基于局部特征和稀疏表示的图像目标检测算法

doi:10.3724/SP.J.1087.2013.01670

计算机应用 ›› 2013, Vol. 33 ›› Issue (06): 1670-1673.DOI: 10.3724/SP.J.1087.2013.01670

基于局部特征和稀疏表示的图像目标检测算法

田元荣,田松,许悦雷,查宇飞

空军工程大学航空航天工程学院，西安 710038

收稿日期:2012-12-23 修回日期:2013-01-22 出版日期:2013-06-01 发布日期:2013-06-05
通讯作者: 田元荣
作者简介:田元荣(1989-)，男，陕西榆林人，硕士研究生，主要研究方向：图像目标检测、机器学习;田松(1973-)，男，四川绵竹人，副教授，博士，主要研究方向：机器智能视觉、图像目标自动检测;许悦雷(1975-)，男，河北辛集人，副教授，博士，主要研究方向：图像及视频序列压缩、压缩感知、目标检测与跟踪;查宇飞(1979-)，男，湖北荆门人，讲师，博士，主要研究方向：目标跟踪、机器学习。
基金资助:
国家自然科学基金资助项目(61203268）;航空科学基金资助项目(20115896022)

Image object detection based on local feature and sparse representation

TIAN Yuanrong,TIAN Song,XU Yuelei,ZHA Yufei

Institute of Aeronautics and Astronautics Engineering, Air Force Engineering University, Xi’an Shaanxi 710038, China

Received:2012-12-23 Revised:2013-01-22 Online:2013-06-05 Published:2013-06-01
Contact: TIAN Yuanrong

摘要/Abstract

摘要： 传统的基于局部特征的图像目标检测算法具有对遮挡和旋转敏感、检测精度不高以及运算速度慢的特点，为了改进该算法的性能，提出了一种将图像局部特征应用于稀疏表示理论的图像目标检测算法。该算法利用随机树的方式有监督地学习样本图像的局部特征形成字典，通过学习好的字典和测试图像的子块来预测图像中目标的中心位置，以此寻求待检测图像稀疏的表示，从而实现对图像中感兴趣目标的检测。实验结果表明,该算法对目标的遮挡、旋转和复杂背景有很好的鲁棒性，而且检测精度和运算速度相对于同类经典算法均有提高。

关键词: 目标检测, 稀疏表示, 局部特征, 随机树, 字典学习

Abstract: Traditional image object detection algorithm based on local feature is sensitive to rotation and occlusion; meanwhile, it also obtains low detection precision and speed in many cases. In order to improve the performance of this algorithm, a new image objects detection method applying objects’ local feature to sparse representation theory was introduced. Employing supervised random tree method to learn local features of sample images, a dictionary could be formed. The combination of sub-image blocks of test image and well trained dictionary in first stage could predict the location of the object in the test image, in this way it could obtain a sparse representation of the test image as well as the object detection goal. The experimental results demonstrate that the proposed method achieves robust detection results in rotation, occlusion condition and intricate background. What’s more, the method obtains higher detection precision and speed.

Key words: object detection, sparse representation, local feature, random tree, dictionary learning

中图分类号:

TP391.41

田元荣田松许悦雷查宇飞. 基于局部特征和稀疏表示的图像目标检测算法[J]. 计算机应用, 2013, 33(06): 1670-1673.

TIAN Yuanrong TIAN Song XU Yuelei ZHA Yufei. Image object detection based on local feature and sparse representation[J]. Journal of Computer Applications, 2013, 33(06): 1670-1673.

参考文献

［1］VINJIE W E, GALLANT J L. Sparse coding and decorrelation in primary visual cortex during nature vision［J］. Science, 2000, 287(5456): 1273-1276.

［2］FISCHLER M A, ELSCHLAGER R A. The representation and matching of pictorial structures［J］. IEEE Transactions on Computers, 1973, c-22(1): 67-92.

［3］ZUO Y Y, ZHANG B. Sparse based image classification with different keypoints descriptors［C］// Proceedings of the 8th International Symposium on Neural Networks. Berlin: Springer, 2011: 323-330.

［4］EISENSTEIN J, AHMED A,XING E P. Sparse additive generative models of text［C］// Proceedings of the 28th International Conference on Machine Learning. Madiso: Omni Press, 2011: 127-134.

［5］GALL J, YAO A, RAZAVI N, et al. Hough forests for object detection, tracking, and action recognition［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(11): 2188-2202.

［6］LI F F, FERGUS R, PERONA P. A Bayesian approach to unsupervised one-shot learning of object categories［C］// Proceedings of the 9th IEEE International Conference on Computer Vision. Washington, DC: IEEE Computer Society, 2003: 1134-1141.

