一種無(wú)人機(jī)航拍影像快速特征提取與匹配算法
doi: 10.11999/JEIT150676 cstr: 32379.14.JEIT150676
基金項(xiàng)目:
國(guó)家自然科學(xué)基金(61271401, 91338113)
A Fast Feature Extraction and Matching Algorithm for Unmanned Aerial Vehicle Images
Funds:
The National Natural Science Foundation of China (61271401, 91338113)
-
摘要: 無(wú)人機(jī)影像具有非常高的分辨率，邊緣和紋理信息更加豐富，基于經(jīng)典SURF特征的影像拼接算法在處理無(wú)人機(jī)影像時(shí)面臨著新的挑戰(zhàn)。為提高無(wú)人機(jī)航拍影像拼接效率，該文提出一種快速特征提取與匹配算法。在特征提取環(huán)節(jié)，提出采用局部差分二進(jìn)制算法描述特征，在不降低特征區(qū)分性的同時(shí)，較SURF描述子而言降低了特征維度。在特征匹配環(huán)節(jié)，提出采用局部敏感哈希搜索算法代替kd樹(shù)搜索算法，提高了最近鄰特征匹配效率。實(shí)驗(yàn)結(jié)果表明，與基于SURF描述子和kd樹(shù)搜索算法的最近鄰匹配拼接算法相比，該文算法特征匹配效率有明顯提升，匹配精度也有所改善，更適合應(yīng)用于基于特征的無(wú)人機(jī)航拍影像快速制圖。
-
關(guān)鍵詞:
- 無(wú)人機(jī) /
- 影像拼接 /
- 特征提取 /
- 特征匹配
Abstract: Unmanned Aerial Vehicle (UAV) images are characterized by a very high spatial resolution, and consequently by more abundant information of the edge and the texture. The conventional stitching methods, which use Speeded Up Robust Features (SURF) and kd-tree based nearest neighbor matching, are facing with new challenges for processing UAV images. In this paper, a fast feature extraction and matching algorithm is proposed for more efficient stitching of UAV images. Firstly, the Local Difference Binary (LDB) algorithm is used to describe the feature, which could reduce the dimension of feature without sacrificing its discrimination. Then, the Local Sensitive Hash (LSH) is used to replace kd-tree search structure, which achieves nearest neighbor matching more efficiently. Compared with the conventional stitching method, experimental results demonstrate that the proposed method achieves a higher accuracy and greater efficiency, which is more applicable to rapid mapping of UAV images.-
Key words:
- Unmanned Aerial Vehicle (UAV) /
- Image stitching /
- Feature extraction /
- Feature matching
-
李德仁, 李明. 無(wú)人機(jī)遙感系統(tǒng)的研究進(jìn)展與應(yīng)用前景[J]. 武漢大學(xué)學(xué)報(bào): 信息科學(xué)版, 2014, 39(5): 505-513.LI Deren and LI Ming. Research advance and application prospect of unmanned aerial vehicle remote sensing system [J]. Geomatics and Information Science of Wuhan University, 2014, 39(5): 505-513. [2] 郭復(fù)勝, 高偉. 基于輔助信息的無(wú)人機(jī)圖像批處理三維重建方法[J]. 自動(dòng)化學(xué)報(bào), 2013, 39(6): 834-845.GUO Fusheng and GAO Wei. Batch reconstruction from UAV images with prior information[J]. Acta Automatica Sinica, 2013, 39(6): 834-845.[3] SZELISKI R. Video mosaics for virtual environments [J]. IEEE Computer Graphics and Applications, 1996, 16(2): 22-30.[4] 張寶龍, 李洪蕊, 李丹, 等. 一種針對(duì)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(bào), 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.[5] LOWE D G. Object recognition from local scale-invariant features[C]. IEEE International Conference on Computer Vision, Kerkyra, Corfu, Greece, 1999, 2: 1150-1157.[6] LOWE D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2): 91-110.[7] BROWN M and LOWE D G. Automatic panoramic image stitching using invariant features[J]. International Journal of Computer Vision, 2007, 74(1): 59-73.[8] BAY H, TUYTELAARS T, and VAN Gool L. Surf: Speeded Up Robust Features[C]. European Conference on Computer Vision, Graz, Austria, 2006: 404-417.