北京邮电大学学报

  • EI核心期刊

北京邮电大学学报 ›› 2016, Vol. 39 ›› Issue (4): 56-59.doi: 10.13190/j.jbupt.2016.04.011

• 论文 • 上一篇    下一篇

利用深度图像改进光场描述符的三维模型检索算法

李海生1,2, 董水龙1,2, 赵天宇1,2, 蔡强1,2, 杜军平3   

  1. 1. 北京工商大学 计算机与信息工程学院, 北京 100048;
    2. 食品安全大数据技术北京市重点实验室, 北京 100048;
    3. 北京邮电大学 计算机学院, 北京 100876
  • 收稿日期:2015-12-29 出版日期:2016-08-28 发布日期:2016-08-28
  • 作者简介:李海生(1974-),男,博士,教授,E-mail:lihsh@th.btbu.edu.cn.
  • 基金资助:
    国家自然科学基金项目(61532006);北京市自然科学基金项目(4162019);北京工商大学两科基金培育项目(LKJJ2015-27)

Improved Light Field Descriptor Using Depth Images for 3D Model Retrieval

LI Hai-sheng1,2, DONG Shui-long1,2, ZHAO Tian-yu1,2, CAI Qiang1,2, DU Jun-ping3   

  1. 1. School of Computer and Information Engineering, Beijing Technology and Business University, Beijing 100048, China;
    2. Beijing Key Laboratory of Big Data Technology for Food Safety, Beijing 100048, China;
    3. School of Computer Science, Beijing University of Posts and Telecommunications, Beijing 100876, China
  • Received:2015-12-29 Online:2016-08-28 Published:2016-08-28

摘要: 针对光场描述符丢失三维模型空间信息以及全景视图描述符投影视图较少的问题,提出一种结合深度图像的三维模型检索算法. 该算法引入深度图像对光场描述符加以改进,得到投影视图后,分别提取其离散小波变换特征和Zernike矩特征;然后对深度图像进行聚类去掉冗余信息,并通过随机游走算法来确定每一类的权重,以更好地反映类间关系;最后设计改进全景视图相似距离计算方法,用于进一步的三维模型检索. 在普林斯顿模型库上的实验结果表明,该算法有效利用了三维模型空间信息,提高了检索精确度.

关键词: 深度图像, 光场描述符, 全景视图描述符, 三维模型检索

Abstract: Due to the problem of light field descriptor lacking spatial information of 3D model, and the problem of little projection of PANORAMA descriptor, a 3D model retrieval algorithm combining depth image was proposed. The depth images are used to improve light field descriptor. Discrete wavelet transform features and Zernike moments are extracted from projection views. Then the depth images are clustered to remove redundancy. The random walk algorithm is employed to determine the weight of each cluster. Finally, the retrieval method of PANORAMA is optimized to calculate similarity distance between two 3D models. Results on princeton shape benchmark show that the proposed algorithm can make good use of spatial information of 3D model and improve the accuracy of retrieval.

Key words: depth image, light field descriptor, PANORAMA descriptor, 3D model retrieval

中图分类号: