|
|
- 2016
一种多特征自适应融合的粒子滤波红外目标跟踪方法
|
Abstract:
提出了一种自适应融合颜色特征和边缘特征的粒子滤波跟踪算法。首先,利用粒子滤波的天然框架,选择在红外条件下最能代表目标信息的颜色特征和边缘特征构造目标的多特征模型;然后,根据不同特征对目标与背景的可分性,对多特征模型中各特征分量的权值进行自适应调节;最后,借助动态空间模型,对粒子滤波跟踪算法进行改进,预测粒子的运动状态,从而克服环境突变对跟踪稳定性的影响。实验结果表明,本文算法能克服各种背景杂波及噪声的干扰,并能很好地解决目标在复杂背景下的尺度变化和突变运动带来的困难,保证了跟踪的鲁棒性和稳定性
| [1] | Erdema E, Dubuissonb S, Blochc I.Visual Tracking by Fusing Multiple Cues with Context-Sensitive Reliabilities[J].<em>Pattern Recognition</em>, 2012, 45(5):1948-1959 |
| [2] | Hiratsuka M. Pedestrian Detection for a Near Infrared Imaging System[C]. The 11th International IEEE Conference on Intelligent Transportation Systems, Beijing, 2008 |
| [3] | van Koller N. An Adaptive Color-Based Particle Filter[J].<em>Image and Vision Computing</em>, 2012, 21(1):99-110 |
| [4] | Vignon D, Lovell B C, Andrews R J. General Purpose Real-Time Object Tracking Using Hausdorff Transforms[C]. The 9th International Conference on IPMU, Annency, France, 2012 |
| [5] | Iwata K, Hongo H, Yamamoto K, et al. Robust Facial Parts Detection by Using Four Directional Features and Relaxation Matching[J]. <em>IEEJ Transactions on Electronics Information and Systems</em>,2004, 124(3):706-712 |
| [6] | Chen S Y. Kalman Filter for Robot Vision:A Survey[J]. <em>IEEE Transactions on Industrial Electronics</em>, 2011, 99:1-2 |
| [7] | Wang Shupeng, Ji Hongbing. Based Target Tracking Method Color Space Model[J].<em>Xi'an Electronic Science and Technology Report</em>, 2009, 34(4):77-78 |
| [8] | Jia Yonghong, Li Deren. An Approach of Classification Based on Pixel Level and Decision Level Fusion of Multi-source Images in Remote Sensing[J].<em>Geomatics and Information Science of Wuhan University</em>,2001,26(5),431-433(贾永红,李德仁.多源遥感影像像素级融合分类与决策级分类融合法的研究[J].武汉大学学报·信息科学版,2001,26(5):431-433) |
| [9] | Li Jianfu,Wang Yang. Pedestrian Tracking in Infrared Image Sequences using Wavelet Entropy Features[C].IEEE Second Asia-Pacific Conference on Computational Intelligence and Industrial Applications, Wuhan, 2009 |
| [10] | Chen Shanjing. Study of Particle Filtering Algorithm Based on Multi-feature Fusion[J].<em>Computer Engineering</em>,2011, 37(7):179-180 |
| [11] | Komeili M, Armanfard N, Kabir E. A Fuzzy Approach for Multi-feature Pedestrian Tracking with Particle Filter[J].<em>IEEE International Symposium on Telecommunications</em>, 2008,2(8):570-576 |
| [12] | Yao Haitao, Zhu Fuxi, Chen Haiqiang. Face Tracking Based on Adaptive PSO Particle Filter[J].<em>Geomatics and Information Science of Wuhan University</em>,2012, 37(4):493-497(姚海涛,朱福喜,陈海强.一种自适应的PSO粒子滤波人脸视频跟踪方法[J].武汉大学学报·信息科学版,2012,37(4):493-497) |
| [13] | Wang Huan,Wang Jiangtao,Ren Mingwu,et al.A Robust Multi-feature Fusion Target Tracking Algorithm[J].<em>Chinese Journal of Image and Graphics</em>, 2011,14(3):489-498(王欢, 王江涛, 任明武, 等.一种鲁棒的多特征融合目标跟踪新算法[J].中国图象图形学报, 2011, 14(3):489-498) |
| [14] | Komeili M, Armanfard N,Kabir E.A Fuzzy Approach for Multi-feature pedestrian tracking with particle filter[C]. Internatioal Symposium on Telecommunications, Tehran, Iran, 2012 |
| [15] | Quadtrees M T. A Data Structure for Restoring Pare to Sets in Multi-object Evolutionary Algorithms with Elitism[M]. New York:Springer Verlag, 2005 |
| [16] | Parsopoulos K E,Vrahati M N. Particle Swarm Optimizer in Noisy and Continuously Changing Environments[M]//Hamza M H. Intelligence and Soft Computing, Anaheim, CA:ACTA Press, 2001 |
| [17] | Liu Jin. Research and Implementation Based on Multi-feature Fusion Particle Filter Algorithm[J].<em>Computer Measurement & Control</em>, 2013, 11(5):1307-1309 |
| [18] | Fen Xu,Zhao Lijuan.A Particle Filter Tracking Algorithm Based on Adaptive Feature Fusion Strategy[J].<em>Intelligent Control and Automation</em>,2012,8(12):4612-4615 |
