Sabarinathan Vadivelu Email and Phone Number

• Acting as an Onsite-Coordinator between the Client and the Offshore development Team at KPIT Technologies.• Experience in Simulation-based Validation using CarMaker, MATLAB, Simulink, Stateflow, and other tools.• Experience in designing & modeling Highway/Urban Scenarios for Level 3 AD Features for a leading OEM in CarMaker & other various Simulation Tools.• Involved in automation script development to Convert the real-world Field-Operational-Test data to Scenario files which can be used to reproduce the defect in Simulation Environment.• Involved in automation of Conversion of CarMaker scenario files to OpenSCENARIO & OpenDRIVE files.• Experience in managing and executing millions of scenarios in an HPC (High-Performance-Computing) environment.• Technical Coordination between the Client & Offshore Team in India.• Responsible for Unit-Testing, Function testing for various AD/ADAS Features from OEM.• Hands-on experience in Requirement Engineering, design, implementation coding, validation, and debugging right from requirements to full function software by following the V model.

• Validating Active Safety functions in CarMaker, Simulink, developing Test Cases from Requirement Specifications.

• Involved in System Engineering & Control Algorithm Development of ADAS Feature – Traffic Jam Assist/Integrated Cruise Assist.• Involved in creating the whole architecture design of ADAS Feature – Traffic Jam Assist/Integrated Cruise Assist.

Video to Data Analytics:- Client: VU Digital Inc., USA. (http://myvu.com/)- Technology: C++, OpenCV, MATLAB.- Description: 90% of the world’s data will be video soon. Most people don’t realize is that all of that video is unstructured data; there’s no way to make sense of it. We convert that unstructured data to structured data, making it understandable data. It takes all of the audio, images, and text from the video – all words, names, faces, etc. – and distils them down to machine readable words indexed according to time; and all faster than real time.Object Detection & Recognition: We have developed a complete learning-based system for detecting and localizing objects in images. Our system represents objects using mixtures of deformable part models. These models are trained using a discriminative method that only requires bounding boxes for the objects in an image. The approach leads to efficient object detectors that achieve state of the art results.

Done various Image Processing & Computer Vision projects.Technologies used: - MATLAB, C++.