Ritesh Kapse
Computer Vision and Automotive Self-Driving Specialist
Senior Development Engineer in Test with 10 years in the Automotive industry, specializing in software testing and development. My expertise in Python, C++, Machine learning, Computer Vision and Agile methodologies complements my work in automotive technologies. I leverage generative AI to enhance development efficiency and innovation in advanced driving assistance systems, leading cross-functional teams to deliver customer-centric solutions.
Core Competencies
This section provides a high-level overview of my fundamental skills. These competencies form the bedrock of my work in developing robust perception systems for autonomous vehicles.
Computer Vision Fundamentals
Image processing, feature extraction, object detection, segmentation, tracking, and 3D vision.
Machine & Deep Learning
CNNs, RNNs, Transformers, transfer learning, and model optimization.
Sensor Fusion
Integrating data from cameras, LiDAR, and Radar for comprehensive understanding.
Perception Systems
Developing robust perception modules for end-to-end autonomous driving.
Data Handling
Large-scale dataset management, annotation, augmentation, and pipeline development.
Performance Optimization
Real-time processing, embedded systems considerations, and computational efficiency.
Key Projects & Areas of Expertise
Explore my hands-on experience by clicking through the different project areas below. Each tab details the project's focus, the skills demonstrated, and its impact on autonomous vehicle systems, along with links to code and live demos.
🔍 Object Detection with PyTorch CNNs and Open-CV
Project Focus:
Implemented object detection models using PyTorch convolutional neural networks (CNNs), focusing on accurate object recognition in images.
Key Skills Demonstrated:
PyTorch, CNNs, OpenCV, Object Recognition, Model Implementation.
Impact:
Enhanced the capability for precise object identification in diverse visual data.
🛣️ Advance Lane Detections using Hough Transforms
Project Focus:
Developed a lane detection system using Hough transforms to enhance autonomous vehicle navigation, ensuring accurate lane tracking in various road conditions.
Key Skills Demonstrated:
Hough Transforms, Lane Detection, Autonomous Navigation, Road Condition Handling.
Impact:
Improved the reliability of lane keeping systems for autonomous vehicles.
🏎️ Race Car Tracking in Video
Project Focus:
Developed a vehicle tracking system to monitor race cars in real-time, providing detailed analytics on speed and position.
Key Skills Demonstrated:
Vehicle Tracking, Real-time Analysis, Speed and Position Analytics, Video Processing.
Impact:
Provided critical performance insights for race analytics and safety monitoring.
🖼️ Image Segmentation using Deep Learning with PyTorch
Project Focus:
Developed a deep learning model using PyTorch for image segmentation tasks, focusing on accurate object isolation in images.
Key Skills Demonstrated:
Deep Learning, PyTorch, Image Segmentation, Object Isolation, Model Development.
Impact:
Enabled precise delineation of objects within complex images, crucial for scene understanding.
☁️ Deploying Computer Vision Applications on Cloud
Project Focus:
Deployed several of the above applications on cloud platforms [Heroku, AWS, GitLab CI-CD] ensuring scalability, reliability, and real-time data processing capabilities.
Key Skills Demonstrated:
Cloud Deployment (Heroku, AWS), CI/CD (GitLab), Scalability, Real-time Data Processing.
Impact:
Ensured robust and accessible deployment of computer vision solutions for wider use.
🤖 Generative AI for Autonomous Vehicle Scenario Simulation
Project Focus:
Created a generative AI tool to simulate diverse driving scenarios for autonomous vehicles, including various weather conditions, road types, and unexpected events. This project utilized AI to generate synthetic sensor data and virtual environments, enabling comprehensive testing of vehicle perception and decision-making algorithms in a controlled manner.
Key Skills Demonstrated:
Generative AI, Scenario Simulation, Synthetic Data Generation, Virtual Environments, Perception Testing.
Impact:
Revolutionized testing methodologies by enabling comprehensive and controlled simulation of complex driving conditions.
Professional Certifications
Highlighting my formal qualifications and continuous learning in key areas of computer vision and deep learning.
Self-Driving Cars Specialization
Coursera (University of Toronto)
Issued: [Date]
Intro to Self-Driving Cars Nanodegree
Udacity
Issued: [Date]
Intermediate Python Nanodegree
Udacity
Issued: [Date]
Machine Learning Advanced Certification
Simpli-learn
Issued: [Date]
Google IT Automation with Python
Issued: [Date]
Technical Skills & Tools
This chart provides a visual representation of my proficiency with key programming languages, frameworks, and tools. Each color group represents a different category of skills.
Experience & Education
This section outlines my professional journey and academic background, presented in two separate timelines for clarity.
Professional Experience
Senior SDET
Nvidia Graphics Pvt. Ltd
08/2021 - Present
Led Automotive Parking ECU team, creating Python/C++ code for SIL/HIL simulations and managing release testing. Utilized Generative AI for synthetic data and developed automation tools, enhancing vehicle perception systems.
Senior Engineer
Tata Consultancy Services
03/2015 - 07/2021
Spearheaded MATLAB model development and validation, leading a team through project delivery. Conducted extensive ECU testing and collaborated on ADAS feature enhancements, managing data analysis with ML libraries.
Education
M.Tech
Amrita School of Engineering
06/2017 - 06/2019
Coimbatore
B.E.
Amravati University
06/2010 - 06/2014
Maharashtra, Amravati