大学开发研制的一种基于3D模型的道路车辆识别与跟踪系统——VIE系统[13],基于VIEWS的研究经验,中科院自动化所模式识别实验室自行设计了拥有自主版权的交通监控原型VStar,该系统在PC环境下运行,用以对车辆进行实时跟踪,并对各种干擾因素如光线变化,斑马线干扰,边界遮挡等都显示了较强的鲁棒性。
4 主流的目标跟踪方法性能比较
几种常见的目标跟踪方法的性能比较见表2所列[14-16]。
5 结 语
就目标检测而言,其发展趋势是寻找算法时间复杂度低、算法鲁棒性强、算法成熟度高和受先验知识影响小的算法。就目标跟踪算法而言,寻找自动化程度高、先验知识依赖程度低、计算复杂度低和应用成熟度高的算法是今后的发展趋势。
参考文献
[1] A. McIvor. Background subtraction techniques[J].In Proc. Image Vis. Compute., 2001,2(2):1135-1140.
[2] M. Piccardi. Background subtraction techniques: A review[C].in Proc. IEEE Int. Conf. Syst., 2004,4(2):3099-3104.
[3]刘长钦,王正志.一个基于生物视觉的运动方向检测模型[J].计算机仿真,2006,23(8):181-183.
[4] 魏波.点时空约束图像目标跟踪理论与实时实现技术研究[D].成都:电子科技大学,2000.
[5]王长军,朱善安.基于统计模型和活动轮廓的运动目标检测与跟踪[J].浙江大学学报(工学版),2006,40(2):249-253.
[6]李红艳.图像低信噪比小目标检测与跟踪算法研究[D].西安:西安电子科技大学,2000.
[7] Tonissen S M, Evans R J. Performance of dynamic programming techniques for track before detect [J].IEEE Trans On AES, 1996,32(2):1440-1451, 1996.
[8] Askar H, Li Z M.A dim moving point target detection technique based on distribution transform method[J].Systems Engineering and Electronics, 2003,25(1):103-106.
[9] Zhang Fei, Li Cheng-fang, Shi Li-na. Algorithm based on mathematical morphology for dim moving point target detection[J].Optical Technique, 2004,30(5):600-602.
[10] Zhang Hua, Zhang Youguang, Li Guoyan. Particle-Filtering-Based Approach to Undetermined Blind Separation[J]. Advances in Information Sciences and Service Sciences,2012,4(6):305-315.
[11] J Trajkova,S Gauch. Improving ontology-based user profiles[D]. Kansas:University of Kansas,2003.
[12] Jen-Chao Tai, Shung-Tsang Tseng. Real-time Image Tracking for Automatic Traffic Monitoring and Enforcement Applications Visual track in[J]. Image and Vision Computing,2004, 22(6): 485-501.
[13] A Hampapur, L Brown, J Connell, et al.Smart surveillance applications technologies and implications information communication and signal Processing[J].Proceedings of the 2003 Joint Conference of the Fourth International Conference on,2004(2): 1133-1138.
[14] Fan Zhou, Yuhong Zhang, Zhen Qin, et al.Tracking and Managing Multiple Moving Objects Using Kernel Particle Filters in Wireless Sensor Network[J].International Journal of Advancements in Computing Technology,2012,4(6):1-9.
[15] Chen L F, Liao H M, Lin J C, et al.A new LDA-based face recognition system which can solve the small sample size problem[J].Pattern recognition,2000,33(10):1713-1726.
[16] Teja G P, Ravi S. Face Recognition using Subspaces Techniques[C].The international conference on recent trends in information technology, 2012:103-107.
[17] KyungimBaek , Bruce A. Draper , J. Ross Beveridge , et al.PCA vs. ICA: a comparison on the FERET data set[C]In Proc. Of the 4th International Conference on Computer Vision, 2002:824-827.
[18] Moghaddam B, pentland A.Probabilistic visual learning for object representation[J].IEEE Trans. on Pattern Analysis and Machine Intelligence, 1997,19(7):696 -710.
[19] M. Turk, A. Pentland.Eigenfaces for Recognition[J].Journal of Cognitive Neuroscience,1991,3(1):71-86.
[20] Juwei Lu, K.N. Plataniotis, A.N. Venetsanopoulos.Face Recognition Using LDA Based Algorithms[J].IEEE Trans. on Neural Networks, 2003,14(1):195-200.
相关热词搜索: 算法 综述 跟踪 检测 目标