If you've already worked with OpenCV, know how to resize an image, and apply all the basics of Computer Vision... you're way passed Level 1!
At Think Autonomous, we provide intermediate to advanced courses on Computer Vision. So let's have a look:
The Computer Vision Sequence is made of 4 main themes:
Whether it's understanding how to transition from OpenCV to Deep Learning with Transformers, or how to use camera parameters and 3D geometry, or how to process batches of images, each of these themes represent a blocking point in the growth of a Computer Vision Engineer.
So let's see how to address them:
Take your Deep Learning skills to the next level. Learn about modern architectures and approaches to classify each pixel of an image.
Understand the Attention mechanism, Transformer Networks, and Vision Transformers in Image Segmentation.
* This DLC is very advanced and therefore only available to students of the segmentation course.
In this course, you'll learn how to build Pseudo-LiDARs and 3D Computer Vision systems that find the 3D positions of obstacles.
A secret Exploration of the world of 3D Reconstruction.
* This DLC is very advanced and therefore only available to students of the stereo vision course.
In this course, you'll learn to build Flow Maps, analyze pixel motions across several frames, and process Videos using Deep Learning.
In this course, you'll learn to build Bird Eye View Maps and turn them into inputs for Localization, Mapping, and Planning algorithms.
Next Up — A sneak peek inside the Neural Optimization Journey...
© 2023 All Rights Reserved
