Workshop Program

Keynote Speaker

Title: AI FOR 3D BIG DATA: WHAT ARE WE LOOKING FOR?

Abstract: It is now easy to create massive point clouds using LiDAR, and to differentiate points by color, with the potential to support an enormous range of applications. The intelligence required to do this clearly extends far beyond the capabilities of humans, and should rightly be termed artificial or machine intelligence. But the human will always be an essential part of the process, in understanding the context of the application: what is the use case, what are we looking for, and what does this tell us about the form of the results? Even the simplest goals, such as find similar or classify, must be based on the structures that result from analysis of the point clouds, not on the point clouds themselves. Examples are given, ranging from archaeology to architecture and geomorphology. The geographic world is not constructed randomly, but instead follows certain principles, including spatial dependence and spatial heterogeneity. Standard 3D data models, such as triangular meshes, rasters, and isolines, are helpful, but attention to the specific use case, together with libraries of basic 3D structural elements, can lead to much more effective techniques.

Biography: Michael F. Goodchild is Emeritus Professor of Geography at the University of California, Santa Barbara, where he also holds the title of Research Professor. He is also Distinguished Chair Professor at the Hong Kong Polytechnic University and Research Professor at Arizona State University, and holds many other affiliate, adjunct, and honorary positions at universities around the world. Until his retirement in June 2012 he was Jack and Laura Dangermond Professor of Geography, and Director of UCSB’s Center for Spatial Studies. He received his BA degree from Cambridge University in Physics in 1965 and his PhD in geography from McMaster University in 1969, and has received five honorary doctorates. He was elected member of the National Academy of Sciences and Foreign Member of the Royal Society of Canada in 2002, member of the American Academy of Arts and Sciences in 2006, and Foreign Member of the Royal Society and Corresponding Fellow of the British Academy in 2010; and in 2007 he received the Prix Vautrin Lud. He was editor of Geographical Analysis between 1987 and 1990 and editor of the Methods, Models, and Geographic Information Sciences section of the Annals of the Association of American Geographers from 2000 to 2006. He serves on the editorial boards of ten other journals and book series, and has published over 15 books and 500 articles. He was Chair of the National Research Council’s Mapping Science Committee from 1997 to 1999, and of the Advisory Committee on Social, Behavioral, and Economic Sciences of the National Science Foundation from 2008 to 2010. His research interests center on geographic information science, spatial analysis, and uncertainty in geographic data.

Accepted Papers

Regular Research Papers

• Wei Li et al. Effective Geo-Social Group Detection in Location-Based Social Networks
• Takayuki Shinohara et al. FWNetAE: Spatial Representation Learning for Full Waveform Data Using Deep Learning
• Haoyi Xiu et al. Dynamic-scale Graph Convolutional Network for Semantic Segmentation of 3D Point Cloud

Short Research Papers

• Taehoon Kim et al. Dotloom: Toward a Decentralized Data Platform for Massive Three-dimensional Point Clouds
• Pratiksha Benagi et al. Vector Based Object Identification in Spherical Images
• Rizwan Ahmed Ansari et al. Texture Based Identification of Informal Settlements in Contourlet Feature Space
• Shalini Gakhar et al. Spectral - Spatial Urban Target Detection in Hyperspectral Remote Sensing Data using Artificial Neural Network