您的位置：山东大学 -> 科技期刊社 -> 《山东大学学报（工学版）》

山东大学学报 (工学版) ›› 2019, Vol. 49 ›› Issue (2): 67-73.doi: 10.6040/j.issn.1672-3961.0.2018.155

• 机器学习与数据挖掘 • 上一篇    下一篇

飞行蝙蝠标记自动提取与追踪算法

杨煦1a(),陈辉1,a*(),林游思2,屠长河1b   

  1. 1a. 山东大学信息科学与工程学院, 山东 青岛 266237
    1b. 山东大学计算机科学与技术学院, 山东 青岛 266237
    2. 弗吉尼亚理工大学电子计算与工程学院, 弗吉尼亚州 黑堡, 24060
  • 收稿日期:2018-04-18 出版日期:2019-04-20 发布日期:2019-04-19
  • 通讯作者: 陈辉 E-mail:yxpeiyang@gmail.com;huichen@sdu.edu.cn
  • 作者简介:杨煦(1991—)，男，河南商丘人，硕士，研究方向为计算机视觉. Email: yxpeiyang@gmail.com
  • 基金资助:
    国家自然科学基金重点项目(61332015);国家自然科学基金重点项目(11574183);山东省自然科学基金项目(ZR2017MF057)

Automatic landmarks identification and tracking of bat flight

Xu YANG1a(),Hui CHEN1,a*(),Yousi LIN2,Changhe TU1b   

  1. 1a. School of Information Science and Engineering, Shandong University, Qingdao 266237, Shandong, China
    1b. School of Computer Science and Technology, Shandong University, Qingdao 266237, Shandong, China
    2. Bradley Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg 24060, USA
  • Received:2018-04-18 Online:2019-04-20 Published:2019-04-19
  • Contact: Hui CHEN E-mail:yxpeiyang@gmail.com;huichen@sdu.edu.cn
  • Supported by:
    国家自然科学基金重点项目(61332015);国家自然科学基金重点项目(11574183);山东省自然科学基金项目(ZR2017MF057)

RichHTML

11

PDF (PC)

520

摘要：

蝙蝠对仿生扑翼飞行器研究具有重要启发价值。通过计算机视觉方法分析蝙蝠运动需要大量特征标记,因此准确提取、追踪标记是蝙蝠飞行研究的关键。常用的底层特征提取方法将局部极值作为特征点容易导致较高的标记错检率。提出一种基于图像分割的标记提取方法。通过帧间差分获取初始蝙蝠区域,对伪装区域进行补偿,利用LoG算子进行标记增强,并通过阈值分割得到标记,计算标记质心作为特征点。提出一种基于迭代最近点的标记追踪方法,将蝙蝠划分为不同区域并对区域内标记点进行点集粗配准,通过最近邻搜索完成匹配。试验结果表明,算法的标记识别率能够达到96%并实现无遮挡情况的标记追踪,优于SIFT、BRISK等特征匹配方法以及光流追踪方法。

关键词: 飞行蝙蝠, 特征提取, 伪装, 标记追踪, 点集本准

Abstract:

Bats could serve as an inspiration for flapping-wing air vehicles. Understanding bats flight with computer vision techniques required a large copious of fiducial landmarks. Thus, accuracy of landmark identification and tracking was critical to bat flight research. General low-level feature extraction methods based on local extrema often resulted in high false positives. A landmark identification method based on image segmentation was proposed. An initial bat silhouette was first obtained using frame difference and then refined by compensating camouflage parts. The landmarks were enhanced by LoG operation. Finally, the coordinates of landmarks were computed from the centroids of connected components. Furthermore, a landmark tracking method based on ICP (Iterative Closet Points) was proposed. Bat region was divided into several parts, in which landmarks were aligned by ICP. The correspondences were determined by the nearest neighbor search. The method reached an identification accuracy up to 96%, and could track the landmark correctly when occlusion wasn′ occurred, which was better than SIFT, BRISK, and optical flow tracking methods.

Key words: flight bat, feature identification, camouflage, landmark tracking, points registration

中图分类号: 

  • TP391

图1

飞行蝙蝠标记提取算法流程图"

图2

ViBe算法(a)与本研究算法(b)效果对比"

图3

平方运算前后背景强度直方图对比"

图4

蝙蝠标记分布图及区域划分"

图5

飞行通道示意图"

图6

SIFT, BRISK和本研究算法的标记提取效果对比"

表1

SIFT, BRISK,光流法与本研究算法性能对比"

算法 P R ACC 匹配准确率
SIFT 0.30 0.61 0.45 0.15
BRISK 0.54 0.98 0.76 0.20
光流法 - - - 0.55
本研究算法 0.98 0.94 0.96 0.93

图7

SIFT,光流和本研究算法的效果对比"

1 HEDENSTROM A , JOHANSSON L C , WOLF M , et al. Bat flight generates complex aerodynamic tracks[J]. Science, 2007, 316 (5826): 894- 897.
doi: 10.1126/science.1142281
2 RAMEZANI A, SHI X, CHUNG S J, et al. Bat Bot (B2), a biologically inspired flying machine[C]//IEEE International Conference on Robotics & Automation. Stockholm, Sweden. IEEE, 2016: 3219-3226.
3 CHENEY JA , KONOW N , BEARNOT A , et al. 2015 A wrinkle in flight: the role of elastin fibres in the mechanical behavior of bat wing membranes[J]. J. R. Soc. Interface, 2014, 12 (106): 1- 9.
4 VON M T , PONS M G , ROSENHAHN B . Human pose estimation from video and IMUs[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2016, 38 (8): 1533- 1547.
5 SIGAL L , BALAN A O , BLACK M J . HumanEva: synchronized video and motion capture dataset for evaluation of articulated human motion[J]. International Journal of Computer Vision, 2010, 87 (1-2): 4.
doi: 10.1007/s11263-009-0273-6
6 PLAGEMANN C, GANAPATHI V, KOLLER D, et al. Real time motion capture using a single Time-Of-Flight camera[C]//Computer Vision & Pattern Recognition. San Francisco, USA. IEEE, 2010: 1-8.
7 JU E , WON J , LEE J , et al. Data-driven control of flapping flight[J]. ACM Transactions on Graphics, 2013, 32 (5): 151.
8 WALDMAN R M, SONG A J, RISKIN D K, et al. Aerodynamic behavior of compliant membranes as related to bat flight[C]//38th AIAA Fluid Dynamic Conference and Exhibit. Seattle, USA. 2008: 1-13.
9 BERGOU A J, SWARTZ S, BREUER K, et al. 3D reconstruction of bat flight kinematics from sparse multiple views[C]//IEEE International Conference on Computer Vision Workshops. Barcelona, Spain. IEEE, 2011: 1618-1625.
10 BENDER M J, MCCLELLAND H M, KURDILA A, et al. Recursive Bayesian estimation of bat flapping flight using kinematic trees[C]//AIAA Modeling and Simulation Technologies Conference. San Diego, USA. 2016: 1-12.
11 LEUTENEGGER S, CHLI M, SIEGWART R Y. BRISK: binary robust invariant scalable keypoints[C]//International Conference on Computer Vision. Barcelona, Spain. IEEE Computer Society, 2011: 2548-2555.
12 Lin Y, YANG X, Chen H, et al. Optimal threshold and LoG based feature identification and tracking of bat flapping flight[C]//Applications of Computer Vision. California, USA. IEEE, 2017: 418-426.
13 OLIVIER B , MARC V D . ViBe: a universal background subtraction algorithm for video sequences[J]. IEEE Transactions on Image Processing, 2011, 20 (6): 1709- 1724.
doi: 10.1109/TIP.2010.2101613
14 BRUTZER S, HOFERLIN B, HEIDEMANN G. Evaluation of background subtraction techniques for video surveillance[C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Colorado Springs, USA. 2011: 1937-1944.
