Journal of Computer Applications ›› 2024, Vol. 44 ›› Issue (5): 1597-1604.DOI: 10.11772/j.issn.1001-9081.2023050692
Special Issue: 多媒体计算与计算机仿真
• Multimedia computing and computer simulation • Previous Articles Next Articles
Guijin HAN1, Xinyuan ZHANG1(), Wentao ZHANG2, Ya HUANG1
Received:
2023-06-01
Revised:
2023-08-18
Accepted:
2023-08-21
Online:
2023-08-28
Published:
2024-05-10
Contact:
Xinyuan ZHANG
About author:
HAN Guijin, born in 1978, Ph. D., associate professor. His research interests include image processing, computer vision.Supported by:
通讯作者:
张馨渊
作者简介:
韩贵金(1978—),男,河南濮阳人,副教授,博士,CCF会员,主要研究方向:图像处理、计算机视觉基金资助:
CLC Number:
Guijin HAN, Xinyuan ZHANG, Wentao ZHANG, Ya HUANG. Self-supervised image registration algorithm based on multi-feature fusion[J]. Journal of Computer Applications, 2024, 44(5): 1597-1604.
韩贵金, 张馨渊, 张文涛, 黄娅. 基于多特征融合的自监督图像配准算法[J]. 《计算机应用》唯一官方网站, 2024, 44(5): 1597-1604.
Add to citation manager EndNote|Ris|BibTeX
URL: https://www.joca.cn/EN/10.11772/j.issn.1001-9081.2023050692
算法 | ILSVRC2012测试集l | ILSVRC2012测试集2 | ||||||
---|---|---|---|---|---|---|---|---|
AMA/% | AEPE | MS/% | 计算时间/s | AMA/% | AEPE | MS/% | 计算时间/s | |
SIFT | 31.94 | 125.47 | 7.79 | 1.182 | 29.89 | 146.36 | 7.79 | 1.056 |
GMN | 54.08 | 32.46 | 18.36 | 1.016 | 42.58 | 46.52 | 18.36 | 0.981 |
PCA-GM | 62.15 | 29.37 | 21.46 | 1.134 | 53.42 | 32.26 | 21.46 | 1.079 |
OpenGlue | 89.55 | 16.32 | 24.89 | 0.703 | 83.97 | 22.47 | 25.89 | 0.686 |
COTR | 8.85 | 25.46 | 17.251 | 87.91 | 9.46 | 24.46 | 18.027 | |
COMMON | 89.43 | 7.99 | 26.54 | 1.388 | 82.44 | 10.27 | 25.81 | 1.752 |
ResMatch | 90.27 | 6.32 | 24.11 | 22.76 | ||||
SIRA-MFF | 95.18 | 0.206 | 93.26 | 7.26 | 0.197 |
Tab. 1 Results of different algorithms on ILSVRC2012 test sets
算法 | ILSVRC2012测试集l | ILSVRC2012测试集2 | ||||||
---|---|---|---|---|---|---|---|---|
AMA/% | AEPE | MS/% | 计算时间/s | AMA/% | AEPE | MS/% | 计算时间/s | |
SIFT | 31.94 | 125.47 | 7.79 | 1.182 | 29.89 | 146.36 | 7.79 | 1.056 |
GMN | 54.08 | 32.46 | 18.36 | 1.016 | 42.58 | 46.52 | 18.36 | 0.981 |
PCA-GM | 62.15 | 29.37 | 21.46 | 1.134 | 53.42 | 32.26 | 21.46 | 1.079 |
OpenGlue | 89.55 | 16.32 | 24.89 | 0.703 | 83.97 | 22.47 | 25.89 | 0.686 |
COTR | 8.85 | 25.46 | 17.251 | 87.91 | 9.46 | 24.46 | 18.027 | |
COMMON | 89.43 | 7.99 | 26.54 | 1.388 | 82.44 | 10.27 | 25.81 | 1.752 |
ResMatch | 90.27 | 6.32 | 24.11 | 22.76 | ||||
SIRA-MFF | 95.18 | 0.206 | 93.26 | 7.26 | 0.197 |
算法 | AMA/% | AEPE/% | MS/% | 计算时间/s |
---|---|---|---|---|
SIFT | 30.27 | 137.42 | 7.79 | 1.160 |
GMN | 53.26 | 42.36 | 18.36 | 0.926 |
PCA-GM | 76.82 | 37.42 | 21.46 | 1.125 |
OpenGlue | 88.57 | 23.58 | 24.89 | 0.625 |
COTR | 91.25 | 24.91 | 18.367 | |
COMMON | 84.62 | 8.87 | 26.31 | 1.427 |
ResMatch | 82.03 | 38.91 | 16.84 | |
SIRA-MFF | 7.86 | 0.184 |
Tab. 2 Results of different algorithms on IMC-PT-SparseGM-50 test set
算法 | AMA/% | AEPE/% | MS/% | 计算时间/s |
---|---|---|---|---|
SIFT | 30.27 | 137.42 | 7.79 | 1.160 |
GMN | 53.26 | 42.36 | 18.36 | 0.926 |
PCA-GM | 76.82 | 37.42 | 21.46 | 1.125 |
OpenGlue | 88.57 | 23.58 | 24.89 | 0.625 |
COTR | 91.25 | 24.91 | 18.367 | |
COMMON | 84.62 | 8.87 | 26.31 | 1.427 |
