基于多层次互补特征的通用目标检测模型

doi:10.3724/SP.J.1146.2011.01109

摘要
图/表
参考文献
相关文章 (1)

全文: PDF (417 KB)
输出: BibTeX | EndNote (RIS)

摘要针对实际场景中多类目标检测问题，该文提出了一种基于多层次特征表示和异质互补描述子的通用目标检测模型。该模型采用基于组件的目标描述思想，提取目标不同层次的互补特征，并将其统一到条件随机场(CRF)框架中。目标中单个组件及其局部特征对应CRF的一元节点，组件之间的几何空间结构特征则体现在节点之间的两两连接关系上。通过引入节点支持向量机(SVM)分类器和边缘拓扑结构学习，极大提高了模型的鉴别能力和灵活性。在UIUC多尺度数据集和PASCAL VOC 2007数据集上测试结果表明，该文模型不仅能有效描述多类复杂目标，还能较好地解决姿态、尺度、光照变化及局部遮挡情况下的目标检测问题。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	潘泓
	金立左
	夏思宇
	夏良正

关键词 ：通用目标检测, 多层次特征描述, 异构特征, 条件随机场

Abstract：This paper proposes a novel model based on the hierarchical representation using heterogeneous descriptors for multi-class generic object detection in real-world scenario. Following the idea of part-based object detection, the model extracts complementary features of object class at different levels and represents them with a unified Conditional Random Field (CRF) framework, in which the individual part and its local features correspond to a unary node and the interactions (edges) between pairwise nodes reflect the underlying geometrical structure of the object class. To improve the discrimination and flexibility of the proposed model, Support Vector Machine (SVM) classifier and the learning of edge structure are combined into CRF according to the geometrical topology of object class. Experimental results on UIUC multi-scale dataset and PASCAL VOC 2007 dataset show that the proposed model can not only effectively represent a variety of complex object classes, also successfully detect objects with pose, scale, illumination variations as well as partial occlusions.

Key words： Generic object detection Hierarchical feature representation Heterogeneous feature Conditional Random Field (CRF)

收稿日期: 2011-10-26

PACS:

TP391

基金资助:

国家自然科学基金(60805002, 90820009)，东南大学优秀青年教师教学科研资助计划(4008001015)和航空科学基金(20115169016)资助课题

通讯作者: 潘泓 E-mail: enhpan@seu.edu.cn

引用本文:

潘泓, 金立左, 夏思宇, 夏良正. 基于多层次互补特征的通用目标检测模型[J]. 电子与信息学报, 2012, 34(7): 1531-1537. Pan Hong, Jin Li-Zuo, Xia Si-Yu, Xia Liang-Zheng. A Hierarchical and Complementary Feature-based Model for Genetic Object Detection. , 2012, 34(7): 1531-1537.

链接本文:

http://jeit.ie.ac.cn/CN/10.3724/SP.J.1146.2011.01109 或 http://jeit.ie.ac.cn/CN/Y2012/V34/I7/1531