Large-scale Geospatial Computer Vision: Cities, Point Clouds, Trees

Speaker: Jan Wegner , ETH Zurich

Date: Friday, November 18, 2016

Time: 12:00 PM to 1:00 PM Note: all times are in the Eastern Time Zone

Public: Yes

Location: 32-D507

Event Type:

Room Description:

Host:

Contact: Katherine Bouman, klbouman@csail.mit.edu

Relevant URL:

Speaker URL: None

Speaker Photo:
None

Reminders to: seminars@csail.mit.edu

Reminder Subject: TALK: Jan Wegner - Large-scale Geospatial Computer Vision: Cities, Point Clouds, Trees

Abstract:

The ever increasing amount of geocoded images at varying scale, view point, and temporal resolution provides a treasure trove of information for better understanding our environment, to help making better decisions, managing resources, and improve quality of life, particularly in big cities. Geospatial computer vision combines vision and machine learning techniques that scale, to solve real-world problems. In this talk I will present three ongoing projects:

(a)Cities: Large-scale semantic 3D reconstruction casts 3D modeling and semantic labeling as a joint problem, where semantic image segmentation enforces class-dependent, geometric priors for reconstruction, while 3D benefits semantic labelling via one joint, convex energy formulation. This leads to more accurate 3D city models, that come with category labels directly.

(b)Point Clouds: Unstructured point clouds from multi-view stereo or laser scanners are a major data source for scene analysis in cities. What makes their analysis challenging is the anisotropic point density, self-occlusions, and sheer size of millions of points. We aim at efficient, direct prediction of CAD models from unstructured point clouds through contour extraction. Such contours shall either be completed manually with minimal effort, or be transferred to standard CAD software directly.

(c)Trees: This project, in collaboration with the Caltech Computational Vision Lab, aims to automatically catalogue trees in public space, classify them at species level, and measure their trunk diameter, to support urban planning as well as ecological. We propose an automated, image-based system to build up-to-date tree inventories at large scale using publicly available aerial images, panoramas at street-level, and open GIS data of US cities.

Bio

Jan Dirk Wegner is a senior research assistant and deputy leader of the Photogrammetry & Remote group at ETH Zurich, Switzerland. He received his PhD (with distinction) in 2011 from Leibniz Universit├Ąt Hannover, Germany, and was granted an ETH Postdoctoral fellowship (acceptance rate ~20%) in 2012. His main interests are in geospatial computer vision, and large-scale machine learning for geospatial applications. He is actively involved in multiple different projects that aim at better understanding and modeling our environment at large scale, combining vision and machine learning.

Core projects are (1) cataloging public trees at city-scale from aerial and street-level images (with Caltech: http://vision.caltech.edu/registree/), (2) semantic 3D reconstruction to generate 3D city models, (3) prediction of CAD models from unstructured point clouds, (4) underwater 3D reconstruction of corals (with Disney Research), and (5) graph CNNs for deep learning on large-scale, non-grid structured data (with EPFL).

Together with colleagues he is running the 1) ISPRS benchmark challenge for 2D pixel-wise semantic segmentation, object recognition, and 3D reconstruction (http://www2.isprs.org/commissions/comm3/wg4/tests.html) and 2) the Large-Scale Point Cloud Classification Benchmark with over one billion labeled points (semantic3D.net).
Attachments area

Research Areas:

Impact Areas:

This event is not part of a series.

Created by Katherine Bouman Email at Friday, November 18, 2016 at 6:07 PM.