Low-Power RISC-V MCU Achieves High-Accuracy License Plate Recognition

Researchers have developed a novel, low-power system for automatic license plate recognition (ALPR) using a RISC-V multi-core microcontroller. This system, powered by a 9-core GAP8 processor, integrates license plate detection with SSDlite-MobilenetV2 and optical character recognition using LPRNet. It achieves a 38.9% mAP for detection and over 99.13% recognition accuracy on public datasets, while consuming only 117 mW and operating at 1.09 FPS. This design is notably 73 times more energy-efficient than previous mobile-class ALPR systems. AI

IMPACT Demonstrates feasibility of complex AI models on low-power edge devices, potentially enabling widespread embedded vision applications.

RANK_REASON Paper detailing a novel system for license plate recognition on an MCU. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• LPRNet
• Raspberry Pi3
• RISC-V
• SSDLite-MobilenetV2

• paper
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →