期刊文献+

基于相似矩阵自适应加权的实景图像相似度计算方法 被引量:7

Geography Image Similarity Measurement Method Based on Adaptive Weighting of Similarity Matrix
下载PDF
导出
摘要 图像相似度计算是众多视觉任务中不可或缺的关键环节,因此文中提出基于相似矩阵自适应加权的实景图像相似度计算方法.首先将图像划分为均匀图像块,基于卷积神经网络构建各图像块的特征描述符.然后计算各图像块间的相似度,组成相似矩阵.最后分析相似矩阵中的数据分布,确定图像对包含同一场景的概率,根据相似矩阵中的数据差异计算各单元相似度权值,确定整幅图像的相似度.实验表明,相比已有方法,文中方法在图像检索应用中鲁棒性更高,可以有效解决即时定位与地图构建中的闭环检测问题. Image similarity measurement is crucial to many vision applications. A similarity measurement method based on adaptive weighting of similarity matrix is proposed in this paper. The image is firstly divided into the same-sized patches, and the convolutional neural networks are adopted to construct the descriptor of each patch. The patch similarities are calculated to constitute the similarity matrix. The probability of image pair coming from the same place is evaluated by analyzing the data distribution in similarity matrix. And the similarity weight of each unit is calculated based on the data difference. Ultimately, the overall image similarity is determined. The experimental results show that the proposed method is more robust than the existing ones in image retrieval. Moreover, it effectively solves the loop closure detection in simultaneous localization and mapping.
出处 《模式识别与人工智能》 EI CSCD 北大核心 2017年第11期1003-1011,共9页 Pattern Recognition and Artificial Intelligence
基金 国家自然科学基金项目(No.41201390) 河南省科技创新(中原学者)项目(No.142101510005)资助~~
关键词 图像描述矩阵 相似矩阵 自适应加权 闭环检测 Image Description Matrix, Similarity Matrix, Adaptive Weighting, Loop Closure Detection
  • 相关文献

参考文献5

二级参考文献84

  • 1Shotton J, Blake A, Cipolla R. Multiscale categorical object recognition using contour fragments. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 30(7): 1270-1281.
  • 2Serre T, Wolf L, Bileschi S, Riesenhuber M, Poggio T. Ro- bust object recognition with cortex-like mechanisms. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(3): 411-426.
  • 3Torralba A, Murphy K P, Freeman W T. Contextual mod- els for object detection using boosted random fields. In: Proceedings of the Neural Information Processing Systems. Vancouver. Canada: NIPS. 2004. 1401-1408.
  • 4Zhu L, Rao A B, Zhang A D. Theory of keyblock-based im- age retrieval. ACM Transactions on Information Systems, 2002, 20(2): 224-257.
  • 5Comaniciu D, Meer P. Mean shift: a robust approach to- ward feature space analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002,24(5): 603-619.
  • 6Gemert J C, Geusebroek J M, Veenman C J, Smeulders A W M. Kernel codebooks for scene categorization. In: Pro- ceedings of the European Conference on Computer Vision. Berlin, Germany: Springer, 2008. 696-709.
  • 7Lazebnik S, Schmid C, Ponce J. Beyond bags of features: spatial pyramid matching for recognizing natural scene cat- egories. In: Proceedings of the IEEE Computer Vision and Pattern Recognition. New York, USA: IEEE, 2006. 2169-2178.
  • 8Belongie S, Malik J, Puzicha J. Shape matching and ob- ject recognition using shape contexts. IEEE Transactions on Pattern AnMysis and Machine Intelligence, 2002, 24(4): 509-522.
  • 9Loupias E, Sebe N, Bres S, Jolion J M. Wavelet-based salient points for image retrieval. In: Proceedings of the Interna- tional Conference on Image Processing. Vancouver, Canada: IEEE, 2000. 518-521.
  • 10Lowe D G. Distinctive image features from scale-invariant keypoints. International Journal oF Computer Vision, 2004, 60(2): 91-110.

共引文献77

同被引文献58

引证文献7

二级引证文献14

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部