期刊信息
- 刊名： 河北师范大学学报（自然科学版）Journal of Hebei Normal University (Natural Science)
- 主办： 河北师范大学
- ISSN： 1000-5854
- CN： 13-1061/N
- 中国科技核心期刊
- 中国期刊方阵入选期刊
- 中国高校优秀科技期刊
- 华北优秀期刊
- 河北省优秀科技期刊
基于多实例特征的稀疏表示目标检测
- 河北师范大学 数学与信息科学学院, 河北 石家庄 050024
-
DOI：10.13763/j.cnki.jhebnu.nse.2017.04.004
Image Representation Based Sparse Multiple Instance Features for Object Detection
摘要/Abstract
摘要：
提出了多实例特征的稀疏表示模型用于静态图像目标检测.首先采用兴趣点获取图像中的目标实例，然后采用多实例特征构造稀疏表示模型应用于目标检测.本算法在UIUC汽车数据集上进行了检测效果对比.
Abstract：
We present an approach that uses a a sparse,multiple instance feature representation to detect static images.We extract the instances from object images using interesting points.Our appraoch is applied to the UIUC car dataset,which shows our result is better than existing approaches.
关键词
Key words：
multiple instance feature
;
sparse representation
;
object detection
参考文献 4
- [1] AGARWAL S,AWAN A,ROTH D.Learning to Detect Objects in Images via a Sparse,Part-based Representation[J].IEEE Transaction on Pattern Analysis and Machine Intelligece,2004,26(11):1475-1490.
- [2] BIEDERMAN,I.Recognition by Components:a Theory of Human Image Understanding[J].Psychol Review,1987,94:115-147.
- [3] KANUNGO T,MOUNT D M,NETANYAHU N S,et al.An Efficient K-means Clustering Algorithm:Analysis and Implementation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(7):881-892.
- [4] CHENG Yizong.Mean Shift,Mode Seeking,and Clustering[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1995,17(8):790-799.