Publications

  • Teng-Yok Lee & Sonali Patil, Srikumar Ramalingam, Yuichi Taguchi, Bedrich Benes, (2017). Barcode: Global Binary Patterns for Fast Visual Inference. 3D Vision (3DV). Published, 09/05/2017.
  • Zhiding Yu & Chen Feng, Ming-Yu Liu, Srikumar Ramalingam (2017). CASENet: Deep Category-Aware Semantic Edge Detection. , IEEE Conference on Computer Vision and Pattern Recognition (CVPR),. Published, 07/21/2017.
  • Srikumar Ramalingam & Peter Sturm (2017). A Unifying Model for Camera Calibration. IEEE Transactions on Pattern Analysis and Machine Intelligence. Vol. 39. Published, 07/01/2017.
  • Srikumar Ramalingam & Arvind Raghunathan, Daniel Nikovski, (2017). Submodular Function Maximization for Group Elevator Scheduling. International conference on automated scheduling and planning (ICAPS),. Published, 06/18/2017.
  • Khalid Yousif & Yuichi Taguchi, Srikumar Ramalingam (2017). MonoRGBD-SLAM: Simultaneous localization and mapping using both monocular and RGBD cameras. International conference on robotics and automation (ICRA). Published, 05/29/2017.
  • Khalid Yousif & Yuichi Taguchi, Srikumar Ramalingam, Alireza Bab-Hadiashar (2017). ROS2D: Image feature detector using rank order statistics. International conference on robotics and automation (ICRA). Published, 05/29/2017.
  • Srikumar Ramalingam & Chris Russell, L’ubor Ladický, Philip H.S. Torr (2017). Efficient Minimization of Submodular Higher Order Functions Using Monotonic Boolean Functions. Discrete Applied Mathematics. Vol. 220, 1-19. Published, 03/31/2017.

Research Statement

I enjoy solving fundamental problems towards building a system with social impact. My research focuses on accomplishing the following two goals:

 

  • Using innovative and cost-effective camera solutions for computers to sense the world.
  • Developing novel algorithms to understand the world using visual and other sensed data.

I conduct research in the intersection of computer vision, machine learning, and robotics. I specialize in a wide variety of problems: probabilistic graphical models, autonomous driving applications (toward building a cyber-physical system), discrete and graph-theoretic algorithms, multi-view geometry for various camera models, and several machine learning algorithms (clustering, conditional random fields, structured learning, and deep learning).

Research Keywords

  • submodularity, deep learning, multi-view geometry, computer vision, robotics, machine learning

Presentations

Research Groups

  • Siddhant Ranade, Graduate Student. 09/01/2017 - present.
  • Craig Roddin, Graduate Student. School of Computing. 09/01/2017 - present.
  • Sagar Chaturvedi, Graduate Student. School of Computing. 09/01/2017 - present.
  • Xin Yu, Graduate Student. School of Computing. 05/01/2017 - present.