基于改進(jìn)BRISK的圖像拼接算法
doi: 10.11999/JEIT160324
-
2.
(中國科學(xué)院長春光學(xué)精密機(jī)械與物理研究所 長春 130033) ②(中國科學(xué)院大學(xué) 北京 100049) ③(解放軍77110部隊(duì) 什邡 618400)
基金項(xiàng)目:
吉林省重大科技攻關(guān)項(xiàng)目(11ZDGG001)，國家林業(yè)公益性行業(yè)科研專項(xiàng)(201204515)
Image Mosaic Algorithm Based on Improved BRISK
-
2.
(Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, China)
Funds:
The Key Science and Technology Project of Jilin Province (11ZDGG001), The Forestry Industry Scientific Research for National Public Welfare Projects (201204515)
-
摘要: 為了獲得精準(zhǔn)的航空拼接圖像，更好地解決圖像拼接中經(jīng)常出現(xiàn)的尺度變化、角度旋轉(zhuǎn)、光照差異以及傳統(tǒng)的BRISK(Binary Robust Invariant Scalable Keypoints)算法匹配正確率較低，圖像拼接精度低等問題，該文提出一種全新的基于有向線段的BRISK特征的圖像拼接模型。首先，使用BRISK算法進(jìn)行圖像匹配，得到粗匹配點(diǎn)對，再構(gòu)造有向線段及其BRISK特征進(jìn)行鄰近線段匹配，通過概率統(tǒng)計模型進(jìn)行特征點(diǎn)的精匹配，最后進(jìn)行加權(quán)融合和亮度均衡化進(jìn)行圖像融合完成圖像拼接。實(shí)驗(yàn)結(jié)果表明，該文算法針對圖像的光照條件不同、角度旋轉(zhuǎn)、分辨率低、尺度變化等均有良好的魯棒性和穩(wěn)定性，該文算法是一種耗時短、精確度高、拼接效果良好的圖像拼接方法。
-
關(guān)鍵詞:
- 圖像配準(zhǔn) /
- 圖像拼接 /
- BRISK特征 /
- 鄰近線段
Abstract: In order to obtain accurate aerial stitching images, this paper proposes a novel image mosaic method based on Binary Robust Invariant Scalable Keypoints (BRISK) feature of directed line segment, aiming to resolve incident scaling, rotation, changes in lighting condition, the low correct matching rate and low accuracy using conventional BRISK algorithm in image mosaic. This method firstly uses BRISK algorithm to match in order to acquire rough point matching. Secondly, it constructs directed line segments, describes them with BRISK feature, and matches those directed segments. The method is used to purified point matching based on statistical voting. Finally, weighted fusion and luminance equalization are used to image fusion to accomplish image mosaic. The experiment results show that the method has strong robustness and stability for lighting, rotation, resolution and scaling. The proposed method has high precision, and can achieve fine image mosaic results. -
GHOSH D and KAABOUCH N. A survey on image mosaicing techniques[J]. Journal of Visual Communication Image Representation, 2015, 34(C): 1-11. doi: org/10.1016/ j.jvcir.2015.10.014. 張寶龍, 李洪蕊, 李丹, 等. 一種針對車載全景系統(tǒng)的圖像拼接算法的仿真[J]. 電子與信息學(xué)報, 2015, 37(5): 1149-1153. doi: 10.11999/JEIT141185. ZHANG Baolong, LI Hongrui, LI Dan, et al. A simulation of image mosaic algorithm based on vehicle panorama system[J]. Journal of Electronics Information Technology, 2015, 37(5): 1149-1153. doi: 10.11999/JEIT141185. XIE X, XU Y, LIU Q, et al. A study on fast SIFT image mosaic algorithm based on compressed sensing and wavelet transform[J]. Journal of Ambient Intelligence Humanized Computing, 2015, 6(6): 835-843. doi: org/10.1007/s12652- 015-0319-2. 余先川, 呂中華, 胡丹. 遙感圖像配準(zhǔn)技術(shù)綜述[J]. 光學(xué)精密工程, 2013, 21(11): 2960-2972. doi: 10.3788/OPE.20132111. 