysis of Feature Detectors and Descriptors for Image Stitching
Source abstract
Abstract
Image stitching is a technique that is often employed in image processing and computer vision applications. The feature points in an image provide a significant amount of key information. Image stitching requires accurate extraction of these features since it may decrease misalignment flaws in the final stitched image. In recent years, a variety of feature detectors and descriptors that may be utilized for image stitching have been presented. However, the computational cost and correctness of feature matching restrict the utilization of these techniques. To date, no work compared feature detectors and descriptors for image stitching applications, i.e., no one has considered the effect of detectors and descriptors on the generated final stitched image. This paper presents a detailed comparative analysis of commonly used feature detectors and descriptors proposed previously. This study gives various contributions to the development of a general comparison of feature detectors and descriptors for image stitching applications. These detectors and descriptors are compared in terms of number of matched points, time taken and quality of stitched image. After analyzing the obtained results, it was observed that the combination of AKAZE with AKAZE can be preferable almost in all possible situations.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Image and Video Retrieval Techniques · Robotics and Sensor-Based Localization · Advanced Neural Network Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Indian Institute of Remote Sensing, Dehradun 248001, India
Indian Institute of Technology Roorkee, Roorkee 247667, India
Manipal School of Architecture and Planning, Manipal Academy of Higher Education, Manipal 576104, India
References (81)
Show source-provided references
1. A fast mosaic method for airborne images: The new Template-Convolution Speed-Up Robust Features (TSURF) algorithm10.1080/2150704X.2014.943320 ↗
2. Efficient seamline determination for UAV image mosaicking using edge detection10.1080/2150704X.2018.1475772 ↗
3. An automated system for mosaicking spaceborne SAR imagery10.1080/01431169008955014 ↗
4. A Mosaic of Airborne SAR Imagery for Geological Mapping in Rolling Topography10.1080/07038992.1995.10874600 ↗
5. Image Mosaicing from Video Sequences10.1080/03772063.2002.11416290 ↗
6. Integrating BIM and Panorama to Create a Semi-Augmented-Reality Experience of a Construction Site
7. Morevec, H.P. (1977, January 22–25). Towards automatic visual obstacle avoidance. Proceedings of the 5th International Joint Conference on Artificial Intelligence, Cambridge, MA, USA.
8. Förstner, W., and Gülch, E. (1987, January 2–4). A fast operator for detection and precise location of distinct points, corners and centres of circular features. Proceedings of the ISPRS Intercommission Conference on Fast Processing of Photogrammetric Data, Interlaken, Switzerland.
9. Harris, C., and Stephens, M. (September, January 31). A combined corner and edge detector. Proceedings of the 4th Alvey Vision Conference, Manchester, UK.
10. Detection and Tracking of Point Features10.1007/BF00129684 ↗
11. Simulation of neural contour mechanisms: From simple to end-stopped cells10.1016/0042-6989(92)90039-L ↗
12. Förstner, W. (1994, January 2–6). A framework for low level feature extraction. Proceedings of the 3rd European Conference on Computer Vision, Stockholm, Sweden.10.1007/BFb0028370 ↗
13. Shi, J., and Tomasi, C. (1994, January 21–23). Good features to track. Proceedings of the Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.
14. Lindeberg, T. (1994, January 13–16). Junction detection with automatic selection of detection scales and localization scales. Proceedings of the 1st International Conference on Image Processing, Austin, TX, USA.10.1109/ICIP.1994.413244 ↗
15. Real-time corner detection algorithm for motion estimation10.1016/0262-8856(95)98864-P ↗
16. SUSAN—A New Approach to Low Level Image Processing10.1023/A:1007963824710 ↗
17. Hall, D., Leibe, B., and Schiele, B. (2002, January 2–5). Saliency of Interest Points under Scale Changes. Proceedings of the British Machine Vision Conference (BMVC’02), Cardiff, UK.10.5244/C.16.63 ↗
18. Feature Detection with Automatic Scale Selection10.1023/A:1008045108935 ↗
19. Indexing based on scale invariant interest points
20. Schmid, C., Mohr, R., and Bauckhage, C. (1998, January 7). Comparing and evaluating interest points. Proceedings of the 6th International Conference on Computer Vision (IEEE Cat. No.98CH36271), Bombay, India.
