Counting the number of people entering or occupying a space using on-device vision. Uses lightweight detection or classification models to track head and body presence without cloud connectivity. Applicable in retail footfall analytics, occupancy-based HVAC control, and building access management. Typically runs quantized MobileNet-SSD or FOMO (Faster Objects, More Objects) architectures optimized for low-memory MCUs.
| Minimum RAM | 192 KB |
| Minimum Flash | 1024 KB |
| Sensor Inputs | camera |
| Typical Model Size | 200 KB (quantized int8) |
| Minimum Clock | 80 MHz |
ESP32
Espressif
520 KB RAM · 240 MHz
$5–$15 (dev board)
ESP32-C3
Espressif
400 KB RAM · 160 MHz
$4–$10 (dev board)
ESP32-C6
Espressif
512 KB RAM · 160 MHz
$5–$15 (dev board)
ESP32-S3
Espressif
512 KB RAM · 240 MHz
$10–$25 (dev board)
i.MX RT1062
NXP
1024 KB RAM · 600 MHz
$25–$40 (dev board)
RA6M5
Renesas
512 KB RAM · 200 MHz
$25–$50 (dev board)
STM32F7
STMicroelectronics
512 KB RAM · 216 MHz
$25–$60 (dev board)
STM32H7
STMicroelectronics
1024 KB RAM · 480 MHz
$30–$80 (dev board)
STM32U5
STMicroelectronics
786 KB RAM · 160 MHz
$20–$50 (dev board)
Good
Espressif's ESP32-C3 is a solid choice for people counting using Edge Impulse. The risc-v core at 160 MHz with 400 KB SRAM accommodates 200 …
Good
The ESP32-C3 handles people counting effectively with TFLite Micro. 400 KB SRAM at 160 MHz provides 2.1x headroom over the 192 KB requiremen…
Good
Espressif's ESP32-C6 is a solid choice for people counting using Edge Impulse. The risc-v core at 160 MHz with 512 KB SRAM accommodates 200 …
Good
The ESP32-C6 handles people counting effectively with TFLite Micro. 512 KB SRAM at 160 MHz provides 2.7x headroom over the 192 KB requiremen…
Good
Running people counting on the ESP32 with Edge Impulse is practical. 520 KB SRAM meets the 192 KB minimum with 2.7x headroom. The 240 MHz xt…
Good
The ESP32 handles people counting effectively with TFLite Micro. 520 KB SRAM at 240 MHz provides 2.7x headroom over the 192 KB requirement f…
Excellent
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 …
Excellent
For people counting, the ESP32-S3 with TFLite Micro scores Excellent. Its 512 KB internal SRAM (2.7x the required 192 KB) and 240 MHz clock …
Excellent
NXP's i.MX RT1062 excels at people counting via CMSIS-NN. The 1-core cortex-m7 at 600 MHz with 1024 KB SRAM handles 200 KB quantized models …
Excellent
For people counting, the i.MX RT1062 with TFLite Micro scores Excellent. Its 1024 KB internal SRAM (5.3x the required 192 KB) and 600 MHz cl…
Good
Renesas's RA6M5 is a solid choice for people counting using CMSIS-NN. The cortex-m33 core at 200 MHz with 512 KB SRAM accommodates 200 KB mo…
Good
Renesas's RA6M5 is a solid choice for people counting using TFLite Micro. The cortex-m33 core at 200 MHz with 512 KB SRAM accommodates 200 K…
Good
STMicroelectronics's STM32F7 is a solid choice for people counting using CMSIS-NN. The cortex-m7 core at 216 MHz with 512 KB SRAM accommodat…
Good
STMicroelectronics's STM32F7 is a solid choice for people counting using TFLite Micro. The cortex-m7 core at 216 MHz with 512 KB SRAM accomm…
Excellent
For people counting, the STM32H7 with CMSIS-NN scores Excellent. Its 1024 KB internal SRAM (5.3x the required 192 KB) and 480 MHz clock ensu…
Excellent
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 process…
Good
The STM32U5 handles people counting effectively with CMSIS-NN. 786 KB SRAM at 160 MHz provides 4.1x headroom over the 192 KB requirement for…
Good
STMicroelectronics's STM32U5 is a solid choice for people counting using TFLite Micro. The cortex-m33 core at 160 MHz with 786 KB SRAM accom…
ForestHub compiles visual AI workflows to C code for your microcontroller. Choose your hardware, build your people counting pipeline, deploy in minutes.