Skip to content. Skip to main navigation.

avatar

William J. Beksi

Name

[Beksi, William J.]
  • Assistant Professor, Department of Computer Science & Engineering

Professional Preparation

    • 2018 Ph.D. in Computer ScienceUniversity of Minnesota
    • 2016 M.S. in Computer ScienceUniversity of Minnesota
    • 2002 B.S. in Mathematics and Computer ScienceStevens Inst. of Tech

Appointments

    • Sept 2018 to Present Assistant Professor
      University of Texas at Arlington

Memberships

  • Membership
    • Sept 2018 to Present IEEE

Awards and Honors

    • Sep  2018 Rising STARs sponsored by University of Texas
    • Dec  2017 UMII MnDRIVE Ph.D. Fellowship sponsored by University of Minnesota Informatics Institute

Research and Expertise

  • Robotics, Computer Vision, Artificial Intelligence, Applied Topology

    My research focuses on developing algorithms and data structures for fundamental robotic vision tasks such as 3D reconstruction, segmentation, and object detection and classification. I also work on problems in networked and cloud robotics where the goal is to allow under-resourced robots remote access to computing, data, and learning resources. I am interested in working with students, faculty members (including across different departments), and initiating partnerships with industry to bring about smart homes, factories, and cities.

Publications

      Conference Paper 2018
      • W.J. Beksi and N. Papanikolopoulos. Signature of Topologically Persistent Points for 3D Point Cloud Description, IEEE International Conference on Robotics and Automation (ICRA), Brisbane, Australia, pp. 3229-3234, 2018.

        {Conference Paper }

      Journal Article 2016
      • D. Fehr, W.J. Beksi, D. Zermas and N. Papanikolopoulos. Covariance Based Point Cloud Descriptors for Object Detection and Recognition, Computer Vision and Image Understanding, 142, pp. 80-93, 2016.

        {Journal Article }

      Conference Paper 2016
      • W.J. Beksi and N. Papanikolopoulos. 3D Point Cloud Segmentation Using Topological Persistence, IEEE International Conference on Robotics and Automation (ICRA), Stockholm, Sweden, pp. 5046-5051, 2016.

        {Conference Paper }
      2016
      • W.J. Beksi and N. Papanikolopoulos. 3D Region Segmentation Using Topological Persistence, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Daejeon, Korea, pp. 1079-1084, 2016.

        {Conference Paper }

      Technical Report 2015
      • W.J. Beksi, K. Choi, D. Canelon and N. Papanikolopoulos. The Microvision Robot and its Capabilities, Technical Report TR 15-003, University of Minnesota, Department of Computer Science and Engineering, 2015.

        {Technical Report }

      Conference Paper 2015
      • W.J. Beksi and N. Papanikolopoulos. Object Classification Using Dictionary Learning and RGB-D Covariance Descriptors, IEEE International Conference on Robotics and Automation (ICRA), Seattle, USA, pp. 1880-1885, 2015.

        {Conference Paper }
      2015
      • W.J. Beksi, J. Spruth and N. Papanikolopoulos. CORE: A Cloud-based Object Recognition Engine for Robotics, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Hamburg, Germany, pp. 4512-4517, 2015.

        {Conference Paper }

      Conference Paper 2014
      • D. Fehr, W.J. Beksi, D. Zermas and N. Papanikolopoulos. RGB-D Object Classification Using Covariance Descriptors, IEEE International Conference on Robotics and Automation (ICRA), Hong Kong, China, pp. 5467-5472, 2014.

        {Conference Paper }
      2014
      • D. Fehr, W.J. Beksi, D. Zermas and N. Papanikolopoulos. Occlusion Alleviation through Motion Using a Mobile Robot, IEEE International Conference on Robotics and Automation (ICRA), Hong Kong, China, pp. 3179-3184, 2014.

        {Conference Paper }
      2014
      • W.J. Beksi and N. Papanikolopoulos. Point Cloud Culling for Robot Vision Tasks Under Communication Constraints, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Chicago, USA, pp. 3747-3752, 2014.

        {Conference Paper }

Courses

      • CSE 6367-001 COMPUTER VISION

        The objective of this course is to provide an introduction to the fundamental concepts of computer vision - how to make computers make sense of images. Topics include: projective geometry, camera geometry and calibration, linear filters, edge detection, feature descriptors, segmentation, epipolar geometry, stereo systems, motion and tracking, 3D reconstruction, image-based rendering, 3D point cloud processing, object recognition, and scene understanding. This course is suitable for gaining a solid technical background and as a preparation for more advanced work in computer vision.

        Spring - Regular Academic Session - 2019 Download Syllabus Contact info & Office Hours
      • CSE 5360-020 Artificial Intelligence I

        This course provides an introduction to the fundamental concepts of Artificial Intelligence (AI). Topics include: agents, search (search space, uninformed and informed search), game playing, planning, knowledge representation (logical encodings of domain knowledge, ontologies), and the programming language Lisp. The course is suitable to gain a solid technical background and as a preparation for more advanced work in AI.

        Fall - Regular Academic Session - 2018 Download Syllabus Contact info & Office Hours

Service to the Community

  • Appointed
    • Sept 2018 to  Present Reviewer for journals

      IEEE Transactions on Robotics, IEEE Transactions on Intelligent Transportation Systems, Computer Vision and Image Understanding, Image and Vision Computing, Robotics and Autonomous System

    • Sept 2018 to  Present Reviewer for conferences

      IEEE International Conference on Robotics and Automation (ICRA), IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE International Conference on Computer Vision (ICCV), IEEE Conference on Computer Vision and Pattern Recognition (CVPR)