[9] 顏雪軍, 趙春霞, 袁夏. 一種魯棒的基于圖像對(duì)比度的局部特征描述方法[J]. 電子與信息學(xué)報(bào), 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.[10] SILPA-ANAN C and HARTLEY R. Optimized KD-trees for fast image descriptor matching[C]. IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, AK, USA, 2008: 1-8.[11] MUJA M and LOWE D G. Fast approximate nearest neighbors with automatic algorithm configuration[C]. The International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, Lisboa, Portugal, 2009: 331-340.[12] CALONDER M, LEPETIT V, STRECHA C, et al. Brief: binary robust independent elementary features[C]. European Conference on Computer Vision, Hersonissos, Heraklion, Crete, Greece, 2010: 778-792.[13] RUBLEE E, RABAUD V, KONOLIGE K, et al. ORB: an efficient alternative to SIFT or SURF[C]. IEEE International Conference on Computer Vision, Barcelona, Spain, 2011: 2564-2571.[14] LEUTENEGGER S, CHLI M, and SIEGWART R Y. BRISK: binary robust invariant scalable keypoints[C]. IEEE International Conference on Computer Vision, Barcelona, Spain, 2011: 2548-2555.[15] ALAHI A, ORTIZ R, and VANDERGHEYNST P. Freak: fast retina keypoint[C]. IEEE Conference on Computer Vision and Pattern Recognition, Providence, Rhode Island, USA, 2012: 510-517.[16] YANG X and CHENG K T. Local difference binary for ultrafast and distinctive feature description[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(1): 188-194.[17] ANDONI A and INDYK P. Near-optimal hashing algorithms for approximate nearest neighbor in high dimensions[J]. Communications of the ACM, 2008, 51(1): 117-122.[18] FISCHLER M A and BOLLES R C. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography[J]. Communications of the ACM, 1981, 24(6): 381-395.[19] VIOLA P and JONES M. Robust real-time object detection [J]. International Journal of Computer Vision, 2004, 57(2): 137-154.[20] 沈秋, 李小凡, 孔繁鏘, 等. 基于仿射模型的無(wú)人機(jī)視頻實(shí)時(shí)壓縮算法[J]. 電子與信息學(xué)報(bào), 2014, 36(12): 2855-2860. doi: 10.3724/SP.J.1146.2014.00080.SHEN Qiu, LI Xiaofan, KONG Fanqiang, et al. A real-time video compression for UAV based on affine model[J]. Journal of Electronics & Information Technology, 2014, 36(12): 2855-2860. doi: 10.3724/SP.J.1146.2014.00080.[21] 李明, 劉歡, 朱欣焰. 一種面向?yàn)?zāi)害應(yīng)急的 UAV 影像快速拼接方法[J]. 災(zāi)害學(xué), 2012, 27(3): 139-144.LI Ming, LIU Huan, and ZHU Xinyan. Approach to fast mosaic UAV images for disaster emergency[J]. Journal of Catastrophology, 2012, 27(3): 139-144.[22] 易磊, 褚中理, 鄭克斌, 等. 面向無(wú)人機(jī)紅外影像拼接的特征提取算法對(duì)比研究[J]. 測(cè)繪科學(xué)技術(shù)學(xué)報(bào), 2014, 31(6): 608-613.YI Lei, CHU Zhongli, ZHENG Kebin, et al. Feature extraction algorithm for UAV infrared image mosaic[J]. Journal of Geomatics Science and Technology, 2014, 31(6): 608-613.[23] 胡同喜, 牛雪峰, 譚洋, 等. 基于 SURF 算法的無(wú)人機(jī)遙感影像拼接技術(shù)[J]. 測(cè)繪通報(bào), 2015, 74(1): 55-58.HU Tongxi, NIU Xuefeng, TAN Yang, et al. Unmanned aerial vehicle images mosaic based on SURF algorithm[J]. Bulletin of Surveying and Mapping, 2015, 74(1): 55-58. -
計(jì)量
- 文章訪問(wèn)數(shù): 2921
- HTML全文瀏覽量: 283
- PDF下載量: 1692
- 被引次數(shù): 0
下載:
