News & Events

183 News items and Awards were found.




  •  NEWS   MERL Researcher Tim Marks presents an invited talk at MIT Lincoln Laboratory
    Date: April 27, 2017
    Where: Lincoln Laboratory, Massachusetts Institute of Technology
    MERL Contact: Tim Marks
    Research Areas: Computer Vision, Machine Learning
    Brief
    • MERL researcher Tim K. Marks presented an invited talk as part of the MIT Lincoln Laboratory CORE Seminar Series on Biometrics. The talk was entitled "Robust Real-Time 2D Face Alignment and 3D Head Pose Estimation."

      Abstract: Head pose estimation and facial landmark localization are key technologies, with widespread application areas including biometrics and human-computer interfaces. This talk describes two different robust real-time face-processing methods, each using a different modality of input image. The first part of the talk describes our system for 3D head pose estimation and facial landmark localization using a commodity depth sensor. The method is based on a novel 3D Triangular Surface Patch (TSP) descriptor, which is viewpoint-invariant as well as robust to noise and to variations in the data resolution. This descriptor, combined with fast nearest-neighbor lookup and a joint voting scheme, enable our system to handle arbitrary head pose and significant occlusions. The second part of the talk describes our method for face alignment, which is the localization of a set of facial landmark points in a 2D image or video of a face. Face alignment is particularly challenging when there are large variations in pose (in-plane and out-of-plane rotations) and facial expression. To address this issue, we propose a cascade in which each stage consists of a Mixture of Invariant eXperts (MIX), where each expert learns a regression model that is specialized to a different subset of the joint space of pose and expressions. We also present a method to include deformation constraints within the discriminative alignment framework, which makes the algorithm more robust. Both our 3D head pose and 2D face alignment methods outperform the previous results on standard datasets. If permitted, I plan to end the talk with a live demonstration.
  •  
  •  NEWS   MERL researcher Tim Marks presents invited talk at University of Utah
    Date: April 10, 2017
    Where: University of Utah School of Computing
    MERL Contact: Tim Marks
    Research Areas: Computer Vision, Machine Learning
    Brief
    • MERL researcher Tim K. Marks presented an invited talk at the University of Utah School of Computing, entitled "Action Detection from Video and Robust Real-Time 2D Face Alignment."

      Abstract: The first part of the talk describes our multi-stream bi-directional recurrent neural network for action detection from video. In addition to a two-stream convolutional neural network (CNN) on full-frame appearance (images) and motion (optical flow), our system trains two additional streams on appearance and motion that have been cropped to a bounding box from a person tracker. To model long-term temporal dynamics within and between actions, the multi-stream CNN is followed by a bi-directional Long Short-Term Memory (LSTM) layer. Our method outperforms the previous state of the art on two action detection datasets: the MPII Cooking 2 Dataset, and a new MERL Shopping Dataset that we have made available to the community. The second part of the talk describes our method for face alignment, which is the localization of a set of facial landmark points in a 2D image or video of a face. Face alignment is particularly challenging when there are large variations in pose (in-plane and out-of-plane rotations) and facial expression. To address this issue, we propose a cascade in which each stage consists of a Mixture of Invariant eXperts (MIX), where each expert learns a regression model that is specialized to a different subset of the joint space of pose and expressions. We also present a method to include deformation constraints within the discriminative alignment framework, which makes the algorithm more robust. Our face alignment system outperforms the previous results on standard datasets. The talk will end with a live demo of our face alignment system.
  •  
  •  NEWS   MERL to present 10 papers at ICASSP 2017
    Date: March 5, 2017 - March 9, 2017
    Where: New Orleans
    MERL Contacts: Petros Boufounos; Chen Feng; John Hershey; Takaaki Hori; Jonathan Le Roux; Dehong Liu; Hassan Mansour; Dong Tian; Anthony Vetro; Ye Wang
    Research Areas: Multimedia, Computer Vision, Computational Geometry, Computational Sensing, Digital Video, Information Security, Speech & Audio
    Brief
    • MERL researchers will presented 10 papers at the upcoming IEEE International Conference on Acoustics, Speech & Signal Processing (ICASSP), to be held in New Orleans from March 5-9, 2017. Topics to be presented include recent advances in speech recognition and audio processing; graph signal processing; computational imaging; and privacy-preserving data analysis.

