基于优化SIFT算法的农田航拍全景图像快速拼接

刘媛媛; 何铭; 王跃勇; 孙宇; 高雪冰

doi:10.11975/j.issn.1002-6819.202210135

基于优化SIFT算法的农田航拍全景图像快速拼接

刘媛媛^1,2,
何铭^1,2,
王跃勇^3,2,
孙宇^1,2,
高雪冰^1,2

1.
吉林农业大学信息技术学院，长春 130118
2.
吉林农业大学智慧农业研究院，长春 130118
3.
吉林农业大学工程技术学院，长春 130118

基金项目: 国家自然科学基金资助项目（42001256）；吉林省科技厅技术创新引导项目（20220402023GH）；吉林省科技厅重点科技项目（20230202039NC，20220203004SF）；吉林省发展和改革委员会创新项目（2019C054）；吉林省教育厅科学技术研究项目（JJKH20220339KJ）

计量
- 文章访问数: 322
- HTML全文浏览量: 14
- PDF下载量: 257
出版历程
- 收稿日期: 2022-10-17
- 修回日期: 2022-12-11
- 发布日期: 2023-01-14

Fast stitching for the farmland aerial panoramic images based on optimized SIFT algorithm

LIU Yuanyuan^1,2,
HE Ming^1,2,
WANG Yueyong^3,2,
SUN Yu^1,2,
GAO Xuebing^1,2

1.
College of Information Technology, Jilin Agricultural University, Changchun 130118, China
2.
Institute of Intelligent Agriculture, Jilin Agricultural University, Changchun 130118, China
3.
College of Engineering and Technology, Jilin Agricultural University, Changchun 130118, China

摘要

摘要: 为了快速准确获取大面积农田图像信息，提高保护性耕作秸秆还田监测效率和准确性，该研究提出一种基于优化SIFT（scale-invariant feature transform）算法的农田航拍全景图像快速拼接方法。首先对高分辨率图像进行降采样处理，针对图像的重叠区域进行有效检测；然后采用基于梯度归一化的特征描述符对特征点进行匹配，同时通过渐进样本一致算法去除误匹配，精准计算拼接转换模型；最后采用基于最佳拼接线的多分辨率融合算法进行图像融合，得到全景拼接图像。试验结果表明：该文方法在图像配准阶段与传统SIFT算法和SURF（speeded up robust feature）算法相比，特征点数量分别减少了97%和90%，运行时间减少了94%和69%，平均匹配效率为65.17%，约为SIFT算法的4倍，SURF算法的9倍；与APAP（ss-projective-as-possible）、SPHP（shape-preserving half-projective）和AANAP（adaptive as-natural-as-possible）算法相比，该方法拼接图像的信息熵、平均梯度和图像对比度均有明显提高。与传统方法相比，该文分层拼接方法提高了全景拼接图像的清晰度和融合效果，解决了传统方法中出现的错位和重影问题，其中全景图像的信息熵、平均梯度小幅提高，对比度明显提高，拼接时间大约缩短了90%以上。研究结果可为保护性耕作秸秆还田监测提供科学参考。
- 无人机 /
- 图像处理 /
- 全景拼接 /
- SIFT算子 /
- 特征点匹配 /
- 图像融合
Abstract: Straw mulching has been a common measure for black land conservation in the northeastern plains of China. It is a great significance of an effective solution to reduce soil erosion for environmental protection and sustainable development in modern agriculture. However, it is difficult to calculate the coverage rate at one time, due to the wide area of crop cultivation. Therefore, it is a high demand for the rapid acquisition of image information on a large area of farmland, in order to improve the efficiency and accuracy of straw mulching. Fortunately, aerial drone images and videos can be widely used in various fields, such as agricultural monitoring, weather forecasting, and geographic mapping. Among them, the application of remote sensing technology focuses mainly on the crops and soil in agriculture. The spectral patterns of the ground can be utilized to monitor the crops and soil in the field. Specifically, the spectral characteristics of the ground are used to monitor the growth of crops, crop quality, crop pests, and diseases. The high-resolution images can be collected by unmanned aerial vehicle (UAV) aerial photography. The panoramic stitching can be selected for rapid and accurate access to the large-area farmland image information. Therefore, it is of great practical significance to agricultural intelligence, particularly for the high efficiency and accuracy of straw cover monitoring of conservation tillage. In this study, a fast-stitching method was proposed for the aerial panoramic images of the fields using the optimized scale-invariant feature transform (SIFT) algorithm. Firstly, the high-resolution image was down-sampled to effectively detect the overlapping regions of the image. The gradient normalization-based feature descriptors were then used to match the feature points. The false matches were removed by the progressive sample consistency algorithm, in order to accurately calculate the stitching conversion model. Finally, the multi-resolution fusion algorithm was used for the high-quality stitched image using the best stitching line. The experimental results show that the improved algorithm reduced the number of feature points by 97% and 90%, the running time by 94% and 69%, and the average matching efficiency by 65.17% in the image alignment stage, respectively, compared with the traditional SIFT and Speeded Up Robust Feature (SURF) algorithm, which was about 4 times that of SIFT algorithm, and 9 times that of SURF algorithm, respectively. Compared with the as-projective-as-possible (APAP), the shape-preserving half-projective (SPHP), and the adaptive as-natural-as-possible (AANAP) algorithms, the new algorithm significantly improved the information entropy, the average gradient, and image contrast of the stitched image. More importantly, the stitched image was of higher quality with more than a 90% reduction in the running time, particularly with better overall performance. The systematic evaluation demonstrated that the layered stitching method significantly improved the clarity and fusion effect of the panoramic stitched images, compared with the traditional. Moreover, there was no misalignment and ghosting that appeared in the traditional. Specifically, the information entropy and average gradient of the panoramic images were slightly improved to increase the contrast by about 20%, indicating a higher stitching efficiency than before. The overall stitching time was also shortened by about 90% or more. The research structure can also provide a scientific reference to monitor the conservation of tillage with straw returning.
- UAV /
- image processing /
- panoramic stitching /
- SIFT operator /
- feature point matching /
- image fusion

HTML全文

参考文献(30)

[1]	田慎重，张玉凤，边文范，等. 深松和秸秆还田对旋耕农田土壤有机碳活性组分的影响[J]. 农业工程学报，2020，36(2)：185-192.TIAN Senzhong, ZHANG Yufeng, BIAN Wenfan, et al. Effect of deep loosening and straw return on the organic carbon activity fraction of rototilled farmland soils[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2020, 36(2): 185-192. (in Chinese with English abstract)
[2]	汪可欣，付强，张中昊，等. 秸秆覆盖与表土耕作对东北黑土根区土壤环境的影响[J]. 农业机械学报，2016，47(3)：131-137.WANG Kexin, FU Qiang, ZHANG Zhonghao, et al. Effects of straw mulching and topsoil tillage on soil environment in the root zone of northeastern black soil[J]. Transactions of the Chinese Society of Agricultural Machinery, 2016, 47(3): 131-137. (in Chinese with English abstract)
[3]	王忠江，王泽宇，司爱龙，等. 秸秆与沼肥同步翻埋还田对秸秆腐解特性的影响[J]. 农业机械学报, 2017，48(6)：271-277.WANG Zhongjiang, WANG Zeyu, SI Ailong, et al. Effect of simultaneous reburial of straw and methane fertilizer on the decomposition characteristics of straw[J]. Transactions of the Chinese Society of Agricultural Machinery, 2017, 48(6): 271-277. (in Chinese with English abstract)
[4]	刘媛媛，孙嘉慧，张书杰，等. 用多阈值多目标无人机图像分割优化算法检测秸秆覆盖率[J]. 农业工程学报，2020，36(20)：134-143.LIU Yuanyuan, SUN Jiahui, ZHANG Shujie, et al. Detection of straw cover with multi-threshold multi-objective UAV image segmentation optimization algorithm[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2020, 36(20): 134-143. (in Chinese with English abstract)
[5]	刘媛媛，周小康，王跃勇，等. 改进U-Net模型的保护性耕作田间秸秆覆盖检测[J]. 光学精密工程，2022，30(9)：1101-1112.LIU Yuanyuan, ZHOU Xiaokang, WANG Yueyong, et al. Improved U-Net model for straw cover detection in conservation tillage fields[J]. Optics and Precision Engineering, 2022, 30(9): 1101-1112. (in Chinese with English abstract)
[6]	刘媛媛，张硕，于海业，等. 基于语义分割的复杂场景下的秸秆检测[J]. 光学精密工程，2020，28(1)：200-211.LIU Yuanyuan, ZHANG Shuo, YU Haiye, et al. Straw detection algorithm based on semantic segmentation in complex farm scenarios[J]. Optics and Precision Engineering, 2020, 28(1): 200-211. (in Chinese with English abstract)
[7]	李欣璐，凌灿权. 无人机遥感技术在农情监测中的应用[J].现代农业装备，2022，43(5)：45-51.LI Xinlu, LING Canquan. Application of UAV remote sensing technology in agricultural situation monitoring[J]. Modern Agricultural Equipment, 2022, 43(5): 45-51. (in Chinese with English abstract)
[8]	刘忠，万炜，黄晋宇，等. 基于无人机遥感的农作物长势关键参数反演研究进展[J]. 农业工程学报，2018，34(24)：60-71.LIU Zhong, WAN Wei, HUANG Jinyu, et al. Research progress on the inversion of key parameters of crop growth based on UAV remote sensing[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2018, 34(24): 60-71. (in Chinese with English abstract)
[9]	Sutherland I E. Sketchpad a man-machine graphical communication system[J]. Simulation, 1964, 2(5): R-3-R-20.
[10]	KUGLIN C. The phase correlation image alignment Methed KUGLIN C. D. Proc. Int. Conference Cybernetics Society, 1975, 163-165.
[11]	Harris C G, Stephens M. Harris C, Stephens M. A combined corner and edge detector[C]//Alvey vision conference. 1988, 15(50): 10-5244.
[12]	LOWE D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision. 2004, 60(2): 91-110.
[13]	BAY H T. Surf: Speeded up robust features[J]. European Conference on Computer Vision. 2006: 404-417.
[14]	MOREL J M, Yu G. ASIFT: A new framework for fully affine invariant image comparison[J]. SIAM Journal on Imaging Sciences, 2009, 2(2): 438-469.
[15]	RUBLEE E, KABAUI V, KONOLIGE K, et al. ORB: An efficient alternative to SIFT or SURF[C]//International Conference on Computer Vision. Barcelona: IEEE Pree, 2011: 2564-2571.
[16]	ZARAGOZA J, CHIN T J, BROWN M S, et al. As-Projective-As-Possible Image Stitching with Moving DLT[C]//IEEE Transactions on Pattern Analysis and Machine Intelligence, OR, USA. 2013: 2339-2346.
[17]	CHANG C H, SATO Y, CHUANG Y Y. Shape-preserving half-projective warps for image stitching[C]//IEEE Conference on Computer Vision and Pattern Recognition, OH, USA. 2014: 3254-3261.
[18]	LIN C C, PANKANTI S U, RAMAMURTHY K N, et al. Adaptive as-natural-as-possible image stitching[C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , Boston, MA, USA. 2015: 1155-1163.
[19]	贾银江，徐哲男，苏中滨，等. 基于优化SIFT算法的无人机遥感作物影像拼接[J]. 农业工程学报，2017，33(10)：123-129.JIA Yinjiang, XU Zhenan, SU Zhongbin, et al. UAV remote sensing crop image stitching based on optimized SIFT algorithm[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2017, 33(10): 123-129. (in Chinese with English abstract)
[20]	沈跃，朱嘉慧，刘慧，等. 基于深度和彩色双信息特征源的Kinect植物图像拼接[J]. 农业工程学报，2018，34(5)：176-182.SHEN Yue, ZHU Jiahui, LIU Hui, et al. Kinect plant image stitching based on depth and color dual information feature sources[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2018, 34(5): 176-182. (in Chinese with English abstract)
[21]	吴如梦，方挺，李文钦. 基于SURF特征的无人机航拍图像拼接方法[J]. 现代制造技术与装备，2019(8)：34-36.WU Rumeng, FANG Ting, LI Wenqin. SURF feature-based stitching method for UAV aerial images[J]. Modern Manufacturing Technology and Equipment, 2019(8): 34-36. (in Chinese with English abstract)
[22]	王红君，刘一鸣，岳有军，等. 基于改进SPHP算法的无人机遥感图像拼接技术[J]. 计算机工程与设计，2020，41(3)：783-788.WANG Hongjun, LIU Yiming, YUE Youjun, et al. UAV remote sensing image stitching technique based on improved SPHP algorithm[J]. Computer Engineering and Design, 2020, 41(3): 783-788. (in Chinese with English abstract)
[23]	王艳，祁萌. 基于 GA-SIFT 算法的无人机航拍图像实时拼接[J]. 测绘通报，2021(8)：28-32，47.WANG Yan, QI Meng. Real-time stitching of UAV aerial images based on GA-SIFT algorithm[J]. Mapping Bulletin, 2021(8): 28-32, 47. (in Chinese with English abstract)
[24]	刘杰，游品鸿，占建斌，等. 改进SIFT快速图像拼接和重影优化[J]. 光学精密工程，2020，28(9)：2076-2084.LIU Jie, YOU Pinhong, ZHAN Jianbin, et al. Improved SIFT fast image stitching and ghosting optimization algorithm[J]. Optics and Precision Engineering, 2020, 28(9): 2076-2084. (in Chinese with English abstract)
[25]	ZHANG W, WANG Y, LIU Y. Generating High-Quality Panorama by View Synthesis Based on Optical Flow Estimation[J]. Sensors, 2022, 22(2): 470.
[26]	DENG L, YUAN X, DENG C, et al. Image stitching based on nonrigid warping for urban scene[J]. Sensors. 2020, 20(24): 7050.
[27]	SALEEM S, BAIS A, SABLATNIG R. Towards feature points based image matching between satellite imagery and aerial photographs of agriculture land[J]. Computers and Electronics in Agriculture, 2016, 126: 12-20.
[28]	LU J, XU Y, GAO Z. An improved method of an image mosaic of a tea garden and tea tree target extraction[J]. 25, 2022, 4(1): 231-254.
[29]	王茜，宁纪锋，曹宇翔，等. 基于SIFT算法的无人机遥感图像拼接技术[J]. 吉林大学学报（信息科学版），2017，35(2)：188-197.WANG XI, NING Jifeng, CAO Yuxiang, et al. UAV remote sensing image stitching technology based on SIFTalgorithm[J]. Journal of Jilin University (Information Science Edition). 2017, 35(2): 188-197. (in Chinese with English abstract)
[30]	沈跃，朱嘉慧，刘慧，等. 基于彩色和深度信息结合K-means聚类算法快速拼接植株图像[J]. 农业工程学报，2018，34(23)：134-141.SHEN Yue, ZHU Jiahui, LIU Hui, et al. Fast stitching of plant images based on color and depth information combined with K-means clustering algorithm[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE). 2018, 34(23): 134-141. (in Chinese with English abstract)

