Hardware Guide
Espressif's ESP32-S3 excels at people counting via Edge Impulse. The 2-core xtensa-lx7 at 240 MHz with 512 KB SRAM handles 200 KB quantized models with 2.7x RAM headroom. Built-in Wi-Fi 802.11 b/g/n enables wireless result reporting.
| Spec | ESP32-S3 |
|---|---|
| Processor | Dual-core Xtensa LX7 @ 240 MHz |
| SRAM | 512 KB |
| Flash | Up to 16 MB (external) |
| Key Features | Vector instructions (SIMD), USB OTG, LCD/Camera interface, Up to 8 MB PSRAM |
| Connectivity | Wi-Fi 802.11 b/g/n, Bluetooth 5.0 LE |
| Price Range | $3 - $8 (chip), $10 - $25 (dev board) |
At 512 KB SRAM, the ESP32-S3 delivers 2.7x the 192 KB minimum needed for people counting. The 200 KB quantized model fits in the tensor arena with enough remaining capacity for input buffers and core application logic. More demanding features (multi-sensor fusion, large protocol stacks) may require careful allocation planning. Flash storage at 16 MB comfortably houses the Edge Impulse runtime, the 200 KB model binary, application firmware, and OTA update partitions for field upgrades. Flash usage is well within budget for this configuration. The ESP32-S3's vector instructions (SIMD) accelerate 8-bit and 16-bit MAC operations common in quantized neural networks. Its native USB-OTG and camera (DVP) interfaces simplify peripheral integration without external chips. For people counting, connect a camera module (e.g., OV2640 via DVP/SPI) via SPI to the ESP32-S3. The camera interface supports QVGA (320×240) or lower resolution for on-device inference. Downsample to the model's input size (typically 96×96 or 128×128 pixels) before feeding the neural network. Edge Impulse provides an end-to-end workflow: data collection from the ESP32-S3 via serial or WiFi, cloud-based training with auto-quantization, and deployment via C++ library export or Arduino library. The platform estimates on-device RAM and flash usage before deployment, reducing trial-and-error. Wi-Fi-connected boards can use the Edge Impulse daemon for direct data ingestion. At $3-8 per chip ($10-25 for dev boards), the ESP32-S3 offers strong value for people counting deployments. With 57 PlatformIO-listed boards, hardware availability is excellent. Key ESP32-S3 features for this workload: Vector instructions (SIMD), USB OTG, LCD/Camera interface, Up to 8 MB PSRAM.
Create Edge Impulse project for ESP32-S3
Sign up at edgeimpulse.com and create a new project for people counting. Install the Edge Impulse CLI (npm install -g edge-impulse-cli). Connect the ESP32-S3 board directly via the EI firmware image, or the data forwarder to stream camera data from your Espressif development board.
Collect camera training data
Connect a camera module (e.g., OV2640 via DVP/SPI) to the ESP32-S3. Use Edge Impulse's data forwarder or direct board connection to stream samples to the cloud. Collect 1000+ labeled samples across all classes. Capture images at the model input resolution (96×96 or lower).
Train model in Edge Impulse Studio
Design an impulse with the appropriate signal processing block (image preprocessing). Add a quantized MobileNet-SSD or YOLO-Tiny learning block. Train and evaluate — Edge Impulse shows estimated latency and memory usage for the ESP32-S3. Target under 160 KB model size and under 400 KB peak RAM.
Deploy and validate on ESP32-S3
Deploy via Edge Impulse CLI (edge-impulse-cli export) or download the C++ library. Allocate a tensor arena of 300-500 KB in a static buffer. Run inference on live camera data and compare predictions against your test set. Report results via MQTT or HTTP for remote validation. Measure inference latency and peak RAM usage to verify they meet application requirements.
Espressif xtensa-lx6 at 240 MHz with 520 KB SRAM. $2-5 per chip. Compared to ESP32-S3: cheaper. Good rated.
Espressif risc-v at 160 MHz with 400 KB SRAM. $1-3 per chip. Compared to ESP32-S3: cheaper. Good rated.
Espressif risc-v at 160 MHz with 512 KB SRAM. $1-3 per chip. Compared to ESP32-S3: cheaper. Good rated.
Connect cameras to on-device inference — design detection workflows visually and compile to optimized firmware.
Get Started Free