Computer Vision

Intermediate Level

TOP COURSES

LEARN IMAGE SEGMENTATION

MASTER STEREO VISION

LEARN BIRD EYE VIEW

Quick Links:

Free Resources

Courses

Webinars

Quick Links:

Free Resources

Books

Programs

Why 'Intermediate' Computer Vision

Many engineers are stuck, and no matter how much they learn, they can't become experts as they planned when they got started. They started with Deep Learning and OpenCV, but even after years in the field, they're still not sure about the next steps to take.

It feels like driving with a handbrake: you can press the acceleration pedal as much as you want, but you won't drive correctly unless you release the handbrake.

In Computer Vision, I identified 3 major gaps that stop engineers from moving forward. These 3 gaps are stopping you from reaching an advanced Level in Computer Vision, and get you stuck; not at Level 1, because you likely already got started... But at Level 2.

Level 2 vs Level 3-4 Engineers

Maybe you've gotten started already, built your first CNN with Keras, trained backpropagation, ran your first YOLO object detectors, and ran a few segmentation or other advanced GitHub repos.

But where do you go from here?

At this stage, it's likely that all you can do to continue your journey is to go wide (learn Chatbots, LLMs, Kalman Filters, ROS, ...) and not go DEEP in Computer Vision.

Going deep means learning employable and advanced skills, like 3D Vision & Transformers, but also insider skills like Bird Eye View & Video Processing.

The only way to do this is to spend years in a Computer Vision job, assuming it allows you to work on this.

Or going via the Think Autonomous "intermediate" Computer Vision products.

What I call the Level 3/4.
These are unlike any other set of courses you may have experienced before.

Because they don't teach "classic" Computer Vision. They don't teach "YOLO", they don't teach "UNet", they teach the advanced.