Vision Field Notes

Computer Vision Engineer Roadmap: What to Learn First

There is no shortage of things to learn in computer vision. The risk is learning them in the wrong order, spending months on theory with nothing built, or the opposite: copying notebooks without understanding why they work.

This roadmap is based on what the job tends to require in production: getting a model to work on real cameras, reliably, on real hardware. The author has more than three years of production computer vision experience, so the order below reflects that kind of work. It is one view, not the only valid path. Adjust it to your goals.

Diagram of eight numbered stages in two columns, connected by arrows in order. Left column: 1 Python and data basics, build: resize a folder of images; 2 Classic OpenCV, build: label frames, write a video; 3 Core machine learning ideas, build: classifier and train/val curves; 4 A deep learning framework, build: fine-tune a pretrained model. An arrow leads from stage 4 to the top of the right column: 5 Object detection, end to end, build: detector on your own data; 6 Deployment and edge hardware, build: time it on a small device; 7 Video analytics, build: people counter or zone alert; 8 Engineering habits, build: tests, logging, licences.
Caption: The whole roadmap on one page. Each stage ends with a small project, and finishing it without copying a tutorial is the signal to move on.

Stage 1: Python and the basics of working with data

You need to be comfortable with Python before anything else. Focus on:

Build: a script that loads a folder of images, prints their sizes, and saves resized copies. Set up a clean environment as described in setting up a clean Python environment for computer vision.

Stage 2: classic image handling with OpenCV

Learn how images and video are represented and manipulated: colour spaces, resizing, cropping, drawing, thresholding, contours and geometric transforms. This is not glamorous, but you will use it in every project, and it teaches you what a pixel array actually is.

Build: a script that reads a video, draws a rectangle and a text label on each frame, and writes a new video. The functions you need are listed in OpenCV essentials every computer vision engineer needs.

Stage 3: core machine learning ideas

You do not need a full degree's worth of mathematics to start, but you do need the ideas:

A little linear algebra, probability and calculus help when you read papers. Learn them as you need them, in small doses, rather than as a gate you must pass first.

Build: train a small image classifier on a public dataset, and plot training and validation curves. Explain to yourself why the two curves differ.

Stage 4: a deep learning framework

Pick PyTorch, which is widely used in research and industry. Learn tensors, datasets and data loaders, models, the training loop, saving and loading weights, and moving work to a GPU. Write a training loop by hand at least once. You will understand later tools much better.

Build: fine-tune a pretrained classification model on your own small dataset. The concept is covered in fine-tuning YOLO and transfer learning, and the same idea applies to classifiers.

Stage 5: object detection, end to end

Now do what most real projects need: detect objects. Learn the pieces in this order:

  1. What the task is and how it differs from classification and segmentation. See classification vs detection vs segmentation.
  2. How detectors work at a high level. See what is YOLO.
  3. IoU, non-maximum suppression and how to read mAP. See IoU and NMS and mAP, precision and recall.
  4. Collecting and labelling data, and the mistakes that ruin it. See annotation mistakes that quietly ruin your model.
  5. Training on a custom dataset and reading the results. See train YOLO on a custom dataset.
  6. Diagnosing problems: overfitting, class imbalance, small objects, data leakage.

Data work is where most of the real improvement comes from. Expect to spend more time on data than on model choice.

Build: a detector for something you can photograph yourself, with at least a few hundred labelled images. Split train and validation by scene, not randomly by image. Write down what fails and why.

Stage 6: deployment and edge hardware

A model in a notebook is not a product. Learn to:

A Raspberry Pi 5 is a cheap way to learn about edge limits, because it forces you to care about model size and speed.

Build: take your detector, export it, run it on a small device or a laptop CPU, and report honest timing from your own measurements.

Stage 7: video analytics

Most commercial work involves video, not single images. Learn:

Build: a people counter or zone alert on a recorded video, then on a live stream. Test it as described in a pre-deployment testing checklist for vision models.

Pipeline diagram of a production camera system with six boxes in a row: camera stream (stage 7), decode and resize (stage 2), detector model (stages 4, 5 and 6, highlighted), tracking (stage 7), events such as counts and zones (stage 7), and alerts and monitoring (stages 7 and 8). Below the detector, a box labelled data loop, stages 3 to 5, lists collect, label, split, train and evaluate, with an arrow feeding into the detector.
Caption: The model is one box among six in a real system. Most of the later stages are about the parts around it, which is why video, deployment and engineering habits sit on the roadmap at all.

Stage 8: engineering habits that make you employable

These are less exciting and make a large difference to how useful you are:

What to skip at first

How long does it take?

It depends on your background, how many hours you can give each week, and how much you build. Do not trust anyone who gives you an exact number of months. A better measure is whether you can complete each "Build" step above without copying a tutorial.

Learning resources

A good book or course can give structure, but they do not replace projects. See best books and courses for learning computer vision for how to choose.

Checklist

Next steps: best books and courses for learning computer vision, building a portfolio that gets clients.