- Blog
- CV generator
- Community
- Documentation
Varun Ravi Kumar
Kups, Germany
******************************"Dedicated lifelong learner." ******************************* I'm Phd candidate with expertise in the field of Neural Networks for Deep Learning(DL) for Self-Driving Cars with a thorough quantitative and physical understanding of concepts. Worked on many challenging Machine Learning and Deep Learning projects. To summarize my Machine Learning experience "It's not who has the best algorithm wins. It's who has the most data."
CodersRank Score
What is this?
This represents your current experience. It calculates by analyzing your connected repositories. By measuring your skills by your code, we are creating the ranking, so you can know how good are you comparing to another developers and what you have to improve to be better
Information on how to increase score and ranking details you can find in this blog post.
563.7
CodersRank Rank
Top 2%
Highest experience points: 0 points,
0 activities in the last year
List your work history, including any contracts or internships
Valeo
Mar 2018 - Aug 2020 (2 years 5 months)
Phd Candidate [Deep Learning]
Add some compelling projects here to demonstrate your experience
Internet of Things (IoT) – Humidity and Temperature Sensor Array.
Apr 2016 - Jun 2016
• Data acquisition and transmission to Arduino using I2C communication.
• Wireless Sensor nodes communication test in Contiki OS using Cooja simulation.
• Data processed by a (IoT) software developed using C#. Data was transmitted to a website for
monitoring and machine learning.
Recognition: The project was selected at the conference for impedance spectroscopy (IWIS) held in Sept 2016 for the “Best Student Poster Selection”.
• Wireless Sensor nodes communication test in Contiki OS using Cooja simulation.
• Data processed by a (IoT) software developed using C#. Data was transmitted to a website for
monitoring and machine learning.
Recognition: The project was selected at the conference for impedance spectroscopy (IWIS) held in Sept 2016 for the “Best Student Poster Selection”.
Comprehensive Research on Signal Processing Tools for Cockpit Voice Recorder Data Analysis.
Jan 2015 - Jun 2015
•Worked for Aerospace Electronics and Systems Division department.
•Developed 2 major signal processing tools on Short Time Fourier Transform (STFT) and Wavelet
Transform (WT) for cockpit voice recorder in MATLAB.
•De-noising was performed with Least Mean Square Algorithm (LMS).
•Found exact cause for the air crash using spectrogram analysis.
Presented our project in ITU seminars under the guidance of an IIT professor.
•Developed 2 major signal processing tools on Short Time Fourier Transform (STFT) and Wavelet
Transform (WT) for cockpit voice recorder in MATLAB.
•De-noising was performed with Least Mean Square Algorithm (LMS).
•Found exact cause for the air crash using spectrogram analysis.
Presented our project in ITU seminars under the guidance of an IIT professor.
Self Driving Car [Nano Degree] [Term 1]
Nov 2016 - Nov 2016
Keep a tab on my Github profile.Project files and personal notes will be updated.
TERM 1: COMPUTER VISION AND DEEP LEARNING
•Detected lane lines from a video stream and test images using OpenCV image analysis techniques to identify lines, including Hough transforms, Gaussian Smoothing and Canny edge detection.
•Trained a model which can decode traffic signs from natural images using the German Traffic Sign Dataset. [Model architecture based on Convolutional Neural Networks (CNN)].
•Generalized the above trained model for new images found on the web.
•Designed and trained a CNN for end-to-end driving in a simulator, usingTensorflow and Keras. Used optimization techniques such as regularizationand dropout to generalize the network for driving on multiple tracks.
•Built an advanced lane-finding using distortion correction, image rectification, color transforms and gradient thresholding. Identified lane curvature and vehicle displacement. Overcame environmental challenges such as shadows and pavement changes.
• Created a vehicle detection and tracking pipeline with OpenCV, histogram of gradients (HOG) and support vector machines (SVM). Optimized and evaluated the model on video data from an automotive camera taken during highway driving.
