基于双模式遮挡检测机制的红外目标跟踪算法

孙护军

红外技术, 2018, 40 (9): 902, 网络出版: 2018-10-06

基于双模式遮挡检测机制的红外目标跟踪算法

An Infrared Object Tracking Algorithm Based on Dual-mode Context Occlusion Detection Mechanism

论文大纲

孙护军 ^*

作者单位

西安航空学院电子工程学院, 陕西西安 710077

目标跟踪检测机制遮挡干扰空时上下文重捕置信度 object tracking detection mechanism occlusion interference spatio-temporal context confidence degree

摘要

由于运动目标存在不同程度的遮挡干扰, 严重制约装备精确打击的能力。本文在空时上下文跟踪算法的基础上, 提出了一种基于双模式遮挡检测机制的目标跟踪算法, 该算法充分利用目标及其局部背景的上下文区域信息来预测遮挡状态, 最大限度地提高遮挡预测的响应能力和重捕的精度。首先, 利用双模式遮挡检测机制实现遮挡状态检测; 一旦目标进入完全遮挡, 对目标进行位置预测, 并利用形态学操作提取疑似目标区域, 降低匹配的复杂度; 最后, 采用基于直方图置信度策略对遮挡后的疑似目标区域进行重捕, 实现整个遮挡过程的稳定跟踪。定性定量仿真实验结果表明, 本文提出的目标跟踪算法在实时性, 稳定性和定量指标上具有明显优势, 适合工程应用。

Abstract

Due to the occlusion interference for moving objects to a certain extent, the precise attack capability of infrared missile seekers is severely restricted. Based on the spatio-temporal context tracking algorithm, an object tracking algorithm based on the dual-mode occlusion detection mechanism is proposed in this paper. This algorithm makes full use of the context information of the object and its local background to calculate the correlation features, which maximumly improve the occlusion predictive response and recapture accuracy. First, dual-mode occlusion detection is implemented to realize the occlusion detection. Once the object is fully occluded, the object position is predicted and morphological operations are used to extract the suspected target region, which reduces the matching complexity. Finally, the histogram-based confidence strategy is adopted to capture the suspected object so as to achieve stable tracking of the entire process. Simulation results show that our proposed tracking algorithm with dual-mode context occlusion detection mechanism has obvious overall advantages in real-time, stability, and quantitative indexesand is suitable for engineering applications.

参考文献

[1] 王敏, 徐文晴. 基于多特征与评估模型的红外小目标跟踪算法[J].华中科技大学学报: 自然科学版, 2017, 45(10): 1-6.

WANG M, XU W Q. A small target tracking algorithm based on multi-feature evaluation model[J]. Journal of Huazhong University of Science and Technology: Natural Science Edition, 2017, 45(10): 1-6.

[2] 程建, 周越, 蔡念, 等. 基于粒子滤波的红外目标跟踪[J].红外与毫米波学报, 2006(2): 113-117.

CHENG J, ZHOU Y, CAI N, et al. Infrared object tracking based on particle filters[J]. J. Infrared Millim. Waves, 2006, 25(2): 113-117.

[3] 杨智雄, 余春超, 严敏, 等. 基于特征融合的粒子滤波红外目标跟踪算法[J].红外技术, 2016, 38(3): 211-217.

YANG Z X, YU C C, YAN M, et al. A particle filter infrared target tracking algorithm based on feature fusion[J]. Infrared Technology, 2016, 38(3): 211-217.

[4] 朱甦, 薄煜明, 何亮. 基于冗余字典的多特征压缩感知目标跟踪算法[J].兵工学报, 2017, 38(6): 1140-1146.

ZHU Su, BO Yuming, HE Liang. A multi-feature compressed target tracking algorithm based on redundant dictionary[J]. Acta Tribune of China, 2017, 38(6): 1140-1146.

[5] ZHANG K H, ZHANG L, LIU Q S, et al. Fast visual tracking via dense spatio-temporal context learning[C]//European Conference on Computer Vision, 2014: 127-141.

[6] LI Qiuchen. Development of airborne downsight target tracker based on embedded GPU[D]. Harbin: Harbin Institute of Technology, 2017.

[7] ZHAO P, ZHANG Y, YANG T, et al. A novel multi-object detection method in complex scene using synthetic aperture imaging[J]. Pattern Recognition, 2012, 45(4): 1637-1658.

[8] ZHAN R, WAN J. Iterated unscented Kalman filter for passive target tracking[J]. IEEE Transactions on Aerospace and Electronic Systems, 2007, 43(3): 1155-1163.

[9] Kalal Z, Mikolajczyk K, Matas J. Tracking-learning-detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(7): 1409-1422.

[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 K, ZHANG L, YANG M, et al. Fast compressive tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(10): 2002-2015.

[12] LIU Q, ZHUANG J, MA J. Robust and fast pedestrian detection method for far-infrared automotive driving assistance systems[J]. Infrared Physics & Technology, 2013, 60(5): 288-299.

孙护军. 基于双模式遮挡检测机制的红外目标跟踪算法[J]. 红外技术, 2018, 40(9): 902. SUN Hujun. An Infrared Object Tracking Algorithm Based on Dual-mode Context Occlusion Detection Mechanism[J]. Infrared Technology, 2018, 40(9): 902.

基于双模式遮挡检测机制的红外目标跟踪算法

关于本站 Cookie 的使用提示

全站搜索

基于双模式遮挡检测机制的红外目标跟踪算法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索