This page is not maintained anymore, my new page is here!
Bio:
Bharath Sankaran is a former Ph.D. student in Computer Science at the University of Southern California. His thesis title is "From Active to Interactive 3D Object Recognition" which he defended in July 2018. He joined the CLMC Lab in 2012. He also received an M.S in Computer Science (2015) from USC. Before coming to USC, Bharath received an M.S in Robotics from the University of Pennsylvania (2012), an M.E specializing in Aerospace Engineering from the University of Maryland, College Park (2008) and a B.E in Mechanical Engineering from Anna University, India (2006).
Bharath has also worked with the Robotics Institute at Carnegie Mellon on the Riverine Mapping project (2010), with Bosch RTC on Shared Autonomy Systems (2011), with the Spatial Analysis Group at MERL on Invariant Image Matching (2015) and with the Computer Vision Group at Qualcomm Corp R&D on Relocalization for Visual-Inertial Odometry (2016). Apart from this, he held industry positions at Human Network Labs (Philadelphia, 2008) and AIS Automation (Dresden, GmbH 2009).
Research Interests:
Computer Vision, Machine Learning, Humanoid Robotics, Reinforcement Learning, Active Perception, Interactive Perception, Online Learning.
Software:
Active Perception:
Active Object Detection
Object Detection and Pose Estimation:
Viewpoint Pose Tree
Contact Information:
Ronald Tutor Hall, RTH-417
3710 S. Mc.Clintock Ave
Los Angeles, CA 90089
tel: (213) 740 6717
Email:
Videos:
Hypothesis Testing Framework for Active Object Detection (ICRA 2013):
| Nonmyopic View Planning for Active Object Detection (TRO):
|
(:youtube rRMYAFxu5Zg width=400 height=300:)
| (:youtube WzuFure5SOI width=400 height=300:)
|
Conference Publications:
(Please refer to my Google Scholar page for a complete list of publications)
Master's Thesis:
A copy of my Master's thesis is available on Google Docs
PhD Thesis:
A copy of my PhD thesis is available on Google Docs