Anup Doshi

Ph.D., Postdoctoral Researcher
Laboratory for Intelligent and Safe Automobiles
Computer Vision and Robotics Research Laboratory
California Institute for Telecommunications and Information Technology (CalIT2)
University of California, San Diego
La Jolla, CA 92037
andoshi_at_ucsd.edu

Current Research
Prior Research

Education and Honors

CV (pdf)


Current Interests and Projects @ CVRR, UC San Diego

Driver Assistance Systems in Intelligent Automobiles
With the LISA Intelligent Test-beds as powerful platforms for researching driver assistance systems, we are developing and analyzing vision-based methods to infer driver behavior and responses. Current experiments include evaluating driver style, attention shifts, behavioral patterns, and response to visual feedback. We are ultimately interested in developing machine-learning based methods for predicting driver intents and improving intelligent, Advanced Driver Assistance Systems. These results could extend to more general human-computer interfaces and applications.

Publications

  • Anup Doshi, Brendan T. Morris, and Mohan M. Trivedi. Context-Sensitive Prediction of Intentions for
    On-road Driver Assistance
    , in submission.

  • Anup Doshi and Mohan M. Trivedi. Towards "Driving Style"-Sensitive Intelligent Driver Assistance Systems, in submission.

  • Anup Doshi and Mohan M. Trivedi. A Bayesian Approach for Estimating Attention by Viewer and View Observations, in submission.

  • Anup Doshi and Mohan M. Trivedi. Head and Eye Gaze Dynamics during Visual Attention Shifts in Complex Environments, in submission.

  • Anup Doshi, Cuong Tran, Matthew Wilder, Michael C. Mozer, and Mohan M. Trivedi. Sequential Dependencies in Driving, in submission.

  • Anup Doshi and Mohan M. Trivedi. Communicating Driver Intents: A Layered Architecture for Cooperative Active Safety Applications, IEEE Conference on Intelligent Transportations Systems, Sept 2010.

  • Anup Doshi and Mohan M. Trivedi. Examining the Impact of Driving Style on the Predictability and Responsiveness of the Driver: Real-world and Simulator Analysis, IEEE Intelligent Vehicles Symposium, pp. 232-237, June 2010. Honorable Mention, Best Paper Award. (pdf) (presentation)

  • Anup Doshi and Mohan M. Trivedi. Attention Estimation by Simultaneous Observation of Viewer and View, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Workshop on CVPR4HB, June 2010. (pdf)

  • Anup Doshi and Mohan M. Trivedi. LACASA: A Layered Architecture for Cooperative Active Safety Applications, 2nd Place - 2010 Student Essay Competition, Presented at ITS America's Annual Meeting , May 2010. (web)

  • Anup Doshi and Mohan M. Trivedi. On the Roles of Eye Gaze and Head Dynamics in Predicting Driver's Intent to Change Lanes, IEEE Transactions on Intelligent Transportation Systems, 10(3), 2009. (pdf)

  • Anup Doshi and Mohan M. Trivedi. Head and Gaze Dynamics in Visual Attention and Context Learning, IEEE CVPR Workshop on Visual and Contextual Learning, June 2009. (pdf)

  • Anup Doshi and Mohan M. Trivedi. Investigating the Relationships Between Gaze Patterns, Dynamic Vehicle Surround Analysis, and Driver Intentions, IEEE Intelligent Vehicles Symposium, June 2009. (pdf)

  • Anup Doshi, Shinko Y. Cheng, and Mohan M. Trivedi. A Novel, Active Heads-up Display for Driver Assistance, IEEE Transactions SMC-B Special Issue on Human Computing, Feb 2009. (pdf)

  • Anup Doshi and Mohan M. Trivedi. A Comparative Exploration of Eye Gaze and Head
    Pose Cues for Lane Change Intent Prediction
    , IEEE Intelligent Vehicles Symposium, June 2008. (pdf)

  • Erik Murphy-Chutorian, Anup Doshi, and Mohan M. Trivedi. Head Pose Estimation for Driver Assistance Systems: A Robust Algorithm and Experimental Evaluation, In IEEE Conf. Intelligent Transportation Systems, Sept 2007. (pdf)

  • Shinko Y. Cheng, Anup Doshi, and Mohan M. Trivedi. Active Heads-up Display based Speed Compliance Aid for Driver Assistance: A Novel Interface and Comparative Experimental Studies, IEEE Intelligent Vehicles Symposium, June 2007. (pdf)

Abstracts and Presentations

  • Anup Doshi, Matthew Wilder, Alaa A. Ahmed, Mohan M. Trivedi, and Michael C. Mozer. Sequential Dependencies in Semi-Real-World Motor Tasks, 51st Annual Meeting of the Psychonomic Society, Nov. 2010.

  • Anup Doshi and Mohan M. Trivedi. Head and Eye Gaze Dynamics during Visual Attention Shifts in Complex Environments, 2010 Cognitive Neuroscience Annual Spring Retreat and Kavli Institute for Brain and Mind Symposium in San Diego, May 1, 2010.

  • Anup Doshi and Mohan M. Trivedi. Towards Learning and Prediction of Driver Cognitive States and Intents, Southern California Computer Vision Meetup, October 30, 2009.

