Kartik Madhira

About Me

I am a Computer Vision Engineer working on perception related problems at Innovasea Systems.

Before joining Innovasea, I was a Robotics Engineering Masters student at the University of Maryland, College Park. My interests lie at the intersection of the fields of vision and lidar-based perception for Robotics. At UMD, I was a Research Assistant in the Robotics Algorithms and Autonomous Systems Lab at the University of Maryland, advised by Dr. Pratap Tokekar. I worked on implementing robust perception pipeline for the precise mapping of bridges from UAVs.

My work in the industry and academia includes an overlap of: Vision based Depth, Visual Odometry, Object Segmentation, Object Detection and Tracking, Visual SLAM, Structure from Motion (SfM), Lidar-Camera calibration and Sensor Fusion.

I did my undergrad in Instrumentation and Control Engineering at Nirma University, Ahmedabad where I worked with Prof. Sandip Mehta and Dr. Dilip Kothari.

Kartik Madhira

Leetcode patterns for ML interviews

I am going to list here some of the most commonly asked LC-style question patterns.

read more

Information theory basics.

Quite a lot of times in deep learning models we across Information, probabilities, data distributions and cross-entropies. So what exactly is information? What does entropy mean in cross-entropy and why do we use it in our loss functions?

read more

Computer Vision/Machine Learning coding interviews Part-2

Over the past 7 years, I have had the chance to give multiple interviews for the computer vision and machine learning roles. This post is to delve down into the common questions asked in these interviews. These are in general 45-60 minute interviews asked with a real world problem in mind. This is part-2 of the interview coding questions.

read more

Computer Vision/Machine Learning coding interviews Part-1

Over the past 7 years, I have had the chance to give multiple interviews for the computer vision and machine learning roles. This post is to delve down into the common questions asked in these interviews. These are in general 45-60 minute interviews asked with a real world problem in mind.

read more