15 CONTE D, FOGGIA P, PERCANNELLA G, et al. An algorithm for detection of partially camouflaged people[C]//6th IEEE International Conference on Advanced Video and Signal Based Surveillance. Genova, Italy. 2009: 340-345.
16 MONDAL A , GHOSH S , GHOSH A . Partially camouflaged object tracking using modified probabilistic neural network and fuzzy energy based active contour[J]. International Journal of Computer Vision, 2017, 122 (1): 116- 148.
doi: 10.1007/s11263-016-0959-5
17 GUNN S R . On the discrete representation of the Laplacian of Gaussian[J]. Pattern Recognition, 1999, 32 (8): 1463- 1472.
doi: 10.1016/S0031-3203(98)00163-0
18 MUJA M. Fast approximate nearest neighbors with automatic algorithm configuration[C]//International Conference on Computer Vision Theory and Application. Lisboa, Portugal. 2009: 331-340.
[1] 范君,业巧林,业宁. 基于改进的有监督无参局部保持投影算法的人脸识别[J]. 山东大学学报 (工学版), 2019, 49(1): 10-16.
[2] 王国新,陈凤东,刘国栋. 基于彩色伪随机编码结构光特征提取方法[J]. 山东大学学报 (工学版), 2018, 48(5): 55-60.
[3] 叶子云,杨金锋. 一种基于加权图模型的手指静脉识别方法[J]. 山东大学学报(工学版), 2018, 48(3): 103-109.
[4] 张振月,李斐,江铭炎. 基于低秩表示投影的无监督人脸特征提取[J]. 山东大学学报(工学版), 2018, 48(1): 15-20.
[5] 于青民,李晓磊,翟勇. 基于改进EMD和数据分箱的轴承内圈故障特征提取方法[J]. 山东大学学报(工学版), 2017, 47(3): 89-95.
[6] 郭超,杨燕,江永全,宋祎. 基于多视图分类集成的高铁工况识别[J]. 山东大学学报(工学版), 2017, 47(1): 7-14.
[7] 钟智彦,文志强, 张潇云,叶德刚. 基于半色调图像的邻域相似性描述子方法[J]. 山东大学学报(工学版), 2016, 46(3): 58-64.
[8] 卢丹, 周以齐. 基于EEMD和CWT的挖掘机座椅振动分析[J]. 山东大学学报(工学版), 2015, 45(3): 58-64.
[9] 于海晶1,2, 李桂菊1*. 基于差分盒维数的彩色烟雾图像识别[J]. 山东大学学报(工学版), 2014, 44(1): 35-40.
[10] 李慧1,2,胡云1,3,李存华1. 基于粗糙集理论的瓦斯灾害信息特征提取技术[J]. 山东大学学报(工学版), 2012, 42(5): 91-95.
[11] 曹红根1,袁宝华1,朱辉生2. 结合对比度信息与LBP的分块人脸识别[J]. 山东大学学报(工学版), 2012, 42(4): 29-34.
[12] 张思懿1,2,王士同1*. 核化空间深度间距的特征提取方法[J]. 山东大学学报(工学版), 2012, 42(3): 45-51.
[13] 王江宁, 纪力强. 昆虫图像特征研究[J]. 山东大学学报(工学版), 2011, 41(2): 51-57.
[14] 张训华1,业宁2,王厚立3. 基于Harris角点的木材CT图像配准[J]. 山东大学学报(工学版), 2010, 40(5): 101-104.
[15] 董乃鹏 赵合计 SCHOMMER Christoph. 作者写作特征提取引擎[J]. 山东大学学报(工学版), 2009, 39(5): 27-31.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
[1] 王素玉,艾兴,赵军,李作丽,刘增文 . 高速立铣3Cr2Mo模具钢切削力建模及预测[J]. 山东大学学报(工学版), 2006, 36(1): 1 -5 .
[2] 孔祥臻,刘延俊,王勇,赵秀华 . 气动比例阀的死区补偿与仿真[J]. 山东大学学报(工学版), 2006, 36(1): 99 -102 .
[3] 来翔 . 用胞映射方法讨论一类MKdV方程[J]. 山东大学学报(工学版), 2006, 36(1): 87 -92 .
[4] 李梁，罗奇鸣，陈恩红. 对象级搜索中基于图的对象排序模型（英文）[J]. 山东大学学报(工学版), 2009, 39(1): 15 -21 .
[5] 李可,刘常春,李同磊 . 一种改进的最大互信息医学图像配准算法[J]. 山东大学学报(工学版), 2006, 36(2): 107 -110 .
[6] 季涛,高旭,孙同景,薛永端,徐丙垠 . 铁路10 kV自闭/贯通线路故障行波特征分析[J]. 山东大学学报(工学版), 2006, 36(2): 111 -116 .
[7] 秦通,孙丰荣*,王丽梅,王庆浩,李新彩. 基于极大圆盘引导的形状插值实现三维表面重建[J]. 山东大学学报(工学版), 2010, 40(3): 1 -5 .
[8] Yue Khing Toh1 ， XIAO Wendong2 ， XIE Lihua1 . 基于无线传感器网络的分散目标跟踪：实际测试平台的开发应用（英文）[J]. 山东大学学报(工学版), 2009, 39(1): 50 -56 .
[9] 孙国华,吴耀华,黎伟. 消费税控制策略对供应链系统绩效的影响[J]. 山东大学学报(工学版), 2009, 39(1): 63 -68 .
[10] 孙炜伟,王玉振. 考虑饱和的发电机单机无穷大系统有限增益镇定[J]. 山东大学学报(工学版), 2009, 39(1): 69 -76 .
版权所有 © 2018 《山东大学学报(工学版)》编辑部　
地址: 济南市山大南路27号（250100）　 电话: 0531-88366735　 E-mail: xbgxb@sdu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发