Hardware Guide

STM32H7 for People Counting with TensorFlow Lite Micro

The STM32H7 is an excellent match for people counting with TFLite Micro. 1024 KB SRAM delivers 5.3x the 192 KB minimum while 480 MHz processes 200 KB models in real time. DSP extensions and double-precision FPU accelerate inference.

Hardware Specs

Spec STM32H7
Processor ARM Cortex-M7 @ 480 MHz
SRAM 1024 KB
Flash 2 MB
Key Features Double-precision FPU, L1 cache (16 KB I + 16 KB D), JPEG codec, Chrom-ART Accelerator (DMA2D)
Connectivity Ethernet, USB OTG HS/FS
Price Range $8 - $20 (chip), $30 - $80 (dev board)

Compatibility: Excellent

At 1024 KB SRAM, the STM32H7 provides 5.3x the 192 KB minimum for people counting. This generous headroom means the 200 KB model tensor arena, sensor input buffers, and application logic (camera polling, Ethernet stack, state management) all fit without contention. The remaining 524 KB after model allocation supports complex application features. Flash storage at 2 MB accommodates the TFLite Micro runtime and 200 KB model. Space remains for firmware and basic OTA capability. The STM32H7 at 480 MHz with double-precision FPU and ART accelerator is among the highest-performance Cortex-M MCUs in ST's lineup. Its 1 MB SRAM accommodates models that smaller MCUs cannot fit in memory. Dual-bank flash enables safe OTA firmware updates during operation. For people counting, connect a camera module (e.g., OV2640 via DVP/SPI) via SPI to the STM32H7. 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. TFLite Micro's static memory allocation model maps well to the STM32H7's memory architecture — define a fixed tensor arena at compile time with no runtime heap fragmentation risk. The framework's operator coverage supports convolutional, depthwise-separable, and pooling layers needed for people counting. Model conversion uses the standard TFLite converter with int8 post-training quantization. At $8-20 per chip ($30-80 for dev boards), the STM32H7 offers strong value for people counting deployments. 22 PlatformIO-listed boards provide decent hardware selection. Key STM32H7 features for this workload: Double-precision FPU, L1 cache (16 KB I + 16 KB D), JPEG codec, Chrom-ART Accelerator (DMA2D).

Getting Started

  1. 1

    Set up STM32H7 development environment

    Install STM32CubeIDE with the latest STM32Cube firmware package. Create a project targeting the STM32H7 and verify basic functionality (blink LED, serial output). For TFLite Micro, clone the framework repository and add it as a library dependency. Ensure the toolchain supports C++11 or later for the ML runtime.

  2. 2

    Collect camera training data

    Connect a camera module (e.g., OV2640 via DVP/SPI) to the STM32H7. Write a data logging sketch that captures camera readings at the target sample rate and outputs via serial/SD card. Collect 1000+ labeled samples across all classes. Capture images at the model input resolution (96×96 or lower).

  3. 3

    Train and quantize model for TFLite Micro

    Build a quantized MobileNet-SSD or YOLO-Tiny in TensorFlow or PyTorch. Apply int8 post-training quantization — this typically reduces model size by 4x with minimal accuracy loss. Convert to .tflite and generate a C array (xxd -i model.tflite > model_data.h). Target model size: under 200 KB to fit the STM32H7's 1024 KB SRAM with room for application code.

  4. 4

    Deploy and validate on STM32H7

    Include the TFLite Micro runtime and compiled model in your STMicroelectronics project. 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. Log results to serial for desktop validation. Measure inference latency and peak RAM usage to verify they meet application requirements.

Alternatives

ESP32-S3 with TFLite Micro

Espressif xtensa-lx7 at 240 MHz with 512 KB SRAM. $3-8 per chip. Compared to STM32H7: less RAM but lower cost, cheaper. Excellent rated.

i.MX RT1062 with TFLite Micro

NXP cortex-m7 at 600 MHz with 1024 KB SRAM. $6-12 per chip. Compared to STM32H7: cheaper. Excellent rated.

STM32F7 with TFLite Micro

STMicroelectronics cortex-m7 at 216 MHz with 512 KB SRAM. $8-15 per chip. Compared to STM32H7: less RAM but lower cost. Good rated.

Explore More

More STM32H7 guides More People Counting guides All resources Find the right MCU

FAQ

Why choose TFLite Micro over other frameworks for STM32H7?
TFLite Micro has the widest operator coverage and largest community for cortex-m7 targets. It supports int8 and float32 models with a static memory allocation model that eliminates heap fragmentation. The STM32H7's 1024 KB SRAM works well with TFLite Micro's predictable memory usage. Alternative: Edge Impulse wraps TFLite Micro with a simpler workflow if you prefer cloud-based training.
Can STM32H7 run people counting inference in real time?
The STM32H7 runs at 480 MHz with DSP acceleration. Whether this enables real-time people counting depends on your specific model architecture and acceptable latency. A 200 KB int8 model is a reasonable target for this hardware class. Larger models may require duty-cycled inference or model optimization (pruning, distillation). Benchmark your specific model on hardware to validate timing.
What is the power consumption for people counting on STM32H7?
Power consumption during inference depends on clock configuration, active peripherals, and duty cycle. Consult the STM32H7 datasheet for detailed power profiles at 480 MHz. For battery-powered people counting, use duty cycling: run inference at intervals and enter low-power sleep mode between cycles. Profile your specific workload to estimate battery life accurately.

Build Vision AI Pipelines in ForestHub

Connect cameras to on-device inference — design detection workflows visually and compile to optimized firmware.

Get Started Free