Sensor Fusion and Localization
• Implemented an Extended Kalman Filter algorithm in C++ capable of tracking a pedestrian’s motion in two dimensions.
• Implemented an Unscented Kalman Filter algorithm in C++ capable of accurately
and performantly tracking a turning object.
• Implemented a 2 dimensional particle filter capable of localizing a vehicle within desired accuracy and time.
• Implemented a PID controller to maneuver a vehicle around a track.
• Implemented Model Predictive Control to drive a vehicle around a track even with additional latency between commands.
TERM 1: COMPUTER VISION AND DEEP LEARNING
•Detected lane lines from a video stream and test images using OpenCV image analysis techniques to identify lines, including Hough transforms, Gaussian Smoothing and Canny edge detection.
•Trained a model which can decode traffic signs from natural images using the German Traffic Sign Dataset. [Model architecture based on Convolutional Neural Networks (CNN)].
•Generalized the above trained model for new images found on the web.
•Designed and trained a CNN for end-to-end driving in a simulator, usingTensorflow and Keras. Used optimization techniques such as regularizationand dropout to generalize the network for driving on multiple tracks.
•Built an advanced lane-finding using distortion correction, image rectification, color transforms and gradient thresholding. Identified lane curvature and vehicle displacement. Overcame environmental challenges such as shadows and pavement changes.
• Created a vehicle detection and tracking pipeline with OpenCV, histogram of gradients (HOG) and support vector machines (SVM). Optimized and evaluated the model on video data from an automotive camera taken during highway driving.
Sensor Fusion and Localization
• Implemented an Extended Kalman Filter algorithm in C++ capable of tracking a pedestrian’s motion in two dimensions.
• Implemented an Unscented Kalman Filter algorithm in C++ capable of accurately
and performantly tracking a turning object.
• Implemented a 2 dimensional particle filter capable of localizing a vehicle within desired accuracy and time.
• Implemented a PID controller to maneuver a vehicle around a track.
• Implemented Model Predictive Control to drive a vehicle around a track even with additional latency between commands.
This section lets you add any degrees or diplomas you have earned.
Udacity
Robotics Nanodegree, Robotics Technology/Technician
Dec 2016 - Dec 2016
Udacity
Self Driving Car Nanodegree, Deep Learning
Dec 2015 - Dec 2016
Computer Vision, Deep Learning, Sensor Fusion, Localization
BMS Institute of Technology and Management
Bachelor of Engineering (B.E.), Telecommunications Engineering
Dec 2010 - Dec 2014
Major Modules:
Computer Communication Networks, Real Time Systems,
Programming in C++. Microprocessors, Microcontrollers. DSP Algorithms and
Architecture, Signals and Systems, Digital Signal Processing, Image Processing, Wireless Communication, Digital Communication,Optical Networking.
Computer Communication Networks, Real Time Systems,
Programming in C++. Microprocessors, Microcontrollers. DSP Algorithms and
Architecture, Signals and Systems, Digital Signal Processing, Image Processing, Wireless Communication, Digital Communication,Optical Networking.
M.E.S College of Arts, Science & Commerce, Malleshwaram, Bangalore-3
Pre-University, Mathematics and Computer Science
Dec 2008 - Dec 2010
Technische Universität Chemnitz
Masters, Embedded Systems
Dec 2014 - Dec 2016
Major Modules:
Principal Subjects: Smart Sensor Systems,Hardware Software Co-Design I/II (prominent knowledge of C++ and VHDL programming), Design of Software for Embedded Systems (prominent knowledge of C and Esterel programming), Real Time Systems and Electronic Design Automation.
Principal Subjects: Smart Sensor Systems,Hardware Software Co-Design I/II (prominent knowledge of C++ and VHDL programming), Design of Software for Embedded Systems (prominent knowledge of C and Esterel programming), Real Time Systems and Electronic Design Automation.
Robotics: Computational Motion Planning
Oct 2016
Algorithms on Strings
Oct 2016
Sequence Models
Feb 2018