  • Anup Doshi and Mohan M. Trivedi. Towards Learning and Predictions of Human Cognitive States and Intents: A Multimodal Framework, 2008 ACM/IEEE International Conference on Distributed Smart Cameras (ICDSC) Ph.D. Forum, Sept. 2008. (Honorable Mention)


Robust Background Subtraction and Shadow Suppression for Outdoor Surveillance
Motivated by the need for deployable and robust real-time background subtraction methods in outdoor test-beds, we have been developing techniques for reliable foreground segmentation. The Hybrid-Cone-Cylinder Codebook model incorporates methods for adaptive background modeling and shadow suppression into a sensitive and coherent methodology. Additionally, we have examined the use of satellite imagery as a multi-sensory source of data to inform illumination parameters in a cloudy scene.

Publications

  • Anup Doshi and Mohan M. Trivedi. Satellite Imagery Based Robust, Adaptive Background Models and Shadow Suppression. Signal, Image, and Video Processing (SIViP) Journal, 1(2):119-132, June 2007 . (pdf)

  • Anup Doshi and Mohan M. Trivedi. Hybrid Cone-Cylinder Codebook Model for Foreground Detection with Shadow and Highlight Suppression. Proc. IEEE International Conference on Advanced Video and Signal based Surveillance, Nov 2006. (pdf)
     


Other Research @ UC San Diego

A Mind-reading Machine
2005-2006 - Under the guidance of Prof. Yoav Freund, an applet was developed to test the abilities of a machine-learning based 'Mind-reading' applet and collect data to enhance its performance. The applet is based upon active learning methods from "A Context-Tree Weighting Method" [Willems et al.] and more info can be found here.
Applet and Website

People Counting and Tracking for Surveillance
2005-2006 - The goal of this project is to implement a system to count and track the people in a database of surveillance footage. Due to several constraints and performance issues, a straightforward algorithm based on background subtraction is implemented and shows acceptable performance levels. Further improvements are considered to improve the performance, including implementations of algorithms such as BraMBLe.
CSE 252c Class Website


Undergrad Research Projects @ Carnegie Mellon

3D Image Processing - Senior Research Project
2004-2005 - The goal was to synthesize 3-D models of human faces from video camera sequences. With depth information from the incoming sequences, I built a 3-D model of the subject's face. Advisor: Dr. Tsuhan Chen. Grad Students: Todd Stephenson.
Multimedia Group Website

Time Reversal - Senior Honors Research Project
2004-2005 - Helped develop code for a project using time reversal techniques in a MIMO system to characterize a communications channel. Automated the measurements process by integrating various motors and the network analyzer using C++. Advisor: Dr. Dan Stancil. Grad Students: Ahmet Cepni, Ben Henty.
Wireless Group Website

Microphone Array Processing - 18551 Course Project
Spring 2004 - Implemented a phased-array of microphones that can localize and track the source of a sound in real time, amidst noise. Led a group of 4 in planning, design, and programming on a TI TMS320C67 DSP. Optimized the algorithm using MATLAB, C and Assembly.

Superresolution - 18798 Course Project
Spring 2004 - Designed and implemented a fast algorithm for Super-resolution enhancement of video sequences in MATLAB and C. Tried to updated the implementation to use Optical Flow for sub-pixel accuracy.

UWB Interference Effects - Clemson University SURE REU
Summer 2003 - Conducted a research project on properties of Ultra-wideband Communications. Modeled and analyzed UWB signals and interference on narrowband devices. Implemented a Monte Carlo simulation of UWB interference effects on 'victim' receivers. Advisor: Dr. Carl Baum
SURE Website - More Info

 


Education and Honors

  • University of California, San Diego, La Jolla, CA
        Ph.D., Electrical and Computer Engineering, December 2010
        Specialization: Signal and Image Processing. GPA: 4.0 / 4.0
        Thesis: "Learning and Inferring Human Intentions: Explorations of Driver Attention and Interactivity"
  • Carnegie Mellon University, Pittsburgh, PA
        M.S., Electrical and Computer Engineering, May 2005. GPA: 4.0 / 4.0
        B.S., Electrical and Computer Engineering, May 2005. GPA: 3.96 / 4.0

    Honors
    - Univ. of California Transportation Center (UCTC) Doctoral Dissertation Grant, 2009-2010
    - Finance Chair and "Most Valuable Volunteer", 2010 IEEE Intelligent Vehicles Symposium
    - Honorable Mention for Best Paper, 2010 IEEE Intelligent Vehicles Symposium
    - 2nd-place Winner, ITS America Student Essay Competition 2010
    - Honorable Mention, 2008 ACM/IEEE International Conference on Distributed Smart Cameras (ICDSC) Ph.D. Forum, Sept. 2008
    - Jacobs Fellow, University of California, San Diego, 2005-2008
    - Finalist, Hertz Foundation Graduate Fellowship, 2005
    - Honorable Mention, NSF Graduate Fellowship, 2005
    - IEC-William L. Everitt Student Award of Excellence, Carnegie Mellon, 2005
    - Andrew Carnegie Merit Scholarship, Carnegie Mellon, 2001
    - Member, Eta Kappa Nu, Tau Beta Pi, and Phi Kappa Phi Honor Societies


  • Home