Zero-cloud defect detection camera on ESP32-S3, case study.
For an electronics-assembly client, Yantrix designed a custom inspection camera that flags solder and placement defects on-device. The whole pipeline — sensor, model, firmware, enclosure — fits in a fanless 40 x 40 x 25 mm module.
Overview
Why this study matters
A production conveyor inspection camera running a quantized INT8 CNN entirely on an ESP32-S3 — no cloud, no PC, 18 FPS at 0.4 W.
Project Type: Edge AI + Custom Hardware
Industry: Electronics manufacturing
Service Used: Edge AI + PCB Design + Embedded Firmware
Objective
What the project needed to achieve
- Detect defined defect classes on placed components with production-grade accuracy
- Run the model entirely on microcontroller-class hardware
- Eliminate cloud and on-prem PC dependencies
- Fit into a compact, fanless enclosure mountable above the conveyor
Challenge
Engineering constraint
The client had a line-side PC-based vision rig that was expensive to scale across many stations and introduced a cloud dependency the plant IT policy didn't allow. They wanted a self-contained inspection module per station — low power, low cost, zero external dependencies.
Deliverables
What the client receives
- Custom PCB design files and fabrication package
- Quantized INT8 model and training pipeline
- FreeRTOS firmware with OTA update path
- Enclosure CAD with thermal and mounting study
- Commissioning report and retraining playbook
Approach
How Yantrix approached the work
- Captured a labelled dataset of nominal and defective assemblies across lighting variants at the client plant.
- Designed a compact CNN sized for ESP32-S3 constraints and trained it with aggressive INT8 quantization-aware training.
- Designed a custom 4-layer PCB combining ESP32-S3-WROOM, an OV5640 camera module, a local ring light, and MQTT telemetry over Wi-Fi.
- Delivered firmware with a ring buffer for failure-case capture so the client can periodically retrain from real edge cases.
Outcome
What improved by the end
- 18 FPS continuous inference at approximately 0.4 W steady-state
- 96.8% accuracy on the validation set; on-line operator override provided for ambiguous cases
- No PC, no cloud — fully autonomous per-station operation
- Unit cost reduced to a fraction of the previous PC-based rig
- Failure-case ring buffer enables continuous dataset growth
Tools used
- ESP32-S3-WROOM-1 (8 MB PSRAM)
- OV5640 camera module
- TFLite Micro with ESP-DL acceleration
- PyTorch (quantization-aware training)
- KiCad for PCB design
- FreeRTOS firmware
- MQTT for telemetry
Impact
- Inspection coverage extended from selected stations to the entire line
- Capex per station reduced by roughly 6x vs. the PC-based alternative
- Plant IT policy satisfied — no external network traffic required
Conclusion
The project shows that thoughtfully quantized models plus hardware co-design can put real-time ML into truly constrained devices — not just on single-board computers.
Next step
Need an inspection system that scales across dozens of stations without a PC fleet? We design the device, the model, and the firmware as one thing.
Have a machine to build? Let's scope it together.
Tell us about your project. We'll respond within 1-2 business days with a preliminary scope and timeline — no boilerplate, no up-sell.