Description
In this course, you will learn:
- Create your own self-driving car (little Tesla).
- The divide-and-conquer approach to addressing difficult issues, such as detection -> (localization + classification).
- Segment lane lines with computer vision techniques such as Canny Edge detection and Color Thresholding.
- Localize items in photos based on certain forms using algorithms such as ShapeApproxPoly and HoughCircles.
- Estimate Straight Line Trajectories. Using Hough Lines and Curved Lanes with Custom Algorithm.
- About artificial neural networks and why convolutional neural networks are the best for image categorization.
- How to select the appropriate Algorithm in OpenCV and how to customize it to your needs.
- Create, train, and deploy a custom CNN model (Deep Learning) for classifying signs.
- Use Python's cProfile to profile and time your program.
- Compare the S.O.A Tracking strategies available in OpenCV to determine which are most suited to the project's objectives.
- Optimize your code with basic yet highly effective IP techniques and threading.
- Make SDV navigate autonomously in Custom Track while still adhering to road speed limitations.
- Learn how to extract actionable info from photos.
- Gain all of the knowledge required to access more advanced versions of the (SDV series) next courses...:).
- A brief overview of SSD for Sign Detection and why it is not a solution for all Object Detection problems.
Syllabus:
- Introduction to Hardware Design of Mini Tesla
- Software Introduction
- Process Breakdown
- Detection
- Control
- How to use The Code
- Self Driving Car
- Concluding