21. Evaluation of Interest Point Detectors10.1023/A:1008199403446 ↗
22. Object recognition from local scale-invariant features
23. Brown, M., and Lowe, D.G. (2003, January 13–16). Recognising panoramas. Proceedings of the 9th International Conference on Computer Vision, Nice, France.10.1109/ICCV.2003.1238630 ↗
24. Automatic panoramic image stitching using invariant features10.1007/s11263-006-0002-3 ↗
25. Image mosaic method based on SIFT features of line segment10.1155/2014/926312 ↗
26. The Improved Algorithm of Fast Panorama Stitching for Image Sequence and Reducing the Distortion Errors10.1155/2015/428076 ↗
27. A performance evaluation of local descriptors10.1109/TPAMI.2005.188 ↗
28. Zuliani, M., Kenney, C., and Manjunath, B.S. (July, January 27). A mathematical comparison of point detectors. Proceedings of the Conference on Computer Vision and Pattern Recognition Workshop, Washington, DC, USA.
29. A quick scale-invariant interest point detecting approach10.1007/s00138-008-0167-6 ↗
30. Effective venue image retrieval using robust feature extraction and model constrained matching for mobile robot localization10.1007/s00138-011-0350-z ↗
31. An improvement to the SIFT descriptor for image representation and matching10.1016/j.patrec.2013.03.021 ↗
32. A comparative study of SIFT and its variants10.2478/msr-2013-0021 ↗
33. Scale & Affine Invariant Interest Point Detectors10.1023/B:VISI.0000027790.02288.f2 ↗
34. A Comparison of Affine Region Detectors10.1007/s11263-005-3848-x ↗
35. Moreels, P., and Perona, P. (2005, January 17–21). Evaluation of features detectors and descriptors based on 3D objects. Proceedings of the 10th International Conference on Computer Vision (ICCV’05), Beijing, China.10.1109/ICCV.2005.89 ↗
36. Robust wide-baseline stereo from maximally stable extremal regions10.1016/j.imavis.2004.02.006 ↗
37. Linear Time Maximally Stable Extremal Regions
38. Van SURF: Speeded Up Robust Features
39. Niu, J., Yang, F., and Shi, L. (2013, January 1–3). Improved method of automatic image stitching based on SURF. Proceedings of the 1st International Symposium on Future Information and Communication Technologies for Ubiquitous HealthCare (Ubi-HealthTech), Jinhua, China.10.1109/Ubi-HealthTech.2013.6708059 ↗
40. Zhu, L., Wang, Y., Zhao, B., and Zhang, X. (2014, January 15–16). A fast image stitching algorithm based on improved SURF. Proceedings of the 10th International Conference on Computational Intelligence and Security, Kunming, China.10.1109/CIS.2014.67 ↗
41. Yang, Z., Shen, D., and Yap, P.-T. (2017). Image mosaicking using SURF features of line segments. PLoS ONE, 12.10.1371/journal.pone.0173627 ↗
42. Machine Learning for High-Speed Corner Detection
43. Local invariant feature detectors: A survey10.1561/0600000017 ↗
44. A comprehensive review of current local features for computer vision10.1016/j.neucom.2007.11.032 ↗
45. Govender, N. (2009, January 8–10). Evaluation of feature detection algorithms for structure from motion. Proceedings of the 3rd Robotics and Mechatronics Symposium (ROBMECH 2009), Pretoria, South Africa.
46. A comparative evaluation of interest point detectors and local descriptors for visual SLAM10.1007/s00138-009-0195-x ↗
47. Hartmann, J., Klussendorff, J.H., and Maehle, E. (2013, January 25–27). A comparison of feature descriptors for visual SLAM. Proceedings of the European Conference on Mobile Robots, Barcelona, Spain.10.1109/ECMR.2013.6698820 ↗
48. Finding a Good Feature Detector-Descriptor Combination for the 2D Keypoint-Based Registration of TLS Point Clouds10.5194/isprsannals-II-3-W5-121-2015 ↗
49. CenSurE: Center Surround Extremas for Realtime Feature Detection and Matching
50. Willis, A., and Sui, Y. (October, January 29). An algebraic model for fast corner detection. Proceedings of the 12th International Conference on Computer Vision, Kyoto, Japan.
