Avinash Kumar
Avinash Kumar (CV)
email : avinash1.kumar@intel.com
I am a staff research scientist at Intel Labs working on computer vision and machine learning problems.
Previously, I earned my Ph.D. in Electrical and Computer Engineering from University of Illinois at Urbana-Champaign, under the supervision of Prof. Narendra Ahuja where I was a member of the Computer Vision and Robotics Lab (CVRL). My research is in the field of camera calibration, depth from focus/defocus, structure from motion, computational imaging and machine learning. Before that, I obtained my B.Tech and M.S degrees in Computer Science from International Institute of Information Technology, Hyderabad at Center for Visual Information Technology (CVIT) specializing in Computer Vision and advised by Prof. C. V. Jawahar.
Publications
A New Non-central Model for Fisheye Calibration [oral]
Radka Tezaur, Avinash Kumar and Oscar Nestares
IEEE 3rd OmniCV Workshop, CVPR 2022, May 1, 2022
Multi-Capture Dynamic Calibration of Multi-Camera Systems [oral]
Avinash Kumar, Manjula Gururaj, Kalpana Seshadrinathan, Ramkumar Narayanswamy,
IEEE Computer Vision and Pattern Recognition (CVPR, CCD Workshop), June 2018, Salt Lake City, US
On the Equivalence of Moving Entrance Pupil and Radial Distortion for Camera Calibration
Avinash Kumar and Narendra Ahuja,
In International Conference on Computer Vision (ICCV), December 2015, Santiago, Chile.
Generalized Radial Alignment Constraint for Camera Calibration [oral]
Avinash Kumar and Narendra Ahuja,
In International Conference on Pattern Recognition (ICPR), August 2014, Stockholm, Sweden.
Non-frontal Camera Calibration using Focal Stack Imagery [oral]
Avinash Kumar and Narendra Ahuja,
In International Conference on Pattern Recognition (ICPR), August 2014, Stockholm, Sweden.
Generalized Pupil-Centric Imaging and Analytical Calibration for a Non-frontal Camera
Avinash Kumar and Narendra Ahuja.
In Computer Vision and Pattern Recognition (CVPR), June 2014, Columbus, Ohio, US.
Motion-Based Background Subtraction and Panoramic Mosaicing for Freight Train Analysis
Avinash Kumar, John M. Hart and Narendra Ahuja.
In IEEE International Conference on Image Processing (ICIP), September 2013, Melbourne, Australia.
A Generative Focus Measure With Application to Omnifocus Imaging [oral]
Avinash Kumar and Narendra Ahuja,
In IEEE International Conference on Computational Photography (ICCP), April 2013, Boston, US.
[Other Publications] Computer Vision for Railroad Applications [2006-2012]
Tristan G. Rickett, Avinash Kumar, John M. Hart, J. Riley Edwards, C. P. L. Barkan and Narendra Ahuja, Machine Vision Analysis of Intermodal Loading Efficiency on Heavy-Haul Railroads, Proceedings of International Heavy Haul Association Conference (IHHA), June 2011, Calgary, Canada
Avinash Kumar, Tristan .G. Rickett, Anirudh Vemula, John M. Hart, J. Riley Edwards, Narendra Ahuja and C.P.L. Barkan, Aerodynamic Analysis of Intermodal Freight Trains Using Machine Vision, Proceedings of the 9th World Congress on Railway Research (WCRR), May 2011, Lille, France.
Tristan G. Rickett., John M. Hart, J. Riley Edwards,Avinash Kumar, C. P. L. Barkan and Narendra Ahuja, Monitoring the Aerodynamic Efficiency of Intermodal Train Loading Using Machine Vision, Proceedings of Transportation Research Board Annual Conference (TRB), January 2011,Washington D.C., US
Qing Jie Kong, Avinash Kumar, Narendra Ahuja and Yuncai Liu, Robust Segmentation of Freight Containers in Train Monitoring Videos, Workshop on Applications of Computer Vision (WACV), January 2009, Salt Lake City, US
Avinash Kumar, Narendra Ahuja, John M. Hart, U. K. Visesh, P. J. Narayanan and C. V. Jawahar, A vision system for monitoring intermodal freight trains, Workshop on Applications of Computer Vision (WACV), January 2007
Yung-Cheng Lai, Narendra Ahuja, C. P. L. Barkan, Joseph Drapa, John M Hart, C. V. Jawahar, Avinash Kumar, Larry Milhon, and P. J. Narayanan, Machine vision analysis of the energy efficiency of intermodal freight trains [TA Stewart-Dyer Prize/Frederick Harvey Trevithick Prize], Journal of Rail and Rapid Transit (JRRT), 2006
PhD Thesis:
Generic camera calibration for omnifocus imaging, depth estimation and a train monitoring system (pdf)
Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign (UIUC), 2015
Advisor: Prof. Narendra Ahuja
Patents
Calibrating Depth Cameras Using Natural Objects with Expected Shapes, (granted), US10,154,176
Dynamic Calibration of Multi-Camera Systems using Multiple Multi-View Image Frames (granted), US10,645,364
Multi-Camera Processor with Feature Matching (granted), US10,762,664
Collaborative 3D Environment Map for Computer-Assisted or Autonomous Driving Vehicles, US20190220003A1
Detection of an Anomalous Image Associated with Image Data from One or More Cameras of a Computer-Aided or Autonomous Driving Vehicle US20190225234A1
Real-time calibration of wide-baseline outside-in multi-camera systems, US17/103,295