IEEE/ISPRS 3rd Joint Workshop on Multi-Sensor Fusion for Dynamic Scene Understanding
December 12, 2015, Santiago, Chile
in conjunction with International Conference on Computer Vision
Venue

The venue for the Workshop and ICCV 2015 will be the CentroParque Convention Center in Santiago, Chile.

Keynote Speakers
Daniel Cremers (TU Munich, Germany)
Direct and Dense 3D Reconstruction from Autonomous Quadrotors

The reconstruction of the 3D world from images is among the central challenges in computer vision. Starting in the 2000s, researchers have pioneered algorithms which can reconstruct camera motion and sparse feature-points in real-time. In my talk, I will show that one can autonomously fly quadrotors and reconstruct their environment using onboard color or RGB-D cameras. In particular, I will introduce dense and direct methods for camera tracking and reconstruction which do not rely on keypoint extraction, which exploit all available input data and which recover dense geometry rather than sparse point clouds. This is joint work with Jakob Engel, Vladyslav Usenko, Jan Stuehmer, Martin R. Oswald, Christian Kerl, Erik Bylow, Jörg Stückler and Juergen Sturm.

Xiaogang Wang (Chinese University of Hong-Kong, China)
Deep Learning in Video Surveillance

This talk will introduce our recent deep learning works in video surveillance. The applications of deep learning include object detection, pedestrian detection, person re-identification, general object tracking, crowd segmentation, crowd density estimation, crowd counting and crowd video classification. Many results have shown that deep learning can advance the state-of-the-art of video surveillance substantially. The focus of this talk would be the strategies of designing network structures and learning feature representations adapting to surveillance applications. With carefully designed network structures and training schemes, the learned features could be effective for general objects, a particular object class, a particular object instance, or a large group of people to fulfill the requirements of different surveillance applications. In video surveillance, it is also critical for the feature representations to be robust across a large number of diversified scenes and camera views, to be robust to background clutters, and to well motion information. Deep learning is effective on addressing these challenges.

Greg Mori (Simon Fraser University, Canada)
Title coming soon !

Coming soon

Program

  • 08:20-08:30 - Introduction: Michael Yang (TU Dresden)

  • 08:30-09:30 - Keynote talk: Daniel Cremers (TU Munich)
    Title: Direct and Dense 3D Reconstruction from Autonomous Quadrotors.

  • 09:30-10:00 - Siavash Hosseinyalamdary, Alper Yilmaz. Surface Recovery: Fusion of Image and Point Cloud.

  • 10:00-10:30 Coffee break.

  • 10:30-11:00 - Andreas Kuhn, Helmut Mayer. Incremental Division of Very Large Point Clouds for Scalable 3D Surface Reconstruction.
  • 11:00-11:30 - Wentong Liao, Bodo Rosenhahn, Michael Yang. Video Event Recognition by Combining HDP and Gaussian Process.
  • 11:30-12:00 - Nicholas Brunetto, Samuele Salti, Nicola Fioraio, Tommaso Cavallari, Luigi Di Stefano. Fusion of Inertial and Visual Measurements for RGB-D SLAM on Mobile Devices.

  • 12:00-14:00 Lunch Break.

  • 14:00-15:00 - Keynote talk: Xiaogang Wang (Chinese University of Hong-Kong)
    Title: Deep Learning in Video Surveillance

  • 15:00-15:30 Coffee Break

  • 15:30-16:30 - Keynote talk: Greg Mori (Simon Fraser University)
    Title: TBD

  • 16:30-18:30 - Poster Session
    • Andreas Kuhn, Helmut Mayer. Incremental Division of Very Large Point Clouds for Scalable 3D Surface Reconstruction.
    • Domonkos Varga, Tamás Szirányi, Attila Kiss, László Spórás, László Havasi. A multi-view pedestrian tracking method in an uncalibrated camera network.
    • Sang-Il Oh, Hang-bong Kang. A Modified Sequential Monte Carlo Bayesian Occupancy Filter using Linear Opinion Pool for Grid Mapping.
    • Nicholas Brunetto, Samuele Salti, Nicola Fioraio, Tommaso Cavallari, Luigi Di Stefano. Fusion of Inertial and Visual Measurements for RGB-D SLAM on Mobile Devices.
    • Wentong Liao, Bodo Rosenhahn, Michael Yang. Video Event Recognition by Combining HDP and Gaussian Process.
    • Siavash Hosseinyalamdary, Alper Yilmaz. Surface Recovery: Fusion of Image and Point Cloud.

Affiliations