The projective camera model in detail, part one: transformation
Many sources exist which discuss about the projective, or pinhole camera model, which is a fundamental concept in computer vision. However, I find that many of them are too concise, or theoretical, or leave out important details, making it hard to get a complete understanding of how the geometry of image formation works. I'm writing this blog for newcomers to computer vision, with a series of blogs which should build on each other, and will try not to leave out any important theoretical or practical details. This blog post is the first in a series, and covers the first part of the projective camera model: Euclidian transformations.My big tech interview experience
In the past two months (the summer of 2020), I interviewed for engineering positions with both Google and Facebook. I prepared extensively, so I wanted to share my advice and preparation material. In this blog, I'll describe the interview process, how I prepared, and some thoughts about the experience.Lessons learned: A retrospective look at a year working in AI
In the middle of last year, I was hired as an AI Scientist, to work on problems in deep learning for computer vision. Before starting work as an AI Scientist, I had worked in computer vision for a few years, and before that did my PhD in electrical engineering, with a focus on numerical methods for computational physics problems, but I hadn't worked directly in the AI field before. Now that the first year is coming to a close, I wanted to collect my thoughts and recollections about working as an AI researcher and share them in this blog...
Older