23960 BPO Way,

Piscataway, NJ - 08854

Ph. 732-762-4888

Email:

Atul Kanaujia

OBJECTIVE

A highly motivated software developer seeking a position as application programmer in the field of machine vision and statistical learning.

SKILL SET

  • Programming Languages - C, C++, VC++ 6.0, Java, Java Swing, Pascal, Prolog
  • Shell Programming - bash, awk, sed and perl scripts.
  • Software Management tools - CVS, Rational Clearcase
  • Statistical and Graphics programming - Matlab, OpenGL, OpenCV, Perl Data Language
  • Database applications developing languages - Perl, Active Server Pages, JDBC ,Java Servlets, XML, XSLT, XPath and DHTML

RESEARCH

Research AssistantComputational Biomedicine Imaging and Modeling Lab Jan 2004-Current

Human Activity and Emotion Recognition using Graphical Models

Worked on activity recognition of human based on 2D features of silhouettes obtained from monocular video sequence.

Incorporated features that could represent contextual dependencies efficiently in conditional graphical models. Worked on recognizing emotional state of an actor using hand and head movement. The state to be recognized were agitated, controlled and relaxed.

  • Implemented Conditional Random Fields with contextual features for better recognition.
  • Implemented Maximum Entropy Markov Model using softmax function learnt using IRLS(iterative reweighted least square).
  • Implemented Multi-Level HMM to recognize emotional state. The output sequence of states from lower level HMM feed the next higher level HMM. Token passing algorithm was used to find most probable sequence of states.
  • Worked with dimension reduction techniques - Laplacian Eigenmaps, Kernel PCA, Kernel Dependency Estimation and Pre-Image Learning.
  • Worked with background subtraction using non-parametric kernel density to extract human silhouettes.

Learning to Reconstruct 3D motion from 2D monocular view

The project involves mapping 2D motion to 3D space using statistical learning models. Used discriminative approach to model the tracking by learning mapping from 2D features to 3D poses using multimodal probability distributions. Used Bayesian Mixture of Experts to learn mappings as a set of function approximators using EM algorithm.

  • Implemented Shape Context by extracting the outermost contour and tracing it using DFS and 8-connected neighbors.
  • Generated motion capture database for controlled testing by creating a Human model in MAYA and importing motion to it.
  • Implemented Pairwise Geometric Histogram using internal edges of the image obtained from Canny Filter.
  • Implemented K-means clustering and K-nearest neighbor classifier for reducing the dimension of the shape.
  • Implemented mixture models - Clusterwise Regression and Bayesian Mixture of experts.
  • Implemented Sparse Bayesian Regression model for multi-way classification.
  • Worked with regression models to compare results. Models Included Generalized Linear Models, Relevance Vector Machines, Support Vector Machines.
  • Implemented Deformable models using parametric super-quadrics and using Kinematics to deform the model under constant force.

Technologies used: Maya 5.0, VC++ 6.0 MFC for GUI and C++ and OpenGL. Image processing was done in Matlab, MEX to interface with C code. Statistical Models were implemented in Matlab.

23960 BPO Way,

Piscataway, NJ - 08854

Ph. 732-762-4888

Email:

PROFESSIONAL EXPERIENCE

  • Associate Member of Technical StaffMentor Graphics (India) R&D LabsJune 2003- Jan2004

Worked on printing framework for the mentor graphics tools (front end and backend EDA Tools). Involved in high level analysis and design of the framework. The framework provided APIs to develop interface for specifying electronic design, printing to the printer, generating a preview or converting it to the PDF document. Responsibilities successfully implemented:

  • Analyzed printing process on UNIX platform.
  • Wrote driver routines to communicate with serial printer.
  • Wrote routines to communicate with RIP (Raster Image Processor) for bidirectional PS and HP network printers using PJL and PCL.
  • Installed and studied CUPS (Common Unix Printing Solution), LPD (Line Printer Daemon) and LPR as a part of project feasibility analysis.
  • Designed APIs for the Graphics Kernel System based on Windows GDI+ and WxWindows GUI framework
  • Designed GUI for printing framework using windows MFC programming.
  • Wrote Functional Specification of the framework

Technologies used: VC++(6.0), MFC, Socket programming (UNIX), PS2, HPGL/2, PCL, PJL, Rational Clearcase (IBM).

GRADUATE COURSE PROJECTS

User Level Thread Library
Implemented User Level thread library similar to POSIX PThreads. The interface functions were same as PThreads. The thread scheduling was done by stride scheduling algorithm. The library functions included thread creation and killing routines, synchronizing routines - mutex, condition variables and semaphores.
Distributed File Server (DFS)
Implemented centralized and decentralized Distributed File Server. In centralized DFS, a central server takes all the request and redirects to any backend server. In decentralized DFS the request can go to any of backend servers depending upon the load on each server. The servers were run on 4 different Sun Solaris machines. The servers communicated amongst themselves or with central server to replicate frequently accessed files. The consistency was maintained by write through policy for every write request. All the communications were done using TCP.
Reliable Connection Over UDP
Implemented reliable connection over User Datagram Protocol which included adding features of TCP to UDP packets. The features like positive acknowledgement, timeout and retransmit, sequencing, duplicate detection and flow control were programmed using datagram packets.
File Replication and access optimization
Worked on Red Hat Linux 6.2 Kernel to modify IDE hard disk driver for file replication and file access optimization. The modified kernel monitored the frequently accessed files and replicated these files. When file is accessed later, depending upon the current position of head, the head was moved to nearest file copy block.

ACADEMIC QUALIFICATIONS

Master of Science in Computer Science Oct2003

Rutgers, The StateUniversity of NJ GPA: 3.7/4.0

Bachelors in Computer Science and Engineering Aug 2000

Indian Institute of Technology (IIT) - Bombay. GPA: 8.3/10

List of Publications at

Current Research Work at