      ICASSP is the flagship conference of the IEEE Signal Processing Society, and the world's largest and most comprehensive technical conference focused on the research advances and latest technological development in signal and information processing. The event attracts more than 2000 participants each year.
  •  
  •  NEWS   MERL presents three papers at the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
    Date: June 27, 2016 - June 30, 2016
    Where: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV
    MERL Contacts: Michael Jones; Tim Marks
    Research Areas: Computer Vision, Machine Learning, Electronics & Communications, Signal Processing
    Brief
    • MERL researchers in the Computer Vision group presented three papers at the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016), which had a paper acceptance rate of 29.9%.
  •  
  •  NEWS   MERL researcher, Oncel Tuzel, gives keynote talk at 2016 International Symposium on Visual Computing
    Date: December 14, 2015 - December 16, 2015
    Where: Las Vegas, NV, USA
    Research Areas: Computer Vision, Machine Learning, Decision Optimization
    Brief
    • MERL researcher, Oncel Tuzel, gave a keynote talk at 2016 International Symposium on Visual Computing in Las Vegas, Dec. 16, 2015. The talk was titled: "Machine vision for robotic bin-picking: Sensors and algorithms" and reviewed MERL's research in the application of 2D and 3D sensing and machine learning to the problem of general pose estimation.

      The talk abstract was: For over four years, at MERL, we have worked on the robot "bin-picking" problem: using a 2D or 3D camera to look into a bin of parts and determine the pose, 3D rotation and translation, of a good candidate to pick up. We have solved the problem several different ways with several different sensors. I will briefly describe the sensors and the algorithms. In the first half of the talk, I will describe the Multi-Flash camera, a 2D camera with 8 flashes, and explain how this inexpensive camera design is used to extract robust geometric features, depth edges and specular edges, from the parts in a cluttered bin. I will present two pose estimation algorithms, (1) Fast directional chamfer matching--a sub-linear time line matching algorithm and (2) specular line reconstruction, for fast and robust pose estimation of parts with different surface characteristics. In the second half of the talk, I will present a voting-based pose estimation algorithm applicable to 3D sensors. We represent three-dimensional objects using a set of oriented point pair features: surface points with normals and boundary points with directions. I will describe a max-margin learning framework to identify discriminative features on the surface of the objects. The algorithm selects and ranks features according to their importance for the specified task which leads to improved accuracy and reduced computational cost.
  •  
  •  NEWS   MERL presented 3 papers at the 2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP)
    Date: December 15, 2015
    Where: 2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP)
    MERL Contacts: Andrew Knyazev; Hassan Mansour; Dong Tian
    Research Areas: Algorithms, Multimedia, Computer Vision, Machine Learning, Speech & Audio, Electronics & Communications, Signal Processing, Wireless Communications, Digital Video
    Brief
    • MERL researcher Andrew Knyazev gave 3 talks at the 2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP). The papers were published in IEEE conference proceedings.
  •  
  •  NEWS   Teng-Yok Lee co-chairs Large Data Analysis and Visualization workshop
    Date: October 25, 2015
    Where: Large Data Analysis and Visualization (LDAV)
    MERL Contact: Teng-Yok Lee
    Research Area: Computer Vision
    Brief
    • Teng-Yok Lee served as the poster co-chair for the Large Data Analysis and Visualization (LDAV) workshop at IEEEVis 2015 in Chicago, Oct. 25-30. At IEEEVis there were over 2000 attendees and three highly competitive main subconferences (SciVis, InfoVis, and Visual Analytics and Technology (VAST)).
  •  
  •  AWARD   Fujisankei Newspaper Gold and Bronze Medal Advertisement Award
    Date: September 30, 2015
    Awarded to: Mitsubishi Electric Corp.
    MERL Contact: Yuichi Taguchi
    Research Area: Computer Vision
    Brief
    • Mitsubishi Electric Corp. (MELCO) advertisements based on 3D reconstruction received a Gold medal and a Bronze medal in the Fujisankei Newspaper. "Will I fit?", "He'll fit just fine.", and "Oops, did you think in 3D?".
  •  
  •  NEWS   Scene interpretation results of SA group members are listed as the leader of benchmark competition
    Date: July 13, 2015 - July 17, 2015
    MERL Contact: Jay Thornton
    Research Areas: Computer Vision, Machine Learning
    Brief
    • SA group members (M. Liu, S. Lin (intern), S. Ramalingam, O. Tuzel) presented a paper at the Robotics Science and Systems Conference in Rome July 13-17 called “Layered Interpretation of Street View Images”. The results they reported are now listed as the leader of the benchmark competition sponsored by Daimler. [Note that at that URL ref 2 is from collaboration with Daimler and it uses a FPGA for high speed, whereas MERL result is obtained with desktop computer and GPU.]
  •  
  •  NEWS   3D reconstruction on Tokyo TV
    Date: February 20, 2015
    MERL Contact: Yuichi Taguchi
    Research Area: Computer Vision
  •  
  •  NEWS   R&D 100 Award for MELFA-3D Vision system
    Date: July 11, 2014
    Where: R&D Magazine
    MERL Contacts: Yuichi Taguchi; Jay Thornton
    Research Area: Computer Vision
    Brief
    • A team with members from MERL, ATC, and Meiden received an R&D 100 award for its work on Mitsubishi Electric's MELFA-3D Vision system for industrial robot arms. This system completely automates bin picking a task for picking up parts that are randomly placed in a bin and aligning their poses for assembly processes.
  •  
  •  NEWS   MERL's High-speed optimization algorithms showcased at Mitsubishi Electric Corporation annual R&D Open House
    Date: February 13, 2014
    MERL Contact: Matthew Brand
    Research Areas: Algorithms, Mechatronics, Computer Vision
    Brief
    • Mitsubishi Electric Corporation announced its development of advanced optimization algorithms and high-speed calculation methods aimed at optimizing the performance of three practical systems: laser-processing machines for high-speed cutting of sheet metal using the shortest possible trajectories, moon probes achieved with minimized fuel consumption, and particle beam therapies for prompt medical treatments.
  •  
  •  NEWS   International Conference on 3DTV-Conference: publication by Ming-Yu Liu and others
    Date: June 29, 2013
    Where: International Conference on 3DTV-Conference
    Research Area: Computer Vision
    Brief
    • The paper "Model-Based Vehicle Pose Estimation and Tracking in Videos Using Random Forests" by Hodlmoser, M., Micusik, B., Pollegeys, M., Liu, M-Y. and Kampel, M. was presented at the International Conference on 3DTV-Conference
  •  
  •  NEWS   CVPR 2013: 3 publications by Yuichi Taguchi, Srikumar Ramalingam, C. Oncel Tuzel, Amit K. Agrawal and Ming-Yu Liu
    Date: June 23, 2013
    Where: IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
    MERL Contact: Yuichi Taguchi
    Research Area: Computer Vision
    Brief
    • The papers "Single Image Calibration of Multi-Axial Imaging Systems" by Agrawal, A. and Ramalingam, S., "Joint Geodesic Upsampling of Depth Images" by Liu, M-Y, Tuzel, O. and Taguchi, Y. and "Manhattan Junction Catalogue for Spatial Reasoning of Indoor Scenes" by Ramalingam, S., Pillai, J.K., Jain, A. and Taguchi, Y. were presented at the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  •  
  •  NEWS   ICRA 2013: publication by Yuichi Taguchi, Srikumar Ramalingam and others
    Date: May 14, 2013
    Where: IEEE International Conference on Robotics & Automation (ICRA)
    MERL Contact: Yuichi Taguchi
    Research Area: Computer Vision
    Brief
    • The paper "Point-Plane SLAM for Hand-Held 3D Sensors" by Taguchi, Y., Jian, Y-D, Ramalingam, S. and Feng, C. was presented at the IEEE International Conference on Robotics & Automation (ICRA)
  •  
  •  NEWS   IEEE Transactions on Pattern Analysis and Machine Intelligence: publication by MERL researchers and others
    Date: April 1, 2013
    Where: IEEE Transactions on Pattern Analysis and Machine Intelligence
    Research Area: Computer Vision
    Brief
    • The article "Support Vector Shape: A Classifier Based Shape Representation" by Nguyen, H. V. and Porikli, F. was published in IEEE Transactions on Pattern Analysis and Machine Intelligence
  •  
  •  NEWS   IEEE Transactions on Pattern Analysis and Machine Intelligence: publication by MERL researchers and others
    Date: February 14, 2013
    Where: IEEE Transactions on Pattern Analysis and Machine Intelligence
    Research Area: Computer Vision
    Brief
    • The article "Nonlinear Camera Response Functions and Image Deblurring: Theoretical Analysis and Practice" by Tai, Y-W, Chen, X., Kim, S., Kim, S.J., Li, F., Yang, J., Yu, J., Matsushita, Y. and Brown, M.S. was published in IEEE Transactions on Pattern Analysis and Machine Intelligence
  •  
  •  NEWS   ICMLA 2012: publication by MERL researchers and others
    Date: December 12, 2012
    Where: International Conference on Machine Learning and Applications (ICMLA)
    Research Areas: Computer Vision, Machine Learning
    Brief
    • The paper "Compressive Clustering of High-Dimensional Data" by Ruta, A. and Porikli, F. was presented at the International Conference on Machine Learning and Applications (ICMLA)
  •  
  •  NEWS   ICPR 2012: publication by Ming-Yu Liu and others
    Date: November 11, 2012
    Where: IEEE International Conference on Pattern Recognition (ICPR)
    Research Area: Computer Vision
    Brief
    • The paper "A Grassmann Manifold-based Domain Adaptation Approach" by Zheng, J., Liu, M.-Y., Chellappa, R. and Phillips, P.J. was presented at the IEEE International Conference on Pattern Recognition (ICPR)
  •  
  •  NEWS   ISMAR 2012: publication by Yuichi Taguchi, Srikumar Ramalingam and others
    Date: November 5, 2012
    Where: International Symposium on Mixed and Augmented Reality (ISMAR)
    MERL Contact: Yuichi Taguchi
    Research Area: Computer Vision
    Brief
    • The paper "SLAM Using Both Points and Planes for Hand-Held 3D Sensors" by Taguchi, Y., Jian, Y.-D., Ramalingam, S. and Feng, C. was presented at the International Symposium on Mixed and Augmented Reality (ISMAR)
  •