TAKE THE JOURNEY FROM 2D OBJECT DETECTION TO 4D PERCEPTION WITH...

THE TRACKING PACK

Learn the skills to break free from object detection projects, and dive in a step by step process to become a 3D Perception Engineers, with skills usable across industries like Robotics, Computer Vision, LiDARs, and more...

This bundle is now closed.

Ditch Object Detection... It's time to focus on Object Tracking!

Dear Object Detection Engineer,

If you've spent some time learning object detection, and now wonder "What's next for me? How do I make it a cutting-edge job like I see on LinkedIn?" — then this page will show you how.

Here's the TLDR of what I'm going to tell you:

Object Detection is a dead-end!

At least, learning ONLY about object detection, spending hours mastering all the types of object detectors, anchor boxes, training on custom datasets... and so on.... is.

Why?

Because while it's all very important to know, nobody cares about bounding boxes!

The skill of finding an object in an image isn't that useful, if you can't tell more information about the object (real 3D position, motion, speed, direction, ...)
With that, almost everybody can run an object detector these days.
There is no value to bring to a company if your only skills is to find rectangles in an image (detect objects).

Instead, I recommend you learn something more useful... Object Tracking!

With tracking, you can take your object detection skills on steroids, and distinguish multiple objects, track their past moves, anticipate their next ones... and engineer a complete perception pipeline!

Object tracking is one of the most interesting sub-fields in Computer Vision, and frankly, it's the #1 best next step to make if you're an engineer who learns about object detection and wants to make an impact.

Why?
Simply because tracking is what naturally follows object detection.
You learn to detect objects, and then you learn to track them.
You can't track what you can't even detect; so you do need object detection, but only as a step 1.

It's also a safe skill.
👉🏼 We're not talking about strange Deep Learning techniques, we're not talking about specific sensors that maybe 1% of the companies use (I teach all of that too), we're talking about a topic that is widely spread, and extensively used inside and outside of the autonomous space.

To me, learning object tracking should be almost mandatory for Perception Engineers, whether on Computer Vision, LiDAR, or even RADAR...

So how do you go from Object Detection to Tracking?

Here are the 2 core skills you should build:

CORE SKILL #1

Multi-Object Tracking

The first skill needed is MOT (Multi-Object Tracking). It's where you learn how to tell which obstacle from frame t is which obstacle from frame t+1

It includes Graph Matching algorithms, Deep Learning, and many optimization techniques...

CORE SKILL #2

Kalman Filters

The second skill is Kalman Filters... in which you learn how to estimate velocities, how to predict the next positions, and how to estimate the motion of obstacles through time.

This is essential for Prediction, but also the main algorithm in Sensor Fusion.

CORE SKILL #3

3D Tracking

Once you've learned how to track and predict object's positions in 2D, the real value is in 3D! We live in a 3D world, and while tracking objects in 2D is already more useful than merely detecting them, the incredible value lies in detecting AND tracking all the objects in 3D!

Do you see how far you can take your existing object detection skills?

This last output is what self-driving car companies use. It's what they implement in their Perception software. Not 2D object detection... 4D Perception!

If you like self-driving cars, then you could take a look at Waymo, and how they implement it...

Notice how the skills are similar to those of Core Skill #3? It's because self-driving cars need the real, 3D position of an object to make decisions, and thus, engineers need to know how to implement detection & tracking in 3D!

Meet the Tracking Pack: Which teaches both of these skills in 2D and 3D!

The Tracking Pack is a combination of 3 of my best courses on Perception. The first course teaches Multi-Object Tracking. The second courses teaches Kalman Filters. And the third courses teaches Multi-Object Tracking with Kalman Filters in 3D! Going through this series of courses in this order is not just taking a bundle of courses, it's following a real curriculum designed to build advanced, hireable, skills.

The Journey goes via these 3 courses:

COURSE #1

MASTER OBSTACLE TRACKING: Robust Perception Skills For Computer Vision Engineers

In this course, you'll learn how to move from object detection to multi-object tracking, and implement several robotics and deep learning based tracking algorithms.

MODULE 1

Object Detection Fundamentals

We'll start with object detection, as it is still a pillar for obstacle tracking. In fact, most of the tracking solutions are based on object detection.

MODULE 2

Multiple Obstacle Tracking

Once we handle object detection, we'll dive into object tracking. We'll learn about the SORT algorithm, the Hungarian Algorithm, Bipartite graphs, and more...

MODULE 3

Deep Obstacle Tracking

In the final module, we'll explore and implement the Deep Learning techniques that are state-of-the-art in object tracking.

This course will not only teach you about tracking, but it will also show you the actual algorithm I implemented in this autonomous shuttle:

After this first course...You'll have strong skills in tracking; and I dare say already employable!

At least, this is what many engineers reported after going through it... See this one for example, named VP (name withheld on request):

"Hi Jeremy,

I have been purchasing your courses for a while now, they are excellent and have given me so much confidence in dealing with tech, I also got an internship in a UGV startup company with your portfolio projects.

The projects that I showed were the Segformer semantic segmentation and object tracking.

The object tracking really stood out to them. Further rounds were taken, they asked me to implement kalman filters on it.

Now I'm a perception engineer intern in this company, as it's a start up, I get to do a lot of hands-on learning and experimenting. I will be taking a lot more of your courses as time goes by and I get deeper into this industry, so I would appreciate it if I could get a discount next time.

Anyways, Excellent quality courses, Excited to see what else is in store for us!
VP"

As you can see, the next skill requested by the UGV (Unmanned Ground Vehicle - typically for defense/military startups) is Kalman Filters:

COURSE #2

LEARN KALMAN FILTERS: The Hidden Algorithm that Silently Powers the Future

In this course, you'll learn step-by-step what is a Kalman Filter (our second core skill), and how to apply it to Object Tracking scenarios.

MODULE 1

Introduction to Bayes Theory & Kalman Filters

Understand how Kalman Filters work, get the hardcore maths simplified, and build a deep understanding of Bayesian Algorithms.

MODULE 2

Coding your first Kalman Filter

In this second part, we'll code linear Kalman Filters in 1D and 2D from scratch. This part will give you the necessary level of understanding to the design a Kalman Filter for any possible situation. 

MODULE 3

Bicycle Tracking Project

Take your skills to the next level and learn to track a bicycle using an object detection algorithm and a Kalman Filter you engineered from scratch.

Bonus ➕: Bounding Box Tracking with Kalman Filters Workshop

For Tracking Pack students only, a secret workshop on how to use Kalman Filters for Bounding Boxes!
  • The Tracking course teaches you how to identify and track objects
  • The Kalman Filter course teaches you how to predict the future position of one object
  • This workshop teaches how to track and predict the position of multiple objects

COURSE #3

MASTER 4D PERCEPTION: Ultimate 3D Tracking Skills for Perception Engineers

This is the final course of the journey, in which you'll build ultra-advanced 4D Perception skills based on 3D Object Detection and 3D Object Tracking with Expanded 3D Kalman Filters.

Here's what's inside the 4D Perception course:

MODULE 1

3D Object Detection

We'll begin the course right with 3D Object Detection. Many engineers know how 2D Object Detection works, but almost nobody knows how 3D Object Detection works. 

MODULE 2

3D Association & Fusion

Now we're going to the heart of the course: 3D Association & Sensor Fusion. You will learn how to merge 3D Bounding Boxes from frame to frame, or from sensor to sensor!

MODULE 3

3D Object Tracking

In the final module, you will build your 4D Perception project. How to engineer a system that detects objects in 3D, assign IDs to them, and track them all along a sequence?

4D PERCEPTION is my most advanced and in-demand course from the entire catalogue!

It's closed most of the time, and only available via waitlist. But when you join the Tracking Pack, you get to access it immediately along with your other courses!

With this, this is the course where you build the real valuable portfolio projects that get you hired... like this one:

FAQs

Do I get immediate and lifetime access to all courses?

Yes, all courses include lifetime access & frequent updates. You also get to unlock them immediately.

Where can I get more details about each course?

