无人机视觉导航着陆地标实时检测跟踪方法 -- 西北工业大学学报,2018,36(2):294-301
论文:2018,Vol:36,Issue(2):294-301
引用本文:
李靖, 马晓东, 陈怀民, 段晓军, 张彦龙. 无人机视觉导航着陆地标实时检测跟踪方法[J]. 西北工业大学学报
Li Jing, Ma Xiaodong, Chen Huaimin, Duan Xiaojun, Zhang Yanlong. Real-time Detection and Tracking Method of Landmark Based on UAV Visual Navigation[J]. Northwestern polytechnical university

无人机视觉导航着陆地标实时检测跟踪方法
李靖1, 马晓东2, 陈怀民2, 段晓军3, 张彦龙1
1. 西北工业大学 机电学院, 陕西 西安 710072;
2. 西北工业大学 自动化学院, 陕西 西安 710072;
3. 西北工业大学 无人机特种技术国防科技重点实验室, 陕西 西安 710072
摘要:
以改进的中值流跟踪算法为核心,基于上下文信息相关性特点,提出了一种适用于无人机视觉导航定点着陆的着陆地标实时检测跟踪方法。以SURF-BoW特征来描述样本图像,基于支持向量机(SVM)进行离线分类器训练,用于准确的识别目标,完成跟踪目标初始化。之后,利用改进后的中值流跟踪算法进行目标跟踪,保证目标跟踪的可靠性、完整性。最后,基于相邻2帧目标相似性原则与线下训练的分类器,设计目标再搜索算法,保证在目标丢失或目标跟踪失败的情况下,仍然能够快速地找回目标,使得整套算法能够长时间准确地跟踪目标。实验结果表明,该算法在目标尺度变化、光照变化及运动模糊等情况下,都能够实时、稳定地跟踪目标。
关键词:    中值流跟踪算法    上下文信息    SURF-BoW特征    视觉导航    实时跟踪   
Real-time Detection and Tracking Method of Landmark Based on UAV Visual Navigation
Li Jing1, Ma Xiaodong2, Chen Huaimin2, Duan Xiaojun3, Zhang Yanlong1
1. School of Mechanical Engineering, Northwestern Polytechnical University, Xi'an 710072, China;
2. School of Automation, Northwestern Polytechnical University, Xi'an 710072, China;
3. National Key Laboratory of Special Technology on UAV, Northwestern Polytechnical University, Xi'an 710072, China
Abstract:
A real-time detection and tracking method of landmark based for UAV visual navigation and fixed landing was proposed. This method used the SVM classification algorithm to train the offline classifier based on SURF-BoW features extracted from samples,which can recognize the landing landmark accurately and complete the initialization of the tracker. Afterwards, tracked the landmark via the improved median flow algorithm to ensure the reliability and integrity of the tracking target. Finally, based on the classifier and the principle of similarity between two adjacent frames' target, this paper designed a target re-search algorithm to ensure that the target can be retrieved quickly even if the target is lost or the target tracking fails, which makes the entire set of algorithm track the target accurately for a long time. The experimental results show that the proposed algorithm has good tracking performance under the conditions of the change of target scale, illumination changes and motion blur.
Key words:    median flow    context information    SURF-BoW features    visual navigation    real-time tracking   
收稿日期: 2017-06-02     修回日期:
DOI:
基金项目: 中航工业产学研专项(cxy2014XGD08)、航空科学基金(20162053021)、国家自然科学基金青年项目(51705424)、中央高校基本科研项目(3102016ZY013)与111引智项目(B13044)资助
通讯作者:     Email:
作者简介: 李靖(1982-),女,西北工业大学博士研究生,主要从事无人装备控制与图像引导算法研究。
相关功能
PDF(2641KB) Free
打印本文
把本文推荐给朋友
作者相关文章
李靖  在本刊中的所有文章
马晓东  在本刊中的所有文章
陈怀民  在本刊中的所有文章
段晓军  在本刊中的所有文章
张彦龙  在本刊中的所有文章

参考文献:
[1] 董国忠, 王省书, 胡春生. 无人机的应用及发展趋势[J]. 国防科技, 2006, 29(10):34-38 Dong Guozhong, Wang Shengshu, Hu Chunsheng. Application and Development Trend of Unmanned Aerial Vehicle[J]. National Defense Science and Technology, 2006, 29(10):34-38(in Chinese)
[2] 吴显亮, 石宗英, 钟宜生. 无人机视觉导航研究综述[J]. 系统仿真学报, 2010, 22(suppl 1):62-65 Wu Xianliang, Shi Zongying, Zhong Yisheng. An Overview of Vision-Based UAV Navigation[J]. Journal of System Simulation, 2010, 22(suppl 1):62-65(in Chinese)
[3] Zheng Z, Wei H, Tang B, et al. A Fast Visual Tracking Method via Spatio-Temporal Context Learning for Unmanned Rotorcrafts Fixed-Pointed Landing[C]//Guidance, Navigation and Control Conference, 2017
[4] Matthews I, Ishikawa T, Baker S. The Template Update Problem[J]. IEEE Trans on Pattern Analysis & Machine Intelligence, 2004, 26(6):810-815
[5] Kulikowsk C. Robust Tracking Using Local Sparse Appearance Model and K-Selection[C]//Computer Vision and Pattern Recognition, 2011:1313-1320
[6] Zhong W, Lu H, Yang M H. Robust Object Tracking via Sparse Collaborative Appearance Model[J]. IEEE Trans on Image Processing, 2014, 23(5):2356-2368
[7] Bai Y, Tang M. Robust Tracking via Weakly Supervised Ranking SVM[C]//IEEE Conference on Computer Vision and Pattern Recognition, 2012:1854-1861
[8] Grabner H, Grabner M, Bischof H. Real-Time Tracking via On-Line Boosting[C]//British Machine Vision Conference 2006, Edinburgh, Uk, 2013:47-56
[9] Kalal Z, Mikolajczyk K, Matas J. Forward-Backward Error:Automatic Detection of Tracking Failures[C]//International Conference on Pattern Recognition, 2010:2756-2759
[10] Kalal Z, Mikolajczyk K, Matas J. Tracking-Learning-Detection[J]. IEEE Trans on Pattern Analysis & Machine Intelligence, 2012, 34(7):1409
[11] Lucas B D, Kanade T. An Iterative Image Registration Technique with an Application to Stereo Vision[C]//International Joint Conference on Artificial Intelligence, 1981:674-679
[12] Shi J, Tomasi. Good Features to Track[C]//1994 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2002:593-600
[13] Bay H, Tuytelaars T, Gool L V. Surf:Speeded up Robust Features[J]. Computer Vision & Image Understanding, 2006, 110(3):404-417
[14] Lewis D D. Naive(Bayes) at Forty:The Independence Assumption in Information Retrieval[C]//Europen Conference on Machine Learning Springer, Berlin, Heidelberg, 1998:4-15
[15] 李远宁, 刘汀, 蒋树强,等. 基于"Bag of Words"的视频匹配方法[J]. 通信学报, 2007, 28(12):147-151 Li Yuanning, Liu Ting, Jiang Shuqiang, et al. Video Matching Method Based on "Bag of Words"[J]. Journal on Communications, 2007, 28(12):147-151(in Chinese)