K均值聚类算法判断单目图像深度层次
Determining the Depth Level of Monocular Image Based on K-Means Clustering Algorithm
DOI: 10.12677/CSA.2021.114102, PDF,    科研立项经费支持
作者: 张惠丽：包头职业技术学院电气工程系，内蒙古 包头；石 炜*, 耿宇聪：内蒙古科技大学机械工程学院，内蒙古 包头
关键词: K均值聚类；单目图像；图像分割；深度层次；K-Means Clustering Algorithm； Monocular Image； Image Segmentation； Depth Level
摘要: 针对单目图像深度层次的判断问题提出一种基于K均值聚类算法判断单目图像深度层次的方法。通过图像增强和图像滤波的方式达到优化图像提高对比度，保留细节特征以及滤除图像噪声的目的。根据K均值聚类算法，通过将灰度值相似的像素聚类，进行图像的分割，从而实现深度层次的划分。本次实验选取不同数目的聚类中心进行深度层次的划分并将结果进行比较。实验结果表明，利用K均值聚类的方法判断深度层次在一些几何场景中取得了比较好的成果。
Abstract: Aiming at the problem of judging the depth levels of monocular images, a method based on the K-means clustering algorithm to judge the depth levels of monocular images is proposed. Through image enhancement and image filtering, the purpose of optimizing the image to improve the contrast, retaining the detailed features and filtering the image noise is achieved. According to the K-means clustering algorithm, the image is segmented by clustering pixels with similar gray values to achieve depth level division. In this experiment, different numbers of clustering centers are selected for indepth division and the results are compared. Experimental results show that the depth level judgment method proposed in this paper has achieved relatively good results in some geometric scenes.
文章引用：张惠丽, 石炜, 耿宇聪. K均值聚类算法判断单目图像深度层次[J]. 计算机科学与应用, 2021, 11(4): 994-1000. https://doi.org/10.12677/CSA.2021.114102

参考文献

[1] Saxena, A., Chung, S.H. and Hg, A.Y. (2007) 3D Depth Reconstruction from a Single Still Image. International Journal of Computer Vision, 76, 53-69. [Google Scholar] [CrossRef] 
[2] Saxena, A., Sun, M. and Ng, A.Y. (2009) Make 3D: Learning 3D Scene Structure from a Single Still Image. IEEE Transactions on Pattern Analysis and Machine Intelligence, 31, 824-840. [Google Scholar] [CrossRef] 
[3] Saxena, A., Schulte, J. and Ng, A.Y. (2007) Depth Estimation Using Monocular and Stereo Cues. Proceedings of the 20th international joint conference on Artifical intelligence, 2197-2103.
[4] Saxena, A., Sun, M. and Ng, A.Y. (2007) Learning 3-D Scene Structure from a Single Still Image. 2007 IEEE 11th International Conference on Computer Vision, Rio de Janeiro, 14-21 October 2007, 1-8. [Google Scholar] [CrossRef] 
[5] Saxena, A., Chun, S.H. and Ng, A.Y. (2005) Learning Depth from Single Monocular Images. Proceedings of the 18th International Conference on Neural Information Processing Systems, 1161-1168.
[6] Saxena, A., Sun, M. and Ng, A.Y. (2007) 3-D Reconstruction from Sparse Views Suing Monocular Vision. 2007 IEEE 11th International Conference on Computer Vision, Rio de Janeiro, 14-21 October 2007, 1-8. [Google Scholar] [CrossRef] 
[7] Horn, B.K.P., 著. 机器视觉[M]. 王亮, 蒋欣兰, 译. 北京: 中国青年出版社, 2014.
[8] Eigen, D., Puhrsch, C. and Fergus, R. (2014) Depth Map Prediction from a Single Image Using a Multi-scale Deep Network. Proceedings of the 27th International Conference on Neural Information Processing Systems, Montreal: MIT Press, 2366-2374.
[9] 裴晨, 徐国彬, 于艺铭, 吴灵, 黄俊轶, 王琪. 基于改进K 均值聚类的图像修复方法[J]. 包装工程, 2020, 41(23): 255-262
[10] Wei, X.Q. and Zhang, Y.E. (2020) Image Segmentation Algorithm Based on Dynamic Particle Swarm Optimization and K-Means Clustering. International Journal of Comput-ers and Applications, 42, 649-654. [Google Scholar] [CrossRef] 
[11] 朱永红, 熊朦, 赵一峰, 王伟. 基于K 均值聚类陶瓷窑炉火焰图像分割方法[J]. 陶瓷学报, 2016, 37(1): 86-90.