基于分层模型和鲁棒字典学习的背景差分炸点检测

doi:10.3969/j.issn.1000-1093.2016.04.019

兵工学报 ›› 2016, Vol. 37 ›› Issue (4): 705-711.doi: 10.3969/j.issn.1000-1093.2016.04.019

基于分层模型和鲁棒字典学习的背景差分炸点检测

计宏磊¹，杨清文¹，秦晓燕²

(1.陆军军官学院远程火箭炮系，安徽合肥 230031; 2.陆军军官学院管理工程系，安徽合肥 230031)

收稿日期:2015-07-03 修回日期:2015-07-03 上线日期:2016-06-20
作者简介:计宏磊(1986—)男硕士研究生
基金资助:
安徽省自然科学基金项目（1508085QF114）

Detection of Blast Point Based on Hierarchical Model of Background Subtraction via Robust Dictionary Learning

JI Hong-lei¹， YANG Qing-wen¹， QIN Xiao-yan²

(1.Department of Long-range Rocket Gun, Army Officer Academy of PLA, Hefei 230031, Anhui, China;2.Department of Management Engineering, Army Officer Academy of PLA, Hefei 230031, Anhui, China)

Received:2015-07-03 Revised:2015-07-03 Online:2016-06-20

摘要/Abstract

摘要： 针对背景差分炸点检测方法中背景模型难以更新背景估计和运算复杂等问题，提出一种分层模型下基于鲁棒字典学习的背景差分炸点检测方法。为提高运算效率,该方法对图像帧建立3层金字塔分层模型，在每层将图像帧分割为互不重叠块，逐层以图像块为单位通过改进的鲁棒字典学习方法进行背景估计，与当前图像帧作背景差分实现炸点检测。采用炮弹炸点图像序列对所提出的方法进行了实验验证。实验结果表明，与现有炮弹炸点检测方法相比，该方法在准确率、误检率和鲁棒性方面均具有优越性能。

关键词: 兵器科学与技术, 炸点检测, 背景差分, 分层模型, 鲁棒字典学习

Abstract: For the background estimation and huge computation problems of background model in the background subtraction blast point detection method, a blast point detection method is proposed based on a hierarchical model of background subtraction via robust dictionary learning. To improve the operation efficiency, a three-tier pyramid hierarchical model is established to divide each frame image into non-overlapping blocks. The blast points are detected from the subtraction between current frame image and image background estimation by using the improved robust dictionary learning method layer by layer. Experimental results on a large number of blast point image sequences show that the proposed method has superior performance in correct detection rate, false positive rate and robustness in comparison with the existing blast point detection method.

Key words: ordnance science and technology, blast point detection, background subtraction, hierarchical model, robust dictionary learning

中图分类号:

TP301.6

计宏磊，杨清文，秦晓燕. 基于分层模型和鲁棒字典学习的背景差分炸点检测[J]. 兵工学报, 2016, 37(4): 705-711.

JI Hong-lei， YANG Qing-wen， QIN Xiao-yan. Detection of Blast Point Based on Hierarchical Model of Background Subtraction via Robust Dictionary Learning[J]. Acta Armamentarii, 2016, 37(4): 705-711.

参考文献

［1］ Yilmaz A, Javed O, Shah M. Object tracking: a survey［J］. Acm Computing Surveys, 2006, 38(1):81-93.
［2］秦晓燕, 王晓芳, 陈萍, 等. 基于Adaboost算法的炮弹炸点检测［J］. 兵工学报, 2012, 33(6):682-687.
QIN Xiao-yan, WANG Xiao-fang, CHEN Ping, et al. Artillery blast point detection based on Adaboost algorithm［J］. Acta Armamentarii, 2012, 33(6):682-687.(in Chinese)
［3］ Benzeth Y, Jodoin P M, Emile B, et al. Comparative study of background subtraction algorithm［J］. Journal Electronic Imaging, 2010, 19(3):1-12.
［4］高仕博, 程咏梅, 肖利平,等. 面向目标检测的稀疏表示方法

研究进展［J］. 电子学报, 2015, 43(2):320-332.
GAO Shi-bo, CHENG Yong-mei, XIAO Li-ping, et al. Recent advances of sparse representation for object detecion［J］. Acta Electronica Sinica, 2015, 43(2): 320-332.(in Chinese)
［5］ Piccardi M. Background subtraction techniques: a review［C］∥International Conference on Systems, Man and Cybernetics. Hong Kong, China:IEEE, 2004:3099-3104.
［6］ Zhou X, Yang C, Yu W. Moving object detection by detecting contiguous outliers in the low-rank representation［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(3): 597－610.
［7］ Lei H, Mei K, Zheng N, et al. Learning group-based dictionaries for discriminative image representation［J］. Pattern Recognition, 2014, 47(2): 899-913.
［8］ Huang J Z, Huang X L, Metaxas D. Learning with dynamic group sparsity［C］∥International Conference on Computer Vision. Kyoto, Japan: IEEE, 2009:64-71.
［9］ Zhao C, Wang X, Cham W K. Background subtraction via robust dictionary learning［J］. Eurasip Journal on Image & Video Processing, 2011, 2011(10):2919-2929.
［10］孔康, 陶卿, 汪群山, 等. 基于次梯度的L1正则化Hinge损失问题求解研究［J］. 计算机研究与发展, 2012, 49(7):1494-1499.
KONG Kang, TAO Qing, WANG Qun-shan, et al. A sub-gadient based solver for L1-rgularization+Hinge -loss problem［J］. Journal of Computer Research and Development, 2012, 49(7): 1494-1499.(in Chinese)
［11］孔康, 汪群山, 梁万路. L1正则化机器学习问题求解分析［J］. 计算机工程, 2011, 37(17):175-177.
KONG Kang, WANG Qun-shan, LIANG Wan-lu. Solution analysis of L1 regularized machine learning problem［J］. Computer Engineering, 2011, 37(17):175-177.(in Chinese)
［12］ Friedman J, Tibshirani R. Pathwise coordinate optimization［J］. Annals of Applied Statistics, 2007, 1(2):302-332.
［13］ Wu T T, Lange K. Coordinate descent algorithms for lasso pena- lized regression［J］. Annals of Applied Statistics, 2008, 2(1):224-244.
［14］ Efron B, Tibshirani R. Least angle regression［J］. Annals of Statistics, 2004, 32(2):404-451.
［15］ Zou H, Hastie T. Regularization and variable selection via the elastic net［J］. Journal of the Royal Statistical Society, 2005, 67(2): 301-320.
［16］ Zhao P, Yu B. On model selection consistency of lasso［J］. Journal of Machine Learning Research, 2006, 7(3):2541-2563.
［17］ Bonnans J F, Shapiro A. Optimization problems with perturbations: A guided tour［J］. Siam Review, 1998, 40(2):228-264.
［18］ Wright J, Yang A Y, Ganesh A, et al. Robust face recognition via sparse representation［J］. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2009, 31(2):210-227.

[1]	周伯俊, 于传强，刘志浩，柯冰. 基于高压储能的特种车辆快速起竖技术与验证[J]. 兵工学报, 2022, 43(7): 1488-1497.
[2]	高月光，冯顺山，刘云辉，黄岐. 不同端盖厚度的圆柱形装药壳体破片初速分布[J]. 兵工学报, 2022, 43(7): 1527-1536.
[3]	娄伟鹏，郑长松，李和言，陈建文，张周立，马源. 高速《Symbol》v湿式换挡离合器排油阀临界开启和关闭压力研究[J]. 兵工学报, 2017, 38(9): 1665-1672.
[4]	王宪成，杨绍卿，马宁，赵文柱. 车辆柴油机缸套动载荷磨损计算模型研究[J]. 兵工学报, 2017, 38(9): 1673-1680.
[5]	孙皓泽，常天庆，王全东，孔德鹏，戴文君. 一种基于分层多尺度卷积特征提取的坦克装甲目标图像检测方法[J]. 兵工学报, 2017, 38(9): 1681-1691.
[6]	张玉燕，孙莎莎，王振春，曹海要，战再吉. 高速载流电枢表面瞬态温度场仿真与测量[J]. 兵工学报, 2017, 38(9): 1692-1698.
[7]	李臣明，宦超，石怀龙. 某箱式火箭炮对面目标分布式杀伤最优火力分配[J]. 兵工学报, 2017, 38(9): 1699-1704.
[8]	雷娟棉，张嘉炜，谭朝明. 小攻角下船尾外形对旋转弹丸马格努斯效应影响的数值研究[J]. 兵工学报, 2017, 38(9): 1705-1715.
[9]	李泽，闫晓鹏，栗苹，郝新红，王建涛. 扫频式干扰对调频多普勒引信的干扰机理研究[J]. 兵工学报, 2017, 38(9): 1716-1722.
[10]	张浩为，谢军伟，张昭建，宗彬锋，陈唐军. 基于混合自适应遗传算法的相控阵雷达任务调度[J]. 兵工学报, 2017, 38(9): 1761-1770.
[11]	李茂，侯海量，朱锡，黄晓明，李典，陈长海，胡年明. 结构间隙对芳纶纤维增强复合装甲结构抗侵彻性能的影响[J]. 兵工学报, 2017, 38(9): 1797-1805.
[12]	王鉴, 韩焱, 王黎明, 张丕状, 陈平. 弹丸在膛内运动的回波信号瞬时频率估计方法研究[J]. 兵工学报, 2017, 38(9): 1806-1814.
[13]	刘海鸥，张文胜，徐宜，赵梓烨. 基于核密度估计的履带车辆传动轴载荷谱编制[J]. 兵工学报, 2017, 38(9): 1830-1838.
[14]	姜缪文，闫健卓，陈继民. 基于拓扑优化技术的军用头盔内胆结构三维打印[J]. 兵工学报, 2017, 38(9): 1845-1853.
[15]	张磊，李世民，朱刚. 基于时间连续灰色Markov模型的维修器材需求预测方法研究[J]. 兵工学报, 2017, 38(9): 1862-1866.

基于分层模型和鲁棒字典学习的背景差分炸点检测

Detection of Blast Point Based on Hierarchical Model of Background Subtraction via Robust Dictionary Learning

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价