施引文献(27)

期刊类型引用(12)

1.	李朝清，谭兴强，李吉，李毅，周艺璇. 基于改进LoFTR算法的草畜平衡监测图像拼接方法. 农业与技术. 2025(06): 65-70 . 百度学术
2.	苑朝，黄诺飞，蒋阳，赵亚冬，赵振兵. 基于改进旋转不变性二进制描述算法的电力场景图像拼接. 电力科学与工程. 2024(01): 31-38 . 百度学术
3.	许鑫，张力，岳继博，钟鹤鸣，王颖，刘杰，乔红波. 农田环境下无人机图像并行拼接识别算法. 农业工程学报. 2024(09): 154-163 . 本站查看
4.	刘媛媛，孙宇，高雪冰，王利斌，王跃勇，刘梦琪，崔舒然. 航拍多光谱田间秸秆覆盖量反演模型的建立与优化. 光学精密工程. 2024(11): 1773-1787 . 百度学术
5.	马小娅. 基于局部精细拼接算法的无人机图像处理技术分析. 佳木斯大学学报(自然科学版). 2024(06): 41-44 . 百度学术
6.	刘明，李永可，靳晟，李悦，余恩. 基于无人机摄影技术的农田场景可视化系统设计与实现. 湖北农业科学. 2024(08): 158-163 . 百度学术
7.	何佳. 基于人工智能的光学表面疵病图像自动化拼接研究. 自动化与仪表. 2024(09): 61-65 . 百度学术
8.	潘维东，李安虎，刘兴盛. 基于区域优化的图像拼接技术研究及应用进展. 激光与光电子学进展. 2024(18): 1-20 . 百度学术
9.	郑蔚. 基于SIFT-GMLBP的动态图像视觉信息提取研究. 现代电子技术. 2024(19): 83-86 . 百度学术
10.	李易达，王雨欣，李晨曦，赵冀，马恢，张漫，李寒. 融合改进头脑风暴与Powell算法的马铃薯多模态图像配准. 农业工程学报. 2024(19): 146-158 . 本站查看
11.	陈颖博. 基于深度学习的桑叶成熟度智能识别. 农业与技术. 2024(24): 56-59 . 百度学术
12.	齐咏生，焦杰，鲍腾飞，王朝霞，杜晓旭 . 基于自适应注意力机制的复杂场景下牛脸检测算法. 农业工程学报. 2023(14): 173-183 . 本站查看