基于特征距離與內(nèi)點(diǎn)的隨機(jī)抽樣一致性算法

張巖; 孫世宇; 胡永江; 李建增; 范聰

doi:10.11999/JEIT170703

基于特征距離與內(nèi)點(diǎn)的隨機(jī)抽樣一致性算法

doi: 10.11999/JEIT170703 cstr: 32379.14.JEIT170703

計(jì)量
- 文章訪問數(shù): 1426
- HTML全文瀏覽量: 116
- PDF下載量: 208
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2017-07-17
- 修回日期: 2017-12-13
- 刊出日期: 2018-04-19

Random Sample Consensus Algorithm Based on Feature Distance and Inliers

摘要

摘要: 為了提高隨機(jī)抽樣一致性算法在特征匹配中的執(zhí)行速度，該文提出一種基于特征距離與內(nèi)點(diǎn)的隨機(jī)抽樣一致性算法。首先提出基于特征距離的先驗(yàn)概率引導(dǎo)方法，來提高算法每步循環(huán)找到正確模型的概率。其次提出基于樣本集與內(nèi)點(diǎn)的隨機(jī)抽樣及計(jì)算方法，來提高算法的收斂速度。最后提出基于最大值不變的循環(huán)跳出方法，來滿足所提循環(huán)方法的跳出，同時(shí)提高運(yùn)行效率。通過理論證明與實(shí)驗(yàn)驗(yàn)證，該文提出的算法在保證算法魯棒性的同時(shí)，提高了執(zhí)行速度。
- 模型估計(jì) /
- 隨機(jī)抽樣一致性 /
- 特征距離 /
- 內(nèi)點(diǎn)抽樣 /
- 單應(yīng)性矩陣
Abstract: In order to improve the operation efficiency of the RANdom SAmple Consensus (RANSAC) in feature registration, the Random Sample Consensus based on Feature Distance and Inliers (RSCFDI) is proposed. Firstly, the priori probability guidance method based on feature distance is proposed for increasing the probability of searching correct model in each loop. Then, to increase the convergence rate, the random sampling and calculation method based on sample set and inliers is adopted. Finally, the jumping out loop based on unchanged maximum is proposed to fit the proposed loop breaking, and the execution speed is elevated. The theoretical proof and experimental results show that the RSCFDI ensures the robustness of the algorithm, and the operation efficiency is improved.
- Model estimation /
- RANdom SAmple Consensus (RANSAC) /
- Feature distance /
- Inliers sample /
- Homograph matrix

HTML全文

參考文獻(xiàn)(25)

丁海燕, 劉合輝, 劉春菊. SIFT遙感影像快速配準(zhǔn)方法[J]. 地理空間信息, 2017, 15(2): 69-71. doi: 10.3969/j.issn.1672-4623. 2017.02.022.

FISCHLER M and BOLLES R. Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography[J]. Communication of the ACM, 1981, 24(6): 381-395. doi: 10.1145/358669.358692.

DING Haiyan, LIU Hehui, and LIU Chunju. Fast registration method of SIFT remote sensing image[J]. Geospatial Information, 2017, 15(2): 69-71. doi: 10.3969/j.issn.1672- 4623.2017.02.022.

管秋, 金俊杰, 張劍華, 等. 基于最優(yōu)RANSAC算法的非增加式多視圖三維重建[J]. 浙江工業(yè)大學(xué)學(xué)報(bào), 2015, 43(5): 473-478. doi: 10.3969/j.issn.1006-4303.2015.05.001.

GUAN Qiu, JIN Junjie, ZHANG Jianhua, et al. Non- sequential multi-view 3D reconstruction based on ac-RANSAC[J]. Journal of Zhejiang University of Technology, 2015, 43(5): 473-478. doi: 10.3969/j.issn.1006-4303.2015.05. 001.

李寰宇, 畢篤彥, 楊源, 等. 基于深度特征表達(dá)與學(xué)習(xí)的視覺跟蹤算法研究[J]. 電子與信息學(xué)報(bào), 2015, 37(9): 2033-2039. doi: 10.3969/j.issn.0372-2112.2016.03.008.

LI Huanyu, BI Duyan, YANG Yuan, et al. Research on visual tracking algorithm based on deep feature expression and learning[J]. Journal of Electronics Information Technology, 2015, 37(9): 2033-2039. doi: 10.3969/j.issn.0372-2112.2016.03. 008.

吳劍亮, 李艷, 高揚(yáng), 等. 基于改進(jìn)RANSAC算法的道路直線提取方法[J]. 地理空間信息, 2017, 15(5): 42-44. doi: 10.3969/j.issn.1672-4623.2017.05.013.

WU Jianliang, LI Yan, GAO Yang, et al. Road straight line extraction method based on improved RANSAC algorithm [J]. Geospatial Information, 2017, 15(5): 42-44. doi: 10.3969/ j.issn.1672-4623.2017.05.013.

余淮, 楊文. 一種無人機(jī)航拍影像快速特征提取與匹配算法[J]. 電子與信息學(xué)報(bào), 2016, 38(3): 509-516. doi: 10.11999/ JEIT150676.

YU Huai and YANG Wen. A fast feature extraction and matching algorithm for unmanned aerial vehicle images[J]. Journal of Electronics Information Technology, 2016, 38(3): 509-516. doi: 10.11999/ JEIT150676.

MATAS J and CHUM O. Randomized RANSAC with sequential probability ratio test[C]. Proceedings of the 10th IEEE International Conference on Computer Vision, Beijing, China, 2005: 1727-1732. doi: 10.1109/ICCV.2005.198.

陳付幸, 王潤(rùn)生. 基于預(yù)檢驗(yàn)的快速隨機(jī)抽樣一致性算法[J]. 軟件學(xué)報(bào), 2005, 16(8): 1431-1437. doi: 10.1360/jos161431.

CHEN Fuxing and WANG Runsheng. Fast RANSAC with preview model parameters evaluation[J]. Journal of Software, 2005, 16(8): 1431-1437. doi: 10.1360/jos161431.

田文, 王宏遠(yuǎn), 徐帆, 等. RANSAC算法的自適應(yīng)Tc, d預(yù)檢驗(yàn)[J]. 中國(guó)圖象圖形學(xué)報(bào), 2009, 14(5): 973-977.

TIAN Wen, WANG Hongyuan, XU Fan, et al. Enhanced RANSAC with adaptive pre-verification[J]. Journal of Image and Graphics, 2009, 14(5): 973-977.

TORDOFF B J and MURRAY D W. Guided-MLESAC: Faster image transform estimation by using matching priors [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10): 1523-1535. doi: 10.1109/TPAMI. 2005.199.

CHUM O and MATAS J. Matching with PROSAC- progressive sample consensus[C]. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington DC, USA, 2005: 220-226. doi: 10.1109/CVPR.2005.221.

賈豐蔓, 康志忠, 于鵬. 影像同名點(diǎn)匹配的SIFT算法與貝葉斯抽樣一致性檢驗(yàn)[J]. 測(cè)繪學(xué)報(bào), 2013, 42(6): 877-883.

JIA Fengman, KANG Zhizhong, and YU Peng. A SIFT and Bayes sampling consensus method for image matching[J]. Acta Geodaetica et Cartographica Sinica, 2013, 42(6): 877-883.

MIKOLAJCZYK K, TUYTELAARS T, SCHMID C, et al. A comparison of affine region detectors[J]. International Journal of Computer Vision, 2005, 65(1-2): 43-72. doi: 10.1007/s11263-005-3848-x.

PABLO F, JESUS N, and ADRIEN B. Fast explicit diffusion for accelerated features in nonlinear scale spaces[C]. Proceedings of the British Machine Vision Conference, London, Britain, 2013: 2157-2163. doi: 10.5244/c.27.13.

PABLO F, ADRIEN B, and ANDREW J. KAZE features[C]. Proceedings of the 12th European Conference on Computer Vision, Florence, Italy, 2012: 214-227. doi: 10.1007/978-3- 642-33783-3_16.

繆君, 儲(chǔ)珺, 張桂梅. 少量交互的多視角圖像目標(biāo)分割算法[J]. 計(jì)算機(jī)輔助設(shè)計(jì)與圖形學(xué)學(xué)報(bào), 2017, 29(1): 115-123. doi: 10.3969/j.issn.1003-9775.2017.01.014.

LIAO Jun, CHU Jun, and ZHANG Guimei. Object segmentation from multi-views images with a few interactions[J]. Journal of Computer-Aided Design Computer Graphics, 2017, 29(1): 115-123. doi: 10.3969/j.issn. 1003-9775.2017.01.014.

相關(guān)文章

施引文獻(xiàn)

資源附件(0)

訪問統(tǒng)計(jì)