2960. YU Xianchuan, L Zhonghua, and HU Dan. Review of remote sensing image registration technique[J]. Optics and Precision Engineering, 2013, 21(11): 2960-2972. doi: 10.3788/ OPE.20132111.2960. AGHAJANI K, YOUSEFPOUR R, SHIRPOUR M, et al. Intensity based image registration by minimizing the complexity of weighted subtraction under illumination changes[J]. Biomedical Signal Processing Control, 2016, 25: 35-45. doi: org/10.1016/j.bspc.2015.10.009. 趙春陽, 趙懷慈. 多模態(tài)魯棒的局部特征描述符[J]. 光學(xué)精密工程, 2015, 23(5): 1474-1483. doi: 10.3788/OPE.20152305. 1474. ZHAO Chunyan and ZHAO Huaici. Multimodality robust local feature descriptors[J]. Optics and Precision Engineering, 2015, 23(5): 1474-1483. doi: 10.3788/OPE.20152305.1474. 顏雪軍, 趙春霞, 袁夏. 一種魯棒的基于圖像對比度的局部特征描述方法[J]. 電子與信息學(xué)報, 2014, 36(4): 882-887. doi: 10.3724/SP.J.1146.2013.00846. YAN Xuejun, ZHAO Chunxia, and YUAN Xia. A robust local feature descriptor based on image contrast[J]. Journal of Electronics Information Technology, 2014, 36(4): 882-887. doi: 10.3724/SP.J.1146.2013.00846. WANG Weixing, CAO Ting, LIU Sheng, et al. Remote sensing image automatic registration on multi-scale harris- laplacian[J]. Journal of the Indian Socity of Remote Sensing, 2015, 43(3): 501-511. doi: org/10.1007/s12524-014-0432-2. LOWE D G. Object recognition from local scaleinvariant features[C]. Proceedings of the 7th International Conference on Computer Vision, Corfu, Greece, ICCV, 1999, 2: 1150-1157. LOWE D G. Distinctive image features from scale-invariant key points[J]. International Journal of Computer Vision, 2004, 60(2): 91-110. doi: org/10.1023/B:VISI.0000029664.99615.94. CALONDER M, LEPETIT V, STRECHA C, et al. BRIEF: Binary Robust Independent Elementary Features[C]. European Conference on Computer Vision, Springer Berlin Heidelberg, Germany, 2010: 778-792. doi: org/10.1007/ 978-3-642- 15561-1_56. LEUTENEGGER S, CHLI M, and SIEGWART R Y. BRISK: Binary Robust Invariant Scalable Keypoints[C]. International Conference on Compater Vision, Barcelona, Spain, 2011: 2548-2555. doi: org/10.1109/ICCV.2011.6126542. KASHIF M, DESERNO T M, HAAK D, et al. Feature description with SIFT, SURF, BRIEF, BRISK, or FREAK? A general question answered for bone age assessment[J]. Computers in Biology and Medicine, 2015, 68: 67-75. doi: org/10.1016/j.compbiomed.2015.11.006. ZHU Jun and REN Mingwu. Image mosaic method based on SIFT features of line segment[J]. Computational and Mathematical Methods in Medicine, 2014, 2014(6): 926312. doi: org/10.1155/2014/926312. ZHAO Chunyang, ZHAO Huaici, L? Jinfeng, et al. Multimodal image matching based on multimodality robust line segment descriptor[J]. Neurocomputing, 2016(177): 290-303. doi: org/10.1016/j.neucom.2015.11.025. 黃立勤, 陳財淦. 全景圖拼接中圖像融合算法的研究[J]. 電子與信息學(xué)報, 2014, 36(6): 1292-1298. doi: 10.3724/SP.J.1146. 2013.01220. HUANG Liqin and CHEN Caigan. Study on image fusion algorithm of panoramic image stitching[J]. Journal of Electronics Information Technology, 2014, 36(6): 1292-1298. doi: 10.3724/SP.J.1146.2013.01220. -
計量
- 文章訪問數(shù): 1650
- HTML全文瀏覽量: 239
- PDF下載量: 387
- 被引次數(shù): 0
下載:
