News & Events

24 Events and Talks were found.


  •  TALK   Visual 3D/4D modeling of urban places and events
    Date & Time: Friday, June 29, 2012; 2:30 PM
    Speaker: Prof. Marc Pollefeys, ETH Zurich and UNC Chapel Hill
    Research Area: Computer Vision
    Brief
    • One of the fundamental problems of computer vision is to extract 3D shape and motion from images. This can be achieved when a scene or object is observed from different viewpoints or over a period of time. First, we will discuss image-based 3D modeling and localization in large environments, e.g. urban 3D reconstruction from vehicle-borne cameras and (geo)localization from mobile-phone images. In this context, we will discuss some of the challenges an opportunities offered by symmetries of architectural structures. We will also discuss how changes in an urban environment can be detected from images, leading to the possibility to efficiently acquire 4D models. In addition to explicit 4D modeling of an event, we'll consider the possibility to perform interactive video-based rendering from casually captured videos.
  •  
  •  TALK   Toward Efficient and Robust Human Pose Estimation
    Date & Time: Tuesday, June 26, 2012; 12:00 PM
    Speaker: Min Sun, University of Michigan
    Research Area: Computer Vision
    Brief
    • Robust human pose estimation is a challenging problem in computer vision in that body part configurations are often subject to severe deformations and occlusions. Moreover, efficient pose estimation is often a desirable requirement in many applications. The trade-off between accuracy and efficiency has been explored in a large number of approaches. On the one hand, models with simple representations (like tree or star models) can be efficiently applied in pose estimation problems. However, these models are often prone to body part misclassification errors. On the other hand, models with rich representations (i.e., loopy graphical models) are theoretically more robust, but their inference complexity may increase dramatically. In this talk, we present an efficient and exact inference algorithm based on branch-and-bound to solve the human pose estimation problem on loopy graphical models. We show that our method is empirically much faster (about 74 times) than the state-of-the-art exact inference algorithm [Sontag et al. UAI'08]. By extending a state-of-the-art tree model [Sapp et al. ECCV'10] to a loopy graphical model, we show that the estimation accuracy improves for most of the body parts (especially lower arms) on popular datasets such as Buffy [Ferrari et al. CVPR'08] and Stickmen [Eichner and Ferrari BMVC'09] datasets. Our method can also be used to exactly solve most of the inference problems of Stretchable Models [Sapp et al. CVPR'11] on video sequences (which contains a few hundreds of variables) in just a few minutes. Finally, we show that the novel inference algorithm can potentially be used to solve human behavior understanding and biological computation problems.
  •  
  •  TALK   Cooperative Cuts: Coupling Edges via Submodularity
    Date & Time: Thursday, April 12, 2012; 12:00 PM
    Speaker: Dr. Stefanie Jegelka, UC Berkeley
    Research Area: Computer Vision
    Brief
    • Graph cuts that represent pairwise Markov random fields have been a popular tool in computer vision, but they have some well-known shortcomings that arise from their locality and conditional independence assumptions. We therefore extend graph cuts to "cooperative cuts", where "cooperating" graph edges incur a lower combined cost. This cooperation is modeled by submodular functions on edges. The resulting family of global energy functions includes recent models in computer vision and also new critieria which e.g. significantly improve image segmentation results for finely structured objects and for images with variation in contrast. While "minimum cooperative cut" is NP-hard, the underlying indirect submodularity and the graph structure enable efficient approximations.

      In the second part of the talk, I will switch topics and briefly address Hilbert space embeddings of distributions. With the kernel trick, such embeddings help generalize clustering objectives to consider higher-order moments of distributions instead of merely point locations.
  •  
  •  TALK   Modeling and Control of Multi-locomotion Robotic System
    Date & Time: Tuesday, June 14, 2011; 4:00 PM
    Speaker: Tadayoshi Aoyama, Nagoya University
    MERL Host: Yuichi Taguchi
    Research Area: Computer Vision
    Brief
    • First, the concept of "Multi-Locomotion Robot" that has multiple types of locomotion is introduced. The robot is developed to achieve a bipedal walk, a quadruped walk and a brachiation, mimicking locomotion ways of a gorilla. It therefore has higher mobility by selecting a proper locomotion type according to its environment and purpose. I show you some experimental videos with respect to realized motions before now.
      Second, I focus on biped walk and talk about detail of bipedal walking. This part proposes a 3-D biped walking algorithm based on Passive Dynamic Autonomous Control (PDAC). The robot dynamics is modeled as an autonomous system of a 3-D inverted pendulum by applying the PDAC concept that is based on the assumption of point contact of the robot foot and the virtual constraint as to robot joints. Due to autonomy, there are two conservative quantities named "PDAC constant", that determine the velocity and direction of the biped walking. We also propose the convergence algorithm to make PDAC constants converge to arbitrary values, so that walking velocity and direction are controllable. Finally, experimental results validate the performance and the energy efficiency of the proposed algorithm.
  •