51. BRIEF: Binary Robust Independent Elementary Features
52. DAISY: An efficient dense descriptor applied to wide-baseline stereo10.1109/TPAMI.2009.77 ↗
53. Leutenegger, S., Chli, M., and Siegwart, R.Y. (2011, January 6–13). BRISK: Binary Robust invariant scalable keypoints. Proceedings of the International Conference on Computer Vision, Barcelona, Spain.10.1109/ICCV.2011.6126542 ↗
54. Rublee, E., Rabaud, V., Konolige, K., and Bradski, G. (2011, January 6–13). ORB: An efficient alternative to SIFT or SURF. Proceedings of the International Conference on Computer Vision, Barcelona, Spain.10.1109/ICCV.2011.6126544 ↗
55. Alahi, A., Ortiz, R., and Vandergheynst, P. (2012, January 16–21). FREAK: Fast retina keypoint. Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, USA.10.1109/CVPR.2012.6247715 ↗
56. KAZE Features
57. Alcantarilla, P.F., Nuevo, J., and Bartoli, A. (2013, January 9–13). Fast explicit diffusion for accelerated features in nonlinear scale spaces. Proceedings of the Tilo Burghardt, Dima Damen, Walterio W. Mayol-Cuevas, Majid Mirmehdi: British Machine Vision Conference, BMVC 2013, Bristol, UK.10.5244/C.27.13 ↗
58. Image Stitching using AKAZE Features10.1007/s12524-020-01163-y ↗
59. A survey on image mosaicing techniques10.1016/j.jvcir.2015.10.014 ↗
60. Review on image-stitching techniques10.1007/s00530-020-00651-y ↗
61. A survey on image and video stitching10.3724/SP.J.2096-5796.2018.0008 ↗
62. A Comparative Study on Different Image Stitching Techniques10.14445/22315381/IJETT-V70I4P205 ↗
63. Comparative Evaluation of Binary Features
64. Noble, F.K. (2016, January 28–30). Comparison of OpenCV’s feature detectors and feature matchers. Proceedings of the 23rd International Conference on Mechatronics and Machine Vision in Practice (M2VIP), Nanjing, China.10.1109/M2VIP.2016.7827292 ↗
65. A Comparative Evaluation of Well-known Feature Detectors and Descriptors
66. Ziegler, A., Christiansen, E., Kriegman, D., and Belongie, S. (2012, January 3–6). Locally Uniform Comparison Image Descriptor. Proceedings of the 26th Annual Conference on Neural Information Processing Systems 2012, Lake Tahoe, NV, USA.
67. A comparative experimental study of image feature detectors and descriptors10.1007/s00138-015-0679-9 ↗
68. Interesting Interest Points
69. Dahl, A.L., Aanæs, H., and Pedersen, K.S. (2011, January 16–19). Finding the best feature detector-descriptor combination. Proceedings of the 2011 International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission, Hangzhou, China.10.1109/3DIMPVT.2011.47 ↗
70. Adaptive and Generic Corner Detection Based on the Accelerated Segment Test
71. Interest Points via Maximal Self-Dissimilarities
72. The survey of subjective and objective methods for quality assessment of 2D and 3D images
73. Image quality assessment: From error visibility to structural similarity10.1109/TIP.2003.819861 ↗
74. FSIM: A feature similarity index for image quality assessment10.1109/TIP.2011.2109730 ↗
75. VSI: A visual saliency-induced index for perceptual image quality assessment10.1109/TIP.2014.2346028 ↗
76. Quantitative evaluation of panorama softwares
77. Zaragoza, J., Chin, T.J., Brown, M.S., and Suter, D. (2013, January 23–28). As-projective-as-possible image stitching with moving DLT. Proceedings of the Conference on Computer Vision and Pattern Recognition, Portland, OR, USA.10.1109/CVPR.2013.303 ↗
78. Image Alignment for Panorama Stitching in Sparsely Structured Environments
79. A fast and mobile system for registration of low-altitude visual and thermal aerial images using multiple small-scale UAVs10.1016/j.isprsjprs.2014.07.015 ↗
80. A view-free image stitching network based on global homography10.1016/j.jvcir.2020.102950 ↗
81. Unsupervised Deep Image Stitching: Reconstructing Stitched Features to Images10.1109/TIP.2021.3092828 ↗