［7］FELZENSZWALB P, HUTTENLOEHER D. Pictorial structures for object recognition［J］. International Journal of Computer Vision, 2005, 61(1): 55-79.

［8］CARNEIRO G, LOWE D G. Sparse flexible models of local features［C］// Proceedings of the 9th European Conference on Computer Vision. Berlin: Springer, 2006: 29-43.

［9］ZHANG J, MARSZALEK M, LAZEBNIK S, et al. Local features and kernels for classification of texture and object categories: A comprehensive study［J］. International Journal of Computer Vision, 2007, 73(2): 213-238.

［10］MARSZALEK M, SCHMID C. Spatial weighting for bag-of-features［C］// Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society, 2006, 2: 2118-2125.

［11］GRAUMAN K, DARRELL T. Pyramid match kernels: Discriminative classification with sets of image features［C］// Proceedings of 10th IEEE International Conference on Computer Vision. Washington, DC: IEEE Computer Society, 2005: 1458-1465.

［12］LAZEBNIK S, SCHMID C, PONCE J. Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories［C］// Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society, 2006, 2: 2169-2178.

［13］AGARWAL S, ROTH D. Learning a sparse representation for object detection［C］// Proceedings of 7th European Conference on Computer Vision. Berlin: Springer, 2002: 113-127.

［14］焦李成, 谭山. 图像的多尺度几何分析：回顾和展望［J］. 电子学报, 2004, 31(B12): 1975-1981.

［15］DALAL N, TRIGGS B. Histograms of oriented gradients for human detection［C］// Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society, 2005, 1: 886-893.

[1]	刘晓光, 靳少康, 韦子辉, 梁铁, 王洪瑞, 刘秀玲. 基于阈值和极端随机树的实时跌倒检测方法[J]. 计算机应用, 2021, 41(9): 2761-2766.
[2]	徐江浪, 李林燕, 万新军, 胡伏原. 结合目标检测的室内场景识别方法[J]. 计算机应用, 2021, 41(9): 2720-2725.
[3]	马佳良, 陈斌, 孙晓飞. 基于改进的Faster R-CNN的通用目标检测框架[J]. 计算机应用, 2021, 41(9): 2712-2719.
[4]	樊玮, 李晨炫, 邢艳, 黄睿, 彭洪健. 航空发动机损伤图像的二分类到多分类递进式检测网络[J]. 计算机应用, 2021, 41(8): 2352-2357.
[5]	陈静, 毛莺池, 陈豪, 王龙宝, 王子成. 基于改进单点多盒检测器的大坝缺陷目标检测方法[J]. 计算机应用, 2021, 41(8): 2366-2372.
[6]	肖振远, 王逸涵, 罗建桥, 熊鹰, 李柏林. 基于部分加权损失函数的RefineDet[J]. 计算机应用, 2021, 41(7): 1928-1932.
[7]	裴春阳, 樊宽刚, 马政. 基于边缘保留分解和改进稀疏表示的医学图像融合[J]. 计算机应用, 2021, 41(7): 2092-2099.
[8]	高钦泉, 黄炳城, 刘文哲, 童同. 基于改进CenterNet的竹条表面缺陷检测方法[J]. 计算机应用, 2021, 41(7): 1933-1938.
[9]	侯笑晗, 金国栋, 谭力宁, 薛远亮. 基于自适应和最优特征的合成孔径雷达舰船检测方法[J]. 计算机应用, 2021, 41(7): 2150-2155.
[10]	李朝, 兰海, 魏宪. 基于注意力的毫米波-激光雷达融合目标检测[J]. 计算机应用, 2021, 41(7): 2137-2144.
[11]	任晓奎, 刘鹏飞, 陶志勇, 刘影, 白立春. 基于单快拍信号到达角估计算法的室内入侵检测[J]. 计算机应用, 2021, 41(4): 1153-1159.
[12]	张康, 陈建平. 复杂环境下基于采样空间自调整的航迹规划算法[J]. 计算机应用, 2021, 41(4): 1207-1213.
[13]	后云龙, 朱磊, 陈琴, 吕燧栋. 基于高斯差分特征网络的显著目标检测[J]. 计算机应用, 2021, 41(3): 706-713.
[14]	蒋宁, 方景龙, 杨庆. 基于单点多盒检测器的全局-局部层级的域适应目标检测[J]. 计算机应用, 2021, 41(2): 517-522.
[15]	曹建荣, 吕俊杰, 武欣莹, 张旭, 杨红娟. 融合运动特征和深度学习的跌倒检测算法[J]. 计算机应用, 2021, 41(2): 583-589.

基于局部特征和稀疏表示的图像目标检测算法

Image object detection based on local feature and sparse representation

PDF

可视化

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