Identifying and localizing objects in camera images on-device. Typical models include quantized MobileNet-SSD or YOLO-based architectures optimized for microcontrollers. Used for presence detection, people counting, quality inspection, and simple classification tasks.
| Minimum RAM | 256 KB |
| Minimum Flash | 2048 KB |
| Sensor Inputs | camera |
| Typical Model Size | 250 KB (quantized int8) |
ESP32
Espressif
520 KB RAM · 240 MHz
$5–$15 (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
The ESP32-C6 handles object detection effectively with Edge Impulse. 512 KB SRAM at 160 MHz provides 2.0x headroom over the 256 KB requireme…
Good
The ESP32-C6 handles object detection effectively with TFLite Micro. 512 KB SRAM at 160 MHz provides 2.0x headroom over the 256 KB requireme…
Good
Espressif's ESP32 is a solid choice for object detection using Edge Impulse. The xtensa-lx6 core at 240 MHz with 520 KB SRAM accommodates 25…
Good
Espressif's ESP32 is a solid choice for object detection using TFLite Micro. The xtensa-lx6 core at 240 MHz with 520 KB SRAM accommodates 25…
Excellent
Edge Impulse provides an end-to-end pipeline for deploying object detection on the ESP32-S3. You collect images, train a FOMO or MobileNet-S…
Good
The ESP32-S3 runs quantized object detection models via TFLite Micro at 2-5 FPS. Its 512 KB SRAM and vector instructions handle int8 MobileN…
Excellent
The i.MX RT1062 is an excellent match for object detection with CMSIS-NN. 1024 KB SRAM delivers 4.0x the 256 KB minimum while 600 MHz proces…
Excellent
For object detection, the i.MX RT1062 with TFLite Micro scores Excellent. Its 1024 KB internal SRAM (4.0x the required 256 KB) and 600 MHz c…
Good
Renesas's RA6M5 is a solid choice for object detection using CMSIS-NN. The cortex-m33 core at 200 MHz with 512 KB SRAM accommodates 250 KB m…
Good
The RA6M5 handles object detection effectively with TFLite Micro. 512 KB SRAM at 200 MHz provides 2.0x headroom over the 256 KB requirement …
Good
STMicroelectronics's STM32F7 is a solid choice for object detection using CMSIS-NN. The cortex-m7 core at 216 MHz with 512 KB SRAM accommoda…
Good
The STM32F7 handles object detection effectively with TFLite Micro. 512 KB SRAM at 216 MHz provides 2.0x headroom over the 256 KB requiremen…
Excellent
The STM32H7 is an excellent match for object detection with CMSIS-NN. 1024 KB SRAM delivers 4.0x the 256 KB minimum while 480 MHz processes …
Excellent
The STM32H7 is one of the most capable MCUs for on-device object detection. Its 1 MB SRAM, 480 MHz Cortex-M7, and L1 cache run quantized Mob…
Good
STMicroelectronics's STM32U5 is a solid choice for object detection using CMSIS-NN. The cortex-m33 core at 160 MHz with 786 KB SRAM accommod…
Good
The STM32U5 handles object detection effectively with TFLite Micro. 786 KB SRAM at 160 MHz provides 3.1x headroom over the 256 KB requiremen…
ForestHub compiles visual AI workflows to C code for your microcontroller. Choose your hardware, build your object detection pipeline, deploy in minutes.