计算机科学 ›› 2013, Vol. 40 ›› Issue (7): 266-269.

• 图形图像与模式识别 • 上一篇    下一篇

基于多分类器融合的多视角目标检测算法

尹维冲,路通   

  1. 南京大学计算机软件新技术国家重点实验室 南京210093;南京大学计算机软件新技术国家重点实验室 南京210093
  • 出版日期:2018-11-16 发布日期:2018-11-16
  • 基金资助:
    本文受国家自然科学基金(61272218),教育部新世纪优秀人才支持计划(NCET-11-0232)资助

Novel Framework for Multi-view Object Detection through Combining Multiple Classifiers

YIN Wei-chong and LU Tong   

  • Online:2018-11-16 Published:2018-11-16

摘要: 提出了从任意视角图像中检测视觉目标的新框架,并通过多视角分类器球面(Multi-View Detector Sphere,MVDS)模型对不同视角分类器之间的关系进行建模,以描述多个视角在识别视觉目标过程中的视角关联。首先,对不同视角的特定目标进行建模,对每个视角训练一个分类器;其次,通过将视角球面三角化,将视角球面均匀划分成若干三角面片,面片顶点所代表的视角之间的关系用以刻画不同视角分类器之间的关系。最后,对于来自未训练视角的目标,可通过融合 球面上相邻视角分类器的输出给出其正确的检测结果。在多个公共数据集上的实验结果表明了该算法的有效性和准确性。

关键词: 多视角,目标检测,MVDS 中图法分类号TP391.4文献标识码A

Abstract: We proposed a novel framework for detecting generic objects from arbitrary viewpoints described by varied object appearances.Our key insight is to exploit the multi-view detection patterns established by a number of detectors from different viewpoints and their relationships through the Multi-View Detector Sphere (MVDS),reflecting the underlying intrinsic structure for detecting multi-view objects.We first modeled the annotated objects from different viewpoints,and then triangulated the sphere into a number of uniformly distributed meshes to represent the explicit correspondences across view detectors.As a result,multi-view objects from untrained viewpoints can be detected by combining the outputs of the adjacent view detectors on the sphere.Our experiments on several public datasets give promising results for the experimental object classes.

Key words: Multi-view,Object detection,MVDS

[1] Thomas A,Ferrari V,Leibe B,et al.Toward multi-view object class detection[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.New York:IEEE Computer Society,2006(2):1589-1596
[2] Viola P,Jones M.Robust Real-Time Face Detection[J].International Journal of Computer Vision,2004,57(2):137-154
[3] 武勃,黄畅,艾海舟,等.基于连续AdaBoost 算法的多视角人脸检测[J].计算机研究与发展,2005,42(9):1612-1621
[4] 徐剑,丁晓青,王生进,等.多视角多行人目标检测、定位与对应算法[J].清华大学学报:自然科学版,2009,49(8):1139-1143
[5] Savarese S,Li F.3D generic object categorization,localization and pose estimation[C]∥Proceedings of the IEEE International Conference on Computer Vision.Riode Janeiro:IEEE,2007:1-8
[6] Su H,Sun M,Li F,et al.Learning a dense multi-view representation for detection,viewpoint classification and synthesis of object categories[C]∥Proceedings of the IEEE International Conference on Computer Vision.Kyoto:IEEE,2009:213-220
[7] Liu X,Gong H,Yan S,et al.Multi-view object detection by classifier interpolation[C]∥Proceedings of the IEEE International Conference on Acoustics,Speech,and Signal Processing.Dallas:IEEE,2010:826-829
[8] Wu B,Nevatia R.Cluster Boosted Tree Classifier for Multi-View,Multi-Pose Object Detection[C]∥Proceedings of the IEEE International Conference on Computer Vision.Riode Janeiro:IEEE,2007:1-8
[9] Razavi N,Gall J,Van Gool L.Backprojection revisited:scalable multi-view object detection and similarity metrics for detections[C]∥Proceedings of 11th European Conference on Computer Vision.Heraklion:Springer,2010:620-633
[10] Friedman J,Hastie T,Tibshirani R.Additive logistic regression:a statistical view of boosting[J].The Annals of Statistics,2000,28(2):337-374
[11] Torralba A,Murphy K,Freeman W.Sharing visual features for multiclass and multiview object detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(5):854-869

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!