基于时空显著性建模的空中飞行器跟踪方法

doi:10.7527/S1000-6893.2019.23388

电子电气工程与控制

本期目录 | 过刊浏览 | 高级检索

前一篇 | 后一篇

基于时空显著性建模的空中飞行器跟踪方法

张伟俊^1,2, 钟胜^1,2, 王建辉^1,2

1. 华中科技大学人工智能与自动化学院, 武汉 430074;
2. 华中科技大学多谱信息处理技术国家级重点实验室, 武汉 430074

收稿日期:2019-08-16 修回日期:2019-10-25 出版日期:2020-03-15 发布日期:2019-10-24
通讯作者: 张伟俊 E-mail:starfire.zhang@foxmail.com
基金资助:
国家自然科学基金（61806081）

Airborne target tracking based on spatio-temporal saliency modeling

ZHANG Weijun^1,2, ZHONG Sheng^1,2, WANG Jianhui^1,2

1. School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China;
2. National Key Laboratory of Science and Technology on Multi-Spectral Information Processing, Huazhong University of Science and Technology, Wuhan 430074, China

Received:2019-08-16 Revised:2019-10-25 Online:2020-03-15 Published:2019-10-24
Supported by:
National Natural Science Foundation of China (61806081)

摘要/Abstract

摘要： 以复杂背景下空中飞行器的鲁棒视觉跟踪问题为研究背景，为解决现有跟踪方法目标表征模型不够精确，算法鲁棒性严重受到目标形变、宽高比变化、复杂背景等因素干扰的问题，提出了建模跟踪场景中独立物体的显著性特性，用于构建精确的目标模型。提出的显著性估计方法有别于传统的单帧检测方法，利用跟踪算法提供的背景先验知识以及多帧图像观测数据，使用时空联合的方式进行建模估计，其结果用来指导目标跟踪算法选取有效视觉特征，建立精确目标表征模型，减小背景区域对算法模型的干扰。实验表明，提出的方法为上述难点问题提供了有效的解决方案，对空中飞行器的跟踪精度与鲁棒性优于大多数最先进的主流方法，在其他类型的目标跟踪任务中也有十分优越的性能表现。

关键词: 视觉跟踪, 飞行器, 目标表征模型, 显著性估计, 时空模型, 贝叶斯推断

Abstract: This paper studies the robust visual tracking problem of airborne aircraft in complex environments. To improve the robustness in tracking airborne targets against challenging factors like target deformation, aspect ratio variation, and complex background, this paper models the saliency characteristics of the independent objects in the tracking scene and builds a more accurate target representation model. Different from traditional single-frame saliency detection methods, this paper proposes a spatio-temporal saliency estimation model, which makes use of prior knowledge of the target provided by the tracking algorithm and multi-frame observation data. The estimated saliency map is used to select of effective visual features and build accurate target representation in the tracking algorithm, which reduces the interference of the background clutter. Experimental results show that the proposed method provides an effective solution to the above problems in airborne tracking tasks and outperforms most state-of-the-art methods in accuracy and robustness. Moreover, the method shows excellent performance in tracking other objects.

Key words: visual tracking, airborne, target representation model, saliency estimation, spatio-temporal model, Bayesian inference

中图分类号:

V249
TP391

张伟俊, 钟胜, 王建辉. 基于时空显著性建模的空中飞行器跟踪方法[J]. 航空学报, 2020, 41(3): 323388-323388.

ZHANG Weijun, ZHONG Sheng, WANG Jianhui. Airborne target tracking based on spatio-temporal saliency modeling[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2020, 41(3): 323388-323388.

参考文献 39

[1]	刘芳, 王洪娟, 黄光伟, 等. 基于自适应深度网络的无人机目标跟踪算法[J]. 航空学报, 2019, 40(3):322332. LIU F, WANG H J, HUANG W G, et al. UAV target tracking algorithm based on adaptive depth network[J]. Acta Aeronautica et Astronautica Sinica, 2019, 40(3):179-188 (in Chinese).
[2]	邵干, 张曙光, 唐鹏. 小型无人机气动参数辨识的新型 HGAPSO 算法[J]. 航空学报, 2017, 38(4):49-59. SHAO G, ZHANG S G, TANG P. HGAPSO:A new aerodynamic parameters identification algorithm for small unmanned aerial vehicles[J]. Acta Aeronautica et Astronautica Sinica, 2017, 38(4):49-59 (in Chinese).
[3]	GANTI S R, KIM Y. Implementation of detection and tracking mechanism for small uas[C]//2016 International Conference on Unmanned Aircraft Systems. Piscataway, NJ:IEEE Press, 2016:1254-1260.
[4]	STURDIVANT R L, CHONG E K. Systems engineering baseline concept of a multispectral drone detection solution for airports[J]. IEEE Access, 2017, 5:7123-7138.
[5]	赵洲, 黄攀峰, 陈路. 一种融合卡尔曼滤波的改进时空上下文跟踪算法[J]. 航空学报, 2017, 38(2):269-279. ZHAO Z, HUANG P F, CHEN L. A tracking algorithm of improved spatio-temporal context with Kalman filter[J]. Acta Aeronautica et Astronautica Sinica, 2017, 38(2):269-279 (in Chinese).
[6]	王晓. 视频中无人机的实时检测与跟踪算法研究[D]. 哈尔滨:哈尔滨工程大学, 2019. WANG X. Research on real-time detection and tracking algorithm of UAV in video[D]. Harbin:Harbin Engineering University, 2019 (in Chinese).
[7]	郭晓冉, 崔少辉, 毛向东, 等. 背景干扰下的捷联图像导引系统目标跟踪方法[J]. 兵器装备工程学报, 2017, 38(3):1-5. GUO X R, CUI S H, MAO X D, et al. Strapdown image homing system target tracking approach under the interference of background[J]. Journal of Ordnance Equipment Engineering, 2017, 38(3):1-5 (in Chinese).
[8]	吕梅柏, 赵小锋, 刘广哲. 空中大机动目标跟踪算法研究[J]. 现代防御技术, 2018, 46(2):45-50. LV M B, ZHAO X F, LIU G Z. Aerial high maneuvering target tracking algorithm[J]. Modern Defence Technology, 2018, 46(2):45-50 (in Chinese).
[9]	WU Y, LIM J, YANG M H. Object tracking benchmark[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9):1834-1848.
[10]	HENRIQUES J F, CASEIRO R, MARTINS P, et al. High-speed tracking with kernelized correlation filters[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(3):583-596.
[11]	ZHANG J, MA S, SCLAROFF S. MEEM:Robust tracking via multiple experts using entropy minimization[C]//2014 European Conference on Computer Vision, 2014:188-203.
[12]	DANELLJAN M, HÄGER G, KHAN F S, et al. Discriminative scale space tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(8):1561-1575.
[13]	孙丰东. 图像显著性检测若干关键问题研究[D]. 长春:吉林大学, 2019. SUN F D. Research on several key issues of image saliency detection[D]. Changchun:Jilin University, 2019 (in Chinese).
[14]	STRAND R, CIESIELSKI K C, MALMBERG F, et al. The minimum barrier distance[J]. Computer Vision and Image Understanding, 2013, 117(4):429-437.
[15]	ZHANG J, SCLAROFF S, LIN Z, et al. Minimum barrier salient object detection at 80 fps[C]//2015 IEEE International Conference on Computer Vision. Piscataway, NJ:IEEE Press, 2015:1404-1412.
[16]	LIU C, YUEN P C, QIU G. Object motion detection using information theoretic spatio-temporal saliency[J]. Pattern Recognition, 2009, 42(11):2897-2906.
[17]	YANG M, YUAN J, WU Y. Spatial selection for attentional visual tracking[C]//2007 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE Press, 2007:1-8.
[18]	FAN J, WU Y, DAI S. Discriminative spatial attention for robust tracking[C]//2010 European Conference on Computer Vision, 2010:480-493.
[19]	HONG S, YOU T, KWAK S, et al. Online tracking by learning discriminative saliency map with convolutional neural network[C]//2015 International Conference on Machine Learning. Lille:The International Machine Learning Society, 2015:597-606.
[20]	CHOI J, JIN CHANG H, JEONG J, et al. Visual tracking using attention-modulated disintegration and integration[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE Press, 2016:4321-4330.
[21]	WEI Y, WEN F, ZHU W, et al. Geodesic saliency using background priors[C]//2012 European Conference on Computer Vision, 2012:29-42.
[22]	POSSEGGER H, MAUTHNER T, BISCHOF H. In defense of color-based model-free tracking[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE Press, 2015:2113-2120.
[23]	BERTINETTO L, VALMADRE J, GOLODETZ S, et al. Staple:Complementary learners for real-time tracking[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE Press, 2016:1401-1409.
[24]	HARE S, GOLODETZ S, SAFFARI A, et al. Struck:Structured output tracking with kernels[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(10):2096-2109.
[25]	NING J, YANG J, JIANG S, et al. Object tracking via dual linear structured svm and explicit feature map[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE Press, 2016:4266-4274.
[26]	FAN H, LIN L, YANG F, et al. Lasot:A high-quality benchmark for large-scale single object tracking[C]//2019 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE Press, 2019:5374-5383.
[27]	HENRIQUES J F, CASEIRO R, MARTINS P, et al. Exploiting the circulant structure of tracking-by-detection with kernels[C]//2012 European Conference on Computer Vision, 2012:702-715.
[28]	LI Y, ZHU J. A scale adaptive kernel correlation filter tracker with feature integration[C]//2014 European Conference on Computer Vision Workshops, 2014:254-265.
[29]	DANELLJAN M, HAGER G, SHAHBAZ KHAN F, et al. Learning spatially regularized correlation filters for visual tracking[C]//2015 IEEE International Conference on Computer Vision. Piscataway, NJ:IEEE Press, 2015:4310-4318.
[30]	MUELLER M, SMITH N, GHANEM B. Context-aware correlation filter tracking[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE Press, 2017:1396-1404.
[31]	LUKEZIC A, VOJIR T, ?EHOVIN ZAJC L, et al. Discriminative correlation filter with channel and spatial reliability[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE Press, 2017:6309-6318.
[32]	DANELLJAN M, BHAT G, SHAHBAZ KHAN F, et al. ECO:Efficient convolution operators for tracking[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE Press, 2017:6638-6646.
[33]	WANG N, ZHOU W, TIAN Q, et al. Multi-cue correlation filters for robust visual tracking[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE Press, 2018:4844-4853.
[34]	VALMADRE J, BERTINETTO L, HENRIQUES J, et al. End-to-end representation learning for correlation filter based tracking[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE Press, 2017:2805-2813.
[35]	SONG Y, MA C, WU X, et al. Vital:Visual tracking via adversarial learning[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE Press, 2018:8990-8999.
[36]	CHOI J, JIN C H, FISCHER T, et al. Context-aware deep feature compression for high-speed visual tracking[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE Press, 2018:479-488.
[37]	DAI K, WANG D, LU H, et al. Visual tracking via adaptive spatially-regularized correlation filters[C]//2019 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE Press, 2019:4670-4679.
[38]	CHOI J, JIN C H, YUN S, et al. Attentional correlation filter network for adaptive visual tracking[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE Press, 2017:4807-4816.
[39]	WANG M, LIU Y, HUANG Z. Large margin object tracking with circulant feature maps[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE Press, 2017:4021-4029.

E-mail：hkxb@buaa.edu.cn

关于我们

期刊社服务

专业学科

封面文章

友情链接

主管单位：中国科学技术协会主办单位：中国航空学会北京航空航天大学

基于时空显著性建模的空中飞行器跟踪方法

Airborne target tracking based on spatio-temporal saliency modeling

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献 39

相关文章 15

编辑推荐

Metrics

本文评价

[1]	孙志坤, 史志伟, 张伟麟, 李铮, 孙琪杰. 等离子体激励器对高速翼型升阻特性的影响[J]. 航空学报, 2022, 43(S2): 23-39.
[2]	宋威, 艾邦成. 多体分离动力学研究进展[J]. 航空学报, 2022, 43(9): 25950-025950.
[3]	王新光, 毛枚良, 何琨, 陈琦, 万钊. 壁面函数在超声速湍流模拟中的应用[J]. 航空学报, 2022, 43(9): 126153-126153.
[4]	郑辉, 邱雷, 袁慎芳, 杨晓飞, 卢绪龙, 薛兆鹏. C/C热防护结构高温气流损伤导波监测实验方法[J]. 航空学报, 2022, 43(8): 225659-225659.
[5]	喻天翔, 庄新臣, 宋笔锋, 孙中超. 飞机连杆机构多铰链磨损寿命综合预测方法[J]. 航空学报, 2022, 43(8): 625113-625113.
[6]	刘强, 涂国华, 罗振兵, 陈坚强, 赵瑞, 袁先旭. 延迟高超声速边界层转捩技术研究进展[J]. 航空学报, 2022, 43(7): 25357-025357.
[7]	何宇廷. 飞行器广义生存性及评估方法[J]. 航空学报, 2022, 43(6): 526118-526118.
[8]	王晨, 杨洋, 沈星, 夏育颖. 用于变体飞行器的波纹板等效强度模型及其优化设计[J]. 航空学报, 2022, 43(6): 526146-526146.
[9]	赵天, 李营, 张超, 姚辽军, 黄怿行, 黄治新, 陈诚, 汪万栋, 祖磊, 周华民, 裘进浩, 邱志平, 方岱宁. 高性能航空复合材料结构的关键力学问题研究进展[J]. 航空学报, 2022, 43(6): 526851-526851.
[10]	孙聪. 高超声速飞行器强度技术的现状、挑战与发展趋势[J]. 航空学报, 2022, 43(6): 527590-527590.
[11]	胡嘉欣, 芮姝, 高瑞朝, 苟建军, 龚春林. 飞行器结构布局与尺寸混合优化方法[J]. 航空学报, 2022, 43(5): 225363-225363.
[12]	赵飞, 刘丽玲, 石泳, 左光, 万千, 张宇佳. 类X-43A飞行器高超声速分离仿真[J]. 航空学报, 2022, 43(5): 125171-125171.
[13]	罗世彬, 庙智超, 宋佳文. 高超声速飞行器前缘主动冷却影响因素[J]. 航空学报, 2022, 43(12): 627023-627023.
[14]	李霞, 齐国元, 郭曦彤, 赵旭. 高阶微分反馈控制及在四旋翼飞行器中的应用[J]. 航空学报, 2022, 43(12): 326047-326047.
[15]	阎超. 航空CFD四十年的成就与困境[J]. 航空学报, 2022, 43(10): 526490-526490.