报告嘉宾2：郭裕兰（国防科技大学）
主持人：白翔（华中科技大学）
报告题目：Distinctive Local Features for 3D Point Clouds and Meshes http://valser.org/webinar/slide/slides/20150408/GuoYulan.pdf 报告时间：2015年4月8日晚20:00（北京时间）
文章信息：
[1] Y. Guo, F. Sohel, M. Bennamoun, M. Lu, J. Wan. Rotational Projection Statistics for 3D Local Surface Description and Object Recognition. International Journal of Computer Vision (IJCV). 105(1): 63-86, 2013.
[2] Y. Guo, M. Bennamoun, F. Sohel, M. Lu, J. Wan. 3D Object Recognition in Cluttered Scenes with Local Surface Features: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI). 36(11):2270–2287, 2014.
[3] Y. Lei, M. Bennamoun, M. Hayat, Y. Guo. An Efficient 3D Face Recognition Approach using Local Geometrical Signatures. Pattern Recognition (PR). 47(2):509-524. 2014.
报告摘要：Recent advances in 3D acquisition systems (e.g., Laser Scanner, Kinect) and computing devices have contributed to the flourishment of research in 3D computer vision. 3D local features have played a significant role in many vision related tasks such as 3D object recognition, 3D modeling, 3D scene reconstruction, 3D model retrieval, 3D shape analysis and 3D biometrics. A local feature extraction algorithm typically involves two major phases: keypoint detection and feature description. In this talk, I will give a brief review on the existing algorithms for 3D keypoint detection and 3D local feature description. I will then introduce two of our proposed feature descriptors (namely RoPS and ARS) for 3D object recognition and 3D face recognition.
报告人简介：郭裕兰，国防科技大学，博士研究生，2008年于国防科技大学电子科学与工程学院获工学学士学位，现于国防科技大学攻读博士学位。主要研究兴趣包括点云特征检测与描述、三维物体/人脸识别以及三维模型重建等方面。2011年至2014年间曾赴澳大利亚西澳大学开展为期两年半的访问研究，师从M. Bennamoun教授。目前已在包括IEEE TPAMI、IJCV、PR、IEEE TMM及Information Sciences等在内的重要国际学术期刊和会议上发表学术论文20余篇（其中在TPAMI和IJCV上的一作论文3篇），撰写book chapter一章，曾为十余个重要国际期刊及会议审理稿件。
个人主页 中文：http://www.escience.cn/people/yulanguo/index.html 英文：https://sites.google.com/site/yulanguo66/
| 