Table 7 Comparative benchmarking of edge devices for Tiny-LiteNet deployment.
From: AI and IoT-powered edge device optimized for crop pest and disease detection
Device | Processor | Power requirement (W) | RAM | Inference time (ms) | Memory usage | Cost (USD) | Tiny-LiteNet Compatibility |
|---|---|---|---|---|---|---|---|
Raspberry pi 5 (RPi 5) | BCM2712 (A76, 2.4 GHz) | 4.7 | 8 GB | 16 ± 2 | 570 MB | 80 | Fully compatible ☑ |
Raspberry pi 4 (RPi 4) | BCM2711 (A72, 1.5 GHz) | 4.5 | 4 GB | 32 ± 4 | 472 MB | 60 | 2 × Slower that RPi 5 ⚠ |
FPGA | Custom HDL (Artix-7) | 3 | Depends on BRAM | 4 ± 1.2 | HDL-dependent | 150 | Verry Complex/Requires HLS redesign ⚠ |
Raspberry pi pico | RP2040 (M0 + , 133 MHz) | 3.7 | 256 KB | N/A | N/A | 20 | Cannot support CNN model ⨉ |
Arduino Nano 33 BLE sense | Cortex-M4F (64 MHz) | 3.3 | 200 KB | N/A | N/A | 50 | Cannot handle Tiny-LiteNet model ⨉ |
ESP32-CAM | Xtensa LX6 (160 MHz) | 3.3 | 500 KB | N/A | N/A | 5 | Cannot handle Tiny-LiteNet model ⨉ |