Each course has its own page where you can enroll separately. Joining the pack provides a discount and has you complete the tracking journey; meaning you'll have built a strong specialization on Perception & Object Tracking.

What are the prerequisites?

This is a bundle of 3 Products, and they are to be followed exactly in the offer presented in this page.

❌ Although all these courses are short and straight to the point, if you have no understanding of what object detection is, you may not be there yet.

❌ If you can't code in Python, or have never worked with Deep Learning before, I also recommend not to join right away, and to start on beginner platforms.

✅ But if you can code in Python, understand backpropagation, have already built basic Deep Learning projects, and feel like your skills are ready to improve, then the entire Tracking Journey is unlockable just for a few days.

At what price?
👉🏼 Rather than the 845€ you would get by purchasing one by one, you can unlock this pack for 3*195€, or a single payment of 585€ (a 35% discount).

To access, enroll below:

Want to learn how it went for others? See these testimonials from students of the Tracking Journey:

Mohammad Anas Khan, MOT & 4D Edgeneer

'I recently completed the updated version of your obstacle tracking course. Really liked it. I liked that you gave a quick walkthrough of all the major 2D OD networks. I also liked the part where we used additional metrics and not just IOU for our hungarian matching. And yes, seeing the classical sort perform better than deep sort gave insights into how problems can still be solved using good classical CV approach. Lastly, what better than seeing all of this being put into action on a live video? 

The 4D Perception courses sound really exciting. With 3D tracking we’d be introducing x,y,z positions, and velocity and the orientation. "

"I really enjoyed the course, the curriculum is flawless."

Mayur Waghchoure, AD software Engineer

"It helped me connect many dots together related to probabilistic robotics.
 
This coursework is really amazing and it has given me some insights about those topics I was really not aware at at the beginning."

"I'm Loving it!"

Dheeraj Madda, Tracking Edgeneer

"I am currently going through the Tracking Pack courses and I am almost near to complete the courses.
Loving it! 😍"

"I got the thing which I am missing as advanced stuff in my resume to shortlist myself."

MLV Prasad, Data Science and analytics - Mentor @codingInvaders

Before purchasing the course, I was doubting because of the course fee wrt Indian purchasing power parity (it's my fathers 1 monthly salary.. to give you context and also the income per person in  India).

But I got the thing which I am missing as advanced stuff in my resume to shortlist myself. I really liked the project Implementation and simplicity of course page. Now I have an advanced project to keep in my resume, and your emails made me keep a high standard for myself. It also made me  keep you as my role model to be proficient in CV space in India in next two 2 years.

I thank you very much, because what I was looking for was found here in structured and guided manner, where I can't find elsewhere for sure.

I would definitely recommend. Thank you very much jeremy..

"I've done many Kalman courses in the past but the example with the bicycle really opened my eyes"

Ivo Germann, Development engineer R&D, Project leader bei Zumbach AG

"This is a great course and it is exactly what I was looking for! I've done many Kalman courses in the past but the example with the bicycle really opened my eyes.

To be honest I played with the code quite a few hours and could develop a really good understanding how a Kalman filter works. 

Thanks a lot!"

☄️

What's unique about the Tracking Pack?

The Tracking Pack is not just a bundle of courses; it's a curriculum created to help you become a 4D Perception Engineer. Other products on tracking may teach some tracking skills independently, but this course really connects all the dots together into a curriculum where any 2D Object Detection Engineer can become a 4D Perception Engineer.

👉🏼 This course will go step-by-step from the fundamentals of 2D Object Detection to Hardcore 4D Perception.

For that, it will start at 2D, explore 2D Object Detection & Tracking, and then take you to 3D Object Detection, and to 3D Object Tracking. The path is incremental, and these courses have been designed to be purchased together.

This matters because it means you can take this pack with no knowledge of tracking or 3D, and end up being a 4D Perception Engineer. 

Here's everything you get when you invest in the Tracking Pack today

✔ LEARN OBSTACLE TRACKING [299€ value]

✔ LEARN KALMAN FILTERS [249€ value]

✔ MASTER 4D PERCEPTION [375€ value]

TOTAL VALUE: 923€ — THIS BUNDLE IS NOW CLOSED