ResMatch | 82.03 | 38.91 | 16.84 | |
SIRA-MFF | 7.86 | 0.184 |
Key.Net | DFE | 特征匹配 | EIL | AMA/% | |||
---|---|---|---|---|---|---|---|
32 | 128 | 256 | ED | PML | |||
√ | √ | 14.42 | |||||
√ | √ | 23.72 | |||||
√ | √ | 49.26 | |||||
√ | √ | 58.84 | |||||
√ | √ | 66.39 | |||||
√ | √ | √ | 89.69 |
Tab. 3 Ablation experiment results of direction descriptors with different channel numbers
Key.Net | DFE | 特征匹配 | EIL | AMA/% | |||
---|---|---|---|---|---|---|---|
32 | 128 | 256 | ED | PML | |||
√ | √ | 14.42 | |||||
√ | √ | 23.72 | |||||
√ | √ | 49.26 | |||||
√ | √ | 58.84 | |||||
√ | √ | 66.39 | |||||
√ | √ | √ | 89.69 |
算法 | 参数量/103 |
---|---|
PCA-GM | 1 471.0 |
OpenGlue | 940.0 |
COTR | 166.0 |
COMMON | 39.0 |
SIRA-MFF | 6.7 |
Tab. 4 Comparison of learnable parameter numbers in network feature extraction layers of different algorithms
算法 | 参数量/103 |
---|---|
PCA-GM | 1 471.0 |
OpenGlue | 940.0 |
COTR | 166.0 |
COMMON | 39.0 |
SIRA-MFF | 6.7 |
1 | LOWE G D. Distinctive image features from scale-invariant key-points[J]. International Journal of Computer Vision, 2004, 60(2): 91-110. 10.1023/b:visi.0000029664.99615.94 |
2 | MUR-ARTAL R, MOTEIL J M M, TARDÓS J D. ORB-SLAM: a versatile and accurate monocular SLAM system[J]. IEEE Transactions on Robotics, 2015, 31(5):1147-1163. 10.1109/tro.2015.2463671 |
3 | FISCHLER M A, BOLLES R C. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography[M]// Readings in Computer Vision: Issues, Problems, Principles, and Paradigms. San Francisco: Morgan Kaufmann Publishers Inc., 1987: 726-740. 10.1016/b978-0-08-051581-6.50070-2 |
4 | RAGURAM R, J-M FRAHN, POLLEFEYS M. A comparative analysis of RANSAC techniques leading to adaptive real-time random sample consensus[C]// Proceedings of the 10th European Conference on Computer Vision. Berlin: Springer, 2008: 500-513. 10.1007/978-3-540-88688-4_37 |
5 | GOLD S, RANGARAJAN A. A graduated assignment algorithm for graph matching[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1996, 18(4): 377-388. 10.1109/34.491619 |
6 | TIAN Y, YAN J, ZHANG H, et al. On the convergence of graph matching: graduated assignment revisited[C]// Proceedings of the 12th European Conference on Computer Vision. Berlin: Springer, 2012: 821-835. 10.1007/978-3-642-33712-3_59 |
7 | 贾雯晓,张贵仓,汪亮亮,等.基于SIFT和改进的RANSAC图像配准算法[J].计算机工程与应用,2018,54(2):203-207. 10.3778/j.issn.1002-8331.1707-0264 |
JIA W X, ZHANG G C, WANG L L, et al. Image registration algorithm based on SIFT and improved RANSAC[J]. Computer Engineering and Applications, 2018, 54(2): 203-207. 10.3778/j.issn.1002-8331.1707-0264 | |
8 | LEORDEANU M, HEBERT M. A spectral technique for correspondence problems using pairwise constraints[C]// Proceedings of the Tenth IEEE International Conference on Computer Vision. Piscataway: IEEE, 2005: 1482-1489. 10.1109/iccv.2005.20 |
9 | 樊玮,王慧敏,邢艳.基于自编码器的多视图属性网络表示学习模型[J].计算机应用,2021,41(4):1064-1070. 10.11772/j.issn.1001-9081.2020061006 |
FAN W, WANG H M, XING Y. Auto-encoder based multi-view attributed network representation learning model[J]. Journal of Computer Applications, 2021, 41(4): 1064-1070. 10.11772/j.issn.1001-9081.2020061006 | |
10 | ZANFIR A, SMINCHISESCU C. Deep learning of graph matching[C]// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 2684-2693. 10.1109/cvpr.2018.00284 |
11 | SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition [EB/OL]. [2023-05-01]. . |
12 | TYSZKIEWICZ M J, FUA P, TRULLS E. DISK: learning local features with policy gradient [EB/OL]. (2022-06-24)[2023-05-01]. . 10.1109/iccv51070.2023.00203 |
13 | LEE J, JEONG Y, KIM S, et al. Learning to distill convolutional features into compact local descriptors[C]// Proceedings of the 2021 IEEE Winter Conference on Applications of Computer Vision. Piscataway: IEEE, 2021: 897-907. 10.1109/wacv48630.2021.00094 |
14 | 徐少康,张战成,姚浩男,等.基于姿态编码器的2D/3D脊椎医学图像实时配准方法[J].计算机应用,2023,43(2):589-594. 10.11772/j.issn.1001-9081.2021122147 |
XU S K, ZHANG Z C, YAO H N, et al. 2D/3D spine medical image real-time registration method based on pose encoder[J]. Journal of Computer Applications, 2023, 43(2):589-594. 10.11772/j.issn.1001-9081.2021122147 | |
15 | WANG R, YAN J, YANG X. Combinatorial learning of robust deep graph matching: an embedding based approach[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(6):6984-7000. 10.1109/tpami.2020.3005590 |
16 | SHEN X, WANG C, LI X, et al. RF-Net: an end-to-end image matching network based on receptive field[C]// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 8124-8132. 10.1109/cvpr.2019.00832 |
17 | WANG F-D, XUE N, ZHANG Y, et al. A functional representation for graph matching[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(11): 2737-2754. |
18 | VINIAVSKYI O, DOBKO M, MISHKIN D, et al. OpenGlue: open-source graph neural net based pipeline for image matching [EB/OL]. [2023-05-01]. . |
19 | LIU H, WANG T, LI Y, et al. Deep probabilistic graph matching [EB/OL]. (2022-01-05) [2023-05-01]. . 10.1158/0008-5472.sabcs12-p4-05-01 |
20 | JIANG W, TRULLS E, HOSANG J, et al. COTR: correspondence transformer for matching across images[C]// Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2021: 6187-6197. 10.1109/iccv48922.2021.00615 |
21 | LIN Y, YANG M, JUN Y, et. al. Graph matching with bi-level noisy correspondence [EB/OL]. (2022-12-08)[2023-05-01]. . 10.1109/iccv51070.2023.02135 |
22 | DENG Y, MA J. ResMatch: residual attention learning for local feature matching [EB/OL]. [2023-05-01]. . 10.1609/aaai.v38i2.27915 |
23 | HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 770-778. 10.1109/cvpr.2016.90 |
24 | LAGUNA A B, RIBA E, PONSA D, et al. Key.Net: key-point detection by handcrafted and learned CNN filters[C]// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2019: 5835-5843. 10.1109/iccv.2019.00593 |
25 | ZHOU J, CUI G, HU S, et al. Graph neural networks: a review of methods and applications [EB/OL]. [2021-10-06]. . |
26 | LIN T-Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]// Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2017: 2999-3001. 10.1109/iccv.2017.324 |
27 | WANG R, GUO Z, JIANG S, et.al. Deep learning of partial graph matching via differentiable top-k [C]// Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2023: 6272-6281. 10.1109/cvpr52729.2023.00607 |
[1] | Yexin PAN, Zhe YANG. Optimization model for small object detection based on multi-level feature bidirectional fusion [J]. Journal of Computer Applications, 2024, 44(9): 2871-2877. |
[2] | Tingjie TANG, Jiajin HUANG, Jin QIN. Session-based recommendation with graph auxiliary learning [J]. Journal of Computer Applications, 2024, 44(9): 2711-2718. |
[3] | Xiyuan WANG, Zhancheng ZHANG, Shaokang XU, Baocheng ZHANG, Xiaoqing LUO, Fuyuan HU. Unsupervised cross-domain transfer network for 3D/2D registration in surgical navigation [J]. Journal of Computer Applications, 2024, 44(9): 2911-2918. |
[4] | Ruihua LIU, Zihe HAO, Yangyang ZOU. Gait recognition algorithm based on multi-layer refined feature fusion [J]. Journal of Computer Applications, 2024, 44(7): 2250-2257. |
[5] | Mengyuan HUANG, Kan CHANG, Mingyang LING, Xinjie WEI, Tuanfa QIN. Progressive enhancement algorithm for low-light images based on layer guidance [J]. Journal of Computer Applications, 2024, 44(6): 1911-1919. |
[6] | Yue LIU, Fang LIU, Aoyun WU, Qiuyue CHAI, Tianxiao WANG. 3D object detection network based on self-attention mechanism and graph convolution [J]. Journal of Computer Applications, 2024, 44(6): 1972-1977. |
[7] | Xin LI, Qiao MENG, Junyi HUANGFU, Lingchen MENG. YOLOv5 multi-attribute classification based on separable label collaborative learning [J]. Journal of Computer Applications, 2024, 44(5): 1619-1628. |
[8] | Hongtian LI, Xinhao SHI, Weiguo PAN, Cheng XU, Bingxin XU, Jiazheng YUAN. Few-shot object detection via fusing multi-scale and attention mechanism [J]. Journal of Computer Applications, 2024, 44(5): 1437-1444. |
[9] | Jiong WANG, Taotao TANG, Caiyan JIA. PAGCL: positive augmentation graph contrastive learning recommendation method without negative sampling [J]. Journal of Computer Applications, 2024, 44(5): 1485-1492. |
[10] | Rong HUANG, Junjie SONG, Shubo ZHOU, Hao LIU. Image aesthetic quality evaluation method based on self-supervised vision Transformer [J]. Journal of Computer Applications, 2024, 44(4): 1269-1276. |
[11] | Yuliang ZHENG, Yunhua CHEN, Weijie BAI, Pinghua CHEN. Vehicle target detection by fusing event data and image frames [J]. Journal of Computer Applications, 2024, 44(3): 931-937. |
[12] | Ning WU, Yangyang LUO, Huajie XU. Semantic segmentation method for remote sensing images based on multi-scale feature fusion [J]. Journal of Computer Applications, 2024, 44(3): 737-744. |
[13] | Zongze JIA, Pengfei GAO, Yinglong MA, Xiaofeng LIU, Haixin XIA. Multi-feature fusion attention-based hierarchical classification method for dialogue act [J]. Journal of Computer Applications, 2024, 44(3): 715-721. |
[14] | Zhanjun JIANG, Baijing WU, Long MA, Jing LIAN. Faster-RCNN water-floating garbage recognition based on multi-scale feature and polarized self-attention [J]. Journal of Computer Applications, 2024, 44(3): 938-944. |
[15] | Xinye LI, Yening HOU, Yinghui KONG, Zhiqi YAN. Few-shot object detection combining feature fusion and enhanced attention [J]. Journal of Computer Applications, 2024, 44(3): 745-751. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||