VIS-201 · Embedded Vision
ISP Tuning & Autofocus
The image signal processor pipeline and the control loops on top of it: exposure, white balance and focus.
Who this course is for
Imaging and vision engineers who own image quality on a camera product and must tune the ISP and its control loops with objective evidence rather than by eye.
Prerequisites
Course outline
Day 1 — Inside the ISP
- Image formation and why raw is the only honest starting point
- Pipeline stages: black level, lens shading, demosaic, denoise, sharpen, colour correction, gamma
- Analog vs digital gain; shot noise vs read noise and where each dominates
- Dynamic range, clipping and the trade the AE loop is actually making
- Designing a repeatable capture rig: fixed scene, fixed light, controlled motion
Day 2 — Exposure and colour control loops
- Auto-exposure metering, convergence behaviour and overshoot
- Flicker and anti-banding under mains lighting
- Auto white balance: grey-world assumptions and how real scenes break them
- Control-loop stability, step response and hysteresis
- Test charts and objective metrics: SNR, MTF proxies, delta-E; experimental confounders that invalidate a run
Day 3 — Autofocus from optics to control loop
- Thin-lens defocus, depth of field and what a focus metric measures
- Contrast-detect AF: metric choice, directional sweeps, peak search and hysteresis
- VCM actuators: linearity, settling, temperature effects and per-camera variation
- Per-camera AF calibration and setpoint storage
- Failure isolation: optics vs actuator vs calibration data vs algorithm
Hands-on labs
Labs follow the academy model — 35% principles, 20% guided investigation, 45% engineering studio. Every claim you make in a lab is backed by a trace, a counter or a measurement you captured yourself. How we teach
- Lab: Build a repeatable capture setup, sweep exposure and analog gain, and plot SNR and noise curves that separate shot from read noise
- Lab: Compare denoise and sharpen settings on chart captures using objective metrics plus controlled crops; document the noise/sharpness trade you chose and why
- Lab: Tune AE and AWB on a changing scene: record convergence traces, find the stability boundary and set hysteresis that holds it
- Lab: Run directional VCM sweeps, compute focus curves, quantify hysteresis and repeatability, and select per-position setpoints
Capstone project
Produce a defensible ISP tuning profile and AF calibration for a low-light or motion-constrained camera: raw/settings manifest, metric plots for every chosen parameter, per-position focus setpoints with repeatability and hysteresis numbers, and a failure-isolation report covering one seeded optics/actuator/algorithm fault.
What you leave with
- An experimental ISP-tuning method: hypothesis, sweep, metric, decision
- Objective image-quality metrics you can run on any chart capture
- AE/AWB convergence behaviour and the hysteresis settings that stabilise it
- A per-camera VCM/AF calibration procedure with repeatability evidence
How it runs
Every course follows the same model: 35% principles, 20% guided investigation, 45% engineering studio. You leave with working code, raw measurements and an evidence-based report — not a certificate of attendance. Read the methodology or see a full sample lesson.
Material is adapted to your kernel version, hardware and workload before a private delivery. For public cohorts, the environment is provided and configured.
Questions
Who is this course for?
Imaging and vision engineers who own image quality on a camera product and must tune the ISP and its control loops with objective evidence rather than by eye. It sits at advanced level within the Embedded Vision track.
What do I need to know already?
Specific prerequisites for this course: Image fundamentals: exposure, analog/digital gain, noise sources; Scripting (Python) for metrics and plots; Access to raw captures — a camera on the bench or the supplied raw set. We confirm levels before the cohort starts and adapt if a group is stronger or weaker than expected.
Can this run privately for my team?
Yes. Any course runs on-site at your offices anywhere, or live online for a distributed team, with labs adapted to your hardware and codebase.
What is the difference between in-person and online?
In person is 3 full days with hardware on your desk, capped at 14. Online is 6 half-day sessions across about two weeks so you can keep working, capped at 20, with remote lab access.
Do you invoice companies?
Yes. Purchase orders are accepted and invoicing is available in USD, EUR, GBP, SAR and CAD.
Upcoming dates
| Dates | Where | Seats | Early bird | Regular | |
|---|---|---|---|---|---|
| 25 Oct – 27 Oct 20263 full days | RiyadhIn person · KAFD Conference Centre | 9 of 14 | — | SAR 9,000 | |
| 1 Nov – 3 Nov 20263 full days | Kuwait CityIn person · Al Hamra Tower | 4 of 14 | — | KWD 740 | |
| 8 Nov – 10 Nov 20263 full days | MuscatIn person · Knowledge Oasis Muscat | 9 of 14 | OMR 830until 9 Oct | ||
| 8 Nov – 15 Nov 20266 half-days | Gulf bandLive online · 09:00–13:00 GMT+3 | 9 of 20 | US$1,580until 9 Oct | ||
| 9 Nov – 11 Nov 20263 full days | OttawaIn person · Kanata North Tech Park | 4 of 14 | CAD 2,930until 10 Oct | ||
| 16 Nov – 18 Nov 20263 full days | TorontoIn person · MaRS Discovery District | 9 of 14 | CAD 2,930until 17 Oct | ||
| 16 Nov – 23 Nov 20266 half-days | Europe bandLive online · 09:00–13:00 CET | 14 of 20 | US$1,580until 17 Oct | ||
| 16 Nov – 23 Nov 20266 half-days | Americas bandLive online · 13:00–17:00 ET | 3 of 20 | US$1,580until 17 Oct | ||
| 23 Nov – 25 Nov 20263 full days | LondonIn person · Shoreditch Works | 4 of 14 | GBP 1,680until 24 Oct | ||
| 23 Nov – 25 Nov 20263 full days | BerlinIn person · Factory Görlitzer Park | 9 of 14 | EUR 1,990until 24 Oct |
Dates shown for the next few months. If nothing fits, tell us where and when — cohorts are added on demand, and private delivery can be scheduled any week.
More in Embedded Vision
VIS-1013 days
MIPI CSI-2 & GMSL2 Camera Interfaces
The physical and protocol layers of embedded camera interfaces, and how to bring up a link that will not start.
Practitioner-taught
SAR 7,880Next 22 Nov
VIS-1104 days
V4L2 Driver Development
Writing and debugging Video4Linux2 drivers, including the media controller graph for complex pipelines.
Practitioner-taught
SAR 12,000Next 1 Nov
VIS-1203 days
Multi-Camera Synchronisation
Keeping many cameras aligned in time, which is where multi-camera systems usually fail.
Practitioner-taught
SAR 9,000Next 18 Oct
VIS-2103 days
Jetson Camera Pipelines with LibArgus
Building capture and processing pipelines on NVIDIA Jetson, from sensor to inference input.
Practitioner-taught
SAR 7,880Next 11 Oct