|
|
- 2018
利用多等级相关性反馈进行空间场景匹配
|
Abstract:
现有的空间场景匹配方法利用低级描述子（如局部几何形状描述子、方向、拓扑）或其组成的简单二元空间关系建立模型来试图满足用户的描述需求，缺乏对用户级主观概念的反馈机制。将用户反馈机制应用到空间场景匹配过程中，以研究机器在学习用户需求后对空间场景匹配的影响。在运算过程中，用户对匹配结果进行相关度评估并反馈给模型，模型根据反馈结果动态地更新检索参数权重以模拟用户的主观感知，从而使得调整后的匹配运算更加贴近用户需求。通过进行用户调查及分析特征向量权重的收敛情况验证了此方法的有效性和效率，实验结果表明，根据用户反馈进行空间场景匹配具有很高的用户主观性强度，用户只需进行2~3次的反馈就能得到较为满意的结果，空间场景的匹配结果更符合人的空间认知
| [1] | Rocha R, Saito P T M, Bugatti P H. A Novel Framework for Content-Based Image Retrieval Through Relevance Feedback Optimization[C]. Iberoamerican Congress on Pattern Recognition, Montevideo, Uruguay, 2015 |
| [2] | Chipofya M, Schwering A, Binor T. Matching Qualitative Spatial Scene Descriptions á la Tabu[M]//Chipofya M, Schwering A, Binor T. Advances in Soft Computing and Its Applications. Berlin, Heidelberg:Springer, 2013 |
| [3] | Liu Tao, Du Qingyun, Mao Haichen. Spatial Similarity Assessment Model and Its Application in Line Groups[J].<em>Geomatics and Information Science of Wuhan University</em>, 2012, 37(8):992-995(刘涛,杜清运,毛海辰. 空间线群目标相似度计算模型研究[J]. 武汉大学学报·信息科学版, 2012, 37(8):992-995) |
| [4] | Chen Zhanlong, Xu Yongyang, Wu Liang. Vector Planar Elements:Geometrical Similarity Measurement Based on Fourier Descriptors[J]. <em>Geomatica</em>,2015, 69(4):385-394 |
| [5] | Zhou X S, Huang T S. Small Sample Learning Du-ring Multimedia Retrieval Using Biasmap[C]. The 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Kauai,Hawaii,USA, 2001 |
| [6] | Liu Tao, Du Qingyun, Yan Haowen.Spatial Similarity Assessment of Point Clusters[J]. <em>Geomatics and Information Science of Wuhan University</em>, 2011, 36(10):1149-1153(刘涛,杜清运,闫浩文. 空间点群目标相似度计算[J]. 武汉大学学报·信息科学版, 2011, 36(10):1149-1153) |
| [7] | Moratz R, Lücke D, Mossakowski T. A Condensed Semantics for Qualitative Spatial Reasoning About Oriented Straight Line Segments[J].<em>Artificial Intelligence</em>, 2011, 175(16):2099-2127 |
| [8] | Li Bonan, Fonseca F. TDD:A Comprehensive Model for Qualitative Spatial Similarity Assessment[J].<em>Spatial Cognition and Computation</em>, 2006, 6(1):31-62 |
| [9] | Chen Zhanlong, Zhou Lin, Gong Xi, et al. A Quantitative Calculation Method of Spatial Direction Similarity Based on Direction Relation Matrix[J].<em>Acta Geodaetica et Cartographica Sinica</em>, 2015, 44(7):813-821(陈占龙, 周林, 龚希, 等. 基于方向关系矩阵的空间方向相似性定量计算方法[J]. 测绘学报, 2015, 44(7):813-821) |
| [10] | Jan S, Schwering A, Schultz C, et al. RCC11:A Finer Topological Representation for the Alignment of Regions in Sketch Maps[C]. International Workshop on Qualitative Reasoning, Minneapolis, USA,2015 |
| [11] | Lu H, Huang X, Yang L, et al. A Novel Long-Term Learning Algorithm for Relevance Feedback in Content-Based Image Retrieval[J]. <em>Telecommunications Systems</em>, 2013, 54(3):265-275 |
| [12] | Chen Zhanlong, Lü Menglou, Wu Liang, et al. Space Scene Similarity Measurement Based on Feature Matrix and Associated Graph[J]. <em>Geomatics and Information Science of Wuhan University</em>, 2017, 42(7):956-962(陈占龙, 吕梦楼, 吴亮, 等. 基于特征矩阵和关联图的空间场景相似性度量方法[J]. 武汉大学学报·信息科学版, 2017, 42(7):956-962 |
| [13] | Chen Zhanlong, Feng Qiqi, Wu Xincai. Representation Model of Topological Relations Between Complex Planar Objects[J]. <em>Acta Geodaetica et Cartographica Sinica</em>, 2015, 44(4):438-444(陈占龙,冯齐奇,吴信才.复合面状对象拓扑关系的表达模型[J].测绘学报, 2015, 44(4):438-444) |
| [14] | Tong S, Koller D. Support Vector Machine Active Learning with Applications to Text Classification[J]. <em>Journal of Machine Learning Research</em>, 2001, 2(11):45-66 |
| [15] | Rui Y, Huang T. Optimizing Learning in Image Retrieval[C]. IEEE Conference on Computer Vision and Pattern Recognition, Hilton Head Island, SC, USA, 2000 |
| [16] | Chen Y, Zhou X S, Huang T S. One-Class SVM for Learning in Image Retrieval[C]. International Conference on Image Processing, Makedonia Palace Hotel,Thessaloniki, Greece, 2001 |
| [17] | Mosbah M, Boucheham B. Majority Voting Re-ranking Algorithm for Content Based-Image Retrieval[C].Metadata and Semantics Research Conference, Manchester, UK, 2015 |
| [18] | Rui Y, Huang T S, Ortega M, et al. Relevance Feedback:A Power Tool for Interactive Content-Based Image Retrieval[J]. <em>IEEE Transactions on Circuits and Systems for Video Technology</em>, 1998, 8(5):644-655 |
